The HPC research projects DEEP-SEA, IO-SEA and RED-SEA are wrapping up this month after a three-year project term. The three projects worked together to develop key technologies for European Exascale supercomputers, based on the Modular Supercomputing Architecture (MSA), a blueprint architecture for highly efficient and scalable heterogeneous Exascale HPC systems. To achieve this, the three projects collaborated on system software and programming environments, data management and storage, as well as interconnects adapted to this architecture. The results of their joint work will be presented at a co-design workshop and poster session at the EuroHPC Summit (Antwerp, 18-21 March, www.eurohpcsummit.eu).

Two months ago, NVIDIA introduced its GeForce RTX 40 SUPER series to the market, bringing a trio of models: RTX 4070 SUPER, RTX 4070 Ti SUPER, and RTX 4080 SUPER. Today, according to the report from ComputerBase, NVIDIA's latest trio has recorded a drop in pricing recently, and it now retails under MSRP in German stores. The RTX 4070 SUPER started with an MSRP of 659 Euros ($599 in the US) and is now available from 589 Euros. Its older brother, the GeForce RTX 4070 Ti SUPER, started with an MSRP listing of 889 Euros ($799 in the US) and is now retailing from 840 Euros. Lastly, the NVIDIA GeForce RTX 4080 SUPER has been listed at 1,109 Euros ($999 in the US) and is now retailing with a small discount at 1,092 Euros.

Once NVIDIA launched a new GPU generation, it became a custom for these cards to be retailed over their MSRP long before prices were adjusted and settled. However, with the latest SUPER refresh, this seems to be one of the fastest price adjustments. This could be caused by either an improvement in the supply chain or leveled supply and demand, making it so that these cards are finally trading below their launch-level MSRPs.

Seasonic introduced a new 12V-2x6 modular PSU cable model late last year—at the time, interested parties were also invited to Beta test early examples. Finalized versions have been introduced, via a freshly uploaded YouTube video (see below) and a dedicated product page. The "H++" connector standard—part of a new ATX 3.1 specification—is expected to replace the troubled "H+" 12VHWPR design. The PC hardware community has engaged in long-running debates about the development and rollout of a danger/peril-free alternative. PCI-SIG drafted the 12V-2x6 design last summer.

Seasonic's introductory section stated: "with the arrival of the new ATX 3 / PCIe 5.0 specifications, some graphic cards will now be powered by the new 12V-2x6 connector. Offering up to 600 W of power, the Seasonic native 12V-2x6 cable has been crafted with high quality materials, such as high current terminal connectors and 16 AWG wires to ensure the highest performance and safety in usage." The new cables are compatible with Seasonic's current ATX 3.0 power supply unit range—including "PRIME TX, PRIME PX, VERTEX GX, PX, GX White and Sakura, FOCUS GX and GX White" models. Owners of older Seasonic ATX 2.0 PSUs are best served with an optional 2x8-pin to 12V-2x6 adapter cable—although 650 W rated and single PCIe connector-equipped units are not supported at all. Two native cable models, and a non-native variant are advertised in the manufacturer's video.

Speculative NVIDIA GeForce RTX 50-series "GB20X" GPU memory interface details appeared online late last week—as disclosed by the kopite7kimi social media account. The inside information aficionado—at the time—posited that the "memory interface configuration of GB20x (Blackwell) is not much different from that of AD10x (Ada Lovelace)." It was inferred that Team Green's next flagship gaming GPU (GB202) could debut with a 384-bit memory bus—kopite7kimi had "fantasized" about a potentially monstrous 512-bit spec for the "GeForce RTX 5090." A new batch of follow-up tweets—from earlier today—rips apart last week's insights. The alleged Blackwell GPU gaming lineup includes the following SKUs: GB202, GB203, GB205, GB206, GB207.

Kopite7kimi's revised thoughts point to Team Green's flagship model possessing 192 streaming multiprocessors and a 512-bit memory bus. VideoCardz decided to interact with the reliable tipster—their queries were answered promptly: "According to kopite7kimi, there's a possibility that the second-in-line GPU, named GB203, could sport half of that core count. Now the new information is that GB203 might stick to 256-bit memory bus, which would make it half of GB202 in its entirety. What this also means is that there would be no GB20x GPU with 384-bit bus." Additional speculation has NVIDIA selecting a 192-bit bus for the GB205 SKU (AKA GeForce RTX 5070). The GeForce RTX 50-series is expected to arrive later this year—industry experts are already whispering about HPC-oriented Blackwell GPUs being unveiled at next week's GTC 2024 event. A formal gaming family announcement could arrive many months later.

