FreshRSS

Zobrazení pro čtení

Jsou dostupné nové články, klikněte pro obnovení stránky.

MediaTek announces Helio P10 and MT6753 arrives in shipping devices

Od: Vegator
MediaTek has announced Helio P10 (MT6755), a performance mid-range smartphone SoC that is the successor of MT6752. Featuring an octa-core Cortex-A53 configuration, Helio P10 improves upon MT6752 by using TSMC's new 28HPC+ manufacturing process, which delivers power efficiency and performance improvements while remaining relatively cost-effective. It can reach a higher maximum CPU clock speed up to 2 GHz and upgrades the GPU to a Mali-T860 MP2. It is expected to be commercially available in end devices by the end of 2015.

Features shared with Helio-X10


The new SoC  incorporates a few features from Helio X10 (MT6795), MediaTek's current high-end offering, including dual ISPs with 21MP camera support and improved capture capability, as well as improved audio quality.

Otherwise, the SoC has significant similarities to MediaTek's MT6752 which it succeeds, most likely including a 32-bit external memory interface, which keeps SoC cost and phone PCB cost down. With MT6752, MediaTek already demonstrated the ability to achieve memory performance adequate for a 1080p device within the constraints of a 32-bit memory interface.

The 28HPC+ process is an upgrade of the existing 28HPC (high-performance compact) process (which is also relatively new, used by Allwinner's A83T and other SoCs), which improves performance and cost relative to the established 28HPM (high-performance mobile) process. Existing MediaTek chips like MT6752 and MT6795 most likely use 28HPM, which is established and has also been used for previous-generation SoCs such as MT6592 and Snapdragon 801/805.

MediaTek migrating to big.LITTLE CPU configurations in new SoCs


A significant departure from existing octa-core MediaTek SoCs such as MT6752 and Helio X10 (MT6795) is the pseudo-big.LITTLE CPU configuration, whereby one cluster of four Cortex-A53 cores is clocked at a higher frequency (up to 2 GHz in this case), while the second of cluster Cortex-A53 cores is optimized for lower frequencies, being clocked at a lower maximum frequency (1.1 GHz according to AnandTech).

Together with the previously announced high-end Helio X20 (MT6797) and tablet/Chromebook-oriented chips such as MT8173, Helio P10 marks a migration to (pseudo-)big.LITTLE, hierarchical CPU designs at MediaTek. While symmetrical octa-core designs such as MT6752 and MT6795 reach very high multi-core processing power by allowing all cores to run at the maximum frequency, there are signs that this configuration impacts power efficiency for tasks that require less CPU power, which can be run on power-optimized low-frequency cores.

In practice, this may be reflected in somewhat mediocre standby battery life for smartphones using MT6752 or MT6795, even though power efficiency for demanding tasks that utilize all cores is likely to be pretty good.

Budget mid-range MT6753 reaches end-market


Meanwhile, MediaTek's previously announced MT6753, which is a cost-effective budget mid-range SoC, has arrived in commercially shipping device in the form of Meizu M2 Note. Despite the name chosen by Meizu, the new model actually has lower performance than the existing Meizu M1 Note, because the MT6753  is a less costly, lower end chip when compared to to the MT6752 inside the M1 Note, with considerably slower maximum CPU speeds for the eight CPU cores, as well as a lower performance GPU. There are also signs that the memory interface and the actual memory frequency used by the M2 Note is slower. The lower cost of the MT6753 platform is reflected in the low selling price of the Meizu M2 Note.

MT6753 implements several cost-reducing features, including a lower maximum clock speed (reported to be 1.3 GHz for the M2 Note), most likely associated with a cheaper manufacturing process (either 28LP or 28HPC) than the 28HPM process of the MT6752. A significant factor for lower performance is likely to be a reduced size of the L2 CPU cache inside the MT6753. MT6753 is likely to become a significant volume driver in MediaTek's 4G product line.

However, early Geekbench entries for the Meizu M2 Note suggest that the CPU cores of the MT6753 SoC used in this model are mostly unable to reach the planned clock frequency. The Geekbench results are mostly consistent with an average maximum CPU clock speed of about 1.1 GHz, significantly lower than the 1.3 GHz reported by the OS and the 1.5 GHz mentioned when the MT6753 was originally announced a few months ago. My following blog article about the use of AArch64 provides more details on this subject.

MT6753 has lower-performance GPU than MT6752


MT6753 also has a significantly lower-performance and smaller GPU (Mali-T720 MP3), compared to the Mali-T760 MP2 inside MT6752. MT6753 marks the first Mali implementation with three pixel processing cores; previous Mali GPUs either had one, two, four, six or eight pixel processing cores, Most likely, Mali-T720 does not have the memory bandwidth usage optimization that are present in Mali-T760, which together with the more limited pixel processing throughput means that devices with a 1080p display such as the Meizu M2 Note may be impacted in terms of 1080p game performance and power efficiency for graphics-intensive operations.

World modem support in new MediaTek platforms


All new MediaTek SoCs (including Helio P10 (MT6755), MT6753, the low-end quad-core MT6735 and the announced high-end Helio X20 (MT6797)) have world-modem support, facilitating compatibility with more cellular networks used worldwide, including legacy CDMA networks in the US and other countries. This makes MediaTek SoCs more attractive to smartphone manufacturers targeting multiple or worldwide markets.

Sources: MediaTek (Helio P10 announcement), AnandTech (Helio P10 article)

Updated 6 June 2015.

HiSilicon introduces Kirin 930/935, a performance-oriented Cortex-A53-based SoC

Od: Vegator
Huawei has introduced the Huawei P8 and P8max smartphones, featuring the Kirin 930 and Kirin 935 SoCs from Huawei's  HiSilicon semiconductor division. The octa-core Kirin 930 SoC is a performance-oriented SoC featuring only Cortex-A53 CPU cores. With a maximum clock frequency in excess of 2.0 GHz, it bears similarities to MediaTek's MT6795, but the use of a pseudo big.LITTLE configuration (four Cortex-A53 cores clocked up to 2.0 GHz and four Cortex-A53 cores clocked up to 1.5 GHz, for a total of eight cores) is reminiscent of Qualcomm's midrange Snapdragon 615 SoC, which runs at lower clock frequencies.

Huawei also introduced high-end models of both the P8 and P8max with larger storage capacity featuring the Kirin 935 SoC, which is a higher-clocked version of Kirin 930. The Huawei P8max is a smartphone with an unusually large 6.8" display.

SoC is targeted at performance-oriented devices


The Huawei P8 models are higher-priced performance-oriented smartphones, and the characteristics of the SoC match this segment. Apart from the high maximum clock speed of the Cortex-A53 cores, the external RAM interface is likely to be a dual-channel 32-bit configuration like previous performance-oriented SoCs from HiSilicon. Presentation materials from Huawei describe the Cortex-A53 cores in the faster cluster of four CPUs as being of a special, performance-enhanced type, which probably reflects the application of ARM's PoP core-hardening technology whereby the core is optimized for running at a specific frequency and a particular power profile, trading performance against die size. The process technology used is likely to be TSMC's proven 28HPM process.

The SoC is reminiscent of MediaTek's recently introduced MT6795 (Helio-X), which also targets the performance segment with an octa-core Cortex-A53 CPU configuration. MediaTek's SoC has been reported to have been adopted by competitors of Huawei such as HTC and Xiaomi.

Previous generation Mali-T628 MP4 GPU used


Rather than using an updated current-generation GPU like Mali-T760, the specs sheet for the P8max indicates the Kirin 930/935 SoCs continue to use the Mali-T628 MP4 GPU that was previously used in the Kirin 920 SoC. This GPU core is not known for great power efficiency, although there are suggestions that the more efficient Mali-T760 (which features memory bandwidth optimizations) has a relatively high silicon area and cost.

HiSilicon's new SoC line-up uses only Cortex-A53 CPU cores


Apart from Kirin 930, HiSilicon has also introduced the Kirin 620 SoC, which is an octa-core Cortex-A53 based SoC for the cost-sensitive segment, clocked up to 1.2 GHz and with a single-channel memory interface. This means Huawei now has in-house Cortex-A53-based SoCs suitable for most of its smartphone product range.

Early benchmarks appear for Cortex-A72-based SoC

Od: Vegator
ARM recently announced the new Cortex-A72 processor core, which is an improved version of the existing high-performance Cortex-A57 processor core.

Alongside the Cortex-A72 CPU core, ARM also announced the CCI-500 interconnect technology as well as the high-end Mali-T880 GPU. Devices incorporating the combination of these technologies are expected to become available in 2016.

However, SoCs using the Cortex-A72 CPU are likely to become available earlier. Qualcomm and MediaTek have both announced SoCs using the Cortex-A72 core with commercial availability in the second half of 2015, suggesting that the CPU core itself is at an advanced stage of introduction. Already, early benchmarks for MediaTek's MT8173 tablet SoC that incorporates the Cortex-A72 have become available.

Cortex-A72 appears to be enhanced version Cortex-A57 optimized for next-generation processes


In its announcement press release from 3 February 2015, ARM claims that more than ten partners have already licensed Cortex-A72, including HiSilicon, MediaTek and Rockchip. Cortex-A72 is based on ARM's ARMv8-A instruction set architecture, and can be combined with the existing Cortex-A53 in a big.LITTLE configuration. Cortex-A72 seems to be positioned as a replacement for Cortex-A57. The similarities with Cortex-A57 are very apparent, for example in the identically sized L1 instruction and data caches, and a feature set that is otherwise very similar.

On a 16 nm FinFET process, the core can sustain operation at speeds up to 2.5 GHz within the constraints of a mobile power envelope (e.g. smartphones), with scalability to higher speeds for larger form-factor devices. However, the first announced devices, such as MediaTek's MT8173, appear to use older processes such as the tried-and-trusted 28 nm HPM process at TSMC, so they are likely to have a lower maximum clock speed.

ARM claims increased performance and power efficiency, although these claims seem to be based on implementation on next-generation processes such as 16 nm FinFET that deliver a significant intrinsic improvement in these metrics. ARM mentions micro-architectural improvements that result in enhancements in floating point, integer and memory performance. When implemented on a 16 nm FinFET process, ARM expects Cortex-A57 to provide 85% higher performance when compared to the Cortex-A57 core on a 20 nm process within a similar smartphone power budget.

Overall, the differences with Cortex-A57 appear to be relatively minor, so that Cortex-A72 is best viewed as an enhanced version of Cortex-A57 that is optimized for next-generation processes such as 16 nm FinFET. Nevertheless, the first SoCs to use the Cortex-A72 core will be manufactured using a less advanced process.

Benchmarks appear for MediaTek's MT8173


MediaTek's MT8173 is a mid-range tablet processor mainly targeting Wi-Fi-only tablets, since it does not have an integrated modem. It has two Cortex-A72 cores and two Cortex-A53 cores in a big.LITTLE configuration. Probably manufactured using the established 28HPM process at TSMC, the maximum clock speed of the Cortex-A57 cores is likely to be lower that the target for 16 nm FinFET, although MediaTek claims a clock speed up to 2.4 GHz, while a much lower frequency is apparent in early benchmarks results.

The chip also features a PowerVR GX6250 GPU, which delivers higher performance than the G6200 GPU used inside MediaTek's existing MT8135 and MT6795.

Recently, early benchmarks for a MT8173 development board have appeared both in the Geekbench Browser and in the results database of GFXBench. The first Geekbench results already appeared in December 2014. The latest set of Geekbench results date from the end of February 2015, although they do show a certain amount variation that may reflect thermal throttling.

Single-core performance good, but not spectacular


As expected, the Geekbench results show good single-core performance, albeit not spectacular. As shown in the following table, singe-core performance is in line with Cortex-A57-based SoCs such as Exynos 5433 and Exynos 7420. It should be noted that the MT8173 test SoC is most likely manufactured at 28 nm with a corresponding relatively low maximum CPU clock speed, while Exynos 5433 and 7420 are manufactured using smaller leading edge processes at Samsung.


SoC          "big" CPU                    Arch     JPEG (int)  Lua (int)   Mandelb. (fp)
                                                   Comp. IPC         IPC         IPC
MT8173       2 x 1.6? GHz Cortex-A72      AArch32  1310  2.13  1380  2.10  1064  1.95
Exynos 5433  4 x 1.80 GHz Cortex-A57r1p0  AArch32  1456  2.10  1397  1.89  1174  1.91
Exynos 7420  4 x 1.97 GHz Cortex-A57r1p0  AArch64  1481  1.97  1409  1.74  1198  1.92

In this table, to determine the IPC index I have made an educated guess about the actual clock speed of MT8173 when running the benchmarks. Geekbench reports a 1.40 GHz clock speed (which probably applies to the Cortex-A53 cores), 1.6 GHz seems to be a good match, providing just a little better IPC than Cortex-A57. Note that Exynos 7420 runs in AArch64 mode, which skews direct IPC comparisons.

Practical implications unclear


Without knowing the exact clock speed of the Cortex-A72 cores, it is hard to draw conclusions about the actual IPC improvement over Cortex-A57. If the MT8173 uses a 28 nm process, the ability to approach the single-core performance of Samsung's Exynos 7420 manufactured using 14 nm FinFET process is impressive. However, although MediaTek demonstrated the MT8173 in an actual tablet at MWC, it is unclear what kind of device the Alps development board in the benchmark entries actually represents, so it remains to be seen whether the benchmarks actually reflect the power budget of a tablet.

The multi-core performance reported is not very impressive, as expected because of the relatively small number of CPU cores. The JPEG Compress multi-core score shows CPU scaling factor of 2.72, which is good and implies utilization of the Cortex-A53 cores. The Mandelbrot floating point benchmark shows similar scaling.

However, the Lua integer benchmark has a very low multi-core scaling factor of 1.41, which is lower than expected, even when allowing for the limited number of cores. For example, MediaTek's MT6795 achieves multi-core scaling of 7.5 in this benchmark, and the Exynos chips range from 3.9 to 5.0. Other chips with a low multi-core scaling factor for Geekbench's Lua subtest include Snapdragon 810 (Cortex-A57-based), MediaTek's MT6595 (Cortex-A17-based) and NVIDIA's Denver-based Tegra-K1 SoC. There are indications that this benchmark test heavily depends on on-chip cache (primarily L2 cache) size and speed.

GPU performance of MT8173's PowerVR GX6250 GPU improves on G6200


The MT8173 test device's GPU performance as shown in GFXBench results database is not overly impressive, but suitable for a mid-range chip and an improvement over the PowerVR G6200 GPU used in other MediaTek SoCs such as MT6595 and MT6795. In the T-Rex Offscreen benchmark, the MT8173 registers a score of 1487, higher than the 1311 of the MT6595 (G6200)-equipped Meizu MX4. In the GFXBench 3.0 low-level tests, alpha blending scores higher than the MT6595 while the other low-level scores are comparable.

Sources: ARM (Cortex-A57 announcement press release), AnandTech (MediaTek MT8173 article), MediaTek (MT8173 announcement), Geekbench Browser (MT8173 test device results), GFXBench (MT8173 test device result)

Updated 10 March 2015.

A deeper look at graphics benchmark results, including GFXBench 3.1 and Basemark X

Od: Vegator
In this post I will take a closer at graphics benchmark results for different SoCs. I will look beyond just GFXBench (for which a new version has appeared), because the workload tested by well-known GFXBench tests such as T-Rex and Manhattan is not necessarily reflective of the actual gaming experience. Alternative benchmarks exist, such as Basemark X which uses the Unity engine that is commonly used in games.

GFXBench 3.1 released for OpenGL ES 3.1, Snapdragon 805 does well


Kishonti recently released a new version of GFXBench, GFXBench 3.1 for OpenGL ES 3.1, that includes tests for the OpenGL ES 3.1 API standard supported by many recent devices. A few results from the new benchmark tests are already available, with the Adreno 420 GPU inside Snapdragon 805 closing most of the performance gap with the Mali-T760 MP6/MP8 in Samsung's Exynos SoCs in the Manhattan 3.1 test.

                                                      Offscreen Manhattan Manhattan
Device               SoC             GPU              T-Rex        3.0       3.1

NVIDIA Shield Tablet NVIDIA K1-32    Tegra K1 GPU        3692     1979      1443  
HTC One M9           Snapdragon 810  Adreno 430          2732     1413
Galaxy S6 Edge       Exynos 7420     Mali-T760 MP8?      3312     1607       793
Sams. Galaxy Note 4  Snapdragon 805  Adreno 420          2386     1153       773
Samsung Galaxy S6    Exynos 7420     Mali-T760 MP8?      3314     1609       634
Sams. Galaxy Note 4  Exynos 5433     Mali-T760 MP6       2163     1110       436
HTC One M8           Snapdragon 801  Adreno 330          1608      768
Teclast X98 Air      Atom Z3736F     Intel HD            1014      564       307
Google Nexus 10      Exynos 5250     Mali-T604 MP4        818      351       185

NVIDIA's Tegra 32-bit version of Tegra K1 leads (the 64-bit Denver-based version of Tegra K1, and Tegra X1, have not yet been tested). Performance of Snapdragon 805 as implemented in certain models of the Samsung Galaxy Note 4 holds up better in the Manhattan 3.1 test than Samsung's Exynos SoCs with Mali-T760 MP6/MP8. Whereas Exynos 7420 (used in the Galaxy S6) has a clear advantage in existing benchmarks (1609 vs 1153 for Manhattan and 3314 vs 2386 for T-Rex), it loses that advantage in the new Manhattan 3.1 test (although the Galaxy S6 Edge benchmarks result suggests it is still slightly superior). Intel's Baytrail SoCs seem to hold up relatively well looking at the result for an Atom Z3736F-based tablet, albeit at a lower performance level.

GFXBench 3.1 results for Snapdragon 801 and the new Snapdragon 810 are not yet available. However, given the fact that GFXBench appears to generally do well on Snapdragon SoCs, they can be expected to score fairly highly. I'll say more about the apparent advantage for Qualcomm's SoC in GFXBench in the final section of this article.

Basemark X is a useful alternative to GFXBench


Basemark X is a gaming benchmark that utilizes the Unity engine that is commonly used in games, and developer Rightware claims that it actually reflects practical performance in games. Although it does include an on-screen demo, the actual benchmark scores appear to be derived from off-screen rendering at a fixed resolution, so that benchmark results can be compared objectively between different devices.

Previous generation SoCs: MT6582 beats Snapdragon 400 in Basemark X


Taking a look at previous-generation cost-sensitive SoCs, while MediaTek's ubiquitous quad-core 3G SoC MT6582 (which supports Open GL ES 2.0 only, through its Mali-400 MP2 GPU) scores lower than Snapdragon 400 in GFXBench's OpenGL ES 2.0-based T-Rex test (about 230 vs 330), in Basemark X MT6582-based devices score higher than Snapdragon 400 based devices. This is despite the fact that Snapdragon was/is often employed in devices with a considerably higher selling price than MT6582-based devices.

Device               SoC             GPU                 Display*   Medium   High

Samsung SM-G800F     Exynos 3470     Mali-400 MP4        1280x720    7527    2712
Vodafone 985N        MT6582          Mali-400 MP2         960x540    4950    1717
Acer E53             MT6582          Mali-400 MP2        1280x720    4870    1694
Wiko Rainbow         MT6582          Mali-400 MP2        1280x720    4826
Galaxy S3 Neo        Snapdragon 400T Adreno 305          1280x720    4540    1551
Moto G (XT1032)      Snapdragon 400  Adreno 305          1280x720    4440
HTC Desire 816d      Snapdragon 400T Adreno 405          1280x720    4354    1441
Samsung SM-A500F     Snapdragon 410  Adreno 306          1280x720    4132    1900
Samsung SM-A300F     Snapdragon 410  Adreno 306           960x540    4076    1892
Samsung SM-G530H     Snapdragon 410  Adreno 306           960x540    3987    1690
Samsung SM-G800A     Snapdragon 400  Adreno 305          1280x720    3946    1362
HTC Desire 820q      Snapdragon 410  Adreno 306          1280x720    3786

* While Basemark X is independent of display resolution in terms of rendering, the
memory bandwidth used for screen refresh has some impact, giving lower-resolution
devices a small advantage.
Notes: Samsung SM-G800F is the Galaxy S5 Mini (Exynos version), while SM-G800A is a Snapdragon 400 running at the non-standard maximum clock speed of 1.4 GHz; Vodafone 985N is the Vodafone Smart 4 Power; Acer E53 is the Acer Liquid E700; Galaxy S3 Neo runs the Snapdragon 400 SoC at a non-standard maximum speed of 1.4 GHz; HTC Desire 816d runs the Snapdragon 400 SoC at 1.6 GHz; SM-A500F is the Galaxy A5, while SM-A300F is the Galaxy A3; SM-G530H is the Galaxy Grand Prime.

For both the medium detail and high detail settings, MT6582-based devices consistently score higher in Basemark X than Snapdragon 400 and also Snapdragon 410-based devices for the medium detail test, which gives a different picture than the one you get from just looking at GFXBench's T-Rex benchmark

Snapdragon 410 performs worse than Snapdragon 400 in Basemark X medium-detail


Also notable is that Snapdragon 410, which is the successor of the Snapdragon 400 and would normally be expected to improve performance, actually has lower performance in practice as judged by the Basemark X medium detail benchmark. This matches earlier findings of performance flaws in Snapdragon 410. When running the high detail Basemark X benchmark, Snapdragon 410 does better and beats Snapdragon 400.

Mid-range SoCs: Snapdragon 615 and MT6752 closely matched


When running GFXBench, Snapdragon 615 and MT6752 are closely matched, with Snapdragon 615 scoring about 830 to 850 in T-Rex while MT6752 scores just above 870. For T-Rex, devices using MediaTek's prior-generation octa-core MT6592 score in the range 650 to 750. In the OpenGL ES 3.0 API-based Manhattan benchmark, Snapdragon 615 and MT6752 are very closely matched, both scoring around 360. We will also take a look at Basemark X results.

The following table shows Basemark X results for the new competing mid-range SoCs Snapdragon 615, MT6752 and HiSilicon's octa-core Hi6210 (Kirin 620), as well as for the prior-generation octa-core MT6592 from MediaTek.

Device               SoC             GPU                 Display*   Medium   High

Lenovo P70-A         MT6752          Mali-T760 MP2       1280x720   11311 
Meizu M1 Note        MT6752          Mali-T760 MP2       1920x1080  11168    4636
HTC Desire 816G      MT6592          Mali-450 MP4        1280x720   10984
Huawei CHE2-TL00     Hi6210          Mali-450 MP4        1280x720   10546    3439
Oppo R8106           Snapdragon 615  Adreno 405          1920x1080  10277    4846 
HTC Desire 820       Snapdragon 615  Adreno 405          1280x720   10133    4814
Samsung SM-A700FD    Snapdragon 615  Adreno 405          1920x1080  10052    4757
Archos 50C Oxygen    MT6592          Mali-450 MP4        1280x720    9867    3702
HTC Desire 616d      MT6592M         Mali-450 MP4        1280x720    7976    3045

* While Basemark X is independent of display resolution in terms of rendering, the
memory bandwidth used for screen refresh has some impact, giving lower-resolution
devices a small advantage.
Notes: SM-A700FD is the Galaxy A7; Huawei CHE2-TL00 is a new version of the Honor 4X.

When running the standard medium-detail version of Basemark X, MediaTek's MT6752 has  a moderate advantange over Snapdragon 615, while at the high detail setting Snapdragon 615 has a small advantage. Huawei's Kirin 620 performs adequately and just ahead of Snapdragon 615 in the medium detail setting.

MediaTek's prior-generation octa-core MT6592 with Mali-450 MP4 GPU keeps up relatively well in Basemark X,  with certain models (e.g. HTC Desire 816G) actually beating Snapdragon 615 in the medium detail setting.

Performance-oriented SoCs with Basemark X


The following table shows Basemark X results for several performance-oriented mobile SoCs.

Device               SoC             GPU                 Display*   Medium   High

Samsung Galaxy S6    Exynos 7420     Mali-T760 MP6       2560x1440  36017
Galaxy S5 LTE-A      Snapdragon 805  Adreno 420          1920x1080  32685   18334
Google Nexus 6       Snapdragon 805  Adreno 420          2560x1440  30362   20265
Sams. Galaxy Note 4  Snapdragon 805  Adreno 420          2560x1440  31963   21152
Sams. Galaxy Note 4  Exynos 5433     Mali-T760 MP6       2560x1440  29335   19019 

Apple iPad Air 2     Apple A8X       PowerVR Series 6    2048x1536  41700   29239
Google Nexus 9       NVIDIA K1-64    Tegra-K1 GPU        2048x1536  37939   28646
Apple iPad Mini 3    Apple A7        PowerVR Series 6    2048x1536  26499   14780
Teclast X98 Air      Atom Z3736F     Intel HD            2048x1536  14825    7160
Teclast P90HD        Rockchip RK3288 Mali-T764           2048x1536  13053    5645
Onda V989 Core8      Allwinner A80   PowerVR G6230       2048x1536  11004    5724

Meizu MX4 Pro        Exynos 5430     Mali-T628 MP6       1920x1200  25547   12674
Samsung SM-G900A     Snapdragon 801  Adreno 330          1920x1080  25178   11930
Samsung SM-G850F     Exynos 5430     Mali-T628 MP6       1280x720   21872   10666
Meizu MX4            MT6595          PowerVR G6200       1920x1200  17038    7817
Huawei MT7-TL10      Kirin 925       Mali-T624 MP4       1920x1080  15973    6802

* While Basemark X is independent of display resolution in terms of rendering, the
memory bandwidth used for screen refresh has some impact, giving lower-resolution
devices a small advantage.
Notes: SM-G900A is the Samsung Galaxy S5 (US version), Huawei MT7-TL10 is the Huawei Mate 7.

Looking at the ultra-high-end smartphone segment (mostly with a display resolution of 2560x1440), Exynos 7420 provides superior performance in Basemark X. Snapdragon 805 follows, a small distance ahead of Exynos 5433 as used in the Samsung Galaxy Note 4.

In the high-end tablet segment, Apple's iPad Air 2 with the Apple A8X leads, but the Nexus 9 with NVIDIA's Tegra K1 (64-bit version) comes fairly close. Apple's prior generation SoCs also delivers good performance, while Intel's current Baytrail SoC for the tablet market outperforms two high-end chips from established Chinese players in the tablet SoC market, Rockchip's RK3288 and Allwinner A80 Octa.

Mainwhile, in the mainstream performance smartphone segment, Snapdragon 801 (in the past the performance leader in the market) still provides good performance, but is actually just beaten by the 32-bit Exynos 5430 in the Meizu MX4 Pro. The chip is also used in the Galaxy Alpha (for which it provides higher-than-necessary performance given its relatively low screen resolution), while the performance of MediaTek's MT6595 SoC, while not bad, falls short of most other high-end solutions. HiSilicon's Kirin 925 as implemented in the Huawei Mate 7 is just behind.

Conclusion


It appears that just concentrating on GFXBench may give a misleading picture with regard to 3D graphics performance of mobile SoCs. In particular it is apparent that Qualcomm's Snapdragon SoCs consistently do better in GFXBench than in other benchmarks such as Basemark X. This is particularly true for the lower-end Snapdragon 400 and higher-end Snapdragon 800 series; for Snapdragon 615, results are more consistent across different benchmarks.

Basemark X, which utilizes the Unity game engine commonly used in mobile games, may more accurately reflect real-world performance.

Sources: Rightware Power Board (Basemark X benchmark results), GFXBench results database

Updated 5 March 2015: Add Galaxy S6 Edge result for GFXBench 3.1.
Updated 15 March 2015.

New mobile SoCs announced at MWC

Od: Vegator
At the Mobile World Congress this week, several new mobile SoCs are being announced.

