During the 2024 RISC-V Summit in Santa Clara, California, NVIDIA was one of the presenting members. RISC-V, being a free and open-source instruction set architecture, is an interesting choice for many companies looking to develop custom solutions. NVIDIA designs accelerators for AI and graphics processing, all of which are equipped with up to tens of thousands of cores. To manage these cores, NVIDIA has developed a custom RISC-V processor called "NV-RISCV," which is a replacement for its predecessor "Falcon." Unlike Falcon, NV-RISCV is based on an open-source ISA and is customized much more deeply, with features like more customized caches and special instructions. Initially, the company reported better performance over its Falcon GPU System Processor (GSP), and NV-RISCV is now running in millions of NVIDIA chips.

Thanks to a post on X by Nick Brown, we learn that NVIDIA is shipping roughly one billion RISC-V cores in the year 2024. Each NVIDIA chip includes between 10 and 40 RISC-V cores, depending on the chip size and complexity. Some more complex designs, like GB200, require massive data coordination, meaning that more cores are needed to handle these requests and distribute them. This includes chip-to-chip interfaces, context switching, memory controller, camera handling, video codecs, display output, resource management, power management, and more. NVIDIA has developed a total of over 20 custom extensions for RISC-V cores, which all serve their specific use cases.

Marvell Technology, Inc. (NASDAQ: MRVL), a leader in data infrastructure semiconductor solutions, today announced the development of FBNIC, a custom 5 nm network interface controller (NIC) ASIC in collaboration with Meta to meet the company's infrastructure and use case requirements. The FBNIC board design will also be contributed by Marvell to the Open Compute Project (OCP) community. FBNIC combines a customized network controller designed by Marvell and Meta, a co-designed board, and Meta's ASIC, firmware and software. This custom design delivers innovative capabilities, optimizes performance, increases efficiencies, and reduces the average time needed to resolve potential network and server issues.

"The future of large-scale, data center computing will increasingly revolve around optimizing semiconductors and other components for specific applications and cloud infrastructure architectures," said Raghib Hussain, President of Products and Technologies at Marvell. "It's been exciting to partner with Meta on developing their custom FBNIC on our industry-leading 5 nm accelerated infrastructure silicon platform. We look forward to the OCP community leveraging the board design for future innovations."

Flex today announced new reference platforms for liquid-cooled servers, rack, and power products that will enable customers to sustainably accelerate data center growth. These innovations build on Flex's ability to address technical challenges associated with power, heat generation, and scale to support artificial intelligence (AI) and high-performance computing (HPC) workloads.

"Flex delivers integrated data center IT and power infrastructure solutions that address the growing power and compute demands in the AI era," said Michael Hartung, president and chief commercial officer, Flex. "We are expanding our unique portfolio of advanced manufacturing capabilities, innovative products, and lifecycle services, enabling customers to deploy IT and power infrastructure at scale and drive AI data center expansion."

MSI, a leading brand in gaming, content creation, and business & productivity laptops, proudly launched several next-gen AI+ gaming and business productivity laptops featuring the new Intel Core Ultra processor (Series 2) and AMD Ryzen AI 300 Series at IFA 2024. These laptops offer more AI computing power, making it the most robust platform for AI PC development, with more AI models, frameworks, and runtimes enable. Additionally, MSI officially launched the new Claw 8 AI+ Windows 11 gaming handheld device, powered by Intel Core Ultra processors (Series 2) and an 8-inch screen, providing a smoother and broader mobile gaming experience. MSI also announced the whole new Venture series laptops, redefining the combination of thin, light and powerful. Equipped with Intel Core Ultra processors (Series 2) and varieties of different size, from 14, 15.6, 16, to 17 inches.

"MSI not only brings the industry's most comprehensive AI+ PC lineup but also introduces multiple new laptops and handheld devices designed for gamers worldwide," said Eric Kuo, MSI's Executive Vice President and General Manager of NB Business Unit. "We welcome global guests to visit the MSI booth to experience next-gen AI computing and exciting gaming products."

The 63rd edition of the TOP500 reveals that Frontier has once again claimed the top spot, despite no longer being the only exascale machine on the list. Additionally, a new system has found its way into the Top 10.