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."

The ecosystem around NVIDIA's technologies has always been verdant—but this is absurd. After a stunning premiere at the World Economic Forum in Davos, immersive artworks based on Refit Anadol Studio's Large Nature Model will come to the U.S. for the first time at NVIDIA GTC. Offering a deep dive into the synergy between AI and the natural world, Anadol's multisensory work, "Large Nature Model: A Living Archive," will be situated prominently on the main concourse of the San Jose Convention Center, where the global AI event is taking place, from March 18-21.

Fueled by NVIDIA's advanced AI technology, including powerful DGX A100 stations and high-performance GPUs, the exhibit offers a captivating journey through our planet's ecosystems with stunning visuals, sounds and scents. These scenes are rendered in breathtaking clarity across screens with a total output of 12.5 million pixels, immersing attendees in an unprecedented digital portrayal of Earth's ecosystems. Refik Anadol, recognized by The Economist as "the artist of the moment," has emerged as a key figure in AI art. His work, notable for its use of data and machine learning, places him at the forefront of a generation pushing the boundaries between technology, interdisciplinary research and aesthetics. Anadol's influence reflects a wider movement in the art world towards embracing digital innovation, setting new precedents in how art is created and experienced.

The Moore Threads MTT S80 first attracted wider media attention last summer due to it being introduced as the world's first PCIe Gen 5 gaming graphics card. Unfortunately, its performance prowess in gaming benchmarks did not match early expectations, especially for a 200 W TDP-rated unit with 4096 "MUSA" cores. Evaluators discovered that driver issues have limited the full potential of MTT GPUs—it is speculated that Moore Threads has simply repurposed existing PowerVR architecture under their in-house design: "Chunxaio." The Chinese firm has concentrated on driver improvements in the interim—mid-February experimentations indicated 100% performance boosts for MTT S80 and S70 discrete GPUs courtesy of driver version 240.90. Germany's ComputerBase managed to import Moore Threads MTT S80 and S30 models for testing purposes—in an effort to corroborate recently published performance figures, as disclosed by Asian review outlets.

The Moore Thread MTT S80—discounted down to $164 last October—was likely designed with MMO gamers in mind. VideoCardz (based on ComputerBase findings) discussed the card's struggles when weighed against Team Red's modern day integrated solutions: "S80 falls short when compared to the Ryzen 5 8600G, featuring the Radeon 760M iGPU with RDNA 3 graphics. A geometric mean across various titles reveals the S80's lag, but there are exceptions, like DOTA 2, where it takes the lead in framerate. It's clear that MTT GPUs (have a) less emphasized focus on supporting AAA titles." ComputerBase confirmed that DirectX 12 API support is still lacking, meaning that many popular Western games titles remain untested on the Moore Threads MTT S80 graphics card. The freshly launched entry-level MTT S30 card produced "1/4 of the performance" when compared to its flagship sibling.

During the 2024 SIEPR Economic Summit, NVIDIA CEO Jensen Huang acknowledged that the company's next-generation DGX systems, designed for AI and high-performance computing workloads, will require liquid cooling due to their immense power consumption. Huang also hinted that these new systems are set to be released in the near future. The revelation comes as no surprise, given the increasing power of GPUs needed to satisfy AI and machine learning applications. As computational requirements continue to grow, so does the need for more powerful hardware. However, with great power comes great heat generation, necessitating advanced cooling solutions to maintain optimal performance and system stability. Liquid cooling has long been a staple in high-end computing systems, offering superior thermal management compared to traditional air cooling methods.

By implementing liquid cooling in the upcoming DGX systems, NVIDIA aims to push the boundaries of performance while ensuring the hardware remains reliable and efficient. Although Huang did not provide a specific release date for the new DGX systems, his statement suggests that they are on the horizon. Whether the next generation of DGX systems uses the current NVIDIA H200 or the upcoming Blackwell B100 GPU as their primary accelerator, the performance will undoubtedly be delivered. As the AI and high-performance computing landscape continues to evolve, NVIDIA's position continues to strengthen, and liquid-cooled systems will certainly play a crucial role in shaping the future of these industries.