MediaTek announces cost-reduced MT6753 for smartphones


MediaTek anounced two mobile SoCs, the MT6753 for smartphones and the MT8173 for tablets.

The MT6753 appears to be a cost-reduced version of the successful MT6752, equpped with "WorldMode" modem technology. By offering compatibility with the CDMA2000 standard, it gives customers worldwide greater diversity and flexibility in their product layouts, according to MediaTek. Features include an octa-core Cortex-A53 CPU up to 1.5 GHz and a Mali-T720 GPU with an unspecified number of cores. ARM's Mali-T720 GPU is positioned at a significantly lower performance bracket than the Mali-T760 used in the MT6752, positioning the MT6753 below the MT6752 in terms of cost and performance.

The MT6753 is described as being compatible with the previously announced MT6735 for entry-level smartphones. The MT6735 has four Cortex-A53 cores instead of eight but otherwise has a similar configuration with a Mali T720 GPU.

High-performance MT8173 tablet SoC uses small big.LITTLE clusters with Cortex-A72


The MT8173 is a high-performance tablet processor (without integrated modem) that utilizes ARM's new Cortex-A72 core in a big.LITTLE configuration. By using only two Cortex-A72 cores (clocked up to 2.4 GHz) as well as two Cortex-A53 cores, the chip has a lower cost than would be the case with the four-by-four core configuration commonly used for big.LITTLE designs, while still providing good performance.

The Cortex-A72 core, the successor of Cortex-A57, appears to be seeing quick adoption as Qualcomm has already announced performance-segment smartphone SoCs (Snapdragon 618 and 620) featuring the core.

MediaTek has previously used a similar two-by-two big.LITTLE configuration in its MT8135(V) tablet SoC, which has two Cortex-A15 cores and Cortex-A7 cores. This chip was used in Amazon tablets but otherwise did not see much adoption.

Other features include a PowerVR GX6250 GPU, which is part of Imagination's Series 6XT family, with higher performance and efficiency than the G6200 GPU used in chips such as the MT8135 and MT6595.

Other tablet SoCs not yet publicly announced by MediaTek


Meanwhile, tablet product announcements by Lenovo also refer to the MT8161 and MT8165 SoCs, which have not been announced. From the specifications of the Lenovo Tab 2 A8 which is using it, the MT8161 appears to be a tablet SoC without modem with quad-core Cortex-A53 CPU running up to 1.3 GHz, while the MT8165 (used in the Tab 2 A10) is a similar SoC with the CPU running up to 1.5 GHz. The 4G version of the Lenovo tablets come equipped with the MT8735 (Tab 2 A8) and MT8732 (Tab 2 A10). These chips are the tablet versions of the MT6735 and MT6732 smartphone SoCs.

MT6795 renamed to Helio X10


In a closed-door presentation at MWC, MediaTek also presented the Helio X10 smartphone SoC, featuring a 64-bit octa-core CPU up to 2.2 GHz, 120 Hz display refresh rate and H.265 video encode up to 4K2K @ 30 fps. A photograph of a slide taken at the presentation strongly suggests that Helio X10 is nothing other than the delayed MT6795 SoC, whose specifications closely match. Devices using this chip are likely to have already started production. MediaTek also talked about the Helio P series, a high-performance platform, which will make its way into devices before the end of the year.

Qualcomm gives preview of next-generation Snapdragon 820 SoC


In a press release, Qualcomm has given a preview of the Snapdragon 820, which utilizes Qualcomm's new custom 64-bit CPU architecture for mobile devices called Kryo. The chip will start sampling in the second half of 2015 according to Qualcomm, with devices becoming available in 2016. It will be manufactured on a next-generation FinFET process (which probably means TSMC's 16FF+, but Samsung cannot be excluded). In the press release, Qualcomm does not mention whether the chip will conform to ARM's ARMv8 instruction set architecture.

In conjuction with the Snapdragon 820, Qualcomm also announced the Zeroth hardware/software platform focusing on device intelligence features including video and audio recognition techniques (such as visual object and face recognition).

Intel introduces tablet and smartphone SoCs with integrated modem


Intel has finally introduced SoCs with an integrated cellular modem in its Atom system-on-a-chip product line. The former SoFIA platform has been renamed to Atom X3 and features multi-core 64-bit Atom processors with integrated 3G or 4G LTE modem technology. The following products are available:
  • Atom X3-C3130, which has dual-core Atom CPU running up to 1.0 GHz and integrates a 3G modem. It features Mali-400 MP2 GPU. Maximum display resolution is 1280x800. It appears to be in the same market segment as MediaTek's previous-generation 3G SoCs such as MT6572 and MT6582 and other SoCs that are already on the market.
  • Atom X3-C3230RK, which was developed by Intel partner Rockchip following the agreement announced last year. It has quad-core Atom CPU, integrates a 3G modem and features a Mali-450 MP4 GPU.
  • Atom X3-C3440, a quad-core Atom CPU platform that integrates a Cat 6 LTE 4G modem. It has an Mali-T720 MP2 GPU. This product appears to be one that is most likely to succeed in the market.
All feature a 32-bit memory interface with support for LPDDR2 (and DDR3/DDR3L with the X3-C3230RK). These are the first Intel products that have features (such as the integrated modem) that make them specifically suitable for the smartphone market. They also target cellular-enabled tablets.

The 3G products are a little behind the times, and their success is uncertain. It will be interesting observe whether Rockchip was able to develop the X3-C3230RK in time (one would expect Intel to have greater expertise/resources so that the other products will appear on the market first).

One notable fact is that these are among the first SoCs to integrate an ARM GPU core with a non-ARM CPU.

Intel announces first 14 nm Atom SoCs for tablets and all-in-ones


Intel also rolled out its first 14 nm Atom SoCs, the Atom x5 and x7 processor series (formely codenamed Cherry Trail) with  Intel Gen 8 graphics, targeting tablets and small screen all-in-ones.

Intel has also introduced a new stand-alone modem chip, XMM 7360, which support LTE Cat 10 and download speeds up to 450 Mbps, as well as wireless connnectivity products (including WiFi/Bluetooth, GNSS/GPS and NFC solutions).

Sources: MediaTek (MT6753 announcement), MediaTek (MT8173 announcement), Qualcomm (Snapdragon 820/Zeroth platform preview), Intel (MWC announcements), Intel Atom x3 Processor Series Brief

Samsung announces Galaxy S6 with Exynos 7420 SoC manufactured on "14nm" FinFET process

Od: Vegator
At the Mobile World Congress today (Sunday 1 March), Samsung announced the Galaxy S6 and Galaxy S6 Edge, featuring a numerous improvements over the previous generation Galaxy S5, including a SoC manufactured on Samsung's 14 nm FinFET-based process. The Galaxy S6 is planned to available in 20 countries starting on April 10th, 2015.

New model implement several improvements


The improvements in the new model include the following:
  • Exynos 7420 SoC manufactured on 14 nm FinFET process with 20 nm interconnects. The CPU is a big.LITTLE configuration with four Cortex-A57 and four Cortex-A53 cores, similar to Exynos 5433. The maximum clock speeds are 2.1 GHz and 1.5 GHz, respectively. Samsung claims 20% better performance and 35% better efficiency for the new chip when compared to Exynos 5433, which is manufactured using Samsung's 20 nm HKMG process.
  • The GPU has been rumoured to be a faster version of the Exynos 5433's Mali-T760 MP6 (either a higher clock rate or an MP8 configuration).
  • Early benchmarks indicate a significant increase in CPU and memory performance combined with a measurable increase in GPU performance (which is required because of the higher screen resolution).
  • Runs in 64-bit AArch64 mode, which has several advantages, as well as some disadvantages.
  • Uses new LPDDR4 SDRAM (3 GB), which has higher memory bandwidth at a given memory bus width due to higher effective clock speeds.
  • The cameras have been improved, including greater light gathering capability.
  • The 5.1" AMOLED screen's resolution is QHD (2560x1440), which is 77% more pixels than the FullHD (1920x1080) screen in Galaxy S5. The higher CPU, GPU and memory performance are essential to keep pace with increased demands caused by the higher resolution.
  • Utilizes the new UFS 2.0 interface for embedded flash memory, providing SSD-like performance according to Samsung.
  • Cat 6 LTE mode.
  • Touchwiz user-interface on top of 64-bit Android 5.0 is said to be more intuitive and less demanding in terms of processing requirements.
At the same time,  Samsung has dropped the MicroSD slot and the battery is non-removable. The battery capacity is also slightly smaller that of the Galaxy S5.

The Galaxy S6 Edge, like the Galaxy Note 4 Edge, features a screen that curves around the edges. It is priced significantly higher than the Galaxy S6, which will not be cheap either.

Quick ramp of 14nm FinFET process brings challenges to Samsung


The initial 14 nm FinFET process used by Samsung has been reported to use 20 nm interconnects with a 14 nm features size. As such it is more of an evolutionary step from 20 nm than full-blooded 14 nm FinFET would be, comparable to some degree with TSMC's 16FF process.

Still, Samsung will face a huge challenge ramping up the process in sufficient volume and acceptable yield rates to equip the high volume of Galaxy S6's expected. Rumours have mentioned low yield for the process in the recent past as Samsung started ramping up (test) production. Given the massive investment in the new process and non-optimal yield rates, it is unlikely that Samsung will significantly benefit financially from production of the chip in the near-term in terms of gross margin and other chip production-related metrics.

However, the performance lead of the Galaxy S6 made possible by the new chip could have significant positive implications for the sales and financial performance of Samsung's smartphone division, allowing Samsung to recoup some of its investment.

A few months ago, Samsung already signed an agreement with Apple whereby Samsung would supply part of the production capacity for future Apple processors. If this bears fruit it would allow Samsung to recoup more of its investment in 14 nm FinFET technology in the future.

Early benchmark performance impressive


In early benchmarks scores reported in Geekbench's result database, a device that probably is the Galaxy S6 shows impressive performance, well ahead of most existing SoCs and devices. In a direct comparison with an Exynos 5433-equipped Galaxy Note 4, the performance gain is fairly significant for most benchmarks (up to 30% for integer tests, higher for floating point), with a few negative outliers such as SHA2 and the Dijkstra integer subtest. The Dijkstra subtest also scores lower on other 64-bit AArch64 platforms, suggesting it suffers from particular AArch64 features such as the doubled size for pointer storage.

Memory performance is also significantly higher, aided by high clock rate and high amount of bandwidth delivered by the LPDDR4 memory interface, which unlike Qualcomm's Snapdragon 810 does not seem to have serious flaws.

Sources: AnandTech (Samsung annnounces the Galaxy S6 and Galaxy S6 Edge), AnandTech (Samsung Unpacked, MWC 2015 Live Blog), Geekbench Browser (Samsung SM-G925F)

Early benchmarks for MT6795 show high performance, suggest use of eight Cortex-A53 cores

Od: Vegator
MediaTek originally announced the MT6795, a SoC targeting the premium-level and performance segments of the smartphone market, in July 2014, with expectations of devices being commercially available to end users before the end of 2014. However, the chip was delayed (problems with the memory controller were reported) and competitive benchmark results are only now beginning to surface for the chip.

According to the announcement, the SoC was to have an octa-core CPU configuration with clock speeds up to 2.2 GHz, a strong dual-channel memory interface with support for LPDDR3 up to 933 MHz, 2K (2560x1600) display support. Other reports and information have suggested that it uses a PowerVR G6200 GPU, similar to the one used in MediaTek's MT6595, which can be seen as 32-bit predecessor of the new chip.

Confusion about processor cores, octa-core Cortex-A53 seems likely


The actual CPU cores used inside the MT6795 continue to be source of confusion. Initially understood to be an octa-core Cortex-A53 CPU configuration clocked at a high frequency, later a purported leaked MediaTek product roadmap surfaced that described the MT6795 as a big.LITTLE design that includes Cortex-A57 cores. However, a recent new entry in the Geekbench database suggesst that the chip actually has eight Cortex-A53 cores as originally suspected, as the IPC (instructions per cycle) of the integer and floating point subtests would be hard to reconcile with Cortex-A57 cores being present.

Geekbench results show mixed performance but high overall score


The Geekbench results show strong CPU performance, with the overall score being superior to that of available results for Snapdragon 810, which has a significantly higher cost design but has been plagued by performance issues, although it scores lower than Exynos 5433/Exynos 7 Octa with Cortex-A57 cores as used in the Galaxy Note 4. Note that MT6795 uses a less advanced 28 nm process compared to the 20 nm process used for Snapdragon 810 and Exynos 5433.

Single-score integer performance is not spectacular and below that of the previous generation high-end chips such as Snapdragon 801. Although this is compatible with the use of medium-performance Cortex-A53 cores, integer single-core performance is actually lower than the mid-range MT6752, despite the higher clock rate, pointing to continuing hardware performance problems with the chip. The Dijkstra benchmark result is particular low. This benchmark has a lot of external memory access and likely branches a lot, taxing certain elements of the CPU and SoC that simpler CPU benchmarks do not. It may be affected by the doubled address size in AArch64 mode, either through the increased size of pointer storage or reduced efficiency of the branch prediction unit inside the processor core.

Single core floating point performance in the Mandelbrot benchmark is higher than the MT6752 and actually compatible with the Cortex-A53 core running at 2.1 GHz, close to the originally envisaged maximum clock speed for the MT6795. Multi-core performance in this subtest is impressive, with a score that is higher than most existing SoCs including Exynos 7 Octa, which employs faster Cortex-A57 cores.

Finally, the dual-channel memory interface seems to working reasonably well in the tested revision of the chip/development board, with memory scores consistent with an optimized dual-channel interface, and higher, for example, than those of Exynos 5433. However, they are generally lower than those of the 32-bit MT6595.

One caveat is that the MT6795 entry is running in AArch64 mode, while the other devices were running in AArch32 (32-bit ARMv8) or 32-bit ARMv7 mode.

Average single-core CPU performance, strong multi-core performance


In a direct comparison with the MT6752, which has a comparable CPU configuration but clocked lower and has only a 32-bit memory interface, the MT6795 is only slightly faster, although the MT6795 uses a full 64-bit AArch64 instruction set model, while the tested MT6752 configurations use AArch32 with partial use of ARMv8 features. There are a few anomalous results, including a low score for the MT6795 in the single-core AES benchmark, and as mentioned it also scores significantly lower in the Dijkstra benchmark. Floating point performance is consistently higher for the MT6795 (more than the increase in clock rate would explain), which may be caused by the higher-performance memory subsystem of the MT6795 and/or the increased number of floating point registers available in AArch64 mode.

The MT6795 is clearly slower than its 32-bit predecessor MT6595 (which uses high-performance Cortex-A17 and Cortex-A7 cores in a big.LITTLE configuration) in most metrics, with only the heavy weighting and large performance gain for the AES and SHA1 cryptography tests  (due to the new ARMv8 instruction set) shifting the advantage for the overall score towards the MT6795.

When making a comparison with a median entry for the high performance Exynos 5433 (Exynos 7 Octa) inside the Samsung Galaxy Note 4, the MT6795 fairly consistently shows clearly lower single-core performance but higher multi-core performance.

MT6795 likely to be most cost-effective performance segment processor on the market


The exclusive use of Cortex-A53 CPU cores, and not the much more expensive and die-space consuming Cortex-A57 (or, in a 32-bit comparison, Cortex-A15/A17 cores), has positive implications for the cost of the chip. Die space dedicated to the CPU cores will be relatively low, although L2 caches will take considerable space when configured with a size that matches the desired performance level and market segment. Overall, the chip is likely to be attractive in terms of performance/dollar for the performance segment.

In terms of SoC optimizations, the chip would probably work better with the employment of additional ARM IP such as a Mali T760 or Mali-T800 series GPU, which offers advantages in combination with ARM cores such as Cortex-A53 in tandem with techniques such as AFBC, smart composition and transaction elimination, and new interconnect buses within the chip. SoCs like the MT6752 probably benefit from these optimizations, while the MT6795 cannot do so fully because of the non-ARM GPU. It seems likely that the MT6795 will be superseeded in next generation products to be announced by MediaTek in the future by a similar SoC with an ARM Mali-T760 or T800 series GPU.

Update (2 March): Based on a closed-door presentation event at the MWC, MediaTek appears to have rebranded MT6795 as Helio X10 with future Helio P series products also being announced.

Sources: MediaTek (MT6795 announcement), Geekbench browser

ONEXGPU 2 graphics dock features Radeon RX 7800M GPU

A bunch of Chinese PC makers have launched compact GPU docks recently that are designed to bring better graphics performance to laptops, handhelds, and mini PCs. But so far most, like the AYANEO AG01, BoostR, GPD G1, MINISFORUM R3GAF, and ONEXGPU all have the same AMD Radeon RX 7600M XT GPU inside. Now One Netbook […]

The post ONEXGPU 2 graphics dock features Radeon RX 7800M GPU appeared first on Liliputing.

MediaTek announces Helio P10 and MT6753 arrives in shipping devices

Od: Vegator
MediaTek has announced Helio P10 (MT6755), a performance mid-range smartphone SoC that is the successor of MT6752. Featuring an octa-core Cortex-A53 configuration, Helio P10 improves upon MT6752 by using TSMC's new 28HPC+ manufacturing process, which delivers power efficiency and performance improvements while remaining relatively cost-effective. It can reach a higher maximum CPU clock speed up to 2 GHz and upgrades the GPU to a Mali-T860 MP2. It is expected to be commercially available in end devices by the end of 2015.

Features shared with Helio-X10


The new SoC  incorporates a few features from Helio X10 (MT6795), MediaTek's current high-end offering, including dual ISPs with 21MP camera support and improved capture capability, as well as improved audio quality.

Otherwise, the SoC has significant similarities to MediaTek's MT6752 which it succeeds, most likely including a 32-bit external memory interface, which keeps SoC cost and phone PCB cost down. With MT6752, MediaTek already demonstrated the ability to achieve memory performance adequate for a 1080p device within the constraints of a 32-bit memory interface.

The 28HPC+ process is an upgrade of the existing 28HPC (high-performance compact) process (which is also relatively new, used by Allwinner's A83T and other SoCs), which improves performance and cost relative to the established 28HPM (high-performance mobile) process. Existing MediaTek chips like MT6752 and MT6795 most likely use 28HPM, which is established and has also been used for previous-generation SoCs such as MT6592 and Snapdragon 801/805.

MediaTek migrating to big.LITTLE CPU configurations in new SoCs


A significant departure from existing octa-core MediaTek SoCs such as MT6752 and Helio X10 (MT6795) is the pseudo-big.LITTLE CPU configuration, whereby one cluster of four Cortex-A53 cores is clocked at a higher frequency (up to 2 GHz in this case), while the second of cluster Cortex-A53 cores is optimized for lower frequencies, being clocked at a lower maximum frequency (1.1 GHz according to AnandTech).

Together with the previously announced high-end Helio X20 (MT6797) and tablet/Chromebook-oriented chips such as MT8173, Helio P10 marks a migration to (pseudo-)big.LITTLE, hierarchical CPU designs at MediaTek. While symmetrical octa-core designs such as MT6752 and MT6795 reach very high multi-core processing power by allowing all cores to run at the maximum frequency, there are signs that this configuration impacts power efficiency for tasks that require less CPU power, which can be run on power-optimized low-frequency cores.

In practice, this may be reflected in somewhat mediocre standby battery life for smartphones using MT6752 or MT6795, even though power efficiency for demanding tasks that utilize all cores is likely to be pretty good.

Budget mid-range MT6753 reaches end-market


Meanwhile, MediaTek's previously announced MT6753, which is a cost-effective budget mid-range SoC, has arrived in commercially shipping device in the form of Meizu M2 Note. Despite the name chosen by Meizu, the new model actually has lower performance than the existing Meizu M1 Note, because the MT6753  is a less costly, lower end chip when compared to to the MT6752 inside the M1 Note, with considerably slower maximum CPU speeds for the eight CPU cores, as well as a lower performance GPU. There are also signs that the memory interface and the actual memory frequency used by the M2 Note is slower. The lower cost of the MT6753 platform is reflected in the low selling price of the Meizu M2 Note.

MT6753 implements several cost-reducing features, including a lower maximum clock speed (reported to be 1.3 GHz for the M2 Note), most likely associated with a cheaper manufacturing process (either 28LP or 28HPC) than the 28HPM process of the MT6752. A significant factor for lower performance is likely to be a reduced size of the L2 CPU cache inside the MT6753. MT6753 is likely to become a significant volume driver in MediaTek's 4G product line.

However, early Geekbench entries for the Meizu M2 Note suggest that the CPU cores of the MT6753 SoC used in this model are mostly unable to reach the planned clock frequency. The Geekbench results are mostly consistent with an average maximum CPU clock speed of about 1.1 GHz, significantly lower than the 1.3 GHz reported by the OS and the 1.5 GHz mentioned when the MT6753 was originally announced a few months ago. My following blog article about the use of AArch64 provides more details on this subject.

MT6753 has lower-performance GPU than MT6752


MT6753 also has a significantly lower-performance and smaller GPU (Mali-T720 MP3), compared to the Mali-T760 MP2 inside MT6752. MT6753 marks the first Mali implementation with three pixel processing cores; previous Mali GPUs either had one, two, four, six or eight pixel processing cores, Most likely, Mali-T720 does not have the memory bandwidth usage optimization that are present in Mali-T760, which together with the more limited pixel processing throughput means that devices with a 1080p display such as the Meizu M2 Note may be impacted in terms of 1080p game performance and power efficiency for graphics-intensive operations.

World modem support in new MediaTek platforms


All new MediaTek SoCs (including Helio P10 (MT6755), MT6753, the low-end quad-core MT6735 and the announced high-end Helio X20 (MT6797)) have world-modem support, facilitating compatibility with more cellular networks used worldwide, including legacy CDMA networks in the US and other countries. This makes MediaTek SoCs more attractive to smartphone manufacturers targeting multiple or worldwide markets.

Sources: MediaTek (Helio P10 announcement), AnandTech (Helio P10 article)

Updated 6 June 2015.

HiSilicon introduces Kirin 930/935, a performance-oriented Cortex-A53-based SoC

Od: Vegator
Huawei has introduced the Huawei P8 and P8max smartphones, featuring the Kirin 930 and Kirin 935 SoCs from Huawei's  HiSilicon semiconductor division. The octa-core Kirin 930 SoC is a performance-oriented SoC featuring only Cortex-A53 CPU cores. With a maximum clock frequency in excess of 2.0 GHz, it bears similarities to MediaTek's MT6795, but the use of a pseudo big.LITTLE configuration (four Cortex-A53 cores clocked up to 2.0 GHz and four Cortex-A53 cores clocked up to 1.5 GHz, for a total of eight cores) is reminiscent of Qualcomm's midrange Snapdragon 615 SoC, which runs at lower clock frequencies.

Huawei also introduced high-end models of both the P8 and P8max with larger storage capacity featuring the Kirin 935 SoC, which is a higher-clocked version of Kirin 930. The Huawei P8max is a smartphone with an unusually large 6.8" display.

SoC is targeted at performance-oriented devices


The Huawei P8 models are higher-priced performance-oriented smartphones, and the characteristics of the SoC match this segment. Apart from the high maximum clock speed of the Cortex-A53 cores, the external RAM interface is likely to be a dual-channel 32-bit configuration like previous performance-oriented SoCs from HiSilicon. Presentation materials from Huawei describe the Cortex-A53 cores in the faster cluster of four CPUs as being of a special, performance-enhanced type, which probably reflects the application of ARM's PoP core-hardening technology whereby the core is optimized for running at a specific frequency and a particular power profile, trading performance against die size. The process technology used is likely to be TSMC's proven 28HPM process.

The SoC is reminiscent of MediaTek's recently introduced MT6795 (Helio-X), which also targets the performance segment with an octa-core Cortex-A53 CPU configuration. MediaTek's SoC has been reported to have been adopted by competitors of Huawei such as HTC and Xiaomi.

Previous generation Mali-T628 MP4 GPU used


Rather than using an updated current-generation GPU like Mali-T760, the specs sheet for the P8max indicates the Kirin 930/935 SoCs continue to use the Mali-T628 MP4 GPU that was previously used in the Kirin 920 SoC. This GPU core is not known for great power efficiency, although there are suggestions that the more efficient Mali-T760 (which features memory bandwidth optimizations) has a relatively high silicon area and cost.

HiSilicon's new SoC line-up uses only Cortex-A53 CPU cores


Apart from Kirin 930, HiSilicon has also introduced the Kirin 620 SoC, which is an octa-core Cortex-A53 based SoC for the cost-sensitive segment, clocked up to 1.2 GHz and with a single-channel memory interface. This means Huawei now has in-house Cortex-A53-based SoCs suitable for most of its smartphone product range.

Early benchmarks appear for Cortex-A72-based SoC

Od: Vegator
ARM recently announced the new Cortex-A72 processor core, which is an improved version of the existing high-performance Cortex-A57 processor core.

Alongside the Cortex-A72 CPU core, ARM also announced the CCI-500 interconnect technology as well as the high-end Mali-T880 GPU. Devices incorporating the combination of these technologies are expected to become available in 2016.

However, SoCs using the Cortex-A72 CPU are likely to become available earlier. Qualcomm and MediaTek have both announced SoCs using the Cortex-A72 core with commercial availability in the second half of 2015, suggesting that the CPU core itself is at an advanced stage of introduction. Already, early benchmarks for MediaTek's MT8173 tablet SoC that incorporates the Cortex-A72 have become available.

Cortex-A72 appears to be enhanced version Cortex-A57 optimized for next-generation processes


In its announcement press release from 3 February 2015, ARM claims that more than ten partners have already licensed Cortex-A72, including HiSilicon, MediaTek and Rockchip. Cortex-A72 is based on ARM's ARMv8-A instruction set architecture, and can be combined with the existing Cortex-A53 in a big.LITTLE configuration. Cortex-A72 seems to be positioned as a replacement for Cortex-A57. The similarities with Cortex-A57 are very apparent, for example in the identically sized L1 instruction and data caches, and a feature set that is otherwise very similar.

On a 16 nm FinFET process, the core can sustain operation at speeds up to 2.5 GHz within the constraints of a mobile power envelope (e.g. smartphones), with scalability to higher speeds for larger form-factor devices. However, the first announced devices, such as MediaTek's MT8173, appear to use older processes such as the tried-and-trusted 28 nm HPM process at TSMC, so they are likely to have a lower maximum clock speed.

ARM claims increased performance and power efficiency, although these claims seem to be based on implementation on next-generation processes such as 16 nm FinFET that deliver a significant intrinsic improvement in these metrics. ARM mentions micro-architectural improvements that result in enhancements in floating point, integer and memory performance. When implemented on a 16 nm FinFET process, ARM expects Cortex-A57 to provide 85% higher performance when compared to the Cortex-A57 core on a 20 nm process within a similar smartphone power budget.

Overall, the differences with Cortex-A57 appear to be relatively minor, so that Cortex-A72 is best viewed as an enhanced version of Cortex-A57 that is optimized for next-generation processes such as 16 nm FinFET. Nevertheless, the first SoCs to use the Cortex-A72 core will be manufactured using a less advanced process.

Benchmarks appear for MediaTek's MT8173


MediaTek's MT8173 is a mid-range tablet processor mainly targeting Wi-Fi-only tablets, since it does not have an integrated modem. It has two Cortex-A72 cores and two Cortex-A53 cores in a big.LITTLE configuration. Probably manufactured using the established 28HPM process at TSMC, the maximum clock speed of the Cortex-A57 cores is likely to be lower that the target for 16 nm FinFET, although MediaTek claims a clock speed up to 2.4 GHz, while a much lower frequency is apparent in early benchmarks results.

The chip also features a PowerVR GX6250 GPU, which delivers higher performance than the G6200 GPU used inside MediaTek's existing MT8135 and MT6795.