The Frontier system at Oak Ridge National Laboratory in Tennessee, USA remains the most powerful system on the list with an HPL score of 1.206 EFlop/s. The system has a total of 8,699,904 combined CPU and GPU cores, an HPE Cray EX architecture that combines 3rd Gen AMD EPYC CPUs optimized for HPC and AI with AMD Instinct MI250X accelerators, and it relies on Cray's Slingshot 11 network for data transfer. On top of that, this machine has an impressive power efficiency rating of 52.93 GFlops/Watt - putting Frontier at the No. 13 spot on the GREEN500.

Dr. Lisa Su introduced AMD's "next-gen AMD Ryzen" processor series during a recent presentation at the Beijing AI PC Innovation Summit—this announcement confirms that Team Red's RDNA 3+ (AKA 3.5) graphics technology is destined to arrive (on board) with the launch of "Strix Point" processors. Product roadmaps remain unchanged—when compared to slides from last December—AMD still anticipates a 2024 launch window. China has been introduced to current-gen "Hawk Point" Ryzen 8040 mobile and 8000G (AM5) desktop processors—key AMD personnel presented a variety of products, including region-specific budget options.

David Wang, SVP of GPU Technology and Engineering R&D, covered the RDNA 3+ and XDNA 2 architectures (very briefly) during his on-stage appearance—he dedicated most of his attention to current-gen "Hawk Point" processors. The Strix Point integrated solution—a GFX1150 target—has been linked to "RDNA 3.5" for a while, a lot of this information was gleaned from publicly visible AMD patch notices. The latest Team Red software engineering activities indicate that Zen 5 CPU enablement is nearing a possible finish line.

AMD's Beijing AI PC Innovation Summit served as introduction point for a Chinese market launch of "Hawk Point" Ryzen 8040 mobile series and 8000G desktop processors—news coverage has, so far, focused on that rollout as well as a teasing of next-gen "Strix Point" processors. HXL/9550pro has put a spotlight on an easy-to-miss presentation slide—their social media post revealed the existence of new budget-friendly Ryzen 8000F CPUs. Team Red seems to be preparing two China-exclusive SKUs: Ryzen 7 8700F and Ryzen 5 8400F—not many details were revealed on-stage, so reporters have played a guessing game with speculated technical information. Industry experts believe that the 8700F is an iGPU-less version of AMD's "Hawk Point" Ryzen 7 8700G APU—utilizing the same 8 core and 16 thread configuration, but missing the Radeon 780M integrated graphics solution.

The lower-end SKU is a more perplexing product, since AMD did not elaborate much during "budget" product unveilings—VideoCardz put its thinking hat on for this one: "meanwhile, the 8400F might be harder to guess, as the name sits between 8500G and 8300G, both featuring vastly different configurations. An educated guess would be 6 cores and 12 threads, possibly with two Zen 4 and four Zen 4c cores." The "F" model suffix gained attention last year—courtesy of Team Red's Ryzen 5 7500F CPU. This iGPU-less "Raphael" Zen 4 SKU was initially released as a Chinese market exclusive, but eventually headed West as an option for system integrators.

Microsoft's DirectX department is scheduled to show off several innovations at this month's Game Developers Conference (GDC), although a late February preview has already spilled their DirectSR Super Resolution API's beans. Today, retail support for Shader Model 6.8 and Work Graphs has been introduced with an updated version of the company's Agility Software Development Kit. Program manager, Joshua Tucker, stated that these technologies will be showcased on-stage at GDC 2024—Shader Model 6.8 arrives with a "host of new features for shader developers, including Start Vertex/Instance Location, Wave Size Range, and Expanded Comparison Sampling." A linked supplementary article—D3D12 Work Graphs—provides an in-depth look into the cutting-edge API's underpinnings, best consumed if you have an hour or two to spare.

Tucker summarized the Work Graphs API: "(it) utilizes the full potential of your GPU. It's not just an upgrade to the existing models, but a whole new paradigm that enables more efficient, flexible, and creative game development. With Work Graphs, you can generate and schedule GPU work on the fly, without relying on the host. This means you can achieve higher performance, lower latency, and greater scalability for your games with tasks such as culling, binning, chaining of compute work, and much more." AMD and NVIDIA are offering driver support on day one. Team Red has discussed the launch of "Microsoft DirectX 12 Work Graphs 1.0 API" in a GPUOpen blog—they confirm that "a deep dive" into the API will happen during their Advanced Graphics Summit presentation. NVIDIA's Wessam Bahnassi has also discussed the significance of Work Graphs—check out his "Advancing GPU-driven rendering" article. Graham Wihlidal—of Epic Games—is excited about the latest development: "we have been advocating for something like this for a number of years, and it is very exciting to finally see the release of Work Graphs."

