ASRock Rack sells the entire stack of servers a data-center could possibly want, and at Computex 2024, the company showed us their servers meant for AI GPUs. The 6U8M-GENOA2, as its name suggests, is a 6U server based on 2P AMD EPYC 9004 series "Genoa" processors in the SP5 package. You can configure it with even the variants of "Genoa" that come with 3D V-cache, for superior compute performance from the large cache. Each of the two SP5 sockets is wired to 12 DDR5 RDIMM slots, for a total of 24 memory channels. The server supports eight AMD Instinct MI300X or MI325X AI GPUs, which it wires out using Infinity Fabric links and PCIe Gen 5 x16 individually. A 3 kW 80 Plus Titanium PSU keeps the server fed. There are vacant Gen 5 x16 slots left even after connecting the GPUs, so you could give it a DPU-based 40 GbE NIC.

The 6U8X-EGS2 B100 is a 6U AI GPU server modeled along the 6U8M-GENOA2, with a couple of big changes. To begin with, the EPYC "Genoa" chips make way for a 2P Intel Xeon Socket E (LGA4677) CPU setup, for 2P Xeon 5 "Emerald Rapids" processors. Each socket is wired to 16 DDR5 DIMM slots (the processor itself has 8-channel DDR5, but this is a 2 DIMM-per-channel setup). The server integrates an NVIDIA NVSwitch that wires out NVLinks to eight NVIDIA B100 "Blackwell" AI GPUs. The server features eight HHHL PCIe Gen 5 x16, and five FHHL PCIe Gen 5 x16 connectors. There are vacant x16 slots for your DPU/NIC, you can even use an AIC NVIDIA BlueField card. The same 3 kW PSU as the "Genoa" system is also featured here.

Intel today launched its Arctic Sound M line of data-center GPUs. These are not positioned as HPC processors like the "Ponte Vecchio," but GPUs targeting cloud-compute providers, with their main applications being in the realm of visual processing, media, and AI inferencing. Their most interesting aspect has to be the silicon, which are the same 6 nm "ACM-G11" and "ACM-G10" chips powering the Arc "Alchemist" client graphics cards, based on the Xe-HPG architecture. Even more interesting is their typical board power values, ranging between 75 W to 150 W. The cards are built in the PCI-Express add-on card form-factor, with their cooling solutions optimized for rack airflow.

The marketing name for these cards is simply Intel Data Center GPU Flex, with two models being offered: The Data Center GPU Flex-140, and Flex-170. The Flex-170 is a full-sized add-on card based on the larger ACM-G10 silicon, which has 32 Xe Cores (4,096 unified shaders), whereas the Flex-140, interestingly, is a low-profile dual-GPU card with two smaller ACM-G11 chips that each has 8 Xe Cores (1,024 unified shaders). The two chips appear to be sharing a PCIe bridge chip in the renders. Both models come with four Xe Media Engines that pack AV1 encode hardware-acceleration, XMX AI acceleration, real-time ray tracing, and GDDR6 memory.

Super Micro Computer, Inc., a global leader in enterprise computing, storage, networking, and green computing technology, is announcing future Total IT Solutions for availability with Android Cloud Gaming and Media Processing & Delivery. These new solutions will incorporate the Intel Data Center GPU, codenamed Arctic Sound-M, and will be supported on several Supermicro servers. Supermicro solutions that will contain the Intel Data Center GPUs codenamed Arctic Sound-M, include the 4U 10x GPU server for transcoding and media delivery, the Supermicro BigTwin system with up to eight Intel Data Center GPUs, codenamed Arctic Sound-M in 2U for media processing applications, the Supermicro CloudDC server for edge AI inferencing, and the Supermicro 2U 2-Node server with three Intel Data Center GPUs, codenamed Arctic Sound-M per node, optimized for cloud gaming. Additional systems will be made available later this year.

"Supermicro will extend our media processing solutions by incorporating the Intel Data Center GPU," said Charles Liang, President, and CEO, Supermicro. "The new solutions will increase video stream rates and enable lower latency Android cloud gaming. As a result, Android cloud gaming performance and interactivity will increase dramatically with the Supermicro BigTwin systems, while media delivery and transcoding will show dramatic improvements with the new Intel Data Center GPUs. The solutions will expand our market-leading accelerated computing offerings, including everything from Media Processing & Delivery to Collaboration, and HPC."