Recently, early benchmarks for a MT8173 development board have appeared both in the Geekbench Browser and in the results database of GFXBench. The first Geekbench results already appeared in December 2014. The latest set of Geekbench results date from the end of February 2015, although they do show a certain amount variation that may reflect thermal throttling.

Single-core performance good, but not spectacular


As expected, the Geekbench results show good single-core performance, albeit not spectacular. As shown in the following table, singe-core performance is in line with Cortex-A57-based SoCs such as Exynos 5433 and Exynos 7420. It should be noted that the MT8173 test SoC is most likely manufactured at 28 nm with a corresponding relatively low maximum CPU clock speed, while Exynos 5433 and 7420 are manufactured using smaller leading edge processes at Samsung.


SoC          "big" CPU                    Arch     JPEG (int)  Lua (int)   Mandelb. (fp)
                                                   Comp. IPC         IPC         IPC
MT8173       2 x 1.6? GHz Cortex-A72      AArch32  1310  2.13  1380  2.10  1064  1.95
Exynos 5433  4 x 1.80 GHz Cortex-A57r1p0  AArch32  1456  2.10  1397  1.89  1174  1.91
Exynos 7420  4 x 1.97 GHz Cortex-A57r1p0  AArch64  1481  1.97  1409  1.74  1198  1.92

In this table, to determine the IPC index I have made an educated guess about the actual clock speed of MT8173 when running the benchmarks. Geekbench reports a 1.40 GHz clock speed (which probably applies to the Cortex-A53 cores), 1.6 GHz seems to be a good match, providing just a little better IPC than Cortex-A57. Note that Exynos 7420 runs in AArch64 mode, which skews direct IPC comparisons.

Practical implications unclear


Without knowing the exact clock speed of the Cortex-A72 cores, it is hard to draw conclusions about the actual IPC improvement over Cortex-A57. If the MT8173 uses a 28 nm process, the ability to approach the single-core performance of Samsung's Exynos 7420 manufactured using 14 nm FinFET process is impressive. However, although MediaTek demonstrated the MT8173 in an actual tablet at MWC, it is unclear what kind of device the Alps development board in the benchmark entries actually represents, so it remains to be seen whether the benchmarks actually reflect the power budget of a tablet.

The multi-core performance reported is not very impressive, as expected because of the relatively small number of CPU cores. The JPEG Compress multi-core score shows CPU scaling factor of 2.72, which is good and implies utilization of the Cortex-A53 cores. The Mandelbrot floating point benchmark shows similar scaling.

However, the Lua integer benchmark has a very low multi-core scaling factor of 1.41, which is lower than expected, even when allowing for the limited number of cores. For example, MediaTek's MT6795 achieves multi-core scaling of 7.5 in this benchmark, and the Exynos chips range from 3.9 to 5.0. Other chips with a low multi-core scaling factor for Geekbench's Lua subtest include Snapdragon 810 (Cortex-A57-based), MediaTek's MT6595 (Cortex-A17-based) and NVIDIA's Denver-based Tegra-K1 SoC. There are indications that this benchmark test heavily depends on on-chip cache (primarily L2 cache) size and speed.

GPU performance of MT8173's PowerVR GX6250 GPU improves on G6200


The MT8173 test device's GPU performance as shown in GFXBench results database is not overly impressive, but suitable for a mid-range chip and an improvement over the PowerVR G6200 GPU used in other MediaTek SoCs such as MT6595 and MT6795. In the T-Rex Offscreen benchmark, the MT8173 registers a score of 1487, higher than the 1311 of the MT6595 (G6200)-equipped Meizu MX4. In the GFXBench 3.0 low-level tests, alpha blending scores higher than the MT6595 while the other low-level scores are comparable.

Sources: ARM (Cortex-A57 announcement press release), AnandTech (MediaTek MT8173 article), MediaTek (MT8173 announcement), Geekbench Browser (MT8173 test device results), GFXBench (MT8173 test device result)

Updated 10 March 2015.

A deeper look at graphics benchmark results, including GFXBench 3.1 and Basemark X

Od: Vegator
In this post I will take a closer at graphics benchmark results for different SoCs. I will look beyond just GFXBench (for which a new version has appeared), because the workload tested by well-known GFXBench tests such as T-Rex and Manhattan is not necessarily reflective of the actual gaming experience. Alternative benchmarks exist, such as Basemark X which uses the Unity engine that is commonly used in games.

GFXBench 3.1 released for OpenGL ES 3.1, Snapdragon 805 does well


Kishonti recently released a new version of GFXBench, GFXBench 3.1 for OpenGL ES 3.1, that includes tests for the OpenGL ES 3.1 API standard supported by many recent devices. A few results from the new benchmark tests are already available, with the Adreno 420 GPU inside Snapdragon 805 closing most of the performance gap with the Mali-T760 MP6/MP8 in Samsung's Exynos SoCs in the Manhattan 3.1 test.

                                                      Offscreen Manhattan Manhattan
Device               SoC             GPU              T-Rex        3.0       3.1

NVIDIA Shield Tablet NVIDIA K1-32    Tegra K1 GPU        3692     1979      1443  
HTC One M9           Snapdragon 810  Adreno 430          2732     1413
Galaxy S6 Edge       Exynos 7420     Mali-T760 MP8?      3312     1607       793
Sams. Galaxy Note 4  Snapdragon 805  Adreno 420          2386     1153       773
Samsung Galaxy S6    Exynos 7420     Mali-T760 MP8?      3314     1609       634
Sams. Galaxy Note 4  Exynos 5433     Mali-T760 MP6       2163     1110       436
HTC One M8           Snapdragon 801  Adreno 330          1608      768
Teclast X98 Air      Atom Z3736F     Intel HD            1014      564       307
Google Nexus 10      Exynos 5250     Mali-T604 MP4        818      351       185

NVIDIA's Tegra 32-bit version of Tegra K1 leads (the 64-bit Denver-based version of Tegra K1, and Tegra X1, have not yet been tested). Performance of Snapdragon 805 as implemented in certain models of the Samsung Galaxy Note 4 holds up better in the Manhattan 3.1 test than Samsung's Exynos SoCs with Mali-T760 MP6/MP8. Whereas Exynos 7420 (used in the Galaxy S6) has a clear advantage in existing benchmarks (1609 vs 1153 for Manhattan and 3314 vs 2386 for T-Rex), it loses that advantage in the new Manhattan 3.1 test (although the Galaxy S6 Edge benchmarks result suggests it is still slightly superior). Intel's Baytrail SoCs seem to hold up relatively well looking at the result for an Atom Z3736F-based tablet, albeit at a lower performance level.

GFXBench 3.1 results for Snapdragon 801 and the new Snapdragon 810 are not yet available. However, given the fact that GFXBench appears to generally do well on Snapdragon SoCs, they can be expected to score fairly highly. I'll say more about the apparent advantage for Qualcomm's SoC in GFXBench in the final section of this article.

Basemark X is a useful alternative to GFXBench


Basemark X is a gaming benchmark that utilizes the Unity engine that is commonly used in games, and developer Rightware claims that it actually reflects practical performance in games. Although it does include an on-screen demo, the actual benchmark scores appear to be derived from off-screen rendering at a fixed resolution, so that benchmark results can be compared objectively between different devices.

Previous generation SoCs: MT6582 beats Snapdragon 400 in Basemark X


Taking a look at previous-generation cost-sensitive SoCs, while MediaTek's ubiquitous quad-core 3G SoC MT6582 (which supports Open GL ES 2.0 only, through its Mali-400 MP2 GPU) scores lower than Snapdragon 400 in GFXBench's OpenGL ES 2.0-based T-Rex test (about 230 vs 330), in Basemark X MT6582-based devices score higher than Snapdragon 400 based devices. This is despite the fact that Snapdragon was/is often employed in devices with a considerably higher selling price than MT6582-based devices.

Device               SoC             GPU                 Display*   Medium   High

Samsung SM-G800F     Exynos 3470     Mali-400 MP4        1280x720    7527    2712
Vodafone 985N        MT6582          Mali-400 MP2         960x540    4950    1717
Acer E53             MT6582          Mali-400 MP2        1280x720    4870    1694
Wiko Rainbow         MT6582          Mali-400 MP2        1280x720    4826
Galaxy S3 Neo        Snapdragon 400T Adreno 305          1280x720    4540    1551
Moto G (XT1032)      Snapdragon 400  Adreno 305          1280x720    4440
HTC Desire 816d      Snapdragon 400T Adreno 405          1280x720    4354    1441
Samsung SM-A500F     Snapdragon 410  Adreno 306          1280x720    4132    1900
Samsung SM-A300F     Snapdragon 410  Adreno 306           960x540    4076    1892
Samsung SM-G530H     Snapdragon 410  Adreno 306           960x540    3987    1690
Samsung SM-G800A     Snapdragon 400  Adreno 305          1280x720    3946    1362
HTC Desire 820q      Snapdragon 410  Adreno 306          1280x720    3786

* While Basemark X is independent of display resolution in terms of rendering, the
memory bandwidth used for screen refresh has some impact, giving lower-resolution
devices a small advantage.
Notes: Samsung SM-G800F is the Galaxy S5 Mini (Exynos version), while SM-G800A is a Snapdragon 400 running at the non-standard maximum clock speed of 1.4 GHz; Vodafone 985N is the Vodafone Smart 4 Power; Acer E53 is the Acer Liquid E700; Galaxy S3 Neo runs the Snapdragon 400 SoC at a non-standard maximum speed of 1.4 GHz; HTC Desire 816d runs the Snapdragon 400 SoC at 1.6 GHz; SM-A500F is the Galaxy A5, while SM-A300F is the Galaxy A3; SM-G530H is the Galaxy Grand Prime.

For both the medium detail and high detail settings, MT6582-based devices consistently score higher in Basemark X than Snapdragon 400 and also Snapdragon 410-based devices for the medium detail test, which gives a different picture than the one you get from just looking at GFXBench's T-Rex benchmark

Snapdragon 410 performs worse than Snapdragon 400 in Basemark X medium-detail


Also notable is that Snapdragon 410, which is the successor of the Snapdragon 400 and would normally be expected to improve performance, actually has lower performance in practice as judged by the Basemark X medium detail benchmark. This matches earlier findings of performance flaws in Snapdragon 410. When running the high detail Basemark X benchmark, Snapdragon 410 does better and beats Snapdragon 400.

Mid-range SoCs: Snapdragon 615 and MT6752 closely matched


When running GFXBench, Snapdragon 615 and MT6752 are closely matched, with Snapdragon 615 scoring about 830 to 850 in T-Rex while MT6752 scores just above 870. For T-Rex, devices using MediaTek's prior-generation octa-core MT6592 score in the range 650 to 750. In the OpenGL ES 3.0 API-based Manhattan benchmark, Snapdragon 615 and MT6752 are very closely matched, both scoring around 360. We will also take a look at Basemark X results.

The following table shows Basemark X results for the new competing mid-range SoCs Snapdragon 615, MT6752 and HiSilicon's octa-core Hi6210 (Kirin 620), as well as for the prior-generation octa-core MT6592 from MediaTek.

Device               SoC             GPU                 Display*   Medium   High

Lenovo P70-A         MT6752          Mali-T760 MP2       1280x720   11311 
Meizu M1 Note        MT6752          Mali-T760 MP2       1920x1080  11168    4636
HTC Desire 816G      MT6592          Mali-450 MP4        1280x720   10984
Huawei CHE2-TL00     Hi6210          Mali-450 MP4        1280x720   10546    3439
Oppo R8106           Snapdragon 615  Adreno 405          1920x1080  10277    4846 
HTC Desire 820       Snapdragon 615  Adreno 405          1280x720   10133    4814
Samsung SM-A700FD    Snapdragon 615  Adreno 405          1920x1080  10052    4757
Archos 50C Oxygen    MT6592          Mali-450 MP4        1280x720    9867    3702
HTC Desire 616d      MT6592M         Mali-450 MP4        1280x720    7976    3045

* While Basemark X is independent of display resolution in terms of rendering, the
memory bandwidth used for screen refresh has some impact, giving lower-resolution
devices a small advantage.
Notes: SM-A700FD is the Galaxy A7; Huawei CHE2-TL00 is a new version of the Honor 4X.

When running the standard medium-detail version of Basemark X, MediaTek's MT6752 has  a moderate advantange over Snapdragon 615, while at the high detail setting Snapdragon 615 has a small advantage. Huawei's Kirin 620 performs adequately and just ahead of Snapdragon 615 in the medium detail setting.

MediaTek's prior-generation octa-core MT6592 with Mali-450 MP4 GPU keeps up relatively well in Basemark X,  with certain models (e.g. HTC Desire 816G) actually beating Snapdragon 615 in the medium detail setting.

Performance-oriented SoCs with Basemark X


The following table shows Basemark X results for several performance-oriented mobile SoCs.

Device               SoC             GPU                 Display*   Medium   High

Samsung Galaxy S6    Exynos 7420     Mali-T760 MP6       2560x1440  36017
Galaxy S5 LTE-A      Snapdragon 805  Adreno 420          1920x1080  32685   18334
Google Nexus 6       Snapdragon 805  Adreno 420          2560x1440  30362   20265
Sams. Galaxy Note 4  Snapdragon 805  Adreno 420          2560x1440  31963   21152
Sams. Galaxy Note 4  Exynos 5433     Mali-T760 MP6       2560x1440  29335   19019 

Apple iPad Air 2     Apple A8X       PowerVR Series 6    2048x1536  41700   29239
Google Nexus 9       NVIDIA K1-64    Tegra-K1 GPU        2048x1536  37939   28646
Apple iPad Mini 3    Apple A7        PowerVR Series 6    2048x1536  26499   14780
Teclast X98 Air      Atom Z3736F     Intel HD            2048x1536  14825    7160
Teclast P90HD        Rockchip RK3288 Mali-T764           2048x1536  13053    5645
Onda V989 Core8      Allwinner A80   PowerVR G6230       2048x1536  11004    5724

Meizu MX4 Pro        Exynos 5430     Mali-T628 MP6       1920x1200  25547   12674
Samsung SM-G900A     Snapdragon 801  Adreno 330          1920x1080  25178   11930
Samsung SM-G850F     Exynos 5430     Mali-T628 MP6       1280x720   21872   10666
Meizu MX4            MT6595          PowerVR G6200       1920x1200  17038    7817
Huawei MT7-TL10      Kirin 925       Mali-T624 MP4       1920x1080  15973    6802

* While Basemark X is independent of display resolution in terms of rendering, the
memory bandwidth used for screen refresh has some impact, giving lower-resolution
devices a small advantage.
Notes: SM-G900A is the Samsung Galaxy S5 (US version), Huawei MT7-TL10 is the Huawei Mate 7.

Looking at the ultra-high-end smartphone segment (mostly with a display resolution of 2560x1440), Exynos 7420 provides superior performance in Basemark X. Snapdragon 805 follows, a small distance ahead of Exynos 5433 as used in the Samsung Galaxy Note 4.

In the high-end tablet segment, Apple's iPad Air 2 with the Apple A8X leads, but the Nexus 9 with NVIDIA's Tegra K1 (64-bit version) comes fairly close. Apple's prior generation SoCs also delivers good performance, while Intel's current Baytrail SoC for the tablet market outperforms two high-end chips from established Chinese players in the tablet SoC market, Rockchip's RK3288 and Allwinner A80 Octa.

Mainwhile, in the mainstream performance smartphone segment, Snapdragon 801 (in the past the performance leader in the market) still provides good performance, but is actually just beaten by the 32-bit Exynos 5430 in the Meizu MX4 Pro. The chip is also used in the Galaxy Alpha (for which it provides higher-than-necessary performance given its relatively low screen resolution), while the performance of MediaTek's MT6595 SoC, while not bad, falls short of most other high-end solutions. HiSilicon's Kirin 925 as implemented in the Huawei Mate 7 is just behind.

Conclusion


It appears that just concentrating on GFXBench may give a misleading picture with regard to 3D graphics performance of mobile SoCs. In particular it is apparent that Qualcomm's Snapdragon SoCs consistently do better in GFXBench than in other benchmarks such as Basemark X. This is particularly true for the lower-end Snapdragon 400 and higher-end Snapdragon 800 series; for Snapdragon 615, results are more consistent across different benchmarks.

Basemark X, which utilizes the Unity game engine commonly used in mobile games, may more accurately reflect real-world performance.

Sources: Rightware Power Board (Basemark X benchmark results), GFXBench results database

Updated 5 March 2015: Add Galaxy S6 Edge result for GFXBench 3.1.
Updated 15 March 2015.

New mobile SoCs announced at MWC

Od: Vegator
At the Mobile World Congress this week, several new mobile SoCs are being announced.

MediaTek announces cost-reduced MT6753 for smartphones


MediaTek anounced two mobile SoCs, the MT6753 for smartphones and the MT8173 for tablets.

The MT6753 appears to be a cost-reduced version of the successful MT6752, equpped with "WorldMode" modem technology. By offering compatibility with the CDMA2000 standard, it gives customers worldwide greater diversity and flexibility in their product layouts, according to MediaTek. Features include an octa-core Cortex-A53 CPU up to 1.5 GHz and a Mali-T720 GPU with an unspecified number of cores. ARM's Mali-T720 GPU is positioned at a significantly lower performance bracket than the Mali-T760 used in the MT6752, positioning the MT6753 below the MT6752 in terms of cost and performance.

The MT6753 is described as being compatible with the previously announced MT6735 for entry-level smartphones. The MT6735 has four Cortex-A53 cores instead of eight but otherwise has a similar configuration with a Mali T720 GPU.

High-performance MT8173 tablet SoC uses small big.LITTLE clusters with Cortex-A72


The MT8173 is a high-performance tablet processor (without integrated modem) that utilizes ARM's new Cortex-A72 core in a big.LITTLE configuration. By using only two Cortex-A72 cores (clocked up to 2.4 GHz) as well as two Cortex-A53 cores, the chip has a lower cost than would be the case with the four-by-four core configuration commonly used for big.LITTLE designs, while still providing good performance.

The Cortex-A72 core, the successor of Cortex-A57, appears to be seeing quick adoption as Qualcomm has already announced performance-segment smartphone SoCs (Snapdragon 618 and 620) featuring the core.

MediaTek has previously used a similar two-by-two big.LITTLE configuration in its MT8135(V) tablet SoC, which has two Cortex-A15 cores and Cortex-A7 cores. This chip was used in Amazon tablets but otherwise did not see much adoption.

Other features include a PowerVR GX6250 GPU, which is part of Imagination's Series 6XT family, with higher performance and efficiency than the G6200 GPU used in chips such as the MT8135 and MT6595.

Other tablet SoCs not yet publicly announced by MediaTek


Meanwhile, tablet product announcements by Lenovo also refer to the MT8161 and MT8165 SoCs, which have not been announced. From the specifications of the Lenovo Tab 2 A8 which is using it, the MT8161 appears to be a tablet SoC without modem with quad-core Cortex-A53 CPU running up to 1.3 GHz, while the MT8165 (used in the Tab 2 A10) is a similar SoC with the CPU running up to 1.5 GHz. The 4G version of the Lenovo tablets come equipped with the MT8735 (Tab 2 A8) and MT8732 (Tab 2 A10). These chips are the tablet versions of the MT6735 and MT6732 smartphone SoCs.

MT6795 renamed to Helio X10


In a closed-door presentation at MWC, MediaTek also presented the Helio X10 smartphone SoC, featuring a 64-bit octa-core CPU up to 2.2 GHz, 120 Hz display refresh rate and H.265 video encode up to 4K2K @ 30 fps. A photograph of a slide taken at the presentation strongly suggests that Helio X10 is nothing other than the delayed MT6795 SoC, whose specifications closely match. Devices using this chip are likely to have already started production. MediaTek also talked about the Helio P series, a high-performance platform, which will make its way into devices before the end of the year.

Qualcomm gives preview of next-generation Snapdragon 820 SoC


In a press release, Qualcomm has given a preview of the Snapdragon 820, which utilizes Qualcomm's new custom 64-bit CPU architecture for mobile devices called Kryo. The chip will start sampling in the second half of 2015 according to Qualcomm, with devices becoming available in 2016. It will be manufactured on a next-generation FinFET process (which probably means TSMC's 16FF+, but Samsung cannot be excluded). In the press release, Qualcomm does not mention whether the chip will conform to ARM's ARMv8 instruction set architecture.

In conjuction with the Snapdragon 820, Qualcomm also announced the Zeroth hardware/software platform focusing on device intelligence features including video and audio recognition techniques (such as visual object and face recognition).

Intel introduces tablet and smartphone SoCs with integrated modem


Intel has finally introduced SoCs with an integrated cellular modem in its Atom system-on-a-chip product line. The former SoFIA platform has been renamed to Atom X3 and features multi-core 64-bit Atom processors with integrated 3G or 4G LTE modem technology. The following products are available:
  • Atom X3-C3130, which has dual-core Atom CPU running up to 1.0 GHz and integrates a 3G modem. It features Mali-400 MP2 GPU. Maximum display resolution is 1280x800. It appears to be in the same market segment as MediaTek's previous-generation 3G SoCs such as MT6572 and MT6582 and other SoCs that are already on the market.
  • Atom X3-C3230RK, which was developed by Intel partner Rockchip following the agreement announced last year. It has quad-core Atom CPU, integrates a 3G modem and features a Mali-450 MP4 GPU.
  • Atom X3-C3440, a quad-core Atom CPU platform that integrates a Cat 6 LTE 4G modem. It has an Mali-T720 MP2 GPU. This product appears to be one that is most likely to succeed in the market.
All feature a 32-bit memory interface with support for LPDDR2 (and DDR3/DDR3L with the X3-C3230RK). These are the first Intel products that have features (such as the integrated modem) that make them specifically suitable for the smartphone market. They also target cellular-enabled tablets.

The 3G products are a little behind the times, and their success is uncertain. It will be interesting observe whether Rockchip was able to develop the X3-C3230RK in time (one would expect Intel to have greater expertise/resources so that the other products will appear on the market first).

One notable fact is that these are among the first SoCs to integrate an ARM GPU core with a non-ARM CPU.

Intel announces first 14 nm Atom SoCs for tablets and all-in-ones


Intel also rolled out its first 14 nm Atom SoCs, the Atom x5 and x7 processor series (formely codenamed Cherry Trail) with  Intel Gen 8 graphics, targeting tablets and small screen all-in-ones.

Intel has also introduced a new stand-alone modem chip, XMM 7360, which support LTE Cat 10 and download speeds up to 450 Mbps, as well as wireless connnectivity products (including WiFi/Bluetooth, GNSS/GPS and NFC solutions).

Sources: MediaTek (MT6753 announcement), MediaTek (MT8173 announcement), Qualcomm (Snapdragon 820/Zeroth platform preview), Intel (MWC announcements), Intel Atom x3 Processor Series Brief

Samsung announces Galaxy S6 with Exynos 7420 SoC manufactured on "14nm" FinFET process

Od: Vegator
At the Mobile World Congress today (Sunday 1 March), Samsung announced the Galaxy S6 and Galaxy S6 Edge, featuring a numerous improvements over the previous generation Galaxy S5, including a SoC manufactured on Samsung's 14 nm FinFET-based process. The Galaxy S6 is planned to available in 20 countries starting on April 10th, 2015.

New model implement several improvements


The improvements in the new model include the following:
  • Exynos 7420 SoC manufactured on 14 nm FinFET process with 20 nm interconnects. The CPU is a big.LITTLE configuration with four Cortex-A57 and four Cortex-A53 cores, similar to Exynos 5433. The maximum clock speeds are 2.1 GHz and 1.5 GHz, respectively. Samsung claims 20% better performance and 35% better efficiency for the new chip when compared to Exynos 5433, which is manufactured using Samsung's 20 nm HKMG process.
  • The GPU has been rumoured to be a faster version of the Exynos 5433's Mali-T760 MP6 (either a higher clock rate or an MP8 configuration).
  • Early benchmarks indicate a significant increase in CPU and memory performance combined with a measurable increase in GPU performance (which is required because of the higher screen resolution).
  • Runs in 64-bit AArch64 mode, which has several advantages, as well as some disadvantages.
  • Uses new LPDDR4 SDRAM (3 GB), which has higher memory bandwidth at a given memory bus width due to higher effective clock speeds.
  • The cameras have been improved, including greater light gathering capability.
  • The 5.1" AMOLED screen's resolution is QHD (2560x1440), which is 77% more pixels than the FullHD (1920x1080) screen in Galaxy S5. The higher CPU, GPU and memory performance are essential to keep pace with increased demands caused by the higher resolution.
  • Utilizes the new UFS 2.0 interface for embedded flash memory, providing SSD-like performance according to Samsung.
  • Cat 6 LTE mode.
  • Touchwiz user-interface on top of 64-bit Android 5.0 is said to be more intuitive and less demanding in terms of processing requirements.
At the same time,  Samsung has dropped the MicroSD slot and the battery is non-removable. The battery capacity is also slightly smaller that of the Galaxy S5.

The Galaxy S6 Edge, like the Galaxy Note 4 Edge, features a screen that curves around the edges. It is priced significantly higher than the Galaxy S6, which will not be cheap either.

Quick ramp of 14nm FinFET process brings challenges to Samsung


The initial 14 nm FinFET process used by Samsung has been reported to use 20 nm interconnects with a 14 nm features size. As such it is more of an evolutionary step from 20 nm than full-blooded 14 nm FinFET would be, comparable to some degree with TSMC's 16FF process.

Still, Samsung will face a huge challenge ramping up the process in sufficient volume and acceptable yield rates to equip the high volume of Galaxy S6's expected. Rumours have mentioned low yield for the process in the recent past as Samsung started ramping up (test) production. Given the massive investment in the new process and non-optimal yield rates, it is unlikely that Samsung will significantly benefit financially from production of the chip in the near-term in terms of gross margin and other chip production-related metrics.

However, the performance lead of the Galaxy S6 made possible by the new chip could have significant positive implications for the sales and financial performance of Samsung's smartphone division, allowing Samsung to recoup some of its investment.

A few months ago, Samsung already signed an agreement with Apple whereby Samsung would supply part of the production capacity for future Apple processors. If this bears fruit it would allow Samsung to recoup more of its investment in 14 nm FinFET technology in the future.

Early benchmark performance impressive


In early benchmarks scores reported in Geekbench's result database, a device that probably is the Galaxy S6 shows impressive performance, well ahead of most existing SoCs and devices. In a direct comparison with an Exynos 5433-equipped Galaxy Note 4, the performance gain is fairly significant for most benchmarks (up to 30% for integer tests, higher for floating point), with a few negative outliers such as SHA2 and the Dijkstra integer subtest. The Dijkstra subtest also scores lower on other 64-bit AArch64 platforms, suggesting it suffers from particular AArch64 features such as the doubled size for pointer storage.

Memory performance is also significantly higher, aided by high clock rate and high amount of bandwidth delivered by the LPDDR4 memory interface, which unlike Qualcomm's Snapdragon 810 does not seem to have serious flaws.

Sources: AnandTech (Samsung annnounces the Galaxy S6 and Galaxy S6 Edge), AnandTech (Samsung Unpacked, MWC 2015 Live Blog), Geekbench Browser (Samsung SM-G925F)

Early benchmarks for MT6795 show high performance, suggest use of eight Cortex-A53 cores

Od: Vegator
MediaTek originally announced the MT6795, a SoC targeting the premium-level and performance segments of the smartphone market, in July 2014, with expectations of devices being commercially available to end users before the end of 2014. However, the chip was delayed (problems with the memory controller were reported) and competitive benchmark results are only now beginning to surface for the chip.