Every country needs to own the production of their own intelligence, NVIDIA founder and CEO Jensen Huang told attendees Monday at the World Governments Summit in Dubai. Huang, who spoke as part of a fireside chat with the UAE's Minister of AI, His Excellency Omar Al Olama, described sovereign AI—which emphasizes a country's ownership over its data and the intelligence it produces—as an enormous opportunity for the world's leaders. "It codifies your culture, your society's intelligence, your common sense, your history - you own your own data," Huang told Al Olama during their conversation, a highlight of an event attended by more than 4,000 delegates from 150 countries.

"We completely subscribe to that vision," Al Olama said. "That's why the UAE is moving aggressively on creating large language models and mobilizing compute." Huang's appearance in the UAE comes as the Gulf State is moving rapidly to transform itself from an energy powerhouse into a global information technology hub. Dubai is the latest stop for Huang in a global tour that has included meetings with leaders in Canada, France, India, Japan, Malaysia, Singapore and Vietnam over the past six months. The Middle East is poised to reap significant benefits from AI, with PwC projecting a $320 billion boost to the region's economy by 2030.

The 62nd edition of the TOP500 reveals that the Frontier system retains its top spot and is still the only exascale machine on the list. However, five new or upgraded systems have shaken up the Top 10.

Housed at the Oak Ridge National Laboratory (ORNL) in Tennessee, USA, Frontier leads the pack with an HPL score of 1.194 EFlop/s - unchanged from the June 2023 list. Frontier utilizes AMD EPYC 64C 2GHz processors and is based on the latest HPE Cray EX235a architecture. The system has a total of 8,699,904 combined CPU and GPU cores. Additionally, Frontier has an impressive power efficiency rating of 52.59 GFlops/watt and relies on HPE's Slingshot 11 network for data transfer.

Intel and Submer, a company specializing in immersion cooling, are set to unveil a creative immersion cooling system at the OCP Global Summit. This system can efficiently dissipate 1,000 W of power in a single-phase liquid cooling setup designed for deployment in data centers. Unlike traditional water cooling, immersion cooling systems offer higher efficiency and reliability. The solution developed by Submer and Intel is based on a Forced Convection Heat Sink (FCHS) and leverages a heat exchanger for heat transfer with a second liquid. The primary advantage of immersion cooling is its lack of active components on the cooling element, making it possible for immersed systems to operate without them for extended periods.

In this new system, a copper cooler is housed with two fans at one end to enhance liquid flow through the heat sink using forced convection. However, this active cooling component contradicts the traditional passive concept of immersion cooling based on natural convection. In its initial phase, Submer and Intel utilized Xeon processors with an 800 W TDP, with plans to increase that figure to 1,000 W in the next step. This Forced Convection Heat Sink (FCHS) offers the advantages of easy manufacturing and cost-effective usage while effectively dissipating up to 1,000 W of waste heat, making it a compelling option for immersion cooling. There are even possibilities of being 3D printed, according to Submer, and the plan is to achieve cooling of 1kW+ chip. We expect to hear more about the system during the OCP Global Summit, running from October 17 to 19, as currently, we only have a lower-resolution image from Submer's press release.

It appears that Silicon Motion is ready to start competing with Phison in the PCIe 5.0 NVMe SSD controller market, as the company has shown a new controller at the Flash Memory Summit 2023 which should give Phison a run for its money. The SM2508 as the controller is called is set to be the most power efficient PCIe 5.0 NVMe controller to date, with a power consumption of 3.5 W, which is in line with most PCIe 4.0 SSD controllers. This still means that a decent heatsink will be needed, but not active cooling or massive heatsinks that we've seen on the current crop of PCIe 5.0 drives based on Phison's E26 controller.

