The new Particle Tachyon is a 2.7GHz single-board computer (SBC) with 5G connectivity and a whopping 12 TOPS of AI-optimized GPU acceleration.
The post Particle Return to their Roots to Kickstart New AI-Enhanced 5G IoT SBC appeared first on Make: DIY Projects and Ideas for Makers.
It just does not work that way
Elon Musk's Neuralink brain-implant venture could revolutionise artificial vision for the visually impaired, but it’s unlikely to deliver on Musk’s bold claim of “better than normal vision,” according to University of Washington researchers.
In a study published in Scientific Reports, UW psychologists Ione Fine and Geoffrey Boynton explain that the brain’s vision system relies on complex neuron interactions that don’t translate into a simple pixel-by-pixel picture.
“Engineers often think of electrodes as producing pixels, but that’s not how biology works,” Fine said.
Neuralink has been developing brain implants to help quadriplegic patients control tools with their minds.
One patient, Noland Arbaugh, received an implant in January and reported being “very happy” despite some performance issues. Musk hopes to expand the number of implant recipients this year, pending regulatory approval.
Musk’s next goal is to provide artificial vision through a system called Blindsight. Early tests in monkeys have shown some promise, but human trials are still a way off.
Musk admitted the initial resolution would be low, like “Atari graphics,” but claimed it could eventually surpass normal vision.
Fine and Boynton’s simulations suggest that even with tens of thousands of electrodes, the images produced wouldn’t match the detail of natural vision. Fine noted the immense challenge of replicating the brain’s visual processing, as each neuron has its unique code.
The study highlights the complexity of creating effective artificial vision and cautions against overhyping the technology.
Fine emphasised the need for realistic expectations, especially for those who become blind later in life and may be desperate for a solution.
The research, funded by the National Institutes of Health, underscores the importance of understanding the limitations and potential of brain-implant technology.
The new Particle Tachyon is a 2.7GHz single-board computer (SBC) with 5G connectivity and a whopping 12 TOPS of AI-optimized GPU acceleration.
The post Particle Return to their Roots to Kickstart New AI-Enhanced 5G IoT SBC appeared first on Make: DIY Projects and Ideas for Makers.
The new Particle Tachyon is a 2.7GHz single-board computer (SBC) with 5G connectivity and a whopping 12 TOPS of AI-optimized GPU acceleration.
The post Particle Return to their Roots to Kickstart New AI-Enhanced 5G IoT SBC appeared first on Make: DIY Projects and Ideas for Makers.
IoT hardware company Particle has launched a crowdfunding campaign for a credit card-sized single-board computer called Tachyon. It has 4GB of RAM, 64GB of UFS flash storage, and a Raspberry Pi-compatible 40-pint GPIO header. But what sets the Tachyon board apart from Raspberry Pi’s devices is that Particle’s little computer is powered by an octa-core […]
The post Particle’s Tachyon is a single-board PC with a Snapdragon chip, a 12 TOPS NPU, and 5G and WiFi 6E support (crowdfunding) appeared first on Liliputing.
John George Todd III, who injured a police officer during the Jan 6, 2021 riot on Capitol Hill and reportedly showed no remorse for his participation in it, is off to jail for 5 years.
After entering the Capitol, Todd repeatedly pushed against officers inside the Rotunda, ignored commands to leave and screamed profanities at police.
The post 5 years in jail for Jan 6 rioter who injured cop appeared first on Boing Boing.
The New York Times apoplectic over basically nothing: "At Justice Alito's House, a 'Stop the Steal' Symbol on Display," reads a New York Times headline from yesterday.
According to the Times, an upside-down American flag was flown at Supreme Court Justice Samuel Alito's house for a few days in January 2021—between the January 6 Capitol riot and President Joe Biden's inauguration. The nation's esteemed paper of record suggests this action indicates that Alito thinks the election was stolen from former President Donald Trump.
There is very little evidence available to make this case. People fly upside-down flags for all kinds of reasons; it typically signals "SOS" or a sense that the country is horribly off course. People have historically flown flags in this manner out of protest for the Vietnam War, out of protest for the Supreme Court's 2022 decision to overturn Roe v. Wade, to contest election results (believing the election was stolen or that voter fraud was rampant), or—and don't get the two confused—to signal displeasure with the election results.