According to the announcement, the SoC was to have an octa-core CPU configuration with clock speeds up to 2.2 GHz, a strong dual-channel memory interface with support for LPDDR3 up to 933 MHz, 2K (2560x1600) display support. Other reports and information have suggested that it uses a PowerVR G6200 GPU, similar to the one used in MediaTek's MT6595, which can be seen as 32-bit predecessor of the new chip.

Confusion about processor cores, octa-core Cortex-A53 seems likely


The actual CPU cores used inside the MT6795 continue to be source of confusion. Initially understood to be an octa-core Cortex-A53 CPU configuration clocked at a high frequency, later a purported leaked MediaTek product roadmap surfaced that described the MT6795 as a big.LITTLE design that includes Cortex-A57 cores. However, a recent new entry in the Geekbench database suggesst that the chip actually has eight Cortex-A53 cores as originally suspected, as the IPC (instructions per cycle) of the integer and floating point subtests would be hard to reconcile with Cortex-A57 cores being present.

Geekbench results show mixed performance but high overall score


The Geekbench results show strong CPU performance, with the overall score being superior to that of available results for Snapdragon 810, which has a significantly higher cost design but has been plagued by performance issues, although it scores lower than Exynos 5433/Exynos 7 Octa with Cortex-A57 cores as used in the Galaxy Note 4. Note that MT6795 uses a less advanced 28 nm process compared to the 20 nm process used for Snapdragon 810 and Exynos 5433.

Single-score integer performance is not spectacular and below that of the previous generation high-end chips such as Snapdragon 801. Although this is compatible with the use of medium-performance Cortex-A53 cores, integer single-core performance is actually lower than the mid-range MT6752, despite the higher clock rate, pointing to continuing hardware performance problems with the chip. The Dijkstra benchmark result is particular low. This benchmark has a lot of external memory access and likely branches a lot, taxing certain elements of the CPU and SoC that simpler CPU benchmarks do not. It may be affected by the doubled address size in AArch64 mode, either through the increased size of pointer storage or reduced efficiency of the branch prediction unit inside the processor core.

Single core floating point performance in the Mandelbrot benchmark is higher than the MT6752 and actually compatible with the Cortex-A53 core running at 2.1 GHz, close to the originally envisaged maximum clock speed for the MT6795. Multi-core performance in this subtest is impressive, with a score that is higher than most existing SoCs including Exynos 7 Octa, which employs faster Cortex-A57 cores.

Finally, the dual-channel memory interface seems to working reasonably well in the tested revision of the chip/development board, with memory scores consistent with an optimized dual-channel interface, and higher, for example, than those of Exynos 5433. However, they are generally lower than those of the 32-bit MT6595.

One caveat is that the MT6795 entry is running in AArch64 mode, while the other devices were running in AArch32 (32-bit ARMv8) or 32-bit ARMv7 mode.

Average single-core CPU performance, strong multi-core performance


In a direct comparison with the MT6752, which has a comparable CPU configuration but clocked lower and has only a 32-bit memory interface, the MT6795 is only slightly faster, although the MT6795 uses a full 64-bit AArch64 instruction set model, while the tested MT6752 configurations use AArch32 with partial use of ARMv8 features. There are a few anomalous results, including a low score for the MT6795 in the single-core AES benchmark, and as mentioned it also scores significantly lower in the Dijkstra benchmark. Floating point performance is consistently higher for the MT6795 (more than the increase in clock rate would explain), which may be caused by the higher-performance memory subsystem of the MT6795 and/or the increased number of floating point registers available in AArch64 mode.

The MT6795 is clearly slower than its 32-bit predecessor MT6595 (which uses high-performance Cortex-A17 and Cortex-A7 cores in a big.LITTLE configuration) in most metrics, with only the heavy weighting and large performance gain for the AES and SHA1 cryptography tests  (due to the new ARMv8 instruction set) shifting the advantage for the overall score towards the MT6795.

When making a comparison with a median entry for the high performance Exynos 5433 (Exynos 7 Octa) inside the Samsung Galaxy Note 4, the MT6795 fairly consistently shows clearly lower single-core performance but higher multi-core performance.

MT6795 likely to be most cost-effective performance segment processor on the market


The exclusive use of Cortex-A53 CPU cores, and not the much more expensive and die-space consuming Cortex-A57 (or, in a 32-bit comparison, Cortex-A15/A17 cores), has positive implications for the cost of the chip. Die space dedicated to the CPU cores will be relatively low, although L2 caches will take considerable space when configured with a size that matches the desired performance level and market segment. Overall, the chip is likely to be attractive in terms of performance/dollar for the performance segment.

In terms of SoC optimizations, the chip would probably work better with the employment of additional ARM IP such as a Mali T760 or Mali-T800 series GPU, which offers advantages in combination with ARM cores such as Cortex-A53 in tandem with techniques such as AFBC, smart composition and transaction elimination, and new interconnect buses within the chip. SoCs like the MT6752 probably benefit from these optimizations, while the MT6795 cannot do so fully because of the non-ARM GPU. It seems likely that the MT6795 will be superseeded in next generation products to be announced by MediaTek in the future by a similar SoC with an ARM Mali-T760 or T800 series GPU.

Update (2 March): Based on a closed-door presentation event at the MWC, MediaTek appears to have rebranded MT6795 as Helio X10 with future Helio P series products also being announced.

Sources: MediaTek (MT6795 announcement), Geekbench browser

MediaTek announces Helio P10 and MT6753 arrives in shipping devices

Od: Vegator
MediaTek has announced Helio P10 (MT6755), a performance mid-range smartphone SoC that is the successor of MT6752. Featuring an octa-core Cortex-A53 configuration, Helio P10 improves upon MT6752 by using TSMC's new 28HPC+ manufacturing process, which delivers power efficiency and performance improvements while remaining relatively cost-effective. It can reach a higher maximum CPU clock speed up to 2 GHz and upgrades the GPU to a Mali-T860 MP2. It is expected to be commercially available in end devices by the end of 2015.

Features shared with Helio-X10


The new SoC  incorporates a few features from Helio X10 (MT6795), MediaTek's current high-end offering, including dual ISPs with 21MP camera support and improved capture capability, as well as improved audio quality.

Otherwise, the SoC has significant similarities to MediaTek's MT6752 which it succeeds, most likely including a 32-bit external memory interface, which keeps SoC cost and phone PCB cost down. With MT6752, MediaTek already demonstrated the ability to achieve memory performance adequate for a 1080p device within the constraints of a 32-bit memory interface.

The 28HPC+ process is an upgrade of the existing 28HPC (high-performance compact) process (which is also relatively new, used by Allwinner's A83T and other SoCs), which improves performance and cost relative to the established 28HPM (high-performance mobile) process. Existing MediaTek chips like MT6752 and MT6795 most likely use 28HPM, which is established and has also been used for previous-generation SoCs such as MT6592 and Snapdragon 801/805.

MediaTek migrating to big.LITTLE CPU configurations in new SoCs


A significant departure from existing octa-core MediaTek SoCs such as MT6752 and Helio X10 (MT6795) is the pseudo-big.LITTLE CPU configuration, whereby one cluster of four Cortex-A53 cores is clocked at a higher frequency (up to 2 GHz in this case), while the second of cluster Cortex-A53 cores is optimized for lower frequencies, being clocked at a lower maximum frequency (1.1 GHz according to AnandTech).

Together with the previously announced high-end Helio X20 (MT6797) and tablet/Chromebook-oriented chips such as MT8173, Helio P10 marks a migration to (pseudo-)big.LITTLE, hierarchical CPU designs at MediaTek. While symmetrical octa-core designs such as MT6752 and MT6795 reach very high multi-core processing power by allowing all cores to run at the maximum frequency, there are signs that this configuration impacts power efficiency for tasks that require less CPU power, which can be run on power-optimized low-frequency cores.

In practice, this may be reflected in somewhat mediocre standby battery life for smartphones using MT6752 or MT6795, even though power efficiency for demanding tasks that utilize all cores is likely to be pretty good.

Budget mid-range MT6753 reaches end-market


Meanwhile, MediaTek's previously announced MT6753, which is a cost-effective budget mid-range SoC, has arrived in commercially shipping device in the form of Meizu M2 Note. Despite the name chosen by Meizu, the new model actually has lower performance than the existing Meizu M1 Note, because the MT6753  is a less costly, lower end chip when compared to to the MT6752 inside the M1 Note, with considerably slower maximum CPU speeds for the eight CPU cores, as well as a lower performance GPU. There are also signs that the memory interface and the actual memory frequency used by the M2 Note is slower. The lower cost of the MT6753 platform is reflected in the low selling price of the Meizu M2 Note.

MT6753 implements several cost-reducing features, including a lower maximum clock speed (reported to be 1.3 GHz for the M2 Note), most likely associated with a cheaper manufacturing process (either 28LP or 28HPC) than the 28HPM process of the MT6752. A significant factor for lower performance is likely to be a reduced size of the L2 CPU cache inside the MT6753. MT6753 is likely to become a significant volume driver in MediaTek's 4G product line.

However, early Geekbench entries for the Meizu M2 Note suggest that the CPU cores of the MT6753 SoC used in this model are mostly unable to reach the planned clock frequency. The Geekbench results are mostly consistent with an average maximum CPU clock speed of about 1.1 GHz, significantly lower than the 1.3 GHz reported by the OS and the 1.5 GHz mentioned when the MT6753 was originally announced a few months ago. My following blog article about the use of AArch64 provides more details on this subject.

MT6753 has lower-performance GPU than MT6752


MT6753 also has a significantly lower-performance and smaller GPU (Mali-T720 MP3), compared to the Mali-T760 MP2 inside MT6752. MT6753 marks the first Mali implementation with three pixel processing cores; previous Mali GPUs either had one, two, four, six or eight pixel processing cores, Most likely, Mali-T720 does not have the memory bandwidth usage optimization that are present in Mali-T760, which together with the more limited pixel processing throughput means that devices with a 1080p display such as the Meizu M2 Note may be impacted in terms of 1080p game performance and power efficiency for graphics-intensive operations.

World modem support in new MediaTek platforms


All new MediaTek SoCs (including Helio P10 (MT6755), MT6753, the low-end quad-core MT6735 and the announced high-end Helio X20 (MT6797)) have world-modem support, facilitating compatibility with more cellular networks used worldwide, including legacy CDMA networks in the US and other countries. This makes MediaTek SoCs more attractive to smartphone manufacturers targeting multiple or worldwide markets.

Sources: MediaTek (Helio P10 announcement), AnandTech (Helio P10 article)

Updated 6 June 2015.

HiSilicon introduces Kirin 930/935, a performance-oriented Cortex-A53-based SoC

Od: Vegator
Huawei has introduced the Huawei P8 and P8max smartphones, featuring the Kirin 930 and Kirin 935 SoCs from Huawei's  HiSilicon semiconductor division. The octa-core Kirin 930 SoC is a performance-oriented SoC featuring only Cortex-A53 CPU cores. With a maximum clock frequency in excess of 2.0 GHz, it bears similarities to MediaTek's MT6795, but the use of a pseudo big.LITTLE configuration (four Cortex-A53 cores clocked up to 2.0 GHz and four Cortex-A53 cores clocked up to 1.5 GHz, for a total of eight cores) is reminiscent of Qualcomm's midrange Snapdragon 615 SoC, which runs at lower clock frequencies.

Huawei also introduced high-end models of both the P8 and P8max with larger storage capacity featuring the Kirin 935 SoC, which is a higher-clocked version of Kirin 930. The Huawei P8max is a smartphone with an unusually large 6.8" display.

SoC is targeted at performance-oriented devices


The Huawei P8 models are higher-priced performance-oriented smartphones, and the characteristics of the SoC match this segment. Apart from the high maximum clock speed of the Cortex-A53 cores, the external RAM interface is likely to be a dual-channel 32-bit configuration like previous performance-oriented SoCs from HiSilicon. Presentation materials from Huawei describe the Cortex-A53 cores in the faster cluster of four CPUs as being of a special, performance-enhanced type, which probably reflects the application of ARM's PoP core-hardening technology whereby the core is optimized for running at a specific frequency and a particular power profile, trading performance against die size. The process technology used is likely to be TSMC's proven 28HPM process.

The SoC is reminiscent of MediaTek's recently introduced MT6795 (Helio-X), which also targets the performance segment with an octa-core Cortex-A53 CPU configuration. MediaTek's SoC has been reported to have been adopted by competitors of Huawei such as HTC and Xiaomi.

Previous generation Mali-T628 MP4 GPU used


Rather than using an updated current-generation GPU like Mali-T760, the specs sheet for the P8max indicates the Kirin 930/935 SoCs continue to use the Mali-T628 MP4 GPU that was previously used in the Kirin 920 SoC. This GPU core is not known for great power efficiency, although there are suggestions that the more efficient Mali-T760 (which features memory bandwidth optimizations) has a relatively high silicon area and cost.

HiSilicon's new SoC line-up uses only Cortex-A53 CPU cores


Apart from Kirin 930, HiSilicon has also introduced the Kirin 620 SoC, which is an octa-core Cortex-A53 based SoC for the cost-sensitive segment, clocked up to 1.2 GHz and with a single-channel memory interface. This means Huawei now has in-house Cortex-A53-based SoCs suitable for most of its smartphone product range.

Early benchmarks appear for Cortex-A72-based SoC

Od: Vegator
ARM recently announced the new Cortex-A72 processor core, which is an improved version of the existing high-performance Cortex-A57 processor core.

Alongside the Cortex-A72 CPU core, ARM also announced the CCI-500 interconnect technology as well as the high-end Mali-T880 GPU. Devices incorporating the combination of these technologies are expected to become available in 2016.

However, SoCs using the Cortex-A72 CPU are likely to become available earlier. Qualcomm and MediaTek have both announced SoCs using the Cortex-A72 core with commercial availability in the second half of 2015, suggesting that the CPU core itself is at an advanced stage of introduction. Already, early benchmarks for MediaTek's MT8173 tablet SoC that incorporates the Cortex-A72 have become available.

Cortex-A72 appears to be enhanced version Cortex-A57 optimized for next-generation processes


In its announcement press release from 3 February 2015, ARM claims that more than ten partners have already licensed Cortex-A72, including HiSilicon, MediaTek and Rockchip. Cortex-A72 is based on ARM's ARMv8-A instruction set architecture, and can be combined with the existing Cortex-A53 in a big.LITTLE configuration. Cortex-A72 seems to be positioned as a replacement for Cortex-A57. The similarities with Cortex-A57 are very apparent, for example in the identically sized L1 instruction and data caches, and a feature set that is otherwise very similar.

On a 16 nm FinFET process, the core can sustain operation at speeds up to 2.5 GHz within the constraints of a mobile power envelope (e.g. smartphones), with scalability to higher speeds for larger form-factor devices. However, the first announced devices, such as MediaTek's MT8173, appear to use older processes such as the tried-and-trusted 28 nm HPM process at TSMC, so they are likely to have a lower maximum clock speed.

ARM claims increased performance and power efficiency, although these claims seem to be based on implementation on next-generation processes such as 16 nm FinFET that deliver a significant intrinsic improvement in these metrics. ARM mentions micro-architectural improvements that result in enhancements in floating point, integer and memory performance. When implemented on a 16 nm FinFET process, ARM expects Cortex-A57 to provide 85% higher performance when compared to the Cortex-A57 core on a 20 nm process within a similar smartphone power budget.

Overall, the differences with Cortex-A57 appear to be relatively minor, so that Cortex-A72 is best viewed as an enhanced version of Cortex-A57 that is optimized for next-generation processes such as 16 nm FinFET. Nevertheless, the first SoCs to use the Cortex-A72 core will be manufactured using a less advanced process.

Benchmarks appear for MediaTek's MT8173


MediaTek's MT8173 is a mid-range tablet processor mainly targeting Wi-Fi-only tablets, since it does not have an integrated modem. It has two Cortex-A72 cores and two Cortex-A53 cores in a big.LITTLE configuration. Probably manufactured using the established 28HPM process at TSMC, the maximum clock speed of the Cortex-A57 cores is likely to be lower that the target for 16 nm FinFET, although MediaTek claims a clock speed up to 2.4 GHz, while a much lower frequency is apparent in early benchmarks results.

The chip also features a PowerVR GX6250 GPU, which delivers higher performance than the G6200 GPU used inside MediaTek's existing MT8135 and MT6795.

Recently, early benchmarks for a MT8173 development board have appeared both in the Geekbench Browser and in the results database of GFXBench. The first Geekbench results already appeared in December 2014. The latest set of Geekbench results date from the end of February 2015, although they do show a certain amount variation that may reflect thermal throttling.

Single-core performance good, but not spectacular


As expected, the Geekbench results show good single-core performance, albeit not spectacular. As shown in the following table, singe-core performance is in line with Cortex-A57-based SoCs such as Exynos 5433 and Exynos 7420. It should be noted that the MT8173 test SoC is most likely manufactured at 28 nm with a corresponding relatively low maximum CPU clock speed, while Exynos 5433 and 7420 are manufactured using smaller leading edge processes at Samsung.


SoC          "big" CPU                    Arch     JPEG (int)  Lua (int)   Mandelb. (fp)
                                                   Comp. IPC         IPC         IPC
MT8173       2 x 1.6? GHz Cortex-A72      AArch32  1310  2.13  1380  2.10  1064  1.95
Exynos 5433  4 x 1.80 GHz Cortex-A57r1p0  AArch32  1456  2.10  1397  1.89  1174  1.91
Exynos 7420  4 x 1.97 GHz Cortex-A57r1p0  AArch64  1481  1.97  1409  1.74  1198  1.92

In this table, to determine the IPC index I have made an educated guess about the actual clock speed of MT8173 when running the benchmarks. Geekbench reports a 1.40 GHz clock speed (which probably applies to the Cortex-A53 cores), 1.6 GHz seems to be a good match, providing just a little better IPC than Cortex-A57. Note that Exynos 7420 runs in AArch64 mode, which skews direct IPC comparisons.

Practical implications unclear


Without knowing the exact clock speed of the Cortex-A72 cores, it is hard to draw conclusions about the actual IPC improvement over Cortex-A57. If the MT8173 uses a 28 nm process, the ability to approach the single-core performance of Samsung's Exynos 7420 manufactured using 14 nm FinFET process is impressive. However, although MediaTek demonstrated the MT8173 in an actual tablet at MWC, it is unclear what kind of device the Alps development board in the benchmark entries actually represents, so it remains to be seen whether the benchmarks actually reflect the power budget of a tablet.

The multi-core performance reported is not very impressive, as expected because of the relatively small number of CPU cores. The JPEG Compress multi-core score shows CPU scaling factor of 2.72, which is good and implies utilization of the Cortex-A53 cores. The Mandelbrot floating point benchmark shows similar scaling.

However, the Lua integer benchmark has a very low multi-core scaling factor of 1.41, which is lower than expected, even when allowing for the limited number of cores. For example, MediaTek's MT6795 achieves multi-core scaling of 7.5 in this benchmark, and the Exynos chips range from 3.9 to 5.0. Other chips with a low multi-core scaling factor for Geekbench's Lua subtest include Snapdragon 810 (Cortex-A57-based), MediaTek's MT6595 (Cortex-A17-based) and NVIDIA's Denver-based Tegra-K1 SoC. There are indications that this benchmark test heavily depends on on-chip cache (primarily L2 cache) size and speed.

GPU performance of MT8173's PowerVR GX6250 GPU improves on G6200


The MT8173 test device's GPU performance as shown in GFXBench results database is not overly impressive, but suitable for a mid-range chip and an improvement over the PowerVR G6200 GPU used in other MediaTek SoCs such as MT6595 and MT6795. In the T-Rex Offscreen benchmark, the MT8173 registers a score of 1487, higher than the 1311 of the MT6595 (G6200)-equipped Meizu MX4. In the GFXBench 3.0 low-level tests, alpha blending scores higher than the MT6595 while the other low-level scores are comparable.

Sources: ARM (Cortex-A57 announcement press release), AnandTech (MediaTek MT8173 article), MediaTek (MT8173 announcement), Geekbench Browser (MT8173 test device results), GFXBench (MT8173 test device result)

Updated 10 March 2015.

A deeper look at graphics benchmark results, including GFXBench 3.1 and Basemark X

Od: Vegator
In this post I will take a closer at graphics benchmark results for different SoCs. I will look beyond just GFXBench (for which a new version has appeared), because the workload tested by well-known GFXBench tests such as T-Rex and Manhattan is not necessarily reflective of the actual gaming experience. Alternative benchmarks exist, such as Basemark X which uses the Unity engine that is commonly used in games.

GFXBench 3.1 released for OpenGL ES 3.1, Snapdragon 805 does well


Kishonti recently released a new version of GFXBench, GFXBench 3.1 for OpenGL ES 3.1, that includes tests for the OpenGL ES 3.1 API standard supported by many recent devices. A few results from the new benchmark tests are already available, with the Adreno 420 GPU inside Snapdragon 805 closing most of the performance gap with the Mali-T760 MP6/MP8 in Samsung's Exynos SoCs in the Manhattan 3.1 test.

                                                      Offscreen Manhattan Manhattan
Device               SoC             GPU              T-Rex        3.0       3.1

NVIDIA Shield Tablet NVIDIA K1-32    Tegra K1 GPU        3692     1979      1443  
HTC One M9           Snapdragon 810  Adreno 430          2732     1413
Galaxy S6 Edge       Exynos 7420     Mali-T760 MP8?      3312     1607       793
Sams. Galaxy Note 4  Snapdragon 805  Adreno 420          2386     1153       773
Samsung Galaxy S6    Exynos 7420     Mali-T760 MP8?      3314     1609       634
Sams. Galaxy Note 4  Exynos 5433     Mali-T760 MP6       2163     1110       436
HTC One M8           Snapdragon 801  Adreno 330          1608      768
Teclast X98 Air      Atom Z3736F     Intel HD            1014      564       307
Google Nexus 10      Exynos 5250     Mali-T604 MP4        818      351       185

NVIDIA's Tegra 32-bit version of Tegra K1 leads (the 64-bit Denver-based version of Tegra K1, and Tegra X1, have not yet been tested). Performance of Snapdragon 805 as implemented in certain models of the Samsung Galaxy Note 4 holds up better in the Manhattan 3.1 test than Samsung's Exynos SoCs with Mali-T760 MP6/MP8. Whereas Exynos 7420 (used in the Galaxy S6) has a clear advantage in existing benchmarks (1609 vs 1153 for Manhattan and 3314 vs 2386 for T-Rex), it loses that advantage in the new Manhattan 3.1 test (although the Galaxy S6 Edge benchmarks result suggests it is still slightly superior). Intel's Baytrail SoCs seem to hold up relatively well looking at the result for an Atom Z3736F-based tablet, albeit at a lower performance level.

GFXBench 3.1 results for Snapdragon 801 and the new Snapdragon 810 are not yet available. However, given the fact that GFXBench appears to generally do well on Snapdragon SoCs, they can be expected to score fairly highly. I'll say more about the apparent advantage for Qualcomm's SoC in GFXBench in the final section of this article.

Basemark X is a useful alternative to GFXBench


Basemark X is a gaming benchmark that utilizes the Unity engine that is commonly used in games, and developer Rightware claims that it actually reflects practical performance in games. Although it does include an on-screen demo, the actual benchmark scores appear to be derived from off-screen rendering at a fixed resolution, so that benchmark results can be compared objectively between different devices.

Previous generation SoCs: MT6582 beats Snapdragon 400 in Basemark X


Taking a look at previous-generation cost-sensitive SoCs, while MediaTek's ubiquitous quad-core 3G SoC MT6582 (which supports Open GL ES 2.0 only, through its Mali-400 MP2 GPU) scores lower than Snapdragon 400 in GFXBench's OpenGL ES 2.0-based T-Rex test (about 230 vs 330), in Basemark X MT6582-based devices score higher than Snapdragon 400 based devices. This is despite the fact that Snapdragon was/is often employed in devices with a considerably higher selling price than MT6582-based devices.

Device               SoC             GPU                 Display*   Medium   High

Samsung SM-G800F     Exynos 3470     Mali-400 MP4        1280x720    7527    2712
Vodafone 985N        MT6582          Mali-400 MP2         960x540    4950    1717
Acer E53             MT6582          Mali-400 MP2        1280x720    4870    1694
Wiko Rainbow         MT6582          Mali-400 MP2        1280x720    4826
Galaxy S3 Neo        Snapdragon 400T Adreno 305          1280x720    4540    1551
Moto G (XT1032)      Snapdragon 400  Adreno 305          1280x720    4440
HTC Desire 816d      Snapdragon 400T Adreno 405          1280x720    4354    1441
Samsung SM-A500F     Snapdragon 410  Adreno 306          1280x720    4132    1900
Samsung SM-A300F     Snapdragon 410  Adreno 306           960x540    4076    1892
Samsung SM-G530H     Snapdragon 410  Adreno 306           960x540    3987    1690
Samsung SM-G800A     Snapdragon 400  Adreno 305          1280x720    3946    1362
HTC Desire 820q      Snapdragon 410  Adreno 306          1280x720    3786

* While Basemark X is independent of display resolution in terms of rendering, the
memory bandwidth used for screen refresh has some impact, giving lower-resolution
devices a small advantage.
Notes: Samsung SM-G800F is the Galaxy S5 Mini (Exynos version), while SM-G800A is a Snapdragon 400 running at the non-standard maximum clock speed of 1.4 GHz; Vodafone 985N is the Vodafone Smart 4 Power; Acer E53 is the Acer Liquid E700; Galaxy S3 Neo runs the Snapdragon 400 SoC at a non-standard maximum speed of 1.4 GHz; HTC Desire 816d runs the Snapdragon 400 SoC at 1.6 GHz; SM-A500F is the Galaxy A5, while SM-A300F is the Galaxy A3; SM-G530H is the Galaxy Grand Prime.

For both the medium detail and high detail settings, MT6582-based devices consistently score higher in Basemark X than Snapdragon 400 and also Snapdragon 410-based devices for the medium detail test, which gives a different picture than the one you get from just looking at GFXBench's T-Rex benchmark

Snapdragon 410 performs worse than Snapdragon 400 in Basemark X medium-detail


Also notable is that Snapdragon 410, which is the successor of the Snapdragon 400 and would normally be expected to improve performance, actually has lower performance in practice as judged by the Basemark X medium detail benchmark. This matches earlier findings of performance flaws in Snapdragon 410. When running the high detail Basemark X benchmark, Snapdragon 410 does better and beats Snapdragon 400.

Mid-range SoCs: Snapdragon 615 and MT6752 closely matched


When running GFXBench, Snapdragon 615 and MT6752 are closely matched, with Snapdragon 615 scoring about 830 to 850 in T-Rex while MT6752 scores just above 870. For T-Rex, devices using MediaTek's prior-generation octa-core MT6592 score in the range 650 to 750. In the OpenGL ES 3.0 API-based Manhattan benchmark, Snapdragon 615 and MT6752 are very closely matched, both scoring around 360. We will also take a look at Basemark X results.

The following table shows Basemark X results for the new competing mid-range SoCs Snapdragon 615, MT6752 and HiSilicon's octa-core Hi6210 (Kirin 620), as well as for the prior-generation octa-core MT6592 from MediaTek.

Device               SoC             GPU                 Display*   Medium   High

Lenovo P70-A         MT6752          Mali-T760 MP2       1280x720   11311 
Meizu M1 Note        MT6752          Mali-T760 MP2       1920x1080  11168    4636
HTC Desire 816G      MT6592          Mali-450 MP4        1280x720   10984
Huawei CHE2-TL00     Hi6210          Mali-450 MP4        1280x720   10546    3439
Oppo R8106           Snapdragon 615  Adreno 405          1920x1080  10277    4846 
HTC Desire 820       Snapdragon 615  Adreno 405          1280x720   10133    4814
Samsung SM-A700FD    Snapdragon 615  Adreno 405          1920x1080  10052    4757
Archos 50C Oxygen    MT6592          Mali-450 MP4        1280x720    9867    3702
HTC Desire 616d      MT6592M         Mali-450 MP4        1280x720    7976    3045

* While Basemark X is independent of display resolution in terms of rendering, the
memory bandwidth used for screen refresh has some impact, giving lower-resolution
devices a small advantage.
Notes: SM-A700FD is the Galaxy A7; Huawei CHE2-TL00 is a new version of the Honor 4X.