Silicon Motion also appears to have the Phison E26 beat, in terms of performance, as the SM2508 promises to deliver sequential read and write speeds of up to 14 GB/s. Random performance is rated at 2.5 million IOPS read and 2.4 million IOPS write. To get the most out of the SM2508 2400 MT/s or faster NAND flash is going to be needed to deliver the claimed performance figures though, but according to Anandtech, the SM2508 is future proofed by supporting NAND flash speeds of up to 3600 MT/s, so we might see faster drives based on the controller once faster NAND appears, such as SK Hynix new 321-layer NAND, which is scheduled for a 2025 introduction. The SM2508 on the other hand is said to be launching at the end of this year or early 2024.

NEO Semiconductor, a leading developer of innovative technologies for 3D NAND flash and DRAM memory, today announced its participation at Flash Memory Summit 2023, taking place in person in Santa Clara, California, on August 8-10. CEO, Andy Hsu, will deliver a keynote address titled "New Architectures which will Drive Future 3D NAND and 3D DRAM Solutions" on August 9th at 11:40 a.m. Pacific Time.

Earlier this year, Neo Semiconductor announced the launch of its ground-breaking technology, 3D X-DRAM. This development is the world's first 3D NAND-like DRAM cell array that is targeted to solve DRAM's capacity bottleneck and replace the entire 2D DRAM market. 3D X-DRAM can be manufactured using the existing 3D NAND flash memory process with minor changes, significantly reducing the time and cost spent developing a new 3D process. During the keynote, Mr. Hsu will reveal the 3D X-DRAM process flow and technical details.

Solidigm over the weekend announced the Solidigm D5-P5336 line of enterprise SSDs. The company earns bragging rights for having the highest capacity among production SSDs, with these coming in capacities of up to 61.44 TB—an incredible amount of storage that HDDs have yet to catch up to. These drives are targeted at the data-center, where they not just replace HDDs due to their sheer density, but also provide the advantage of responsive flash storage. The drives aren't gunning to top SSD performance charts, the design goal is simply capacity and reliability. The D5-P5336 series feature enterprise-grade QLC NAND flash memory that's been extensively tested for reliability and write endurance.

The Solidigm D5-P5336 series comes in three data-center relevant form-factors—15 mm-thick U.2, 7.5 mm-thick E3.S, and the E1.L (ruler) form-factor. Capacities start at 7.68 TB for the U.2 and E3.S models, and 15.36 TB for the E1.L. The maximum capacity on offer is 61.44 TB for the U.2 and E1.L form-factors, and 30.72 TB for the E3.S. Among the capacity variants are 15.36 TB, 30.72 TB, and 61.44 TB. The drives use a proprietary controller that takes advantage of the PCI-Express 4.0 x4 host interface, and NVMe 1.4c protocol. The star attraction, however, is the 192-layer 3D QLC NAND flash memory made in-house by Solidigm.

The United Kingdom's Prime Minister Rishi Sunak has recently announced a semiconductor-related partnership with with Japan (at the G7 Hiroshima Summit), as well as a $1 billion ($1.25 billion) support package for microchip industries within the UK - with the intended goal of turning the nation into a "technology superpower." The 10-year investment strategy was initially expected to kick of last Autumn, but the announcement was delayed, for various reasons, to last weekend's intergovernmental political forum held in Japan. Sunak hopes that the new strategy "will grow our economy, create new jobs and (make the UK) stay at the forefront of new technological breakthroughs."

The United Kingdom's microchip industry has been described as a "fledgling" operation when compared to its neighbors' undertakings, and industry figures think that the government's pledge of £1 billion in support is "insignificant" in the grand scheme of things. They cite the USA's CHIPS Act ($52 billion) and an equivalent scheme devised by the European Union (€43 billion of aid) as glowing examples of proper expenditure and reinforcement of their respective semiconductor industries. One technology critic thinks that the UK's support package is good enough for improving research and development departments, but it will in no way pave the way for local companies to reach the same level as big international players such as NVIDIA, Qualcomm, Broadcom and AMD. Cambridge, UK-based firm Arm opted to file for an IPO in the United States earlier this month, and ignored London's stock exchange entirely - the semiconductor and software design company is wholly owned by Japan's Softbank - prior to a change in ownership, Arm was viewed as Britain's leading light in the technology biz.