Alito reports that his wife was the one who flew the flag in this manner and that it concerned a dispute with a neighbor who posted an anti-Trump sign in their yard, following the election, that used expletives. Mrs. Alito was reportedly angered by this, and flew her flag upside-down in response. It is very hard to tell what intentions were behind one single gesture, reportedly not even done by the justice himself, and no account from neighbors or friends of the Alito family has bolstered the idea that Mrs. Alito is a "Stop the Steal" type.
This reminds me of when media outlets and the Anti-Defamation League claimed the "OK" symbol was actually a white supremacist gesture. If you look hard enough, you can find disturbing symbols anywhere you look, but you must sometimes suspend logic and reason in order to do so. This does not seem like a situation where a sitting Supreme Court justice is supporting overthrowing election results; it looks like a situation where The New York Times is straining to make that the narrative.
How Taiwan handles TikTok: Taiwan, which has long labeled TikTok a national security threat, eschews a national ban on the Chinese-owned app.
Five years ago, the government banned it on the devices of employees. For the last eight years, the ruling party (which will be in power for another four, at least, as the new president is being inaugurated on Monday) has refused to use the app. Legislators in Taiwan say "they do not have the luxury of thinking of TikTok as the only threat," reports The New York Times. "Disinformation reaches Taiwanese internet users on every type of social media, from chat rooms to short videos."
With China—which contests Taiwanese independence and wants reunification (and seems likely to attempt it by military force at some point)—always looming as a threat, TikTok is the least of Taiwanese politicians' worries.
Note that Taiwan is no libertarian tech paradise. Lawmakers there are weighing "measures that tackle internet threats—fraud, scams and cybercrime—broadly enough to apply to all these existing social media platforms," which may end up encroaching on free speech rights. Still, Taiwan has a robust online fact-checking ecosystem and lots of alternative media sites where users might be able to get better information.
All of this is instructive as legislators in the U.S. have passed a ban on the app and more broadly contemplate how much of a threat to national security the Chinese-owned app poses.
Scenes from New York: The Food and Drug Administration hates this photo since they have decided that Elf Bars—which come in a multitude of flavors—are harming America's youth. They're hard to find these days and Customs keeps seizing shipments at the border. AS FOR ME, I will keep enjoying my NICOTINE FREEDOM, and you can pry my little Miami Mint vape from my cold, dead hands!
The post Mrs. Alito and the Bad Flag appeared first on Reason.com.
Enlarge / This is essentially the kind of water heater the author has hooked up, minus the Wi-Fi module that led him down a rabbit hole. Also, not 140-degrees F—yikes. (credit: Getty Images)
The hot water took too long to come out of the tap. That is what I was trying to solve. I did not intend to discover that, for a while there, water heaters like mine may have been open to anybody. That, with some API tinkering and an email address, a bad actor could possibly set its temperature or make it run constantly. That’s just how it happened.
Let’s take a step back. My wife and I moved into a new home last year. It had a Rinnai tankless water heater tucked into a utility closet in the garage. The builder and home inspector didn't say much about it, just to run a yearly cleaning cycle on it.
Because it doesn’t keep a big tank of water heated and ready to be delivered to any house tap, tankless water heaters save energy—up to 34 percent, according to the Department of Energy. But they're also, by default, slower. Opening a tap triggers the exchanger, heats up the water (with natural gas, in my case), and the device has to push it through the line to where it's needed.
Samsung and Synopsys collaborated on the first production tapeout of a high-performance mobile SoC design, including CPUs and GPUs, using the Synopsys.ai EDA suite on Samsung Foundry’s gate-all-around (GAA) process. Samsung plans to begin mass production of 2nm process GAA chips in 2025, reports BusinessKorea.
UMC developed the first radio frequency silicon on insulator (RF-SOI)-based 3D IC process for chips used in smartphones and other 5G/6G mobile devices. The process uses wafer-to-wafer bonding technology to address radio frequency interference between stacked dies and reduces die size by 45%.
Fig. 1: UMC’s 3D IC solution for RFSOI technology. Source: UMC
The first programmable chip capable of shaping, splitting, and steering beams of light is now being produced by Skywater Technology and Lumotive. The technology is critical for advancing lidar-based systems used in robotics, automotive, and other 3D sensing applications.
Driven by demand for AI chips, SK hynix revealed it has already booked its entire production of high-bandwidth memory chips for 2024 and is nearly sold out of its production capacity for 2025, reported the Korea Times, while SEMI reported that silicon wafer shipments declined in Q1 2024, quarter over quarter, a 13% drop, attributed to continued weakness in IC fab utilization and inventory adjustments.