Earlier in the week it was revealed that NVIDIA had distributed next-gen AI GPUs to its most important ecosystem partners and customers—Dell's CEO expressed enthusiasm with his discussion of "Blackwell" B100 and B200 evaluation samples. Team Green's next-gen family of gaming GPUs have received less media attention in early 2024—a mid-February TPU report pointed to a rumored PCIe 6.0 CEM specification for upcoming RTX 50-series cards, but leaks have become uncommon since late last year. Top technology tipster, kopite7kimi, has broken the relative silence on Blackwell's gaming configurations—an early hours tweet posits a slightly underwhelming scenario: "although I still have fantasies about 512 bit, the memory interface configuration of GB20x is not much different from that of AD10x."

Past disclosures have hinted about next-gen NVIDIA gaming GPUs sporting memory interface configurations comparable to the current crop of "Ada Lovelace" models. The latest batch of insider information suggests that Team Green's next flagship GeForce RTX GPU—GB202—will stick with a 384-bit memory bus. The beefiest current-gen GPU AD102—as featured in GeForce RTX 4090 graphics cards—is specced with a 384-bit interface. A significant upgrade for GeForce RTX 50xx cards could arrive with a step-up to next-gen GDDR7 memory—kopite7kimi reckons that top GPU designers will stick with 16 Gbit memory chip densities (2 GB). JEDEC officially announced its "GDDR7 Graphics Memory Standard" a couple of days ago. VideoCardz has kindly assembled the latest batch of insider info into a cross-generation comparison table (see below).

Lately Tiny Corp. CEO—George Hotz—has used his company's social media account to publicly criticize AMD Radeon RX 7900 XTX GPU firmware. The creator of Tinybox, a pre-orderable $15,000 AI compute cluster, has not selected "traditional" hardware for his systems—it is possible that AMD's Instinct MI300X accelerator is quite difficult to acquire, especially for a young startup operation. The decision to utilize gaming-oriented XFX-branded RDNA 3.0 GPUs instead of purpose-built CDNA 3.0 platforms—for local model training and AI inference—is certainly a peculiar one. Hotz and his colleagues have encountered roadblocks in the development of their Tinybox system—recently, public attention was drawn to an "LLVM spilling bug." AMD President/CEO/Chair, Dr. Lisa Su, swiftly stepped in and promised a "good solution." Earlier in the week, Tiny Corp. reported satisfaction with a delivery of fixes—courtesy of Team Red's software engineering department. They also disclosed that they would be discussing matters with AMD directly, regarding the possibility of open-sourcing Radeon GPU MES firmware.

Subsequently, Hotz documented his interactions with Team Red representatives—he expressed 70% confidence in AMD approving open-sourcing certain bits of firmware in a week's time: "Call went pretty well. We are gating the commitment to 6x Radeon RX 7900 XTX on a public release of a roadmap to get the firmware open source. (and obviously the MLPerf training bug being fixed). We aren't open source purists, it doesn't matter to us if the HDCP stuff is open for example. But we need the scheduler and the memory hierarchy management to be open. This is what it takes to push the performance of neural networks. The Groq 500 T/s mixtral demo should be possible on a tinybox, but it requires god tier software and deep integration with the scheduler. We also advised that the build process for amdgpu-dkms should be more open. While the driver itself is open, we haven't found it easy to rebuild and install. Easy REPL cycle is a key driver for community open source. We want the firmware to be easy to rebuild and install also." Prior to this week's co-operations, Tiny Corp. hinted that it could move on from utilizing Radeon RX 7900 XTX, in favor of Intel Alchemist graphics hardware—if AMD's decision making does not favor them, Hotz & Co. could pivot to builds including Acer Predator BiFrost Arc A770 16 GB OC cards.

2024 will be the year generative AI gets personal, the CEOs of NVIDIA and HP said today in a fireside chat, unveiling new laptops that can build, test and run large language models. "This is a renaissance of the personal computer," said NVIDIA founder and CEO Jensen Huang at HP Amplify, a gathering in Las Vegas of about 1,500 resellers and distributors. "The work of creators, designers and data scientists is going to be revolutionized by these new workstations."