When running the standard medium-detail version of Basemark X, MediaTek's MT6752 has  a moderate advantange over Snapdragon 615, while at the high detail setting Snapdragon 615 has a small advantage. Huawei's Kirin 620 performs adequately and just ahead of Snapdragon 615 in the medium detail setting.

MediaTek's prior-generation octa-core MT6592 with Mali-450 MP4 GPU keeps up relatively well in Basemark X,  with certain models (e.g. HTC Desire 816G) actually beating Snapdragon 615 in the medium detail setting.

Performance-oriented SoCs with Basemark X


The following table shows Basemark X results for several performance-oriented mobile SoCs.

Device               SoC             GPU                 Display*   Medium   High

Samsung Galaxy S6    Exynos 7420     Mali-T760 MP6       2560x1440  36017
Galaxy S5 LTE-A      Snapdragon 805  Adreno 420          1920x1080  32685   18334
Google Nexus 6       Snapdragon 805  Adreno 420          2560x1440  30362   20265
Sams. Galaxy Note 4  Snapdragon 805  Adreno 420          2560x1440  31963   21152
Sams. Galaxy Note 4  Exynos 5433     Mali-T760 MP6       2560x1440  29335   19019 

Apple iPad Air 2     Apple A8X       PowerVR Series 6    2048x1536  41700   29239
Google Nexus 9       NVIDIA K1-64    Tegra-K1 GPU        2048x1536  37939   28646
Apple iPad Mini 3    Apple A7        PowerVR Series 6    2048x1536  26499   14780
Teclast X98 Air      Atom Z3736F     Intel HD            2048x1536  14825    7160
Teclast P90HD        Rockchip RK3288 Mali-T764           2048x1536  13053    5645
Onda V989 Core8      Allwinner A80   PowerVR G6230       2048x1536  11004    5724

Meizu MX4 Pro        Exynos 5430     Mali-T628 MP6       1920x1200  25547   12674
Samsung SM-G900A     Snapdragon 801  Adreno 330          1920x1080  25178   11930
Samsung SM-G850F     Exynos 5430     Mali-T628 MP6       1280x720   21872   10666
Meizu MX4            MT6595          PowerVR G6200       1920x1200  17038    7817
Huawei MT7-TL10      Kirin 925       Mali-T624 MP4       1920x1080  15973    6802

* While Basemark X is independent of display resolution in terms of rendering, the
memory bandwidth used for screen refresh has some impact, giving lower-resolution
devices a small advantage.
Notes: SM-G900A is the Samsung Galaxy S5 (US version), Huawei MT7-TL10 is the Huawei Mate 7.

Looking at the ultra-high-end smartphone segment (mostly with a display resolution of 2560x1440), Exynos 7420 provides superior performance in Basemark X. Snapdragon 805 follows, a small distance ahead of Exynos 5433 as used in the Samsung Galaxy Note 4.

In the high-end tablet segment, Apple's iPad Air 2 with the Apple A8X leads, but the Nexus 9 with NVIDIA's Tegra K1 (64-bit version) comes fairly close. Apple's prior generation SoCs also delivers good performance, while Intel's current Baytrail SoC for the tablet market outperforms two high-end chips from established Chinese players in the tablet SoC market, Rockchip's RK3288 and Allwinner A80 Octa.

Mainwhile, in the mainstream performance smartphone segment, Snapdragon 801 (in the past the performance leader in the market) still provides good performance, but is actually just beaten by the 32-bit Exynos 5430 in the Meizu MX4 Pro. The chip is also used in the Galaxy Alpha (for which it provides higher-than-necessary performance given its relatively low screen resolution), while the performance of MediaTek's MT6595 SoC, while not bad, falls short of most other high-end solutions. HiSilicon's Kirin 925 as implemented in the Huawei Mate 7 is just behind.

Conclusion


It appears that just concentrating on GFXBench may give a misleading picture with regard to 3D graphics performance of mobile SoCs. In particular it is apparent that Qualcomm's Snapdragon SoCs consistently do better in GFXBench than in other benchmarks such as Basemark X. This is particularly true for the lower-end Snapdragon 400 and higher-end Snapdragon 800 series; for Snapdragon 615, results are more consistent across different benchmarks.

Basemark X, which utilizes the Unity game engine commonly used in mobile games, may more accurately reflect real-world performance.

Sources: Rightware Power Board (Basemark X benchmark results), GFXBench results database

Updated 5 March 2015: Add Galaxy S6 Edge result for GFXBench 3.1.
Updated 15 March 2015.

New mobile SoCs announced at MWC

Od: Vegator
At the Mobile World Congress this week, several new mobile SoCs are being announced.

MediaTek announces cost-reduced MT6753 for smartphones


MediaTek anounced two mobile SoCs, the MT6753 for smartphones and the MT8173 for tablets.

The MT6753 appears to be a cost-reduced version of the successful MT6752, equpped with "WorldMode" modem technology. By offering compatibility with the CDMA2000 standard, it gives customers worldwide greater diversity and flexibility in their product layouts, according to MediaTek. Features include an octa-core Cortex-A53 CPU up to 1.5 GHz and a Mali-T720 GPU with an unspecified number of cores. ARM's Mali-T720 GPU is positioned at a significantly lower performance bracket than the Mali-T760 used in the MT6752, positioning the MT6753 below the MT6752 in terms of cost and performance.

The MT6753 is described as being compatible with the previously announced MT6735 for entry-level smartphones. The MT6735 has four Cortex-A53 cores instead of eight but otherwise has a similar configuration with a Mali T720 GPU.

High-performance MT8173 tablet SoC uses small big.LITTLE clusters with Cortex-A72


The MT8173 is a high-performance tablet processor (without integrated modem) that utilizes ARM's new Cortex-A72 core in a big.LITTLE configuration. By using only two Cortex-A72 cores (clocked up to 2.4 GHz) as well as two Cortex-A53 cores, the chip has a lower cost than would be the case with the four-by-four core configuration commonly used for big.LITTLE designs, while still providing good performance.

The Cortex-A72 core, the successor of Cortex-A57, appears to be seeing quick adoption as Qualcomm has already announced performance-segment smartphone SoCs (Snapdragon 618 and 620) featuring the core.

MediaTek has previously used a similar two-by-two big.LITTLE configuration in its MT8135(V) tablet SoC, which has two Cortex-A15 cores and Cortex-A7 cores. This chip was used in Amazon tablets but otherwise did not see much adoption.

Other features include a PowerVR GX6250 GPU, which is part of Imagination's Series 6XT family, with higher performance and efficiency than the G6200 GPU used in chips such as the MT8135 and MT6595.

Other tablet SoCs not yet publicly announced by MediaTek


Meanwhile, tablet product announcements by Lenovo also refer to the MT8161 and MT8165 SoCs, which have not been announced. From the specifications of the Lenovo Tab 2 A8 which is using it, the MT8161 appears to be a tablet SoC without modem with quad-core Cortex-A53 CPU running up to 1.3 GHz, while the MT8165 (used in the Tab 2 A10) is a similar SoC with the CPU running up to 1.5 GHz. The 4G version of the Lenovo tablets come equipped with the MT8735 (Tab 2 A8) and MT8732 (Tab 2 A10). These chips are the tablet versions of the MT6735 and MT6732 smartphone SoCs.

MT6795 renamed to Helio X10


In a closed-door presentation at MWC, MediaTek also presented the Helio X10 smartphone SoC, featuring a 64-bit octa-core CPU up to 2.2 GHz, 120 Hz display refresh rate and H.265 video encode up to 4K2K @ 30 fps. A photograph of a slide taken at the presentation strongly suggests that Helio X10 is nothing other than the delayed MT6795 SoC, whose specifications closely match. Devices using this chip are likely to have already started production. MediaTek also talked about the Helio P series, a high-performance platform, which will make its way into devices before the end of the year.

Qualcomm gives preview of next-generation Snapdragon 820 SoC


In a press release, Qualcomm has given a preview of the Snapdragon 820, which utilizes Qualcomm's new custom 64-bit CPU architecture for mobile devices called Kryo. The chip will start sampling in the second half of 2015 according to Qualcomm, with devices becoming available in 2016. It will be manufactured on a next-generation FinFET process (which probably means TSMC's 16FF+, but Samsung cannot be excluded). In the press release, Qualcomm does not mention whether the chip will conform to ARM's ARMv8 instruction set architecture.

In conjuction with the Snapdragon 820, Qualcomm also announced the Zeroth hardware/software platform focusing on device intelligence features including video and audio recognition techniques (such as visual object and face recognition).

Intel introduces tablet and smartphone SoCs with integrated modem


Intel has finally introduced SoCs with an integrated cellular modem in its Atom system-on-a-chip product line. The former SoFIA platform has been renamed to Atom X3 and features multi-core 64-bit Atom processors with integrated 3G or 4G LTE modem technology. The following products are available:
  • Atom X3-C3130, which has dual-core Atom CPU running up to 1.0 GHz and integrates a 3G modem. It features Mali-400 MP2 GPU. Maximum display resolution is 1280x800. It appears to be in the same market segment as MediaTek's previous-generation 3G SoCs such as MT6572 and MT6582 and other SoCs that are already on the market.
  • Atom X3-C3230RK, which was developed by Intel partner Rockchip following the agreement announced last year. It has quad-core Atom CPU, integrates a 3G modem and features a Mali-450 MP4 GPU.
  • Atom X3-C3440, a quad-core Atom CPU platform that integrates a Cat 6 LTE 4G modem. It has an Mali-T720 MP2 GPU. This product appears to be one that is most likely to succeed in the market.
All feature a 32-bit memory interface with support for LPDDR2 (and DDR3/DDR3L with the X3-C3230RK). These are the first Intel products that have features (such as the integrated modem) that make them specifically suitable for the smartphone market. They also target cellular-enabled tablets.

The 3G products are a little behind the times, and their success is uncertain. It will be interesting observe whether Rockchip was able to develop the X3-C3230RK in time (one would expect Intel to have greater expertise/resources so that the other products will appear on the market first).

One notable fact is that these are among the first SoCs to integrate an ARM GPU core with a non-ARM CPU.

Intel announces first 14 nm Atom SoCs for tablets and all-in-ones


Intel also rolled out its first 14 nm Atom SoCs, the Atom x5 and x7 processor series (formely codenamed Cherry Trail) with  Intel Gen 8 graphics, targeting tablets and small screen all-in-ones.

Intel has also introduced a new stand-alone modem chip, XMM 7360, which support LTE Cat 10 and download speeds up to 450 Mbps, as well as wireless connnectivity products (including WiFi/Bluetooth, GNSS/GPS and NFC solutions).

Sources: MediaTek (MT6753 announcement), MediaTek (MT8173 announcement), Qualcomm (Snapdragon 820/Zeroth platform preview), Intel (MWC announcements), Intel Atom x3 Processor Series Brief

Samsung announces Galaxy S6 with Exynos 7420 SoC manufactured on "14nm" FinFET process

Od: Vegator
At the Mobile World Congress today (Sunday 1 March), Samsung announced the Galaxy S6 and Galaxy S6 Edge, featuring a numerous improvements over the previous generation Galaxy S5, including a SoC manufactured on Samsung's 14 nm FinFET-based process. The Galaxy S6 is planned to available in 20 countries starting on April 10th, 2015.

New model implement several improvements


The improvements in the new model include the following:
  • Exynos 7420 SoC manufactured on 14 nm FinFET process with 20 nm interconnects. The CPU is a big.LITTLE configuration with four Cortex-A57 and four Cortex-A53 cores, similar to Exynos 5433. The maximum clock speeds are 2.1 GHz and 1.5 GHz, respectively. Samsung claims 20% better performance and 35% better efficiency for the new chip when compared to Exynos 5433, which is manufactured using Samsung's 20 nm HKMG process.
  • The GPU has been rumoured to be a faster version of the Exynos 5433's Mali-T760 MP6 (either a higher clock rate or an MP8 configuration).
  • Early benchmarks indicate a significant increase in CPU and memory performance combined with a measurable increase in GPU performance (which is required because of the higher screen resolution).
  • Runs in 64-bit AArch64 mode, which has several advantages, as well as some disadvantages.
  • Uses new LPDDR4 SDRAM (3 GB), which has higher memory bandwidth at a given memory bus width due to higher effective clock speeds.
  • The cameras have been improved, including greater light gathering capability.
  • The 5.1" AMOLED screen's resolution is QHD (2560x1440), which is 77% more pixels than the FullHD (1920x1080) screen in Galaxy S5. The higher CPU, GPU and memory performance are essential to keep pace with increased demands caused by the higher resolution.
  • Utilizes the new UFS 2.0 interface for embedded flash memory, providing SSD-like performance according to Samsung.
  • Cat 6 LTE mode.
  • Touchwiz user-interface on top of 64-bit Android 5.0 is said to be more intuitive and less demanding in terms of processing requirements.
At the same time,  Samsung has dropped the MicroSD slot and the battery is non-removable. The battery capacity is also slightly smaller that of the Galaxy S5.

The Galaxy S6 Edge, like the Galaxy Note 4 Edge, features a screen that curves around the edges. It is priced significantly higher than the Galaxy S6, which will not be cheap either.

Quick ramp of 14nm FinFET process brings challenges to Samsung


The initial 14 nm FinFET process used by Samsung has been reported to use 20 nm interconnects with a 14 nm features size. As such it is more of an evolutionary step from 20 nm than full-blooded 14 nm FinFET would be, comparable to some degree with TSMC's 16FF process.

Still, Samsung will face a huge challenge ramping up the process in sufficient volume and acceptable yield rates to equip the high volume of Galaxy S6's expected. Rumours have mentioned low yield for the process in the recent past as Samsung started ramping up (test) production. Given the massive investment in the new process and non-optimal yield rates, it is unlikely that Samsung will significantly benefit financially from production of the chip in the near-term in terms of gross margin and other chip production-related metrics.

However, the performance lead of the Galaxy S6 made possible by the new chip could have significant positive implications for the sales and financial performance of Samsung's smartphone division, allowing Samsung to recoup some of its investment.

A few months ago, Samsung already signed an agreement with Apple whereby Samsung would supply part of the production capacity for future Apple processors. If this bears fruit it would allow Samsung to recoup more of its investment in 14 nm FinFET technology in the future.

Early benchmark performance impressive


In early benchmarks scores reported in Geekbench's result database, a device that probably is the Galaxy S6 shows impressive performance, well ahead of most existing SoCs and devices. In a direct comparison with an Exynos 5433-equipped Galaxy Note 4, the performance gain is fairly significant for most benchmarks (up to 30% for integer tests, higher for floating point), with a few negative outliers such as SHA2 and the Dijkstra integer subtest. The Dijkstra subtest also scores lower on other 64-bit AArch64 platforms, suggesting it suffers from particular AArch64 features such as the doubled size for pointer storage.

Memory performance is also significantly higher, aided by high clock rate and high amount of bandwidth delivered by the LPDDR4 memory interface, which unlike Qualcomm's Snapdragon 810 does not seem to have serious flaws.

Sources: AnandTech (Samsung annnounces the Galaxy S6 and Galaxy S6 Edge), AnandTech (Samsung Unpacked, MWC 2015 Live Blog), Geekbench Browser (Samsung SM-G925F)

Early benchmarks for MT6795 show high performance, suggest use of eight Cortex-A53 cores

Od: Vegator
MediaTek originally announced the MT6795, a SoC targeting the premium-level and performance segments of the smartphone market, in July 2014, with expectations of devices being commercially available to end users before the end of 2014. However, the chip was delayed (problems with the memory controller were reported) and competitive benchmark results are only now beginning to surface for the chip.

According to the announcement, the SoC was to have an octa-core CPU configuration with clock speeds up to 2.2 GHz, a strong dual-channel memory interface with support for LPDDR3 up to 933 MHz, 2K (2560x1600) display support. Other reports and information have suggested that it uses a PowerVR G6200 GPU, similar to the one used in MediaTek's MT6595, which can be seen as 32-bit predecessor of the new chip.

Confusion about processor cores, octa-core Cortex-A53 seems likely


The actual CPU cores used inside the MT6795 continue to be source of confusion. Initially understood to be an octa-core Cortex-A53 CPU configuration clocked at a high frequency, later a purported leaked MediaTek product roadmap surfaced that described the MT6795 as a big.LITTLE design that includes Cortex-A57 cores. However, a recent new entry in the Geekbench database suggesst that the chip actually has eight Cortex-A53 cores as originally suspected, as the IPC (instructions per cycle) of the integer and floating point subtests would be hard to reconcile with Cortex-A57 cores being present.

Geekbench results show mixed performance but high overall score


The Geekbench results show strong CPU performance, with the overall score being superior to that of available results for Snapdragon 810, which has a significantly higher cost design but has been plagued by performance issues, although it scores lower than Exynos 5433/Exynos 7 Octa with Cortex-A57 cores as used in the Galaxy Note 4. Note that MT6795 uses a less advanced 28 nm process compared to the 20 nm process used for Snapdragon 810 and Exynos 5433.

Single-score integer performance is not spectacular and below that of the previous generation high-end chips such as Snapdragon 801. Although this is compatible with the use of medium-performance Cortex-A53 cores, integer single-core performance is actually lower than the mid-range MT6752, despite the higher clock rate, pointing to continuing hardware performance problems with the chip. The Dijkstra benchmark result is particular low. This benchmark has a lot of external memory access and likely branches a lot, taxing certain elements of the CPU and SoC that simpler CPU benchmarks do not. It may be affected by the doubled address size in AArch64 mode, either through the increased size of pointer storage or reduced efficiency of the branch prediction unit inside the processor core.

Single core floating point performance in the Mandelbrot benchmark is higher than the MT6752 and actually compatible with the Cortex-A53 core running at 2.1 GHz, close to the originally envisaged maximum clock speed for the MT6795. Multi-core performance in this subtest is impressive, with a score that is higher than most existing SoCs including Exynos 7 Octa, which employs faster Cortex-A57 cores.

Finally, the dual-channel memory interface seems to working reasonably well in the tested revision of the chip/development board, with memory scores consistent with an optimized dual-channel interface, and higher, for example, than those of Exynos 5433. However, they are generally lower than those of the 32-bit MT6595.

One caveat is that the MT6795 entry is running in AArch64 mode, while the other devices were running in AArch32 (32-bit ARMv8) or 32-bit ARMv7 mode.

Average single-core CPU performance, strong multi-core performance


In a direct comparison with the MT6752, which has a comparable CPU configuration but clocked lower and has only a 32-bit memory interface, the MT6795 is only slightly faster, although the MT6795 uses a full 64-bit AArch64 instruction set model, while the tested MT6752 configurations use AArch32 with partial use of ARMv8 features. There are a few anomalous results, including a low score for the MT6795 in the single-core AES benchmark, and as mentioned it also scores significantly lower in the Dijkstra benchmark. Floating point performance is consistently higher for the MT6795 (more than the increase in clock rate would explain), which may be caused by the higher-performance memory subsystem of the MT6795 and/or the increased number of floating point registers available in AArch64 mode.

The MT6795 is clearly slower than its 32-bit predecessor MT6595 (which uses high-performance Cortex-A17 and Cortex-A7 cores in a big.LITTLE configuration) in most metrics, with only the heavy weighting and large performance gain for the AES and SHA1 cryptography tests  (due to the new ARMv8 instruction set) shifting the advantage for the overall score towards the MT6795.

When making a comparison with a median entry for the high performance Exynos 5433 (Exynos 7 Octa) inside the Samsung Galaxy Note 4, the MT6795 fairly consistently shows clearly lower single-core performance but higher multi-core performance.

MT6795 likely to be most cost-effective performance segment processor on the market


The exclusive use of Cortex-A53 CPU cores, and not the much more expensive and die-space consuming Cortex-A57 (or, in a 32-bit comparison, Cortex-A15/A17 cores), has positive implications for the cost of the chip. Die space dedicated to the CPU cores will be relatively low, although L2 caches will take considerable space when configured with a size that matches the desired performance level and market segment. Overall, the chip is likely to be attractive in terms of performance/dollar for the performance segment.

In terms of SoC optimizations, the chip would probably work better with the employment of additional ARM IP such as a Mali T760 or Mali-T800 series GPU, which offers advantages in combination with ARM cores such as Cortex-A53 in tandem with techniques such as AFBC, smart composition and transaction elimination, and new interconnect buses within the chip. SoCs like the MT6752 probably benefit from these optimizations, while the MT6795 cannot do so fully because of the non-ARM GPU. It seems likely that the MT6795 will be superseeded in next generation products to be announced by MediaTek in the future by a similar SoC with an ARM Mali-T760 or T800 series GPU.

Update (2 March): Based on a closed-door presentation event at the MWC, MediaTek appears to have rebranded MT6795 as Helio X10 with future Helio P series products also being announced.

Sources: MediaTek (MT6795 announcement), Geekbench browser

AOOSTAR AG01 OCuLink eGPU dock is now available for $149

The AOOSTAR AG01 is an external graphics dock that lets you connect a desktop-class graphics card to any laptop, mini PC or handheld computer that has an OCuLink connector. First unveiled earlier this year, the AG01 eGPU Dock is now available for $149, making it one of the more affordable devices in this category. But […]

The post AOOSTAR AG01 OCuLink eGPU dock is now available for $149 appeared first on Liliputing.

Setting a meshcollider's sharedmesh to a mesh which has been generated directly on the GPU gives "Failed extracting collision mesh"

I've been attempting to modify this example project https://github.com/keijiro/ComputeMarchingCubes

I'm trying to repurpose it to build terrain. After the Update() method in Assets/NoiseField/NoiseFieldVisualizer.cs I want to set a MeshCollider's sharedMesh to use the mesh that's been generated.

All I've done is add a line after the mesh is set:

GetComponent<MeshCollider>().sharedMesh = GetComponent<MeshFilter>().sharedMesh;

Currently I get an error:

Failed extracting collision mesh because vertex at index 2817 contains a non-finite value (0.000000, -nan, 1.000000). Mesh asset path "" Mesh name ""

When I iterate over sharedMesh.vertices and log them to console, I get either (0, 0, 0) or (-431602100.00, -431602100.00, -431602100.00) for each vertex value. Presumably because the values haven't been sent back to the CPU?

I have mesh cleaning enabled for the MeshCollider.

Is it possible to generate a mesh collider with a GPU-only mesh? Preferably without transferring the points back to the CPU.

MediaTek announces Helio P10 and MT6753 arrives in shipping devices

Od: Vegator
MediaTek has announced Helio P10 (MT6755), a performance mid-range smartphone SoC that is the successor of MT6752. Featuring an octa-core Cortex-A53 configuration, Helio P10 improves upon MT6752 by using TSMC's new 28HPC+ manufacturing process, which delivers power efficiency and performance improvements while remaining relatively cost-effective. It can reach a higher maximum CPU clock speed up to 2 GHz and upgrades the GPU to a Mali-T860 MP2. It is expected to be commercially available in end devices by the end of 2015.

Features shared with Helio-X10


The new SoC  incorporates a few features from Helio X10 (MT6795), MediaTek's current high-end offering, including dual ISPs with 21MP camera support and improved capture capability, as well as improved audio quality.

Otherwise, the SoC has significant similarities to MediaTek's MT6752 which it succeeds, most likely including a 32-bit external memory interface, which keeps SoC cost and phone PCB cost down. With MT6752, MediaTek already demonstrated the ability to achieve memory performance adequate for a 1080p device within the constraints of a 32-bit memory interface.

The 28HPC+ process is an upgrade of the existing 28HPC (high-performance compact) process (which is also relatively new, used by Allwinner's A83T and other SoCs), which improves performance and cost relative to the established 28HPM (high-performance mobile) process. Existing MediaTek chips like MT6752 and MT6795 most likely use 28HPM, which is established and has also been used for previous-generation SoCs such as MT6592 and Snapdragon 801/805.

MediaTek migrating to big.LITTLE CPU configurations in new SoCs


A significant departure from existing octa-core MediaTek SoCs such as MT6752 and Helio X10 (MT6795) is the pseudo-big.LITTLE CPU configuration, whereby one cluster of four Cortex-A53 cores is clocked at a higher frequency (up to 2 GHz in this case), while the second of cluster Cortex-A53 cores is optimized for lower frequencies, being clocked at a lower maximum frequency (1.1 GHz according to AnandTech).

Together with the previously announced high-end Helio X20 (MT6797) and tablet/Chromebook-oriented chips such as MT8173, Helio P10 marks a migration to (pseudo-)big.LITTLE, hierarchical CPU designs at MediaTek. While symmetrical octa-core designs such as MT6752 and MT6795 reach very high multi-core processing power by allowing all cores to run at the maximum frequency, there are signs that this configuration impacts power efficiency for tasks that require less CPU power, which can be run on power-optimized low-frequency cores.

In practice, this may be reflected in somewhat mediocre standby battery life for smartphones using MT6752 or MT6795, even though power efficiency for demanding tasks that utilize all cores is likely to be pretty good.

Budget mid-range MT6753 reaches end-market


Meanwhile, MediaTek's previously announced MT6753, which is a cost-effective budget mid-range SoC, has arrived in commercially shipping device in the form of Meizu M2 Note. Despite the name chosen by Meizu, the new model actually has lower performance than the existing Meizu M1 Note, because the MT6753  is a less costly, lower end chip when compared to to the MT6752 inside the M1 Note, with considerably slower maximum CPU speeds for the eight CPU cores, as well as a lower performance GPU. There are also signs that the memory interface and the actual memory frequency used by the M2 Note is slower. The lower cost of the MT6753 platform is reflected in the low selling price of the Meizu M2 Note.

MT6753 implements several cost-reducing features, including a lower maximum clock speed (reported to be 1.3 GHz for the M2 Note), most likely associated with a cheaper manufacturing process (either 28LP or 28HPC) than the 28HPM process of the MT6752. A significant factor for lower performance is likely to be a reduced size of the L2 CPU cache inside the MT6753. MT6753 is likely to become a significant volume driver in MediaTek's 4G product line.

However, early Geekbench entries for the Meizu M2 Note suggest that the CPU cores of the MT6753 SoC used in this model are mostly unable to reach the planned clock frequency. The Geekbench results are mostly consistent with an average maximum CPU clock speed of about 1.1 GHz, significantly lower than the 1.3 GHz reported by the OS and the 1.5 GHz mentioned when the MT6753 was originally announced a few months ago. My following blog article about the use of AArch64 provides more details on this subject.

MT6753 has lower-performance GPU than MT6752


MT6753 also has a significantly lower-performance and smaller GPU (Mali-T720 MP3), compared to the Mali-T760 MP2 inside MT6752. MT6753 marks the first Mali implementation with three pixel processing cores; previous Mali GPUs either had one, two, four, six or eight pixel processing cores, Most likely, Mali-T720 does not have the memory bandwidth usage optimization that are present in Mali-T760, which together with the more limited pixel processing throughput means that devices with a 1080p display such as the Meizu M2 Note may be impacted in terms of 1080p game performance and power efficiency for graphics-intensive operations.

World modem support in new MediaTek platforms


All new MediaTek SoCs (including Helio P10 (MT6755), MT6753, the low-end quad-core MT6735 and the announced high-end Helio X20 (MT6797)) have world-modem support, facilitating compatibility with more cellular networks used worldwide, including legacy CDMA networks in the US and other countries. This makes MediaTek SoCs more attractive to smartphone manufacturers targeting multiple or worldwide markets.