PCI-SIG published the CopprLink Internal and External Cable specifications to provide PCIe 5.0 and 6.0 signaling at 32 and 64 GT/s and leverage standard connector form factors for applications including storage, data centers, AI/ML, and disaggregated memory.
The U.S. Department of Commerce (DoC) launched the CHIPS Women in Construction Framework to boost the participation of women and economically disadvantaged people in the workforce, aiming to support on-time and successful completion of CHIPS Act-funded projects. Intel and Micron adopted the framework.
Quick links to more news:
Market Reports
Global
In-Depth
Education and Training
Security
Product News
Quantum
Research
Events
Further Reading
The SiC wafer processing equipment market is growing rapidly, reports Yole. SiC devices will exceed $10B by 2029 at a CAGR of 25%, and the SiC manufacturing tool market is projected to reach $5B by 2026.
imec.xpand launched a €300 million (~$321 million) fund that will invest in semiconductor and nanotechnology startups with the potential to push semiconductor innovation beyond traditional applications and drive next-gen technologies.
Blaize raised $106 million for its programmable graph streaming processor architecture suite and low-code/no-code software platform for edge AI.
Guerrilla RF completed the acquisition of Gallium Semiconductor‘s portfolio of GaN power amplifiers and front-end modules.
About 90% of connected cars sold in 2030 will have embedded 5G capability, reported Counterpoint. Also, about 75% of laptop PCs sold in 2027 will be AI laptop PCs with advanced generative AI, and the global high-level OS (HLOS) or advanced smartwatch market is predicted to grow 15% in 2024.
Powerchip Semiconductor opened a new 300mm facility in northwestern Taiwan targeting the production of AI semiconductors. The facility is expected to produce 50,000 wafers per month at 55, 40, and 28nm nodes.
Taiwan-based KYEC Semiconductor will withdraw its China operations by the third quarter due to increasing geopolitical tensions, reports the South China Morning Post.
Japan will expand its semiconductor export restrictions to China related to four technologies: Scanning electron microscopes, CMOS, FD-SOI, and the outputs of quantum computers, according to TrendForce.
IBM will invest CAD$187 million (~US$137M in Canada’s semiconductor industry, with the bulk of the investment focused on advanced assembly, testing, and packaging operations.
Microsoft will invest US$2.2 billion over the next four years to build Malaysia’s digital infrastructure, create AI skilling opportunities, establish an AI Center of Excellence, and enhance cybersecurity.
New stories and tech talks published by Semiconductor Engineering this week:
Infineon collaborated with ETAS to integrate the ESCRYPT CycurHSM 3.x automotive security software stack into its next-gen AURIX MCUs to optimize security, performance, and functionality.
Synopsys released Polaris Assist, an AI-powered application security assistant on its Polaris Software Integrity Platform, combining LLM technology with application security knowledge and intelligence.
In security research:
U.S. President Biden signed a National Security Memorandum to enhance the resilience of critical infrastructure, and the White House announced key actions taken since Biden’s AI Executive Order, including measures to mitigate risk.
CISA and partners published a fact sheet on pro-Russia hacktivists who seek to compromise industrial control systems and small-scale operational technology systems in North American and European critical infrastructure sectors. CISA issued other alerts including two Microsoft vulnerabilities.
The U.S. National Institute for Innovation and Technology (NIIT) and the Department of Labor (DoL) partnered to celebrate the inaugural Youth Apprenticeship Week on May 5 to 11, highlighting opportunities in critical industries such as semiconductors and advanced manufacturing.
SUNY Poly received an additional $4 million from New York State for its Semiconductor Processing to Packaging Research, Education, and Training Center.
The University of Pennsylvania launched an online Master of Science in Engineering in AI degree.
The American University of Armenia celebrated its 10-year collaboration with Siemens, which provides AUA’s Engineering Research Center with annual research grants.
Renesas and SEGGER Embedded Studio launched integrated code generator support for its 32-bit RISC-V MCU.
Rambus introduced a family of DDR5 server Power Management ICs (PMICs), including an extreme current device for high-performance applications.
Fig. 2: Rambus’ server PMIC on DDR5 RDIMM. Source: Rambus
Keysight added capabilities to Inspector, part of the company’s recently acquired device security research and test lab Riscure, that are designed to test the robustness of post-quantum cryptography (PQC) and help device and chip vendors identify and fix hardware vulnerabilities. Keysight also validated new conformance test cases for narrowband IoT non-terrestrial networks standards.