Greater Speed and Security
"AI is the biggest thing to come to the PC in decades," said HP's Enrique Lores, in the runup to the announcement of what his company billed as "the industry's largest portfolio of AI PCs and workstations." Compared to running their AI work in the cloud, the new systems will provide increased speed and security while reducing costs and energy, Lores said in a keynote at the event. New HP ZBooks provide a portfolio of mobile AI workstations powered by a full range of NVIDIA RTX Ada Generation GPUs. Entry-level systems with the NVIDIA RTX 500 Ada Generation Laptop GPU let users run generative AI apps and tools wherever they go. High-end models pack the RTX 5000 to deliver up to 682 TOPS, so they can create and run LLMs locally, using retrieval-augmented generation (RAG) to connect to their content for results that are both personalized and private.

Omdia, an independent analyst and consultancy firm, has bestowed the title of "Kingmaker" on NVIDIA—thanks to impressive 2023 results in the data server market. The research firm predicts very buoyant numbers for the financial year of 2024—their February Cloud and Datacenter Market snapshot/report guesstimates that Team Green's data center GPU business group has the potential to rake in $87 billion of revenue. Omdia's forecast is based on last year's numbers—Jensen & Co. managed to pull in $34 billion, courtesy of an unmatched/dominant position in the AI GPU industry sector. Analysts have estimated a 150% rise in revenues for in 2024—the majority of popular server manufacturers are reliant on NVIDIA's supply of chips. Super Micro Computer Inc. CEO—Charles Liang—disclosed that his business is experiencing strong demand for cutting-edge server equipment, but complications have slowed down production: "once we have more supply from the chip companies, from NVIDIA, we can ship more to customers."

Demand for AI inference in 2023 accounted for 40% of NVIDIA data center GPU revenue—according Omdia's expert analysis—they predict further growth this year. Team Green's comfortable AI-centric business model could expand to a greater extent—2023 market trends indicated that enterprise customers had spent less on acquiring/upgrading traditional server equipment. Instead, they prioritized the channeling of significant funds into "AI heavyweight hardware." Omdia's report discussed these shifted priorities: "This reaffirms our thesis that end users are prioritizing investment in highly configured server clusters for AI to the detriment of other projects, including delaying the refresh of older server fleets." Late February reports suggest that NVIDIA H100 GPU supply issues are largely resolved—with much improved production timeframes. Insiders at unnamed AI-oriented organizations have admitted that leadership has resorted to selling-off of excess stock. The Omdia forecast proposes—somewhat surprisingly—that H100 GPUs will continue to be "supply-constrained" throughout 2024.

NVIDIA and HP Inc. today announced that NVIDIA CUDA-X data processing libraries will be integrated with HP AI workstation solutions to turbocharge the data preparation and processing work that forms the foundation of generative AI development.

Built on the NVIDIA CUDA compute platform, CUDA-X libraries speed data processing for a broad range of data types, including tables, text, images and video. They include the NVIDIA RAPIDS cuDF library, which accelerates the work of the nearly 10 million data scientists using pandas software by up to 110x using an NVIDIA RTX 6000 Ada Generation GPU instead of a CPU-only system, without requiring any code changes.

Tulpar, an emerging PC gaming hardware company, has been doing the rounds across several European tech events—they demoed Meteor Lake-powered handheld devices at last month's Intel Extreme Masters tour stop in Katowice, Poland. A Hardwareluxx Germany report presented evidence of the Turkish company expanding into graphics card market sectors—Tulpar exhibited their "customized" Intel Arc A770 16 GB model at a recent trade show in Berlin. Andreas Schilling, resident editor at Hardwareluxx, realized that Tulpar had simply rebadged and color adjusted ASRock's Arc A770 Phantom D OC card design.

Tulpar's product placard boasted about their own "3X Cooling System"—a thin renaming of the already well-known ASRock Phantom Gaming triple-fan cooling solution. Their reliance on OEM designs is not a major revelation—the Tulpar 7-inch handheld gaming PC appears to be based on an existing platform—somewhat similar to Emdoor's EM-GP080MTL. Company representatives estimate that their "first dedicated gaming GPU" will be hitting retail within the third quarter of this year. News outlets have questioned this curious launch window—first generation Intel Arc "Alchemist" graphics cards (released in late 2022) are a tough sell, even with a much improved driver ecosystem delivering significant improvements throughout 2023/2024. Tulpar could be targeting a super budget price point, since Team Blue has signalled that their next-gen "Battlemage" GPUs are due later on in the year.