Super Micro Computer, Inc. (Nasdaq: SMCI), a global leader in enterprise computing, storage, networking, and green computing technology, supports two new Intel-based accelerators for demanding cloud gaming, media delivery, AI and ML workloads, enabling customers to deploy the latest acceleration technology from Intel and Intel Habana. "Supermicro continues to work closely with Intel and Habana Labs to deliver a range of server solutions supporting Arctic Sound-M and Gaudi 2 that address the demanding needs of organizations that require highly efficient media delivery and AI training," said Charles Liang, president and CEO. "We continue to collaborate with leading technology suppliers to deliver application-optimized total system solutions for complex workloads while also increasing system performance."

Supermicro can quickly bring to market new technologies by using a Building Block Solutions approach to designing new systems. This methodology allows new GPUs and acceleration technology to be easily placed into existing designs or, when necessary, quickly adapt an existing design when needed for higher-performing components. "Supermicro helps deliver advanced AI and media processing with systems that leverage our latest Gaudi 2 and Arctic Sound-M accelerators," stated Sandra Rivera, executive vice president and general manager of the Datacenter and AI Group at Intel. "Supermicro's Gaudi AI Training Server will accelerate deep learning training in some of the fastest growing workloads in the datacenter."

Intel showed off the video encode acceleration capabilities of its upcoming Data Center GPU codenamed "Arctic Sound M," which features AV1 video encode hardware-acceleration. Intel has been pushing for AV1 to be adopted as the streaming video standard for some years now, as it offers comparable bitrate savings and quality to H.265, but is royalty free, resulting in tens of millions of Dollars of royalty savings for streaming content providers such as Netflix, as well as consumer electronics manufacturers, particularly smart TV makers.

Intel's accelerator is a single-slot, full-height add-on card with a PCI-Express x16 interface. It relies on rack airflow for cooling, and features a metal-channel heatsink. Power is drawn from a single 8-pin PCIe power connector. There are no encoding performance numbers put out, except the 30% bitrate savings AV1 offers compared to the current industry standard, H.264. This 30% saving adds up in a big way for a streaming content provider.Intel's video presentation follows.

At Intel's 2022 investor meeting, the company has presented a technology roadmap update to give its clients an insight into what is to come. Today, team blue announced one of the first discrete data-centric graphics cards in the lineup, codenamed Arctic Sound-M GPU. Based on the DG2 Xe-HPG variation of Intel Xe GPUs, Arctic Sound-M is the company's first design to enter the data center space. The DG2 GPU features 512 Execution Units (EUs), which get passive cooling from the single-slot design of Arctic Sound's heatsink, envisioned for data center enclosures with external airflow.

One of the most significant selling points that Intel advertises is support for hardware-based AV1 encoding standard. This feature allows the card to achieve a 30% greater bandwidth, and it is the main differentiator between consumer-oriented Arc Alchemist GPUs and itself. The card is powered by PCIe power and an 8-pin EPS power connector. Arctic Sound-M is already sampling to select customers and it will become available in the middle of 2022.Below is Intel's teaser video.

At Intel's 2022 Investor Meeting, Chief Executive Officer Pat Gelsinger and Intel's business leaders outlined key elements of the company's strategy and path for long-term growth. Intel's long-term plans will capitalize on transformative growth during an era of unprecedented demand for semiconductors. Among the presentations, Intel announced product roadmaps across its major business units and key execution milestones, including: Accelerated Computing Systems and Graphics, Intel Foundry Services, Software and Advanced Technology, Network and Edge, Technology Development, More: For more from Intel's Investor Meeting 2022, including the presentations and news, please visit the Intel Newsroom and Intel.com's Investor Meeting site.

Intel has been extensively teasing its Xe HP scalable compute architecture for some time now, and Igor's Lab has an exclusive look at GPU compute cards based on the Xe HP silicon. We know from older reports that Intel's Xe HP compute accelerator packages come in three essential variants—1 tile, 2 tiles, and 4 tiles. A "tile" here is an independent GPU accelerator die. Each of these tiles has 512 execution units, which convert to 4,096 programmable shaders. The single-tile card is a compact, half-height card capable of 1U and 2U chassis. According to Igor's Lab, it comes with 16 GB of HBM2E memory with 716 GB/s memory bandwidth, and the single tile has 384 out of 512 EUs enabled (3,072 shaders). The card also has a typical board power of just 150 W.

The Arctic Sound 2T card is an interesting contraption. A much larger 2-slot card of length easily above 28 cm, and a workstation spacer, the 2T card uses a 2-tile variant of the Xe HP package, but each of the two tiles only has 480 out of 512 EUs enabled. This works out to 7,680 shaders. The dual-chiplet MCM uses 32 GB of HBM2E memory (16 GB per tile), and a typical board power of 300 W. A single 4+4 pin EPS connector, capable of up to 225 W, is used to power the card.