Ansys’ RedHawk-SC and Totem power integrity platforms were certified for TSMC‘s N2 nanosheet-based process technology, while its RaptorX solution for on-chip electromagnetic modeling was certified for TSMC’s N5 process.
Netherlands-based athleisure brand PREMIUM INC selected CLEVR to implement Siemens’ Mendix Digital Lifecycle Management for Fashion & Retail solution.
Micron will begin shipping high-capacity DRAM for AI data centers.
Microchip uncorked radiation-tolerant SoC FPGAs for space applications that uses a real-time Linux-capable RISC-V-based microprocessor subsystem.
University of Chicago researchers developed a system to boost the efficiency of quantum error correction using a framework based on quantum low-density party-check (qLDPC) codes and new hardware involving reconfigurable atom arrays.
PsiQuantum will receive AUD $940 million (~$620 million) in equity, grants, and loans from the Australian and Queensland governments to deploy a utility-scale quantum computer in the regime of 1 million physical qubits in Brisbane, Australia.
Japan-based RIKEN will co-locate IBM’s Quantum System Two with its Fugaku supercomputer for integrated quantum-classical workflows in a heterogeneous quantum-HPC hybrid computing environment. Fugaku is currently one of the world’s most powerful supercomputers.
QuEra Computing was awarded a ¥6.5 billion (~$41 million) contract by Japan’s National Institute of Advanced Industrial Science and Technology (AIST) to deliver a gate-based neutral-atom quantum computer alongside AIST’s ABCI-Q supercomputer as part of a quantum-classical computing platform.
Novo Holdings, the controlling stakeholder of pharmaceutical company Novo Nordisk, plans to boost the quantum technology startup ecosystem in Denmark with DKK 1.4 billion (~$201 million) in investments.
The University of Sydney received AUD $18.4 million (~$12 million) from the Australian government to help grow the quantum industry and ecosystem.
The European Commission plans to spend €112 million (~$120 million) to support AI and quantum research and innovation.
Intel researchers developed a 300-millimeter cryogenic probing process to collect high-volume data on the performance of silicon spin qubit devices across whole wafers using CMOS manufacturing techniques.
EPFL researchers used a form of ML called deep reinforcement learning (DRL) to train a four-legged robot to avoid falls by switching between walking, trotting, and pronking.=
The University of Cambridge researchers developed tiny, flexible nerve cuff devices that can wrap around individual nerve fibers without damaging them, useful to treat a range of neurological disorders.
Argonne National Laboratory and Toyota are exploring a direct recycling approach that carefully extracts components from spent batteries. Argonne is also working with Talon Metals on a process that could increase the number of EV batteries produced from mined nickel ore.
Find upcoming chip industry events here, including:
| Event | Date | Location |
|---|---|---|
| IEEE International Symposium on Hardware Oriented Security and Trust (HOST) | May 6 – 9 | Washington DC |
| MRS Spring Meeting & Exhibit | May 7 – 9 | Virtual |
| ASMC: Advanced Semiconductor Manufacturing Conference | May 13 – 16 | Albany, NY |
| ISES Taiwan 2024: International Semiconductor Executive Summit | May 14 – 15 | New Taipei City |
| Ansys Simulation World 2024 | May 14 – 16 | Online |
| NI Connect Austin 2024 | May 20 – 22 | Austin, Texas |
| ITF World 2024 (imec) | May 21 – 22 | Antwerp, Belgium |
| Embedded Vision Summit | May 21 – 23 | Santa Clara, CA |
| ASIP Virtual Seminar 2024 | May 22 | Online |
| Electronic Components and Technology Conference (ECTC) 2024 | May 28 – 31 | Denver, Colorado |
| Hardwear.io Security Trainings and Conference USA 2024 | May 28 – Jun 1 | Santa Clara, CA |
| Find All Upcoming Events Here | ||
Upcoming webinars are here.
Read the latest special reports and top stories, or check out the latest newsletters:
Systems and Design
Low Power-High Performance
Test, Measurement and Analytics
Manufacturing, Packaging and Materials
Automotive, Security and Pervasive Computing
The post Chip Industry Week In Review appeared first on Semiconductor Engineering.
Here's a killer quote — it really captures how a MAGA type can be a kind, decent individual, love their family, pet the dog, etc., and still defend absurd, noxious, or plain monstrous ideas to the death:
"Half the harm that is done in this world is due to people who want to feel important.