NVIDIA's Compute Unified Device Architecture (CUDA) has long been the de facto standard programming interface for developing GPU-accelerated software. Over the years, NVIDIA has built an entire ecosystem around CUDA, cementing its position as the leading GPU computing and AI manufacturer. However, rivals AMD and Intel have been trying to make inroads with their own open API offerings—ROCm from AMD and oneAPI from Intel. The idea was that developers could more easily run existing CUDA code on non-NVIDIA GPUs by providing open access through translation layers. Developers had created projects like ZLUDA to translate CUDA to ROCm, and Intel's CUDA to SYCL aimed to do the same for oneAPI. However, with the release of CUDA 11.5, NVIDIA appears to have cracked down on these translation efforts by modifying its terms of use, according to developer Longhorn on X.

"You may not reverse engineer, decompile or disassemble any portion of the output generated using Software elements for the purpose of translating such output artifacts to target a non-NVIDIA platform," says the CUDA 11.5 terms of service document. The changes don't seem to be technical in nature but rather licensing restrictions. The impact remains to be seen, depending on how much code still requires translation versus running natively on each vendor's API. While CUDA gave NVIDIA a unique selling point, its supremacy has diminished as more libraries work across hardware. Still, the move could slow the adoption of AMD and Intel offerings by making it harder for developers to port existing CUDA applications. As GPU-accelerated computing grows in fields like AI, the battle for developer mindshare between NVIDIA, AMD, and Intel is heating up.

The AI infrastructure of today is mostly fueled by the expansion that relies on GPU-accelerated servers. Google, one of the world's largest hyperscalers, has noted that CPUs are still a leading compute for AI/ML workloads, recorded on their Google Cloud Services cloud internal analysis. During the TechFieldDay event, a speech by Brandon Royal, product manager at Google Cloud, explained the position of CPUs in today's AI game. The AI lifecycle is divided into two parts: training and inference. During training, massive compute capacity is needed, along with enormous memory capacity, to fit ever-expanding AI models into memory. The latest models, like GPT-4 and Gemini, contain billions of parameters and require thousands of GPUs or other accelerators working in parallel to train efficiently.

On the other hand, inference requires less compute intensity but still benefits from acceleration. The pre-trained model is optimized and deployed during inference to make predictions on new data. While less compute is needed than training, latency and throughput are essential for real-time inference. Google found out that, while GPUs are ideal for the training phase, models are often optimized and run inference on CPUs. This means that there are customers who choose CPUs as their medium of AI inference for a wide variety of reasons.

TechPowerUp's resident GPU reviewer extraordinaire—W1zzard—has grappled with a handful of custom design AMD Radeon RX 7900 GRE 16 GB models. Team Red and its board partners are pushing a proper/widespread Western release of the formerly China market-exclusive "Golden Rabbit Edition" GPU. TPU's initial review selection of three Sapphire cards and a lone ASRock Steel Legend OC variant garnered two Editor's Choice Awards, and two Highly Recommended badges. Sapphire's Radeon RX 7900 GRE Nitro+ was also honored with a "...But Expensive" tag, due to its MSRP of $600—the premium tier design was one of last year's launch day models in China. Western reviewers have latched onto a notable GRE overclocking limitation—all of TPU's review samples were found to have "overclocking artificially limited by AMD." Steve Walton of Hardware Unboxed has investigated whether the GRE's inherent heavily limited power specification was less of an issue on Sapphire's Nitro+ variant—check out his "re-re-review" video below.

The higher board power design—305 W OC TGP limit and 351 W total board power—is expected to exhibit "up to 10% higher performance than Radeon RX 7800 XT" according to VideoCardz, but falls short. TPU's W1zzard found the GRE Nitro+ card's maximum configurable clock of 2803 MHz: "Overclocking worked quite well on our card, we gained over 8% in real-life performance, which is well above what we usually see, but less than other GRE cards tested today. Sapphire's factory OC eats into OC potential, and maximizes performance out of the box instead. Unfortunately AMD restricted overclocking on their card quite a lot, probably to protect sales of the RX 7900 XT. While NVIDIA doesn't have any artificial limitations for overclockers, AMD keeps limiting the slider lengths for many models, this is not a gamer-friendly approach. For the GRE, both GPU and memory overclocking could definitely go higher based on the results that we've seen in our reviews today." An AMD representative has contacted Hardware Unboxed, in reaction to yesterday's Update review—the GRE's overclocking limitation is a "bug," and a fix is in the works. This situation is a bit odd, given that the Golden Rabbit Edition is not a brand-new product.