Sources: MediaTek (Helio P10 announcement), AnandTech (Helio P10 article)

Updated 6 June 2015.

HiSilicon introduces Kirin 930/935, a performance-oriented Cortex-A53-based SoC

Od: Vegator
Huawei has introduced the Huawei P8 and P8max smartphones, featuring the Kirin 930 and Kirin 935 SoCs from Huawei's  HiSilicon semiconductor division. The octa-core Kirin 930 SoC is a performance-oriented SoC featuring only Cortex-A53 CPU cores. With a maximum clock frequency in excess of 2.0 GHz, it bears similarities to MediaTek's MT6795, but the use of a pseudo big.LITTLE configuration (four Cortex-A53 cores clocked up to 2.0 GHz and four Cortex-A53 cores clocked up to 1.5 GHz, for a total of eight cores) is reminiscent of Qualcomm's midrange Snapdragon 615 SoC, which runs at lower clock frequencies.

Huawei also introduced high-end models of both the P8 and P8max with larger storage capacity featuring the Kirin 935 SoC, which is a higher-clocked version of Kirin 930. The Huawei P8max is a smartphone with an unusually large 6.8" display.

SoC is targeted at performance-oriented devices


The Huawei P8 models are higher-priced performance-oriented smartphones, and the characteristics of the SoC match this segment. Apart from the high maximum clock speed of the Cortex-A53 cores, the external RAM interface is likely to be a dual-channel 32-bit configuration like previous performance-oriented SoCs from HiSilicon. Presentation materials from Huawei describe the Cortex-A53 cores in the faster cluster of four CPUs as being of a special, performance-enhanced type, which probably reflects the application of ARM's PoP core-hardening technology whereby the core is optimized for running at a specific frequency and a particular power profile, trading performance against die size. The process technology used is likely to be TSMC's proven 28HPM process.

The SoC is reminiscent of MediaTek's recently introduced MT6795 (Helio-X), which also targets the performance segment with an octa-core Cortex-A53 CPU configuration. MediaTek's SoC has been reported to have been adopted by competitors of Huawei such as HTC and Xiaomi.

Previous generation Mali-T628 MP4 GPU used


Rather than using an updated current-generation GPU like Mali-T760, the specs sheet for the P8max indicates the Kirin 930/935 SoCs continue to use the Mali-T628 MP4 GPU that was previously used in the Kirin 920 SoC. This GPU core is not known for great power efficiency, although there are suggestions that the more efficient Mali-T760 (which features memory bandwidth optimizations) has a relatively high silicon area and cost.

HiSilicon's new SoC line-up uses only Cortex-A53 CPU cores


Apart from Kirin 930, HiSilicon has also introduced the Kirin 620 SoC, which is an octa-core Cortex-A53 based SoC for the cost-sensitive segment, clocked up to 1.2 GHz and with a single-channel memory interface. This means Huawei now has in-house Cortex-A53-based SoCs suitable for most of its smartphone product range.

Early benchmarks appear for Cortex-A72-based SoC

Od: Vegator
ARM recently announced the new Cortex-A72 processor core, which is an improved version of the existing high-performance Cortex-A57 processor core.

Alongside the Cortex-A72 CPU core, ARM also announced the CCI-500 interconnect technology as well as the high-end Mali-T880 GPU. Devices incorporating the combination of these technologies are expected to become available in 2016.

However, SoCs using the Cortex-A72 CPU are likely to become available earlier. Qualcomm and MediaTek have both announced SoCs using the Cortex-A72 core with commercial availability in the second half of 2015, suggesting that the CPU core itself is at an advanced stage of introduction. Already, early benchmarks for MediaTek's MT8173 tablet SoC that incorporates the Cortex-A72 have become available.

Cortex-A72 appears to be enhanced version Cortex-A57 optimized for next-generation processes


In its announcement press release from 3 February 2015, ARM claims that more than ten partners have already licensed Cortex-A72, including HiSilicon, MediaTek and Rockchip. Cortex-A72 is based on ARM's ARMv8-A instruction set architecture, and can be combined with the existing Cortex-A53 in a big.LITTLE configuration. Cortex-A72 seems to be positioned as a replacement for Cortex-A57. The similarities with Cortex-A57 are very apparent, for example in the identically sized L1 instruction and data caches, and a feature set that is otherwise very similar.

On a 16 nm FinFET process, the core can sustain operation at speeds up to 2.5 GHz within the constraints of a mobile power envelope (e.g. smartphones), with scalability to higher speeds for larger form-factor devices. However, the first announced devices, such as MediaTek's MT8173, appear to use older processes such as the tried-and-trusted 28 nm HPM process at TSMC, so they are likely to have a lower maximum clock speed.

ARM claims increased performance and power efficiency, although these claims seem to be based on implementation on next-generation processes such as 16 nm FinFET that deliver a significant intrinsic improvement in these metrics. ARM mentions micro-architectural improvements that result in enhancements in floating point, integer and memory performance. When implemented on a 16 nm FinFET process, ARM expects Cortex-A57 to provide 85% higher performance when compared to the Cortex-A57 core on a 20 nm process within a similar smartphone power budget.

Overall, the differences with Cortex-A57 appear to be relatively minor, so that Cortex-A72 is best viewed as an enhanced version of Cortex-A57 that is optimized for next-generation processes such as 16 nm FinFET. Nevertheless, the first SoCs to use the Cortex-A72 core will be manufactured using a less advanced process.

Benchmarks appear for MediaTek's MT8173


MediaTek's MT8173 is a mid-range tablet processor mainly targeting Wi-Fi-only tablets, since it does not have an integrated modem. It has two Cortex-A72 cores and two Cortex-A53 cores in a big.LITTLE configuration. Probably manufactured using the established 28HPM process at TSMC, the maximum clock speed of the Cortex-A57 cores is likely to be lower that the target for 16 nm FinFET, although MediaTek claims a clock speed up to 2.4 GHz, while a much lower frequency is apparent in early benchmarks results.

The chip also features a PowerVR GX6250 GPU, which delivers higher performance than the G6200 GPU used inside MediaTek's existing MT8135 and MT6795.

Recently, early benchmarks for a MT8173 development board have appeared both in the Geekbench Browser and in the results database of GFXBench. The first Geekbench results already appeared in December 2014. The latest set of Geekbench results date from the end of February 2015, although they do show a certain amount variation that may reflect thermal throttling.

Single-core performance good, but not spectacular


As expected, the Geekbench results show good single-core performance, albeit not spectacular. As shown in the following table, singe-core performance is in line with Cortex-A57-based SoCs such as Exynos 5433 and Exynos 7420. It should be noted that the MT8173 test SoC is most likely manufactured at 28 nm with a corresponding relatively low maximum CPU clock speed, while Exynos 5433 and 7420 are manufactured using smaller leading edge processes at Samsung.


SoC          "big" CPU                    Arch     JPEG (int)  Lua (int)   Mandelb. (fp)
                                                   Comp. IPC         IPC         IPC
MT8173       2 x 1.6? GHz Cortex-A72      AArch32  1310  2.13  1380  2.10  1064  1.95
Exynos 5433  4 x 1.80 GHz Cortex-A57r1p0  AArch32  1456  2.10  1397  1.89  1174  1.91
Exynos 7420  4 x 1.97 GHz Cortex-A57r1p0  AArch64  1481  1.97  1409  1.74  1198  1.92

In this table, to determine the IPC index I have made an educated guess about the actual clock speed of MT8173 when running the benchmarks. Geekbench reports a 1.40 GHz clock speed (which probably applies to the Cortex-A53 cores), 1.6 GHz seems to be a good match, providing just a little better IPC than Cortex-A57. Note that Exynos 7420 runs in AArch64 mode, which skews direct IPC comparisons.

Practical implications unclear


Without knowing the exact clock speed of the Cortex-A72 cores, it is hard to draw conclusions about the actual IPC improvement over Cortex-A57. If the MT8173 uses a 28 nm process, the ability to approach the single-core performance of Samsung's Exynos 7420 manufactured using 14 nm FinFET process is impressive. However, although MediaTek demonstrated the MT8173 in an actual tablet at MWC, it is unclear what kind of device the Alps development board in the benchmark entries actually represents, so it remains to be seen whether the benchmarks actually reflect the power budget of a tablet.

The multi-core performance reported is not very impressive, as expected because of the relatively small number of CPU cores. The JPEG Compress multi-core score shows CPU scaling factor of 2.72, which is good and implies utilization of the Cortex-A53 cores. The Mandelbrot floating point benchmark shows similar scaling.

However, the Lua integer benchmark has a very low multi-core scaling factor of 1.41, which is lower than expected, even when allowing for the limited number of cores. For example, MediaTek's MT6795 achieves multi-core scaling of 7.5 in this benchmark, and the Exynos chips range from 3.9 to 5.0. Other chips with a low multi-core scaling factor for Geekbench's Lua subtest include Snapdragon 810 (Cortex-A57-based), MediaTek's MT6595 (Cortex-A17-based) and NVIDIA's Denver-based Tegra-K1 SoC. There are indications that this benchmark test heavily depends on on-chip cache (primarily L2 cache) size and speed.

GPU performance of MT8173's PowerVR GX6250 GPU improves on G6200


The MT8173 test device's GPU performance as shown in GFXBench results database is not overly impressive, but suitable for a mid-range chip and an improvement over the PowerVR G6200 GPU used in other MediaTek SoCs such as MT6595 and MT6795. In the T-Rex Offscreen benchmark, the MT8173 registers a score of 1487, higher than the 1311 of the MT6595 (G6200)-equipped Meizu MX4. In the GFXBench 3.0 low-level tests, alpha blending scores higher than the MT6595 while the other low-level scores are comparable.

Sources: ARM (Cortex-A57 announcement press release), AnandTech (MediaTek MT8173 article), MediaTek (MT8173 announcement), Geekbench Browser (MT8173 test device results), GFXBench (MT8173 test device result)

Updated 10 March 2015.

A deeper look at graphics benchmark results, including GFXBench 3.1 and Basemark X

Od: Vegator
In this post I will take a closer at graphics benchmark results for different SoCs. I will look beyond just GFXBench (for which a new version has appeared), because the workload tested by well-known GFXBench tests such as T-Rex and Manhattan is not necessarily reflective of the actual gaming experience. Alternative benchmarks exist, such as Basemark X which uses the Unity engine that is commonly used in games.

GFXBench 3.1 released for OpenGL ES 3.1, Snapdragon 805 does well


Kishonti recently released a new version of GFXBench, GFXBench 3.1 for OpenGL ES 3.1, that includes tests for the OpenGL ES 3.1 API standard supported by many recent devices. A few results from the new benchmark tests are already available, with the Adreno 420 GPU inside Snapdragon 805 closing most of the performance gap with the Mali-T760 MP6/MP8 in Samsung's Exynos SoCs in the Manhattan 3.1 test.

                                                      Offscreen Manhattan Manhattan
Device               SoC             GPU              T-Rex        3.0       3.1

NVIDIA Shield Tablet NVIDIA K1-32    Tegra K1 GPU        3692     1979      1443  
HTC One M9           Snapdragon 810  Adreno 430          2732     1413
Galaxy S6 Edge       Exynos 7420     Mali-T760 MP8?      3312     1607       793
Sams. Galaxy Note 4  Snapdragon 805  Adreno 420          2386     1153       773
Samsung Galaxy S6    Exynos 7420     Mali-T760 MP8?      3314     1609       634
Sams. Galaxy Note 4  Exynos 5433     Mali-T760 MP6       2163     1110       436
HTC One M8           Snapdragon 801  Adreno 330          1608      768
Teclast X98 Air      Atom Z3736F     Intel HD            1014      564       307
Google Nexus 10      Exynos 5250     Mali-T604 MP4        818      351       185

NVIDIA's Tegra 32-bit version of Tegra K1 leads (the 64-bit Denver-based version of Tegra K1, and Tegra X1, have not yet been tested). Performance of Snapdragon 805 as implemented in certain models of the Samsung Galaxy Note 4 holds up better in the Manhattan 3.1 test than Samsung's Exynos SoCs with Mali-T760 MP6/MP8. Whereas Exynos 7420 (used in the Galaxy S6) has a clear advantage in existing benchmarks (1609 vs 1153 for Manhattan and 3314 vs 2386 for T-Rex), it loses that advantage in the new Manhattan 3.1 test (although the Galaxy S6 Edge benchmarks result suggests it is still slightly superior). Intel's Baytrail SoCs seem to hold up relatively well looking at the result for an Atom Z3736F-based tablet, albeit at a lower performance level.

GFXBench 3.1 results for Snapdragon 801 and the new Snapdragon 810 are not yet available. However, given the fact that GFXBench appears to generally do well on Snapdragon SoCs, they can be expected to score fairly highly. I'll say more about the apparent advantage for Qualcomm's SoC in GFXBench in the final section of this article.

Basemark X is a useful alternative to GFXBench


Basemark X is a gaming benchmark that utilizes the Unity engine that is commonly used in games, and developer Rightware claims that it actually reflects practical performance in games. Although it does include an on-screen demo, the actual benchmark scores appear to be derived from off-screen rendering at a fixed resolution, so that benchmark results can be compared objectively between different devices.

Previous generation SoCs: MT6582 beats Snapdragon 400 in Basemark X


Taking a look at previous-generation cost-sensitive SoCs, while MediaTek's ubiquitous quad-core 3G SoC MT6582 (which supports Open GL ES 2.0 only, through its Mali-400 MP2 GPU) scores lower than Snapdragon 400 in GFXBench's OpenGL ES 2.0-based T-Rex test (about 230 vs 330), in Basemark X MT6582-based devices score higher than Snapdragon 400 based devices. This is despite the fact that Snapdragon was/is often employed in devices with a considerably higher selling price than MT6582-based devices.

Device               SoC             GPU                 Display*   Medium   High

Samsung SM-G800F     Exynos 3470     Mali-400 MP4        1280x720    7527    2712
Vodafone 985N        MT6582          Mali-400 MP2         960x540    4950    1717
Acer E53             MT6582          Mali-400 MP2        1280x720    4870    1694
Wiko Rainbow         MT6582          Mali-400 MP2        1280x720    4826
Galaxy S3 Neo        Snapdragon 400T Adreno 305          1280x720    4540    1551
Moto G (XT1032)      Snapdragon 400  Adreno 305          1280x720    4440
HTC Desire 816d      Snapdragon 400T Adreno 405          1280x720    4354    1441
Samsung SM-A500F     Snapdragon 410  Adreno 306          1280x720    4132    1900
Samsung SM-A300F     Snapdragon 410  Adreno 306           960x540    4076    1892
Samsung SM-G530H     Snapdragon 410  Adreno 306           960x540    3987    1690
Samsung SM-G800A     Snapdragon 400  Adreno 305          1280x720    3946    1362
HTC Desire 820q      Snapdragon 410  Adreno 306          1280x720    3786

* While Basemark X is independent of display resolution in terms of rendering, the
memory bandwidth used for screen refresh has some impact, giving lower-resolution
devices a small advantage.
Notes: Samsung SM-G800F is the Galaxy S5 Mini (Exynos version), while SM-G800A is a Snapdragon 400 running at the non-standard maximum clock speed of 1.4 GHz; Vodafone 985N is the Vodafone Smart 4 Power; Acer E53 is the Acer Liquid E700; Galaxy S3 Neo runs the Snapdragon 400 SoC at a non-standard maximum speed of 1.4 GHz; HTC Desire 816d runs the Snapdragon 400 SoC at 1.6 GHz; SM-A500F is the Galaxy A5, while SM-A300F is the Galaxy A3; SM-G530H is the Galaxy Grand Prime.

For both the medium detail and high detail settings, MT6582-based devices consistently score higher in Basemark X than Snapdragon 400 and also Snapdragon 410-based devices for the medium detail test, which gives a different picture than the one you get from just looking at GFXBench's T-Rex benchmark

Snapdragon 410 performs worse than Snapdragon 400 in Basemark X medium-detail


Also notable is that Snapdragon 410, which is the successor of the Snapdragon 400 and would normally be expected to improve performance, actually has lower performance in practice as judged by the Basemark X medium detail benchmark. This matches earlier findings of performance flaws in Snapdragon 410. When running the high detail Basemark X benchmark, Snapdragon 410 does better and beats Snapdragon 400.

Mid-range SoCs: Snapdragon 615 and MT6752 closely matched


When running GFXBench, Snapdragon 615 and MT6752 are closely matched, with Snapdragon 615 scoring about 830 to 850 in T-Rex while MT6752 scores just above 870. For T-Rex, devices using MediaTek's prior-generation octa-core MT6592 score in the range 650 to 750. In the OpenGL ES 3.0 API-based Manhattan benchmark, Snapdragon 615 and MT6752 are very closely matched, both scoring around 360. We will also take a look at Basemark X results.

The following table shows Basemark X results for the new competing mid-range SoCs Snapdragon 615, MT6752 and HiSilicon's octa-core Hi6210 (Kirin 620), as well as for the prior-generation octa-core MT6592 from MediaTek.

Device               SoC             GPU                 Display*   Medium   High

Lenovo P70-A         MT6752          Mali-T760 MP2       1280x720   11311 
Meizu M1 Note        MT6752          Mali-T760 MP2       1920x1080  11168    4636
HTC Desire 816G      MT6592          Mali-450 MP4        1280x720   10984
Huawei CHE2-TL00     Hi6210          Mali-450 MP4        1280x720   10546    3439
Oppo R8106           Snapdragon 615  Adreno 405          1920x1080  10277    4846 
HTC Desire 820       Snapdragon 615  Adreno 405          1280x720   10133    4814
Samsung SM-A700FD    Snapdragon 615  Adreno 405          1920x1080  10052    4757
Archos 50C Oxygen    MT6592          Mali-450 MP4        1280x720    9867    3702
HTC Desire 616d      MT6592M         Mali-450 MP4        1280x720    7976    3045

* While Basemark X is independent of display resolution in terms of rendering, the
memory bandwidth used for screen refresh has some impact, giving lower-resolution
devices a small advantage.
Notes: SM-A700FD is the Galaxy A7; Huawei CHE2-TL00 is a new version of the Honor 4X.

When running the standard medium-detail version of Basemark X, MediaTek's MT6752 has  a moderate advantange over Snapdragon 615, while at the high detail setting Snapdragon 615 has a small advantage. Huawei's Kirin 620 performs adequately and just ahead of Snapdragon 615 in the medium detail setting.

MediaTek's prior-generation octa-core MT6592 with Mali-450 MP4 GPU keeps up relatively well in Basemark X,  with certain models (e.g. HTC Desire 816G) actually beating Snapdragon 615 in the medium detail setting.

Performance-oriented SoCs with Basemark X


The following table shows Basemark X results for several performance-oriented mobile SoCs.

Device               SoC             GPU                 Display*   Medium   High

Samsung Galaxy S6    Exynos 7420     Mali-T760 MP6       2560x1440  36017
Galaxy S5 LTE-A      Snapdragon 805  Adreno 420          1920x1080  32685   18334
Google Nexus 6       Snapdragon 805  Adreno 420          2560x1440  30362   20265
Sams. Galaxy Note 4  Snapdragon 805  Adreno 420          2560x1440  31963   21152
Sams. Galaxy Note 4  Exynos 5433     Mali-T760 MP6       2560x1440  29335   19019 

Apple iPad Air 2     Apple A8X       PowerVR Series 6    2048x1536  41700   29239
Google Nexus 9       NVIDIA K1-64    Tegra-K1 GPU        2048x1536  37939   28646
Apple iPad Mini 3    Apple A7        PowerVR Series 6    2048x1536  26499   14780
Teclast X98 Air      Atom Z3736F     Intel HD            2048x1536  14825    7160
Teclast P90HD        Rockchip RK3288 Mali-T764           2048x1536  13053    5645
Onda V989 Core8      Allwinner A80   PowerVR G6230       2048x1536  11004    5724

Meizu MX4 Pro        Exynos 5430     Mali-T628 MP6       1920x1200  25547   12674
Samsung SM-G900A     Snapdragon 801  Adreno 330          1920x1080  25178   11930
Samsung SM-G850F     Exynos 5430     Mali-T628 MP6       1280x720   21872   10666
Meizu MX4            MT6595          PowerVR G6200       1920x1200  17038    7817
Huawei MT7-TL10      Kirin 925       Mali-T624 MP4       1920x1080  15973    6802

* While Basemark X is independent of display resolution in terms of rendering, the
memory bandwidth used for screen refresh has some impact, giving lower-resolution
devices a small advantage.
Notes: SM-G900A is the Samsung Galaxy S5 (US version), Huawei MT7-TL10 is the Huawei Mate 7.

Looking at the ultra-high-end smartphone segment (mostly with a display resolution of 2560x1440), Exynos 7420 provides superior performance in Basemark X. Snapdragon 805 follows, a small distance ahead of Exynos 5433 as used in the Samsung Galaxy Note 4.

In the high-end tablet segment, Apple's iPad Air 2 with the Apple A8X leads, but the Nexus 9 with NVIDIA's Tegra K1 (64-bit version) comes fairly close. Apple's prior generation SoCs also delivers good performance, while Intel's current Baytrail SoC for the tablet market outperforms two high-end chips from established Chinese players in the tablet SoC market, Rockchip's RK3288 and Allwinner A80 Octa.

Mainwhile, in the mainstream performance smartphone segment, Snapdragon 801 (in the past the performance leader in the market) still provides good performance, but is actually just beaten by the 32-bit Exynos 5430 in the Meizu MX4 Pro. The chip is also used in the Galaxy Alpha (for which it provides higher-than-necessary performance given its relatively low screen resolution), while the performance of MediaTek's MT6595 SoC, while not bad, falls short of most other high-end solutions. HiSilicon's Kirin 925 as implemented in the Huawei Mate 7 is just behind.

Conclusion


It appears that just concentrating on GFXBench may give a misleading picture with regard to 3D graphics performance of mobile SoCs. In particular it is apparent that Qualcomm's Snapdragon SoCs consistently do better in GFXBench than in other benchmarks such as Basemark X. This is particularly true for the lower-end Snapdragon 400 and higher-end Snapdragon 800 series; for Snapdragon 615, results are more consistent across different benchmarks.

Basemark X, which utilizes the Unity game engine commonly used in mobile games, may more accurately reflect real-world performance.

Sources: Rightware Power Board (Basemark X benchmark results), GFXBench results database

Updated 5 March 2015: Add Galaxy S6 Edge result for GFXBench 3.1.
Updated 15 March 2015.

New mobile SoCs announced at MWC

Od: Vegator
At the Mobile World Congress this week, several new mobile SoCs are being announced.

MediaTek announces cost-reduced MT6753 for smartphones


MediaTek anounced two mobile SoCs, the MT6753 for smartphones and the MT8173 for tablets.

The MT6753 appears to be a cost-reduced version of the successful MT6752, equpped with "WorldMode" modem technology. By offering compatibility with the CDMA2000 standard, it gives customers worldwide greater diversity and flexibility in their product layouts, according to MediaTek. Features include an octa-core Cortex-A53 CPU up to 1.5 GHz and a Mali-T720 GPU with an unspecified number of cores. ARM's Mali-T720 GPU is positioned at a significantly lower performance bracket than the Mali-T760 used in the MT6752, positioning the MT6753 below the MT6752 in terms of cost and performance.

The MT6753 is described as being compatible with the previously announced MT6735 for entry-level smartphones. The MT6735 has four Cortex-A53 cores instead of eight but otherwise has a similar configuration with a Mali T720 GPU.

High-performance MT8173 tablet SoC uses small big.LITTLE clusters with Cortex-A72


The MT8173 is a high-performance tablet processor (without integrated modem) that utilizes ARM's new Cortex-A72 core in a big.LITTLE configuration. By using only two Cortex-A72 cores (clocked up to 2.4 GHz) as well as two Cortex-A53 cores, the chip has a lower cost than would be the case with the four-by-four core configuration commonly used for big.LITTLE designs, while still providing good performance.

The Cortex-A72 core, the successor of Cortex-A57, appears to be seeing quick adoption as Qualcomm has already announced performance-segment smartphone SoCs (Snapdragon 618 and 620) featuring the core.

MediaTek has previously used a similar two-by-two big.LITTLE configuration in its MT8135(V) tablet SoC, which has two Cortex-A15 cores and Cortex-A7 cores. This chip was used in Amazon tablets but otherwise did not see much adoption.

Other features include a PowerVR GX6250 GPU, which is part of Imagination's Series 6XT family, with higher performance and efficiency than the G6200 GPU used in chips such as the MT8135 and MT6595.

Other tablet SoCs not yet publicly announced by MediaTek


Meanwhile, tablet product announcements by Lenovo also refer to the MT8161 and MT8165 SoCs, which have not been announced. From the specifications of the Lenovo Tab 2 A8 which is using it, the MT8161 appears to be a tablet SoC without modem with quad-core Cortex-A53 CPU running up to 1.3 GHz, while the MT8165 (used in the Tab 2 A10) is a similar SoC with the CPU running up to 1.5 GHz. The 4G version of the Lenovo tablets come equipped with the MT8735 (Tab 2 A8) and MT8732 (Tab 2 A10). These chips are the tablet versions of the MT6735 and MT6732 smartphone SoCs.

MT6795 renamed to Helio X10


In a closed-door presentation at MWC, MediaTek also presented the Helio X10 smartphone SoC, featuring a 64-bit octa-core CPU up to 2.2 GHz, 120 Hz display refresh rate and H.265 video encode up to 4K2K @ 30 fps. A photograph of a slide taken at the presentation strongly suggests that Helio X10 is nothing other than the delayed MT6795 SoC, whose specifications closely match. Devices using this chip are likely to have already started production. MediaTek also talked about the Helio P series, a high-performance platform, which will make its way into devices before the end of the year.

Qualcomm gives preview of next-generation Snapdragon 820 SoC


In a press release, Qualcomm has given a preview of the Snapdragon 820, which utilizes Qualcomm's new custom 64-bit CPU architecture for mobile devices called Kryo. The chip will start sampling in the second half of 2015 according to Qualcomm, with devices becoming available in 2016. It will be manufactured on a next-generation FinFET process (which probably means TSMC's 16FF+, but Samsung cannot be excluded). In the press release, Qualcomm does not mention whether the chip will conform to ARM's ARMv8 instruction set architecture.

In conjuction with the Snapdragon 820, Qualcomm also announced the Zeroth hardware/software platform focusing on device intelligence features including video and audio recognition techniques (such as visual object and face recognition).

Intel introduces tablet and smartphone SoCs with integrated modem


Intel has finally introduced SoCs with an integrated cellular modem in its Atom system-on-a-chip product line. The former SoFIA platform has been renamed to Atom X3 and features multi-core 64-bit Atom processors with integrated 3G or 4G LTE modem technology. The following products are available:
  • Atom X3-C3130, which has dual-core Atom CPU running up to 1.0 GHz and integrates a 3G modem. It features Mali-400 MP2 GPU. Maximum display resolution is 1280x800. It appears to be in the same market segment as MediaTek's previous-generation 3G SoCs such as MT6572 and MT6582 and other SoCs that are already on the market.
  • Atom X3-C3230RK, which was developed by Intel partner Rockchip following the agreement announced last year. It has quad-core Atom CPU, integrates a 3G modem and features a Mali-450 MP4 GPU.
  • Atom X3-C3440, a quad-core Atom CPU platform that integrates a Cat 6 LTE 4G modem. It has an Mali-T720 MP2 GPU. This product appears to be one that is most likely to succeed in the market.
All feature a 32-bit memory interface with support for LPDDR2 (and DDR3/DDR3L with the X3-C3230RK). These are the first Intel products that have features (such as the integrated modem) that make them specifically suitable for the smartphone market. They also target cellular-enabled tablets.