The post This literary giant of the early 20th century understood the MAGA Mentality appeared first on Boing Boing.
Particle's new M-series of wireless solutions feature Wi-Fi, cellular, LoRaWAN, and satellite on a single board.
The post Particle’s New M-Series Connects Everything, Everywhere, All At Once appeared first on Make: DIY Projects and Ideas for Makers.
By Dana Neustadter (Synopsys), Ruud Derwig (Synopsys), and Martin Rösner (G+D)
IoT expansion requires secure and efficient connectivity between machines. Integrated SIM technology and remote SIM provisioning can make this possible.
Subscriber Identity Module (SIM) cards have been around for a long time, with Giesecke+Devrient (G+D) developing and delivering the first commercial SIM cards in 1991. If you have a cell phone, you will be familiar with these small security anchors that protect phones, networks, and data from fraud and misuse. They also enable phones to securely authenticate and communicate within a mobile network infrastructure managed by carriers. With deployment starting over the last few years, iSIM, also called an integrated Universal Integrated Circuit Card (iUICC), is the newest SIM kid on the block. iSIMs are embedded directly into a system on chip (SoC) as a tamper-resistant secure element, bringing trust and enabling secure connectivity and control, while saving cost and space, simplifying the system development process, and overall offering a significant ease-of-use improvement in the way IoT device connectivity is activated and secured. In addition to the functional advantages, the iSIM also offers sustainability benefits such as reduced CO2 emissions.
Enabling iSIM to support remote SIM provisioning (RSP) calls for an integrated solution that brings together secure services and a secure SIM operating system (OS) with secure hardware. This is the type of challenge that has led to a collaboration between G+D, which continues to lead the way in SIM innovation, and Synopsys, with its expertise in trusted hardware. Putting their heads together, the two companies have come up with an innovative integrated, secure iSIM solution. In a nutshell, Synopsys tRoot Hardware Secure Modules (HSMs) provide silicon-proven, self-contained security IP solutions with root of trust. The HSMs are combined with G+D’s secure SIM OS to enable tamper-resistant elements which are usable within an SoC and serve as an isolated hardware component. G+D’s award-winning RSP services provide seamless management of the SIM profiles. Figure 1 depicts the secure iSIM solution.
“Offering the promise of seamless secure management of SIM profiles, iSIMs help accelerate the broad scaling of the IoT by providing high flexibility to choose the preferred cellular networks throughout the lifetime of devices,” said Andreas Morawietz, global head of Digital Connectivity Portfolio Strategy at G+D. “Our standards-compliant remote SIM provisioning service together with the secure SIM OS integrated with Synopsys’ tRoot Hardware Secure Modules provide an integrated iSIM secure solution at the start of the IoT value chain, delivering benefits to downstream IoT players.”
Fig. 1: Integrated, secure iSIM solution featuring Synopsys and G+D technologies.
The breadth of the IoT has become expansive thanks to the prevalence of cellular networks, sensors, cloud computing, AI, and other technologies that enable connectivity and intelligence. Consider, as one example, all the devices and systems that can bring a smart city to life. From traffic signals and streetlights to meters and energy grids, each of these systems must be able to collect and share data that leads to better decision-making and outcomes, as well as more efficient and effective processes. With the integration of AI capabilities, these devices would also be able to act autonomously. SIM technology acts as a trust anchor for secure identification, authentication, and communication. Over the years as new devices enter the IoT realm, users have expectations of increasingly seamless connectivity, simple remote management, and the ability to select their preferred carriers. This has seen removable physical SIMs giving way to embedded SIMs (eSIM) which are soldered onto devices.
As the newest entry in this evolution, iSIMs are anticipated to grow in popularity, answering the call for more optimized, flexible, and secure solutions to allow more things to be connected and controlled. Because it isn’t a disparate chipset, an iSIM provides cost, power, and area efficiency, ideal for small, battery-powered IoT devices, particularly those that operate in low-power wide area networks (LPWANs) through narrowband IoT (NB-IoT) or long-term evolution for machines (LTE-M) technologies. iSIMs also work well in larger industrial systems such as smart meters or even vehicles. In such systems, the SIM technology could be located in hard-to-reach places, making remote management an ideal approach.