MiTAC Computing Technology, a subsidiary of MiTAC Holdings Corp., proudly reveals its groundbreaking suite of server solutions that deliver unsurpassed capabilities with the 5th Gen Intel Xeon Scalable Processors. MiTAC introduces its cutting-edge signature platforms that seamlessly integrate the Intel Data Center GPUs, both Intel Max Series and Intel Flex Series, an unparalleled leap in computing performance is unleashed targeting HPC and AI applications.

MiTAC Announce its Full Array of Platforms Supporting the latest 5th Gen Intel Xeon Scalable Processors
Last year, Intel transitioned the right to manufacture and sell products based on Intel Data Center Solution Group designs to MiTAC. MiTAC confidently announces a transformative upgrade to its product offerings, unveiling advanced platforms that epitomize the future of computing. Featured with up to 64 cores, expanded shared cache, increased UPI and DDR5 support, the latest 5th Gen Intel Xeon Scalable Processors deliver remarkable performance per watt gains across various workloads. MiTAC's Intel Server M50FCP Family and Intel Server D50DNP Family fully support the latest 5th Gen Intel Xeon Scalable Processors, made possible through a quick BIOS update and easy technical resource revisions which provide unsurpassed performance to diverse computing environments.

The latest version of AMD's open-source GPU compute stack, ROCm, is due for launch soon according to a Phoronix article—chief author, Michael Larabel, has been poring over Team Red's public GitHub repositories over the past couple of days. AMD ROCm version 6.0 was released last December—bringing official support for the AMD Instinct MI300A/MI300X, alongside PyTorch improvements, expanded AI libraries, and many other upgrades and optimizations. The v6.0 milestone placed Team Red in a more competitive position next to NVIDIA's very mature CUDA software layer. A mid-February 2024 update added support for Radeon PRO W7800 and RX 7900 GRE GPUs, as well as ONNX Runtime.

Larabel believes that "ROCm 6.1" is in for an imminent release, given his tracking of increased activity on publicly visible developer platforms: "For MIPOpen 3.1 with ROCm 6.1 there's been many additions including new solvers, an AI-based parameter prediction model for the conv_hip_igemm_group_fwd_xdlops solver, numerous fixes, and other updates. AMD MIGraphX will see an important update with ROCm 6.1. For the next ROCm release, MIGraphX 2.9 brings FP8 support, support for more operators, documentation examples for Whisper / Llama-2 / Stable Diffusion 2.1, new ONNX examples, BLAS auto-tuning for GEMMs, and initial code for MIGraphX running on Microsoft Windows." The change-logs/documentation updates also point to several HIPIFY for ROCm 6.1 improvements—including the addition of CUDA 12.3.2 support.

The spirit of software pioneer Grace Hopper will live on at NVIDIA GTC. Accelerated systems using powerful processors - named in honor of the pioneer of software programming - will be on display at the global AI conference running March 18-21, ready to take computing to the next level. System makers will show more than 500 servers in multiple configurations across 18 racks, all packing NVIDIA GH200 Grace Hopper Superchips. They'll form the largest display at NVIDIA's booth in the San Jose Convention Center, filling the MGX Pavilion.

MGX Speeds Time to Market
NVIDIA MGX is a blueprint for building accelerated servers with any combination of GPUs, CPUs and data processing units (DPUs) for a wide range of AI, high performance computing and NVIDIA Omniverse applications. It's a modular reference architecture for use across multiple product generations and workloads. GTC attendees can get an up-close look at MGX models tailored for enterprise, cloud and telco-edge uses, such as generative AI inference, recommenders and data analytics. The pavilion will showcase accelerated systems packing single and dual GH200 Superchips in 1U and 2U chassis, linked via NVIDIA BlueField-3 DPUs and NVIDIA Quantum-2 400 Gb/s InfiniBand networks over LinkX cables and transceivers. The systems support industry standards for 19- and 21-inch rack enclosures, and many provide E1.S bays for nonvolatile storage.