The 3G products are a little behind the times, and their success is uncertain. It will be interesting observe whether Rockchip was able to develop the X3-C3230RK in time (one would expect Intel to have greater expertise/resources so that the other products will appear on the market first).

One notable fact is that these are among the first SoCs to integrate an ARM GPU core with a non-ARM CPU.

Intel announces first 14 nm Atom SoCs for tablets and all-in-ones


Intel also rolled out its first 14 nm Atom SoCs, the Atom x5 and x7 processor series (formely codenamed Cherry Trail) with  Intel Gen 8 graphics, targeting tablets and small screen all-in-ones.

Intel has also introduced a new stand-alone modem chip, XMM 7360, which support LTE Cat 10 and download speeds up to 450 Mbps, as well as wireless connnectivity products (including WiFi/Bluetooth, GNSS/GPS and NFC solutions).

Sources: MediaTek (MT6753 announcement), MediaTek (MT8173 announcement), Qualcomm (Snapdragon 820/Zeroth platform preview), Intel (MWC announcements), Intel Atom x3 Processor Series Brief

Samsung announces Galaxy S6 with Exynos 7420 SoC manufactured on "14nm" FinFET process

Od: Vegator
At the Mobile World Congress today (Sunday 1 March), Samsung announced the Galaxy S6 and Galaxy S6 Edge, featuring a numerous improvements over the previous generation Galaxy S5, including a SoC manufactured on Samsung's 14 nm FinFET-based process. The Galaxy S6 is planned to available in 20 countries starting on April 10th, 2015.

New model implement several improvements


The improvements in the new model include the following:
  • Exynos 7420 SoC manufactured on 14 nm FinFET process with 20 nm interconnects. The CPU is a big.LITTLE configuration with four Cortex-A57 and four Cortex-A53 cores, similar to Exynos 5433. The maximum clock speeds are 2.1 GHz and 1.5 GHz, respectively. Samsung claims 20% better performance and 35% better efficiency for the new chip when compared to Exynos 5433, which is manufactured using Samsung's 20 nm HKMG process.
  • The GPU has been rumoured to be a faster version of the Exynos 5433's Mali-T760 MP6 (either a higher clock rate or an MP8 configuration).
  • Early benchmarks indicate a significant increase in CPU and memory performance combined with a measurable increase in GPU performance (which is required because of the higher screen resolution).
  • Runs in 64-bit AArch64 mode, which has several advantages, as well as some disadvantages.
  • Uses new LPDDR4 SDRAM (3 GB), which has higher memory bandwidth at a given memory bus width due to higher effective clock speeds.
  • The cameras have been improved, including greater light gathering capability.
  • The 5.1" AMOLED screen's resolution is QHD (2560x1440), which is 77% more pixels than the FullHD (1920x1080) screen in Galaxy S5. The higher CPU, GPU and memory performance are essential to keep pace with increased demands caused by the higher resolution.
  • Utilizes the new UFS 2.0 interface for embedded flash memory, providing SSD-like performance according to Samsung.
  • Cat 6 LTE mode.
  • Touchwiz user-interface on top of 64-bit Android 5.0 is said to be more intuitive and less demanding in terms of processing requirements.
At the same time,  Samsung has dropped the MicroSD slot and the battery is non-removable. The battery capacity is also slightly smaller that of the Galaxy S5.

The Galaxy S6 Edge, like the Galaxy Note 4 Edge, features a screen that curves around the edges. It is priced significantly higher than the Galaxy S6, which will not be cheap either.

Quick ramp of 14nm FinFET process brings challenges to Samsung


The initial 14 nm FinFET process used by Samsung has been reported to use 20 nm interconnects with a 14 nm features size. As such it is more of an evolutionary step from 20 nm than full-blooded 14 nm FinFET would be, comparable to some degree with TSMC's 16FF process.

Still, Samsung will face a huge challenge ramping up the process in sufficient volume and acceptable yield rates to equip the high volume of Galaxy S6's expected. Rumours have mentioned low yield for the process in the recent past as Samsung started ramping up (test) production. Given the massive investment in the new process and non-optimal yield rates, it is unlikely that Samsung will significantly benefit financially from production of the chip in the near-term in terms of gross margin and other chip production-related metrics.

However, the performance lead of the Galaxy S6 made possible by the new chip could have significant positive implications for the sales and financial performance of Samsung's smartphone division, allowing Samsung to recoup some of its investment.

A few months ago, Samsung already signed an agreement with Apple whereby Samsung would supply part of the production capacity for future Apple processors. If this bears fruit it would allow Samsung to recoup more of its investment in 14 nm FinFET technology in the future.

Early benchmark performance impressive


In early benchmarks scores reported in Geekbench's result database, a device that probably is the Galaxy S6 shows impressive performance, well ahead of most existing SoCs and devices. In a direct comparison with an Exynos 5433-equipped Galaxy Note 4, the performance gain is fairly significant for most benchmarks (up to 30% for integer tests, higher for floating point), with a few negative outliers such as SHA2 and the Dijkstra integer subtest. The Dijkstra subtest also scores lower on other 64-bit AArch64 platforms, suggesting it suffers from particular AArch64 features such as the doubled size for pointer storage.

Memory performance is also significantly higher, aided by high clock rate and high amount of bandwidth delivered by the LPDDR4 memory interface, which unlike Qualcomm's Snapdragon 810 does not seem to have serious flaws.

Sources: AnandTech (Samsung annnounces the Galaxy S6 and Galaxy S6 Edge), AnandTech (Samsung Unpacked, MWC 2015 Live Blog), Geekbench Browser (Samsung SM-G925F)

Early benchmarks for MT6795 show high performance, suggest use of eight Cortex-A53 cores

Od: Vegator
MediaTek originally announced the MT6795, a SoC targeting the premium-level and performance segments of the smartphone market, in July 2014, with expectations of devices being commercially available to end users before the end of 2014. However, the chip was delayed (problems with the memory controller were reported) and competitive benchmark results are only now beginning to surface for the chip.

According to the announcement, the SoC was to have an octa-core CPU configuration with clock speeds up to 2.2 GHz, a strong dual-channel memory interface with support for LPDDR3 up to 933 MHz, 2K (2560x1600) display support. Other reports and information have suggested that it uses a PowerVR G6200 GPU, similar to the one used in MediaTek's MT6595, which can be seen as 32-bit predecessor of the new chip.

Confusion about processor cores, octa-core Cortex-A53 seems likely


The actual CPU cores used inside the MT6795 continue to be source of confusion. Initially understood to be an octa-core Cortex-A53 CPU configuration clocked at a high frequency, later a purported leaked MediaTek product roadmap surfaced that described the MT6795 as a big.LITTLE design that includes Cortex-A57 cores. However, a recent new entry in the Geekbench database suggesst that the chip actually has eight Cortex-A53 cores as originally suspected, as the IPC (instructions per cycle) of the integer and floating point subtests would be hard to reconcile with Cortex-A57 cores being present.

Geekbench results show mixed performance but high overall score


The Geekbench results show strong CPU performance, with the overall score being superior to that of available results for Snapdragon 810, which has a significantly higher cost design but has been plagued by performance issues, although it scores lower than Exynos 5433/Exynos 7 Octa with Cortex-A57 cores as used in the Galaxy Note 4. Note that MT6795 uses a less advanced 28 nm process compared to the 20 nm process used for Snapdragon 810 and Exynos 5433.

Single-score integer performance is not spectacular and below that of the previous generation high-end chips such as Snapdragon 801. Although this is compatible with the use of medium-performance Cortex-A53 cores, integer single-core performance is actually lower than the mid-range MT6752, despite the higher clock rate, pointing to continuing hardware performance problems with the chip. The Dijkstra benchmark result is particular low. This benchmark has a lot of external memory access and likely branches a lot, taxing certain elements of the CPU and SoC that simpler CPU benchmarks do not. It may be affected by the doubled address size in AArch64 mode, either through the increased size of pointer storage or reduced efficiency of the branch prediction unit inside the processor core.

Single core floating point performance in the Mandelbrot benchmark is higher than the MT6752 and actually compatible with the Cortex-A53 core running at 2.1 GHz, close to the originally envisaged maximum clock speed for the MT6795. Multi-core performance in this subtest is impressive, with a score that is higher than most existing SoCs including Exynos 7 Octa, which employs faster Cortex-A57 cores.

Finally, the dual-channel memory interface seems to working reasonably well in the tested revision of the chip/development board, with memory scores consistent with an optimized dual-channel interface, and higher, for example, than those of Exynos 5433. However, they are generally lower than those of the 32-bit MT6595.

One caveat is that the MT6795 entry is running in AArch64 mode, while the other devices were running in AArch32 (32-bit ARMv8) or 32-bit ARMv7 mode.

Average single-core CPU performance, strong multi-core performance


In a direct comparison with the MT6752, which has a comparable CPU configuration but clocked lower and has only a 32-bit memory interface, the MT6795 is only slightly faster, although the MT6795 uses a full 64-bit AArch64 instruction set model, while the tested MT6752 configurations use AArch32 with partial use of ARMv8 features. There are a few anomalous results, including a low score for the MT6795 in the single-core AES benchmark, and as mentioned it also scores significantly lower in the Dijkstra benchmark. Floating point performance is consistently higher for the MT6795 (more than the increase in clock rate would explain), which may be caused by the higher-performance memory subsystem of the MT6795 and/or the increased number of floating point registers available in AArch64 mode.

The MT6795 is clearly slower than its 32-bit predecessor MT6595 (which uses high-performance Cortex-A17 and Cortex-A7 cores in a big.LITTLE configuration) in most metrics, with only the heavy weighting and large performance gain for the AES and SHA1 cryptography tests  (due to the new ARMv8 instruction set) shifting the advantage for the overall score towards the MT6795.

When making a comparison with a median entry for the high performance Exynos 5433 (Exynos 7 Octa) inside the Samsung Galaxy Note 4, the MT6795 fairly consistently shows clearly lower single-core performance but higher multi-core performance.

MT6795 likely to be most cost-effective performance segment processor on the market


The exclusive use of Cortex-A53 CPU cores, and not the much more expensive and die-space consuming Cortex-A57 (or, in a 32-bit comparison, Cortex-A15/A17 cores), has positive implications for the cost of the chip. Die space dedicated to the CPU cores will be relatively low, although L2 caches will take considerable space when configured with a size that matches the desired performance level and market segment. Overall, the chip is likely to be attractive in terms of performance/dollar for the performance segment.

In terms of SoC optimizations, the chip would probably work better with the employment of additional ARM IP such as a Mali T760 or Mali-T800 series GPU, which offers advantages in combination with ARM cores such as Cortex-A53 in tandem with techniques such as AFBC, smart composition and transaction elimination, and new interconnect buses within the chip. SoCs like the MT6752 probably benefit from these optimizations, while the MT6795 cannot do so fully because of the non-ARM GPU. It seems likely that the MT6795 will be superseeded in next generation products to be announced by MediaTek in the future by a similar SoC with an ARM Mali-T760 or T800 series GPU.

Update (2 March): Based on a closed-door presentation event at the MWC, MediaTek appears to have rebranded MT6795 as Helio X10 with future Helio P series products also being announced.

Sources: MediaTek (MT6795 announcement), Geekbench browser

MINISFORUM DEG1 barebones eGPU dock with OCuLink now available for $99

The MINISFORUM DEG1 is an external graphics dock with an OCuLink connector that provides a 63 Gbps connection to a laptop, handheld or mini PC. And that’s literally all this compact eGPU dock with a minimalist design does. It doesn’t act as a USB hub or port extender. It doesn’t even have a case. But it’s a […]

The post MINISFORUM DEG1 barebones eGPU dock with OCuLink now available for $99 appeared first on Liliputing.

MediaTek announces Helio P10 and MT6753 arrives in shipping devices

Od: Vegator
MediaTek has announced Helio P10 (MT6755), a performance mid-range smartphone SoC that is the successor of MT6752. Featuring an octa-core Cortex-A53 configuration, Helio P10 improves upon MT6752 by using TSMC's new 28HPC+ manufacturing process, which delivers power efficiency and performance improvements while remaining relatively cost-effective. It can reach a higher maximum CPU clock speed up to 2 GHz and upgrades the GPU to a Mali-T860 MP2. It is expected to be commercially available in end devices by the end of 2015.

Features shared with Helio-X10


The new SoC  incorporates a few features from Helio X10 (MT6795), MediaTek's current high-end offering, including dual ISPs with 21MP camera support and improved capture capability, as well as improved audio quality.

Otherwise, the SoC has significant similarities to MediaTek's MT6752 which it succeeds, most likely including a 32-bit external memory interface, which keeps SoC cost and phone PCB cost down. With MT6752, MediaTek already demonstrated the ability to achieve memory performance adequate for a 1080p device within the constraints of a 32-bit memory interface.

The 28HPC+ process is an upgrade of the existing 28HPC (high-performance compact) process (which is also relatively new, used by Allwinner's A83T and other SoCs), which improves performance and cost relative to the established 28HPM (high-performance mobile) process. Existing MediaTek chips like MT6752 and MT6795 most likely use 28HPM, which is established and has also been used for previous-generation SoCs such as MT6592 and Snapdragon 801/805.

MediaTek migrating to big.LITTLE CPU configurations in new SoCs


A significant departure from existing octa-core MediaTek SoCs such as MT6752 and Helio X10 (MT6795) is the pseudo-big.LITTLE CPU configuration, whereby one cluster of four Cortex-A53 cores is clocked at a higher frequency (up to 2 GHz in this case), while the second of cluster Cortex-A53 cores is optimized for lower frequencies, being clocked at a lower maximum frequency (1.1 GHz according to AnandTech).

Together with the previously announced high-end Helio X20 (MT6797) and tablet/Chromebook-oriented chips such as MT8173, Helio P10 marks a migration to (pseudo-)big.LITTLE, hierarchical CPU designs at MediaTek. While symmetrical octa-core designs such as MT6752 and MT6795 reach very high multi-core processing power by allowing all cores to run at the maximum frequency, there are signs that this configuration impacts power efficiency for tasks that require less CPU power, which can be run on power-optimized low-frequency cores.

In practice, this may be reflected in somewhat mediocre standby battery life for smartphones using MT6752 or MT6795, even though power efficiency for demanding tasks that utilize all cores is likely to be pretty good.

Budget mid-range MT6753 reaches end-market


Meanwhile, MediaTek's previously announced MT6753, which is a cost-effective budget mid-range SoC, has arrived in commercially shipping device in the form of Meizu M2 Note. Despite the name chosen by Meizu, the new model actually has lower performance than the existing Meizu M1 Note, because the MT6753  is a less costly, lower end chip when compared to to the MT6752 inside the M1 Note, with considerably slower maximum CPU speeds for the eight CPU cores, as well as a lower performance GPU. There are also signs that the memory interface and the actual memory frequency used by the M2 Note is slower. The lower cost of the MT6753 platform is reflected in the low selling price of the Meizu M2 Note.

MT6753 implements several cost-reducing features, including a lower maximum clock speed (reported to be 1.3 GHz for the M2 Note), most likely associated with a cheaper manufacturing process (either 28LP or 28HPC) than the 28HPM process of the MT6752. A significant factor for lower performance is likely to be a reduced size of the L2 CPU cache inside the MT6753. MT6753 is likely to become a significant volume driver in MediaTek's 4G product line.

However, early Geekbench entries for the Meizu M2 Note suggest that the CPU cores of the MT6753 SoC used in this model are mostly unable to reach the planned clock frequency. The Geekbench results are mostly consistent with an average maximum CPU clock speed of about 1.1 GHz, significantly lower than the 1.3 GHz reported by the OS and the 1.5 GHz mentioned when the MT6753 was originally announced a few months ago. My following blog article about the use of AArch64 provides more details on this subject.

MT6753 has lower-performance GPU than MT6752


MT6753 also has a significantly lower-performance and smaller GPU (Mali-T720 MP3), compared to the Mali-T760 MP2 inside MT6752. MT6753 marks the first Mali implementation with three pixel processing cores; previous Mali GPUs either had one, two, four, six or eight pixel processing cores, Most likely, Mali-T720 does not have the memory bandwidth usage optimization that are present in Mali-T760, which together with the more limited pixel processing throughput means that devices with a 1080p display such as the Meizu M2 Note may be impacted in terms of 1080p game performance and power efficiency for graphics-intensive operations.

World modem support in new MediaTek platforms


All new MediaTek SoCs (including Helio P10 (MT6755), MT6753, the low-end quad-core MT6735 and the announced high-end Helio X20 (MT6797)) have world-modem support, facilitating compatibility with more cellular networks used worldwide, including legacy CDMA networks in the US and other countries. This makes MediaTek SoCs more attractive to smartphone manufacturers targeting multiple or worldwide markets.

Sources: MediaTek (Helio P10 announcement), AnandTech (Helio P10 article)

Updated 6 June 2015.

HiSilicon introduces Kirin 930/935, a performance-oriented Cortex-A53-based SoC

Od: Vegator
Huawei has introduced the Huawei P8 and P8max smartphones, featuring the Kirin 930 and Kirin 935 SoCs from Huawei's  HiSilicon semiconductor division. The octa-core Kirin 930 SoC is a performance-oriented SoC featuring only Cortex-A53 CPU cores. With a maximum clock frequency in excess of 2.0 GHz, it bears similarities to MediaTek's MT6795, but the use of a pseudo big.LITTLE configuration (four Cortex-A53 cores clocked up to 2.0 GHz and four Cortex-A53 cores clocked up to 1.5 GHz, for a total of eight cores) is reminiscent of Qualcomm's midrange Snapdragon 615 SoC, which runs at lower clock frequencies.

Huawei also introduced high-end models of both the P8 and P8max with larger storage capacity featuring the Kirin 935 SoC, which is a higher-clocked version of Kirin 930. The Huawei P8max is a smartphone with an unusually large 6.8" display.

SoC is targeted at performance-oriented devices


The Huawei P8 models are higher-priced performance-oriented smartphones, and the characteristics of the SoC match this segment. Apart from the high maximum clock speed of the Cortex-A53 cores, the external RAM interface is likely to be a dual-channel 32-bit configuration like previous performance-oriented SoCs from HiSilicon. Presentation materials from Huawei describe the Cortex-A53 cores in the faster cluster of four CPUs as being of a special, performance-enhanced type, which probably reflects the application of ARM's PoP core-hardening technology whereby the core is optimized for running at a specific frequency and a particular power profile, trading performance against die size. The process technology used is likely to be TSMC's proven 28HPM process.

The SoC is reminiscent of MediaTek's recently introduced MT6795 (Helio-X), which also targets the performance segment with an octa-core Cortex-A53 CPU configuration. MediaTek's SoC has been reported to have been adopted by competitors of Huawei such as HTC and Xiaomi.

Previous generation Mali-T628 MP4 GPU used


Rather than using an updated current-generation GPU like Mali-T760, the specs sheet for the P8max indicates the Kirin 930/935 SoCs continue to use the Mali-T628 MP4 GPU that was previously used in the Kirin 920 SoC. This GPU core is not known for great power efficiency, although there are suggestions that the more efficient Mali-T760 (which features memory bandwidth optimizations) has a relatively high silicon area and cost.

HiSilicon's new SoC line-up uses only Cortex-A53 CPU cores


Apart from Kirin 930, HiSilicon has also introduced the Kirin 620 SoC, which is an octa-core Cortex-A53 based SoC for the cost-sensitive segment, clocked up to 1.2 GHz and with a single-channel memory interface. This means Huawei now has in-house Cortex-A53-based SoCs suitable for most of its smartphone product range.

Early benchmarks appear for Cortex-A72-based SoC

Od: Vegator
ARM recently announced the new Cortex-A72 processor core, which is an improved version of the existing high-performance Cortex-A57 processor core.

Alongside the Cortex-A72 CPU core, ARM also announced the CCI-500 interconnect technology as well as the high-end Mali-T880 GPU. Devices incorporating the combination of these technologies are expected to become available in 2016.

However, SoCs using the Cortex-A72 CPU are likely to become available earlier. Qualcomm and MediaTek have both announced SoCs using the Cortex-A72 core with commercial availability in the second half of 2015, suggesting that the CPU core itself is at an advanced stage of introduction. Already, early benchmarks for MediaTek's MT8173 tablet SoC that incorporates the Cortex-A72 have become available.

Cortex-A72 appears to be enhanced version Cortex-A57 optimized for next-generation processes


In its announcement press release from 3 February 2015, ARM claims that more than ten partners have already licensed Cortex-A72, including HiSilicon, MediaTek and Rockchip. Cortex-A72 is based on ARM's ARMv8-A instruction set architecture, and can be combined with the existing Cortex-A53 in a big.LITTLE configuration. Cortex-A72 seems to be positioned as a replacement for Cortex-A57. The similarities with Cortex-A57 are very apparent, for example in the identically sized L1 instruction and data caches, and a feature set that is otherwise very similar.

On a 16 nm FinFET process, the core can sustain operation at speeds up to 2.5 GHz within the constraints of a mobile power envelope (e.g. smartphones), with scalability to higher speeds for larger form-factor devices. However, the first announced devices, such as MediaTek's MT8173, appear to use older processes such as the tried-and-trusted 28 nm HPM process at TSMC, so they are likely to have a lower maximum clock speed.

ARM claims increased performance and power efficiency, although these claims seem to be based on implementation on next-generation processes such as 16 nm FinFET that deliver a significant intrinsic improvement in these metrics. ARM mentions micro-architectural improvements that result in enhancements in floating point, integer and memory performance. When implemented on a 16 nm FinFET process, ARM expects Cortex-A57 to provide 85% higher performance when compared to the Cortex-A57 core on a 20 nm process within a similar smartphone power budget.

Overall, the differences with Cortex-A57 appear to be relatively minor, so that Cortex-A72 is best viewed as an enhanced version of Cortex-A57 that is optimized for next-generation processes such as 16 nm FinFET. Nevertheless, the first SoCs to use the Cortex-A72 core will be manufactured using a less advanced process.

Benchmarks appear for MediaTek's MT8173


MediaTek's MT8173 is a mid-range tablet processor mainly targeting Wi-Fi-only tablets, since it does not have an integrated modem. It has two Cortex-A72 cores and two Cortex-A53 cores in a big.LITTLE configuration. Probably manufactured using the established 28HPM process at TSMC, the maximum clock speed of the Cortex-A57 cores is likely to be lower that the target for 16 nm FinFET, although MediaTek claims a clock speed up to 2.4 GHz, while a much lower frequency is apparent in early benchmarks results.

The chip also features a PowerVR GX6250 GPU, which delivers higher performance than the G6200 GPU used inside MediaTek's existing MT8135 and MT6795.

Recently, early benchmarks for a MT8173 development board have appeared both in the Geekbench Browser and in the results database of GFXBench. The first Geekbench results already appeared in December 2014. The latest set of Geekbench results date from the end of February 2015, although they do show a certain amount variation that may reflect thermal throttling.

Single-core performance good, but not spectacular


As expected, the Geekbench results show good single-core performance, albeit not spectacular. As shown in the following table, singe-core performance is in line with Cortex-A57-based SoCs such as Exynos 5433 and Exynos 7420. It should be noted that the MT8173 test SoC is most likely manufactured at 28 nm with a corresponding relatively low maximum CPU clock speed, while Exynos 5433 and 7420 are manufactured using smaller leading edge processes at Samsung.


SoC          "big" CPU                    Arch     JPEG (int)  Lua (int)   Mandelb. (fp)
                                                   Comp. IPC         IPC         IPC
MT8173       2 x 1.6? GHz Cortex-A72      AArch32  1310  2.13  1380  2.10  1064  1.95
Exynos 5433  4 x 1.80 GHz Cortex-A57r1p0  AArch32  1456  2.10  1397  1.89  1174  1.91
Exynos 7420  4 x 1.97 GHz Cortex-A57r1p0  AArch64  1481  1.97  1409  1.74  1198  1.92

In this table, to determine the IPC index I have made an educated guess about the actual clock speed of MT8173 when running the benchmarks. Geekbench reports a 1.40 GHz clock speed (which probably applies to the Cortex-A53 cores), 1.6 GHz seems to be a good match, providing just a little better IPC than Cortex-A57. Note that Exynos 7420 runs in AArch64 mode, which skews direct IPC comparisons.

Practical implications unclear


Without knowing the exact clock speed of the Cortex-A72 cores, it is hard to draw conclusions about the actual IPC improvement over Cortex-A57. If the MT8173 uses a 28 nm process, the ability to approach the single-core performance of Samsung's Exynos 7420 manufactured using 14 nm FinFET process is impressive. However, although MediaTek demonstrated the MT8173 in an actual tablet at MWC, it is unclear what kind of device the Alps development board in the benchmark entries actually represents, so it remains to be seen whether the benchmarks actually reflect the power budget of a tablet.

The multi-core performance reported is not very impressive, as expected because of the relatively small number of CPU cores. The JPEG Compress multi-core score shows CPU scaling factor of 2.72, which is good and implies utilization of the Cortex-A53 cores. The Mandelbrot floating point benchmark shows similar scaling.

However, the Lua integer benchmark has a very low multi-core scaling factor of 1.41, which is lower than expected, even when allowing for the limited number of cores. For example, MediaTek's MT6795 achieves multi-core scaling of 7.5 in this benchmark, and the Exynos chips range from 3.9 to 5.0. Other chips with a low multi-core scaling factor for Geekbench's Lua subtest include Snapdragon 810 (Cortex-A57-based), MediaTek's MT6595 (Cortex-A17-based) and NVIDIA's Denver-based Tegra-K1 SoC. There are indications that this benchmark test heavily depends on on-chip cache (primarily L2 cache) size and speed.

GPU performance of MT8173's PowerVR GX6250 GPU improves on G6200


The MT8173 test device's GPU performance as shown in GFXBench results database is not overly impressive, but suitable for a mid-range chip and an improvement over the PowerVR G6200 GPU used in other MediaTek SoCs such as MT6595 and MT6795. In the T-Rex Offscreen benchmark, the MT8173 registers a score of 1487, higher than the 1311 of the MT6595 (G6200)-equipped Meizu MX4. In the GFXBench 3.0 low-level tests, alpha blending scores higher than the MT6595 while the other low-level scores are comparable.

Sources: ARM (Cortex-A57 announcement press release), AnandTech (MediaTek MT8173 article), MediaTek (MT8173 announcement), Geekbench Browser (MT8173 test device results), GFXBench (MT8173 test device result)

Updated 10 March 2015.

A deeper look at graphics benchmark results, including GFXBench 3.1 and Basemark X

Od: Vegator
In this post I will take a closer at graphics benchmark results for different SoCs. I will look beyond just GFXBench (for which a new version has appeared), because the workload tested by well-known GFXBench tests such as T-Rex and Manhattan is not necessarily reflective of the actual gaming experience. Alternative benchmarks exist, such as Basemark X which uses the Unity engine that is commonly used in games.

GFXBench 3.1 released for OpenGL ES 3.1, Snapdragon 805 does well


Kishonti recently released a new version of GFXBench, GFXBench 3.1 for OpenGL ES 3.1, that includes tests for the OpenGL ES 3.1 API standard supported by many recent devices. A few results from the new benchmark tests are already available, with the Adreno 420 GPU inside Snapdragon 805 closing most of the performance gap with the Mali-T760 MP6/MP8 in Samsung's Exynos SoCs in the Manhattan 3.1 test.