Increasing its HPL score from 1.02 Eflop/s in November 2022 to an impressive 1.194 Eflop/s on this list, Frontier was able to improve upon its score after a stagnation between June 2022 and November 2022. Considering exascale was only a goal to aspire to just a few years ago, a roughly 17% increase here is an enormous success. Additionally, Frontier earned a score of 9.95 Eflop/s on the HLP-MxP benchmark, which measures performance for mixed-precision calculation. This is also an increase over the 7.94 EFlop/s that the system achieved on the previous list and nearly 10 times more powerful than the machine's HPL score. Frontier is based on the HPE Cray EX235a architecture and utilizes AMD EPYC 64C 2 GHz processors. It also has 8,699,904 cores and an incredible energy efficiency rating of 52.59 Gflops/watt. It also relies on gigabit ethernet for data transfer.

During the Snapdragon Summit 2022, Qualcomm Technologies, Inc. and Adobe announced an expanded collaboration to support creative experiences on Snapdragon powered devices across mobile, compute, and XR platforms. Together, the companies will push the boundaries of creativity and document productivity for Snapdragon users.

Building on the rich experiences already found with Adobe Photoshop and Adobe Lightroom for Windows on Snapdragon devices, Adobe remains committed to bringing the best of Creative Cloud natively to the Snapdragon platform, including Adobe Fresco and Adobe Acrobat. Bringing the strength of Adobe Sensei, Adobe's artificial intelligence (AI) technologies, alongside the dedicated on-device Qualcomm AI Engine on Snapdragon compute platforms, users can experience enhanced device performance for creative workflows and tasks including super-resolution, background removal and color enhancement, editing content on-the-go, and more.

According to TrendForce research, material supply improvement and spiking demand for enterprise SSDs from North American hyperscale data center and enterprise clients in 2Q22 coupled with the Kioxia contamination incident in 1Q22 prompted customers to ramp up procurement to avoid future supply shortages. Manufacturers also give priority to meeting the needs of server customers due to the high pricing of enterprise SSD. In the second quarter, overall revenue of the enterprise SSD market increased by 31.3% to US$7.32 billion.

As the market leader, Samsung has grown its enterprise SSD revenue to US$3.26 billion with the recovery of enterprise SSD procurement. Especially in the second quarter, when orders for other consumer products continued to decline, enterprise SSD became the company's outlet for reducing production capacity. At present, Samsung has been continuously investing in the development of next-generation transmission specification products such as the CXL 2.0 product released at the Flash Summit in early August, in order to maintain a leading position in the market.

IBM today announced its new 127-quantum bit (qubit) 'Eagle' processor at the IBM Quantum Summit 2021, its annual event to showcase milestones in quantum hardware, software, and the growth of the quantum ecosystem. The 'Eagle' processor is a breakthrough in tapping into the massive computing potential of devices based on quantum physics. It heralds the point in hardware development where quantum circuits cannot be reliably simulated exactly on a classical computer. IBM also previewed plans for IBM Quantum System Two, the next generation of quantum systems.

Quantum computing taps into the fundamental quantum nature of matter at subatomic levels to offer the possibility of vastly increased computing power. The fundamental computational unit of quantum computing is the quantum circuit, an arrangement of qubits into quantum gates and measurements. The more qubits a quantum processor possesses, the more complex and valuable the quantum circuits that it can run.

The 58th annual edition of the TOP500 saw little change in the Top10. The Microsoft Azure system called Voyager-EUS2 was the only machine to shake up the top spots, claiming No. 10. Based on an AMD EPYC processor with 48 cores and 2.45GHz working together with an NVIDIA A100 GPU and 80 GB of memory, Voyager-EUS2 also utilizes a Mellanox HDR Infiniband for data transfer.

While there were no other changes to the positions of the systems in the Top10, Perlmutter at NERSC improved its performance to 70.9 Pflop/s. Housed at the Lawrence Berkeley National Laboratory, Perlmutter's increased performance couldn't move it from its previously held No. 5 spot.

It is often a dilemma for business users to choose between performance and portability when buying a laptop, but MSI is now offering the best of both worlds. If you're looking for a commercial laptop that is convertible, with pen support, and has excellent graphics, MSI Summit E16 Flip may be the solution for someone like you who demand performance on the go.