While iSIM and remote provisioning are opening up a new ecosystem, these capabilities are only appealing if they’re backed by rock-solid security. Fortunately, there’s quite a lot of technology available to secure network connections and authenticate communicating partners. iSIMs must be developed to offer the same level of security as traditional SIM solutions. For network operators to trust iSIMs, security certification of iSIMs is essential. This is especially important since the network operators don’t control the SIM hardware and software, as it comes with the IoT device and can originate from any number of vendors.
The Synopsys and G+D collaboration has been successfully deployed in the field and acknowledged by Tier1 operators for several years. Our efforts bring together complementary technologies that form a complete iSIM security solution for integration into a baseband SoC.
Synopsys’ tRoot HSMs are ideal for SoCs supporting a variety of applications in addition to the IoT, including industrial control, networking, automotive, media, and mobile devices. A hardware root of trust allows chip manufacturers and their OEM customers to create a strong cryptographic device identity for a unique device instance and provides a secure environment for protecting sensitive data and operations. In addition to the secure SIM OS, G+D also provides remote provisioning and device management secure services. The resulting iSIM solution comes with a small footprint and low power consumption and allows for more efficient production, faster time to market and, without extra housing or plastic, greater sustainability. With encrypted loading of chip-unique data (the SIM BLOB, or binary large object), the iSIM can be installed on a chipset without certification of the production facility.
As smart, connected devices become more ubiquitous, ensuring trust that the devices and their data will remain safe from security threats will remain a top priority. Secure remote SIM provisioning helps to streamline device connections and controls in a safe manner. Through our collaboration, Synopsys and G+D are providing mobile network operators and semiconductor manufacturers with a complete security solution for all-in-one connectivity that can nurture the continued expansion of the IoT.
For more information, see Synopsys tRoot Hardware Secure Modules (HSMs).
Ruud Derwig is a principal software engineer for Security IP Solutions at Synopsys.
Martin Rösner is the director for the Digital Connectivity Portfolio Strategy at G+D.
The post Navigating IoT Security appeared first on Semiconductor Engineering.
A technical paper titled “Low Power and Temperature-Resilient Compute-In-Memory Based on Subthreshold-FeFET” was published by researchers at Zhejiang University, University of Notre Dame, Technical University of Munich, Munich Institute of Robotics and Machine Intelligence, and the Laboratory of Collaborative Sensing and Autonomous Unmanned Systems of Zhejiang Province.
“Compute-in-memory (CiM) is a promising solution for addressing the challenges of artificial intelligence (AI) and the Internet of Things (IoT) hardware such as ‘memory wall’ issue. Specifically, CiM employing nonvolatile memory (NVM) devices in a crossbar structure can efficiently accelerate multiply-accumulation (MAC) computation, a crucial operator in neural networks among various AI models. Low power CiM designs are thus highly desired for further energy efficiency optimization on AI models. Ferroelectric FET (FeFET), an emerging device, is attractive for building ultra-low power CiM array due to CMOS compatibility, high ION /IOF ratio, etc. Recent studies have explored FeFET based CiM designs that achieve low power consumption. Nevertheless, subthreshold-operated FeFETs, where the operating voltages are scaled down to the subthreshold region to reduce array power consumption, are particularly vulnerable to temperature drift, leading to accuracy degradation. To address this challenge, we propose a temperature-resilient 2T-1FeFET CiM design that performs MAC operations reliably at subthreahold region from 0 to 85 Celsius, while consuming ultra-low power. Benchmarked against the VGG neural network architecture running the CIFAR-10 dataset, the proposed 2T-1FeFET CiM design achieves 89.45% CIFAR-10 test accuracy. Compared to previous FeFET based CiM designs, it exhibits immunity to temperature drift at an 8-bit wordlength scale, and achieves better energy efficiency with 2866 TOPS/W.”
Find the technical paper here. Published January 2024 (preprint).
Zhou, Yifei, Xuchu Huang, Jianyi Yang, Kai Ni, Hussam Amrouch, Cheng Zhuo, and Xunxhao Yin. “Low Power and Temperature-Resilient Compute-In-Memory Based on Subthreshold-FeFET.” arXiv preprint arXiv:2312.17442 (2023).
Related Reading
Increasing AI Energy Efficiency With Compute In Memory
How to process zettascale workloads and stay within a fixed power budget.
Modeling Compute In Memory With Biological Efficiency
Generative AI forces chipmakers to use compute resources more intelligently.
The post Ultra-Low Power CiM Design For Practical Edge Scenarios appeared first on Semiconductor Engineering.
Přihlásit se