Jon Peddie Research reports the growth of the global PC-based graphics processor unit (GPU) market reached 76.2 million units in Q4'23 and PC CPU shipments increased an astonishing 24% year over year, the biggest year-to-year increase in two and a half decades. Overall, GPUs will have a compound annual growth rate of 3.6% during 2024-2026 and reach an installed base of almost 5 billion units at the end of the forecast period. Over the next five years, the penetration of discrete GPUs (dGPUs) in the PC will be 30%.

AMD's overall market share decreased by -1.4% from last quarter, Intel's market share increased 2.8, and Nvidia's market share decreased by -1.36%, as indicated in the following chart.

World's most important fuel of the AI frenzy, NVIDIA, is facing accusations of acting as a "GPU cartel" and controlling supply in the data center market, according to statements made by executives at rival chipmaker Groq and former AMD executive Scott Herkelman. In an interview with the Wall Street Journal, Groq CEO Jonathan Ross alleged that some of NVIDIA's data center customers are afraid to even meet with rival AI chipmakers out of fear that NVIDIA will retaliate by delaying shipments of already ordered GPUs. This is despite NVIDIA's claims that it is trying to allocate supply fairly during global shortages. "This happens more than you expect, NVIDIA does this with DC customers, OEMs, AIBs, press, and resellers. They learned from GPP to not put it into writing. They just don't ship after a customer has ordered. They are the GPU cartel, and they control all supply," said former Senior Vice President and General Manager at AMD Radeon, Scott Herkelman, in response to the accusations on X/Twitter.

The NVIDIA H100 Tensor Core GPU was last year's hot item for HPC and AI industry segments—the largest purchasers were reported to have acquired up to 150,000 units each. Demand grew so much that lead times of 36 to 52 weeks became the norm for H100-based server equipment. The latest rumblings indicate that things have stabilized—so much so that some organizations are "offloading chips" as the supply crunch cools off. Apparently it is more cost-effective to rent AI processing sessions through cloud service providers (CSPs)—the big three being Amazon Web Services, Google Cloud, and Microsoft Azure.

According to a mid-February Seeking Alpha report, wait times for the NVIDIA H100 80 GB GPU model have been reduced down to around three to four months. The Information believes that some companies have already reduced their order counts, while others have hardware sitting around, completely unused. Maintenance complexity and costs are reportedly cited as a main factors in "offloading" unneeded equipment, and turning to renting server time from CSPs. Despite improved supply conditions, AI GPU demand is still growing—driven mainly by organizations dealing with LLM models. A prime example being Open AI—as pointed out by The Information—insider murmurings have Sam Altman & Co. seeking out alternative solutions and production avenues.

In Sept. 2023, Quantum Machines (QM) unveiled OPX1000, our most advanced quantum control system to date - and the industry's leading controller in terms of performance and channel density. OPX1000 is the third generation of QM's processor-based quantum controllers. It enhances its predecessor, OPX+, by expanding analog performance and multiplying channel density to support the control of over 1,000 qubits. However, QM's vision for quantum controllers extends far beyond.

OPX1000 is designed as a platform for orchestrating the control of large-scale QPUs (quantum processing units). It's equipped with 8 frontend modules (FEMs) slots, representing the cutting-edge modular architecture for quantum control. The first low-frequency (LF) module was introduced in September 2023, and today, we're happy to introduce the Microwave (MW) FEM, which delivers additional value to our rapidly expanding customer base.

FurMark's development team, Geeks3D, seems to be relieved after work was completed on version 2.1.0's public release—according to release notes: "It took me more time than expected but it's there!" The Beta version was made available back in December 2022 (through Geeks3D's Discord)—a milestone achievement for the Furmark dev team, since no major updates had been implemented since 2007. The GPU stress test and benchmarking tool was improved once again—last August, when the Beta was upgraded to v2.0.10.

Main author, JEGX, provided a little bit of background information: "FurMark 2 is built with GeeXLab. The GUI is a pure GeeXLab application while the furmark command line tool is built with the GeeXLab SDK. GeeXLab being cross-platform, this first version of FurMark 2 is available for Windows and Linux (the Linux 32-bit version is also available, I will re-compile it for the next update). I plan to release FurMark 2 for Raspberry Pi (I just received my Raspberry Pi 5 board!) and maybe for macOS too." He states that feedback is welcome, and requests for OpenGL 2.1 and 3.0/3.1 support will be considered. The full timeline of changelog updates can be found here.