After its announcement in CES 2021, MSI Summit E16 Flip, this powerful yet beautifully-designed laptop, is finally on the market. Not only has it exemplified the law of "Golden Ratio" with the 16:10 QHD+ Display, the performance will not disappoint mobile commercial users. Moreover, the Dynamic Cooler Boost design will help users to distribute its CPU and GPU performance to the tasks accordingly. If you are engineer, architect, designer, or even startup ownerwho needs to pitch and show proposals, you will no longer have to struggle with loading and editing the files on the spot with the 11th Gen Intel Core i7 processors and NVIDIA GeForce RTX 30 Series graphics.Along with the support of the MSI Pen, the first award-winning stylus on 2021 CES, it will be a booster for your productivity and allows you to work more modernly with its low latency, stable connection, long battery life, and customizable functions.

MSI first Summit laptops have been well-acclaimed by business users. Now the new members are introduced! Surrounded by the captivating golden ratio spiral special effect, MSI grandly unveiled the "MSIology: Determined to Succeed 2021" virtual event. Exemplifying the perfection of the golden ratio, MSI launched the Summit series, including the honorees of "CES Innovation Awards" MSI Summit E16 Flip and MSI Pen, "Best of the CES 2021" winner Summit E13 Flip Evo, and the MSI USB-C Docking Station Gen 2. During the virtual event, MSI showcased the versatile work styles and displayed how the MSI Summit series can unleash users' potential to boost business and productivity.

"As the famous author Arthur C. Clarke once said, any sufficiently advanced technology is equivalent to magic. Today, we are here to witness the magic of the new MSI Summit.", Iris Chuang, Product Management Director of MSI Notebook, proudly announced in the opening of the new product launch. A symbol of aesthetics, a giant golden ratio spiral outlined the spirit of MSIology, which is to design impeccable laptops for perfectionists who are determined to succeed.

AMD's mysterious Nashira Summit GPU has been spotted in Ashes of the Singularity database. A similarly named Nashira Point GPU has appeared some time ago on the USB-IF website, which was also a mysterious product in AMD's Radeon graphics processors lineup. The Nashira Summit and Nashira Point seem to be a part of the common Nashira GPU family, which is presumably a codename for a lower-end Navi 22 or Navi 23 GPU models. Today, we managed to get a Nashira Summit score in the Ashes of the Singularity database. The GPU has been put through a set of AotS benchmarks and we have the scores. Unfortunately, tests have been run using all-custom settings, so it is impossible to compare it to some other GPU as a reference. The test was probably performed by AMD or some AIB. So far it is impossible to distinct whatever this is a mobile or a desktop product as both mobile and desktop GPUs are tested in the same manner. It remains a question what the mysterious Nashira Summit GPU is, so we have to wait for more information to find out.

During the first day of the Snapdragon Tech Summit Digital, Qualcomm Incorporated President, Cristiano Amon took the virtual stage with global industry leaders to highlight the critical role Qualcomm Snapdragon 8-Series mobile platforms have played to drive experiences forward for the next generation of devices. Qualcomm Technologies' innovation in the premium tier, coupled with the evolution of 5G, is accelerating and continuing to redefine immersive consumer experiences. The proliferation of these premium tier experiences has and will continue to enrich the lives of billions of smartphone users around the world.

"Creating premium experiences takes a relentless focus on innovation. It takes long term commitment, even in the face of immense uncertainty," said Cristiano Amon, president, Qualcomm Incorporated. "It takes an organization that's focused on tomorrow, to continue to deliver the technologies that redefine premium experiences."

The 56th edition of the TOP500 saw the Japanese Fugaku supercomputer solidify its number one status in a list that reflects a flattening performance growth curve. Although two new systems managed to make it into the top 10, the full list recorded the smallest number of new entries since the project began in 1993.

The entry level to the list moved up to 1.32 petaflops on the High Performance Linpack (HPL) benchmark, a small increase from 1.23 petaflops recorded in the June 2020 rankings. In a similar vein, the aggregate performance of all 500 systems grew from 2.22 exaflops in June to just 2.43 exaflops on the latest list. Likewise, average concurrency per system barely increased at all, growing from 145,363 cores six months ago to 145,465 cores in the current list.