                                                      Offscreen Manhattan Manhattan
Device               SoC             GPU              T-Rex        3.0       3.1

NVIDIA Shield Tablet NVIDIA K1-32    Tegra K1 GPU        3692     1979      1443  
HTC One M9           Snapdragon 810  Adreno 430          2732     1413
Galaxy S6 Edge       Exynos 7420     Mali-T760 MP8?      3312     1607       793
Sams. Galaxy Note 4  Snapdragon 805  Adreno 420          2386     1153       773
Samsung Galaxy S6    Exynos 7420     Mali-T760 MP8?      3314     1609       634
Sams. Galaxy Note 4  Exynos 5433     Mali-T760 MP6       2163     1110       436
HTC One M8           Snapdragon 801  Adreno 330          1608      768
Teclast X98 Air      Atom Z3736F     Intel HD            1014      564       307
Google Nexus 10      Exynos 5250     Mali-T604 MP4        818      351       185

NVIDIA's Tegra 32-bit version of Tegra K1 leads (the 64-bit Denver-based version of Tegra K1, and Tegra X1, have not yet been tested). Performance of Snapdragon 805 as implemented in certain models of the Samsung Galaxy Note 4 holds up better in the Manhattan 3.1 test than Samsung's Exynos SoCs with Mali-T760 MP6/MP8. Whereas Exynos 7420 (used in the Galaxy S6) has a clear advantage in existing benchmarks (1609 vs 1153 for Manhattan and 3314 vs 2386 for T-Rex), it loses that advantage in the new Manhattan 3.1 test (although the Galaxy S6 Edge benchmarks result suggests it is still slightly superior). Intel's Baytrail SoCs seem to hold up relatively well looking at the result for an Atom Z3736F-based tablet, albeit at a lower performance level.

GFXBench 3.1 results for Snapdragon 801 and the new Snapdragon 810 are not yet available. However, given the fact that GFXBench appears to generally do well on Snapdragon SoCs, they can be expected to score fairly highly. I'll say more about the apparent advantage for Qualcomm's SoC in GFXBench in the final section of this article.

Basemark X is a useful alternative to GFXBench


Basemark X is a gaming benchmark that utilizes the Unity engine that is commonly used in games, and developer Rightware claims that it actually reflects practical performance in games. Although it does include an on-screen demo, the actual benchmark scores appear to be derived from off-screen rendering at a fixed resolution, so that benchmark results can be compared objectively between different devices.

Previous generation SoCs: MT6582 beats Snapdragon 400 in Basemark X


Taking a look at previous-generation cost-sensitive SoCs, while MediaTek's ubiquitous quad-core 3G SoC MT6582 (which supports Open GL ES 2.0 only, through its Mali-400 MP2 GPU) scores lower than Snapdragon 400 in GFXBench's OpenGL ES 2.0-based T-Rex test (about 230 vs 330), in Basemark X MT6582-based devices score higher than Snapdragon 400 based devices. This is despite the fact that Snapdragon was/is often employed in devices with a considerably higher selling price than MT6582-based devices.

Device               SoC             GPU                 Display*   Medium   High

Samsung SM-G800F     Exynos 3470     Mali-400 MP4        1280x720    7527    2712
Vodafone 985N        MT6582          Mali-400 MP2         960x540    4950    1717
Acer E53             MT6582          Mali-400 MP2        1280x720    4870    1694
Wiko Rainbow         MT6582          Mali-400 MP2        1280x720    4826
Galaxy S3 Neo        Snapdragon 400T Adreno 305          1280x720    4540    1551
Moto G (XT1032)      Snapdragon 400  Adreno 305          1280x720    4440
HTC Desire 816d      Snapdragon 400T Adreno 405          1280x720    4354    1441
Samsung SM-A500F     Snapdragon 410  Adreno 306          1280x720    4132    1900
Samsung SM-A300F     Snapdragon 410  Adreno 306           960x540    4076    1892
Samsung SM-G530H     Snapdragon 410  Adreno 306           960x540    3987    1690
Samsung SM-G800A     Snapdragon 400  Adreno 305          1280x720    3946    1362
HTC Desire 820q      Snapdragon 410  Adreno 306          1280x720    3786

* While Basemark X is independent of display resolution in terms of rendering, the
memory bandwidth used for screen refresh has some impact, giving lower-resolution
devices a small advantage.
Notes: Samsung SM-G800F is the Galaxy S5 Mini (Exynos version), while SM-G800A is a Snapdragon 400 running at the non-standard maximum clock speed of 1.4 GHz; Vodafone 985N is the Vodafone Smart 4 Power; Acer E53 is the Acer Liquid E700; Galaxy S3 Neo runs the Snapdragon 400 SoC at a non-standard maximum speed of 1.4 GHz; HTC Desire 816d runs the Snapdragon 400 SoC at 1.6 GHz; SM-A500F is the Galaxy A5, while SM-A300F is the Galaxy A3; SM-G530H is the Galaxy Grand Prime.

For both the medium detail and high detail settings, MT6582-based devices consistently score higher in Basemark X than Snapdragon 400 and also Snapdragon 410-based devices for the medium detail test, which gives a different picture than the one you get from just looking at GFXBench's T-Rex benchmark

Snapdragon 410 performs worse than Snapdragon 400 in Basemark X medium-detail


Also notable is that Snapdragon 410, which is the successor of the Snapdragon 400 and would normally be expected to improve performance, actually has lower performance in practice as judged by the Basemark X medium detail benchmark. This matches earlier findings of performance flaws in Snapdragon 410. When running the high detail Basemark X benchmark, Snapdragon 410 does better and beats Snapdragon 400.

Mid-range SoCs: Snapdragon 615 and MT6752 closely matched


When running GFXBench, Snapdragon 615 and MT6752 are closely matched, with Snapdragon 615 scoring about 830 to 850 in T-Rex while MT6752 scores just above 870. For T-Rex, devices using MediaTek's prior-generation octa-core MT6592 score in the range 650 to 750. In the OpenGL ES 3.0 API-based Manhattan benchmark, Snapdragon 615 and MT6752 are very closely matched, both scoring around 360. We will also take a look at Basemark X results.

The following table shows Basemark X results for the new competing mid-range SoCs Snapdragon 615, MT6752 and HiSilicon's octa-core Hi6210 (Kirin 620), as well as for the prior-generation octa-core MT6592 from MediaTek.

Device               SoC             GPU                 Display*   Medium   High

Lenovo P70-A         MT6752          Mali-T760 MP2       1280x720   11311 
Meizu M1 Note        MT6752          Mali-T760 MP2       1920x1080  11168    4636
HTC Desire 816G      MT6592          Mali-450 MP4        1280x720   10984
Huawei CHE2-TL00     Hi6210          Mali-450 MP4        1280x720   10546    3439
Oppo R8106           Snapdragon 615  Adreno 405          1920x1080  10277    4846 
HTC Desire 820       Snapdragon 615  Adreno 405          1280x720   10133    4814
Samsung SM-A700FD    Snapdragon 615  Adreno 405          1920x1080  10052    4757
Archos 50C Oxygen    MT6592          Mali-450 MP4        1280x720    9867    3702
HTC Desire 616d      MT6592M         Mali-450 MP4        1280x720    7976    3045

* While Basemark X is independent of display resolution in terms of rendering, the
memory bandwidth used for screen refresh has some impact, giving lower-resolution
devices a small advantage.
Notes: SM-A700FD is the Galaxy A7; Huawei CHE2-TL00 is a new version of the Honor 4X.

When running the standard medium-detail version of Basemark X, MediaTek's MT6752 has  a moderate advantange over Snapdragon 615, while at the high detail setting Snapdragon 615 has a small advantage. Huawei's Kirin 620 performs adequately and just ahead of Snapdragon 615 in the medium detail setting.

MediaTek's prior-generation octa-core MT6592 with Mali-450 MP4 GPU keeps up relatively well in Basemark X,  with certain models (e.g. HTC Desire 816G) actually beating Snapdragon 615 in the medium detail setting.

Performance-oriented SoCs with Basemark X


The following table shows Basemark X results for several performance-oriented mobile SoCs.

Device               SoC             GPU                 Display*   Medium   High

Samsung Galaxy S6    Exynos 7420     Mali-T760 MP6       2560x1440  36017
Galaxy S5 LTE-A      Snapdragon 805  Adreno 420          1920x1080  32685   18334
Google Nexus 6       Snapdragon 805  Adreno 420          2560x1440  30362   20265
Sams. Galaxy Note 4  Snapdragon 805  Adreno 420          2560x1440  31963   21152
Sams. Galaxy Note 4  Exynos 5433     Mali-T760 MP6       2560x1440  29335   19019 

Apple iPad Air 2     Apple A8X       PowerVR Series 6    2048x1536  41700   29239
Google Nexus 9       NVIDIA K1-64    Tegra-K1 GPU        2048x1536  37939   28646
Apple iPad Mini 3    Apple A7        PowerVR Series 6    2048x1536  26499   14780
Teclast X98 Air      Atom Z3736F     Intel HD            2048x1536  14825    7160
Teclast P90HD        Rockchip RK3288 Mali-T764           2048x1536  13053    5645
Onda V989 Core8      Allwinner A80   PowerVR G6230       2048x1536  11004    5724

Meizu MX4 Pro        Exynos 5430     Mali-T628 MP6       1920x1200  25547   12674
Samsung SM-G900A     Snapdragon 801  Adreno 330          1920x1080  25178   11930
Samsung SM-G850F     Exynos 5430     Mali-T628 MP6       1280x720   21872   10666
Meizu MX4            MT6595          PowerVR G6200       1920x1200  17038    7817
Huawei MT7-TL10      Kirin 925       Mali-T624 MP4       1920x1080  15973    6802

* While Basemark X is independent of display resolution in terms of rendering, the
memory bandwidth used for screen refresh has some impact, giving lower-resolution
devices a small advantage.
Notes: SM-G900A is the Samsung Galaxy S5 (US version), Huawei MT7-TL10 is the Huawei Mate 7.

Looking at the ultra-high-end smartphone segment (mostly with a display resolution of 2560x1440), Exynos 7420 provides superior performance in Basemark X. Snapdragon 805 follows, a small distance ahead of Exynos 5433 as used in the Samsung Galaxy Note 4.

In the high-end tablet segment, Apple's iPad Air 2 with the Apple A8X leads, but the Nexus 9 with NVIDIA's Tegra K1 (64-bit version) comes fairly close. Apple's prior generation SoCs also delivers good performance, while Intel's current Baytrail SoC for the tablet market outperforms two high-end chips from established Chinese players in the tablet SoC market, Rockchip's RK3288 and Allwinner A80 Octa.

Mainwhile, in the mainstream performance smartphone segment, Snapdragon 801 (in the past the performance leader in the market) still provides good performance, but is actually just beaten by the 32-bit Exynos 5430 in the Meizu MX4 Pro. The chip is also used in the Galaxy Alpha (for which it provides higher-than-necessary performance given its relatively low screen resolution), while the performance of MediaTek's MT6595 SoC, while not bad, falls short of most other high-end solutions. HiSilicon's Kirin 925 as implemented in the Huawei Mate 7 is just behind.

Conclusion


It appears that just concentrating on GFXBench may give a misleading picture with regard to 3D graphics performance of mobile SoCs. In particular it is apparent that Qualcomm's Snapdragon SoCs consistently do better in GFXBench than in other benchmarks such as Basemark X. This is particularly true for the lower-end Snapdragon 400 and higher-end Snapdragon 800 series; for Snapdragon 615, results are more consistent across different benchmarks.

Basemark X, which utilizes the Unity game engine commonly used in mobile games, may more accurately reflect real-world performance.

Sources: Rightware Power Board (Basemark X benchmark results), GFXBench results database

Updated 5 March 2015: Add Galaxy S6 Edge result for GFXBench 3.1.
Updated 15 March 2015.

New mobile SoCs announced at MWC

Od: Vegator
At the Mobile World Congress this week, several new mobile SoCs are being announced.

MediaTek announces cost-reduced MT6753 for smartphones


MediaTek anounced two mobile SoCs, the MT6753 for smartphones and the MT8173 for tablets.

The MT6753 appears to be a cost-reduced version of the successful MT6752, equpped with "WorldMode" modem technology. By offering compatibility with the CDMA2000 standard, it gives customers worldwide greater diversity and flexibility in their product layouts, according to MediaTek. Features include an octa-core Cortex-A53 CPU up to 1.5 GHz and a Mali-T720 GPU with an unspecified number of cores. ARM's Mali-T720 GPU is positioned at a significantly lower performance bracket than the Mali-T760 used in the MT6752, positioning the MT6753 below the MT6752 in terms of cost and performance.

The MT6753 is described as being compatible with the previously announced MT6735 for entry-level smartphones. The MT6735 has four Cortex-A53 cores instead of eight but otherwise has a similar configuration with a Mali T720 GPU.

High-performance MT8173 tablet SoC uses small big.LITTLE clusters with Cortex-A72


The MT8173 is a high-performance tablet processor (without integrated modem) that utilizes ARM's new Cortex-A72 core in a big.LITTLE configuration. By using only two Cortex-A72 cores (clocked up to 2.4 GHz) as well as two Cortex-A53 cores, the chip has a lower cost than would be the case with the four-by-four core configuration commonly used for big.LITTLE designs, while still providing good performance.

The Cortex-A72 core, the successor of Cortex-A57, appears to be seeing quick adoption as Qualcomm has already announced performance-segment smartphone SoCs (Snapdragon 618 and 620) featuring the core.

MediaTek has previously used a similar two-by-two big.LITTLE configuration in its MT8135(V) tablet SoC, which has two Cortex-A15 cores and Cortex-A7 cores. This chip was used in Amazon tablets but otherwise did not see much adoption.

Other features include a PowerVR GX6250 GPU, which is part of Imagination's Series 6XT family, with higher performance and efficiency than the G6200 GPU used in chips such as the MT8135 and MT6595.

Other tablet SoCs not yet publicly announced by MediaTek


Meanwhile, tablet product announcements by Lenovo also refer to the MT8161 and MT8165 SoCs, which have not been announced. From the specifications of the Lenovo Tab 2 A8 which is using it, the MT8161 appears to be a tablet SoC without modem with quad-core Cortex-A53 CPU running up to 1.3 GHz, while the MT8165 (used in the Tab 2 A10) is a similar SoC with the CPU running up to 1.5 GHz. The 4G version of the Lenovo tablets come equipped with the MT8735 (Tab 2 A8) and MT8732 (Tab 2 A10). These chips are the tablet versions of the MT6735 and MT6732 smartphone SoCs.

MT6795 renamed to Helio X10


In a closed-door presentation at MWC, MediaTek also presented the Helio X10 smartphone SoC, featuring a 64-bit octa-core CPU up to 2.2 GHz, 120 Hz display refresh rate and H.265 video encode up to 4K2K @ 30 fps. A photograph of a slide taken at the presentation strongly suggests that Helio X10 is nothing other than the delayed MT6795 SoC, whose specifications closely match. Devices using this chip are likely to have already started production. MediaTek also talked about the Helio P series, a high-performance platform, which will make its way into devices before the end of the year.

Qualcomm gives preview of next-generation Snapdragon 820 SoC


In a press release, Qualcomm has given a preview of the Snapdragon 820, which utilizes Qualcomm's new custom 64-bit CPU architecture for mobile devices called Kryo. The chip will start sampling in the second half of 2015 according to Qualcomm, with devices becoming available in 2016. It will be manufactured on a next-generation FinFET process (which probably means TSMC's 16FF+, but Samsung cannot be excluded). In the press release, Qualcomm does not mention whether the chip will conform to ARM's ARMv8 instruction set architecture.

In conjuction with the Snapdragon 820, Qualcomm also announced the Zeroth hardware/software platform focusing on device intelligence features including video and audio recognition techniques (such as visual object and face recognition).

Intel introduces tablet and smartphone SoCs with integrated modem


Intel has finally introduced SoCs with an integrated cellular modem in its Atom system-on-a-chip product line. The former SoFIA platform has been renamed to Atom X3 and features multi-core 64-bit Atom processors with integrated 3G or 4G LTE modem technology. The following products are available:
  • Atom X3-C3130, which has dual-core Atom CPU running up to 1.0 GHz and integrates a 3G modem. It features Mali-400 MP2 GPU. Maximum display resolution is 1280x800. It appears to be in the same market segment as MediaTek's previous-generation 3G SoCs such as MT6572 and MT6582 and other SoCs that are already on the market.
  • Atom X3-C3230RK, which was developed by Intel partner Rockchip following the agreement announced last year. It has quad-core Atom CPU, integrates a 3G modem and features a Mali-450 MP4 GPU.
  • Atom X3-C3440, a quad-core Atom CPU platform that integrates a Cat 6 LTE 4G modem. It has an Mali-T720 MP2 GPU. This product appears to be one that is most likely to succeed in the market.
All feature a 32-bit memory interface with support for LPDDR2 (and DDR3/DDR3L with the X3-C3230RK). These are the first Intel products that have features (such as the integrated modem) that make them specifically suitable for the smartphone market. They also target cellular-enabled tablets.

The 3G products are a little behind the times, and their success is uncertain. It will be interesting observe whether Rockchip was able to develop the X3-C3230RK in time (one would expect Intel to have greater expertise/resources so that the other products will appear on the market first).

One notable fact is that these are among the first SoCs to integrate an ARM GPU core with a non-ARM CPU.

Intel announces first 14 nm Atom SoCs for tablets and all-in-ones


Intel also rolled out its first 14 nm Atom SoCs, the Atom x5 and x7 processor series (formely codenamed Cherry Trail) with  Intel Gen 8 graphics, targeting tablets and small screen all-in-ones.

Intel has also introduced a new stand-alone modem chip, XMM 7360, which support LTE Cat 10 and download speeds up to 450 Mbps, as well as wireless connnectivity products (including WiFi/Bluetooth, GNSS/GPS and NFC solutions).

Sources: MediaTek (MT6753 announcement), MediaTek (MT8173 announcement), Qualcomm (Snapdragon 820/Zeroth platform preview), Intel (MWC announcements), Intel Atom x3 Processor Series Brief

Samsung announces Galaxy S6 with Exynos 7420 SoC manufactured on "14nm" FinFET process

Od: Vegator
At the Mobile World Congress today (Sunday 1 March), Samsung announced the Galaxy S6 and Galaxy S6 Edge, featuring a numerous improvements over the previous generation Galaxy S5, including a SoC manufactured on Samsung's 14 nm FinFET-based process. The Galaxy S6 is planned to available in 20 countries starting on April 10th, 2015.

New model implement several improvements


The improvements in the new model include the following:
  • Exynos 7420 SoC manufactured on 14 nm FinFET process with 20 nm interconnects. The CPU is a big.LITTLE configuration with four Cortex-A57 and four Cortex-A53 cores, similar to Exynos 5433. The maximum clock speeds are 2.1 GHz and 1.5 GHz, respectively. Samsung claims 20% better performance and 35% better efficiency for the new chip when compared to Exynos 5433, which is manufactured using Samsung's 20 nm HKMG process.
  • The GPU has been rumoured to be a faster version of the Exynos 5433's Mali-T760 MP6 (either a higher clock rate or an MP8 configuration).
  • Early benchmarks indicate a significant increase in CPU and memory performance combined with a measurable increase in GPU performance (which is required because of the higher screen resolution).
  • Runs in 64-bit AArch64 mode, which has several advantages, as well as some disadvantages.
  • Uses new LPDDR4 SDRAM (3 GB), which has higher memory bandwidth at a given memory bus width due to higher effective clock speeds.
  • The cameras have been improved, including greater light gathering capability.
  • The 5.1" AMOLED screen's resolution is QHD (2560x1440), which is 77% more pixels than the FullHD (1920x1080) screen in Galaxy S5. The higher CPU, GPU and memory performance are essential to keep pace with increased demands caused by the higher resolution.
  • Utilizes the new UFS 2.0 interface for embedded flash memory, providing SSD-like performance according to Samsung.
  • Cat 6 LTE mode.
  • Touchwiz user-interface on top of 64-bit Android 5.0 is said to be more intuitive and less demanding in terms of processing requirements.
At the same time,  Samsung has dropped the MicroSD slot and the battery is non-removable. The battery capacity is also slightly smaller that of the Galaxy S5.

The Galaxy S6 Edge, like the Galaxy Note 4 Edge, features a screen that curves around the edges. It is priced significantly higher than the Galaxy S6, which will not be cheap either.

Quick ramp of 14nm FinFET process brings challenges to Samsung


The initial 14 nm FinFET process used by Samsung has been reported to use 20 nm interconnects with a 14 nm features size. As such it is more of an evolutionary step from 20 nm than full-blooded 14 nm FinFET would be, comparable to some degree with TSMC's 16FF process.

Still, Samsung will face a huge challenge ramping up the process in sufficient volume and acceptable yield rates to equip the high volume of Galaxy S6's expected. Rumours have mentioned low yield for the process in the recent past as Samsung started ramping up (test) production. Given the massive investment in the new process and non-optimal yield rates, it is unlikely that Samsung will significantly benefit financially from production of the chip in the near-term in terms of gross margin and other chip production-related metrics.

However, the performance lead of the Galaxy S6 made possible by the new chip could have significant positive implications for the sales and financial performance of Samsung's smartphone division, allowing Samsung to recoup some of its investment.

A few months ago, Samsung already signed an agreement with Apple whereby Samsung would supply part of the production capacity for future Apple processors. If this bears fruit it would allow Samsung to recoup more of its investment in 14 nm FinFET technology in the future.

Early benchmark performance impressive


In early benchmarks scores reported in Geekbench's result database, a device that probably is the Galaxy S6 shows impressive performance, well ahead of most existing SoCs and devices. In a direct comparison with an Exynos 5433-equipped Galaxy Note 4, the performance gain is fairly significant for most benchmarks (up to 30% for integer tests, higher for floating point), with a few negative outliers such as SHA2 and the Dijkstra integer subtest. The Dijkstra subtest also scores lower on other 64-bit AArch64 platforms, suggesting it suffers from particular AArch64 features such as the doubled size for pointer storage.

Memory performance is also significantly higher, aided by high clock rate and high amount of bandwidth delivered by the LPDDR4 memory interface, which unlike Qualcomm's Snapdragon 810 does not seem to have serious flaws.

Sources: AnandTech (Samsung annnounces the Galaxy S6 and Galaxy S6 Edge), AnandTech (Samsung Unpacked, MWC 2015 Live Blog), Geekbench Browser (Samsung SM-G925F)

Early benchmarks for MT6795 show high performance, suggest use of eight Cortex-A53 cores

Od: Vegator
MediaTek originally announced the MT6795, a SoC targeting the premium-level and performance segments of the smartphone market, in July 2014, with expectations of devices being commercially available to end users before the end of 2014. However, the chip was delayed (problems with the memory controller were reported) and competitive benchmark results are only now beginning to surface for the chip.

According to the announcement, the SoC was to have an octa-core CPU configuration with clock speeds up to 2.2 GHz, a strong dual-channel memory interface with support for LPDDR3 up to 933 MHz, 2K (2560x1600) display support. Other reports and information have suggested that it uses a PowerVR G6200 GPU, similar to the one used in MediaTek's MT6595, which can be seen as 32-bit predecessor of the new chip.

Confusion about processor cores, octa-core Cortex-A53 seems likely


The actual CPU cores used inside the MT6795 continue to be source of confusion. Initially understood to be an octa-core Cortex-A53 CPU configuration clocked at a high frequency, later a purported leaked MediaTek product roadmap surfaced that described the MT6795 as a big.LITTLE design that includes Cortex-A57 cores. However, a recent new entry in the Geekbench database suggesst that the chip actually has eight Cortex-A53 cores as originally suspected, as the IPC (instructions per cycle) of the integer and floating point subtests would be hard to reconcile with Cortex-A57 cores being present.

Geekbench results show mixed performance but high overall score


The Geekbench results show strong CPU performance, with the overall score being superior to that of available results for Snapdragon 810, which has a significantly higher cost design but has been plagued by performance issues, although it scores lower than Exynos 5433/Exynos 7 Octa with Cortex-A57 cores as used in the Galaxy Note 4. Note that MT6795 uses a less advanced 28 nm process compared to the 20 nm process used for Snapdragon 810 and Exynos 5433.

Single-score integer performance is not spectacular and below that of the previous generation high-end chips such as Snapdragon 801. Although this is compatible with the use of medium-performance Cortex-A53 cores, integer single-core performance is actually lower than the mid-range MT6752, despite the higher clock rate, pointing to continuing hardware performance problems with the chip. The Dijkstra benchmark result is particular low. This benchmark has a lot of external memory access and likely branches a lot, taxing certain elements of the CPU and SoC that simpler CPU benchmarks do not. It may be affected by the doubled address size in AArch64 mode, either through the increased size of pointer storage or reduced efficiency of the branch prediction unit inside the processor core.

Single core floating point performance in the Mandelbrot benchmark is higher than the MT6752 and actually compatible with the Cortex-A53 core running at 2.1 GHz, close to the originally envisaged maximum clock speed for the MT6795. Multi-core performance in this subtest is impressive, with a score that is higher than most existing SoCs including Exynos 7 Octa, which employs faster Cortex-A57 cores.

Finally, the dual-channel memory interface seems to working reasonably well in the tested revision of the chip/development board, with memory scores consistent with an optimized dual-channel interface, and higher, for example, than those of Exynos 5433. However, they are generally lower than those of the 32-bit MT6595.

One caveat is that the MT6795 entry is running in AArch64 mode, while the other devices were running in AArch32 (32-bit ARMv8) or 32-bit ARMv7 mode.

Average single-core CPU performance, strong multi-core performance


In a direct comparison with the MT6752, which has a comparable CPU configuration but clocked lower and has only a 32-bit memory interface, the MT6795 is only slightly faster, although the MT6795 uses a full 64-bit AArch64 instruction set model, while the tested MT6752 configurations use AArch32 with partial use of ARMv8 features. There are a few anomalous results, including a low score for the MT6795 in the single-core AES benchmark, and as mentioned it also scores significantly lower in the Dijkstra benchmark. Floating point performance is consistently higher for the MT6795 (more than the increase in clock rate would explain), which may be caused by the higher-performance memory subsystem of the MT6795 and/or the increased number of floating point registers available in AArch64 mode.

The MT6795 is clearly slower than its 32-bit predecessor MT6595 (which uses high-performance Cortex-A17 and Cortex-A7 cores in a big.LITTLE configuration) in most metrics, with only the heavy weighting and large performance gain for the AES and SHA1 cryptography tests  (due to the new ARMv8 instruction set) shifting the advantage for the overall score towards the MT6795.

When making a comparison with a median entry for the high performance Exynos 5433 (Exynos 7 Octa) inside the Samsung Galaxy Note 4, the MT6795 fairly consistently shows clearly lower single-core performance but higher multi-core performance.

MT6795 likely to be most cost-effective performance segment processor on the market


The exclusive use of Cortex-A53 CPU cores, and not the much more expensive and die-space consuming Cortex-A57 (or, in a 32-bit comparison, Cortex-A15/A17 cores), has positive implications for the cost of the chip. Die space dedicated to the CPU cores will be relatively low, although L2 caches will take considerable space when configured with a size that matches the desired performance level and market segment. Overall, the chip is likely to be attractive in terms of performance/dollar for the performance segment.

In terms of SoC optimizations, the chip would probably work better with the employment of additional ARM IP such as a Mali T760 or Mali-T800 series GPU, which offers advantages in combination with ARM cores such as Cortex-A53 in tandem with techniques such as AFBC, smart composition and transaction elimination, and new interconnect buses within the chip. SoCs like the MT6752 probably benefit from these optimizations, while the MT6795 cannot do so fully because of the non-ARM GPU. It seems likely that the MT6795 will be superseeded in next generation products to be announced by MediaTek in the future by a similar SoC with an ARM Mali-T760 or T800 series GPU.

Update (2 March): Based on a closed-door presentation event at the MWC, MediaTek appears to have rebranded MT6795 as Helio X10 with future Helio P series products also being announced.

Sources: MediaTek (MT6795 announcement), Geekbench browser
❌