Intel is preparing to flood the market with its Xe GPU lineup, covering the entire vector from low-end to high-end consumer graphics cards. Just a few days ago, the company has announced its Iris Xe MAX GPU, the first discrete GPU from Intel, aimed at 1080p gamer and content creators. However, that seems to be only the beginning of Intel's GPU plan and just a small piece of the entire lineup. Next year, the company is expected to launch two GPU families - Xe-HP and Xe-HPG. With the former being a data-centric GPU codenamed Arctic Sound, and the latter being a gaming-oriented GPU called DG2. Today, thanks to the GeekBench listing, we have some information on the Xe-HP GPU.

Being listed with 512 EUs (Execution Units), translating into 4096 shading units, the GPU is reportedly a Xe-HP variant codenamed "NEO Graphics". This is not the first time that the NEO graphics has been mentioned. Intel has called a processor Neo graphics before, on its Architecture day when the company was demonstrating the FP32 performance. The new GeekBench leak shows the GPU running at 1.15 GHz clock speed, where at the Architecture day the same GPU ran at 1.3 GHz frequency, indicating that this is only an engineering sample. The GPU ran the GeekBench'es OpenCL test and scored very low 25,475 points. Compared to NVIDIA's GeForce RTX 3070 GPU that scored 140,484, the Intel GPU is at least four times slower. That is possibly due to the non-optimization of the benchmark, which could greatly improve in the future. In the first picture below, this Xe-HP GPU would represent the single-tile design.

A reportedly leaked Intel slide via DigitalTrends has given us a load of information on Intel's upcoming take on the high performance graphics accelerators market - whether in its server or consumer iterations. Intel's Xe has already been cause for much discussion in a market that has only really seen two real competitors for ages now - the coming of a third player with muscles and brawl such as Intel against the already-established players NVIDIA and AMD would surely spark competition in the segment - and competition is the lifeblood of advancement, as we've recently seen with AMD's Ryzen CPU line.

The leaked slide reveals that Intel will be looking to employ a Multi-Chip-Module (MCM) approach to its high performance "Arctic Sound" graphics architecture. The GPUs will be available in up to 4-tile configuration (the name Intel is giving each module), which will then be joined via Foveros 3D stacking (first employed in Intel Lakefield. This leaked slide shows Intel's approach starting with a 1-tile GPU (with only 96 of its 128 total EUs active) for the entry level market (at 75 W TDP) a-la DG1 SDV (Software Development Vehicle).

During interview with Russian YouTube channel called PRO Hi-Tech, Raja Koduri, Intel's chief architect and senior vice president of architecture, software and graphics, talked about his career, why he left AMD, and where Intel is going with its discrete GPU attempts. However, one of the most notable things Mr Koduri said was regarding upcoming GPU lineup code-named Arctic Sound. He noted that Intel plans to release first GPU as a mid-range model at a price of $200, while enterprise solutions that utilize HBM memory will follow that.

Koduri said that he wants to replicate AMD's strategy of capturing high-volume price-points, such as the $199 Radeon RX 480. The plan here is to bring an affordable, good performing GPU to the masses - "GPUs for everyone" as he calls them. Additionally, he states that Intel's current strategy revolves around price, not performance, providing best possible value to consumers. Intel's approach for the next two or three years is to launch a complete lineup of GPUs, with a common architecture being used for everything from iGPUs found inside consumer CPUs to data-center GPUs.Update: PRO Hi-Tech has posted a snippet of Raja Koduri interview, without the Russian overlay commentary. What he said was actually: "...Eventually our architecture, as publicly said, has to get from mainstream, which is starting at around $100, all the way to data-center class graphics with HBM memory...". This means that the previous speculation about $200 graphics card is false, as he didn't say that. All he said is that Intel wants to enter the "mainstream" GPU market and work its way up to data center.

According to DigiTimes, Intel's top graphics executive Raja Koduri and other senior Intel partners will be hosting a discrete GPU-focused conference this December. The conference aims to instill confidence in shareholders and customers alike in that Intel is pursuing its high-performance discrete entry into the graphics card market at a fast pace. The GPU architecture, codenamed Arctic Sound, is expected to debut by 2020, aiming for the gaming, AI, and machine learning sectors - much like any GPU solution these days. It remains to be seen which details - if any - can be gleaned from this conference, but we'll keep you up to date when those surface.

Intel did the impossible in 2017, by collaborating with rival AMD after decades, on a product. The new Core i7-8000G series processors are multi-chip modules that combine quad-core "Kaby Lake" CPU dies with discrete AMD Radeon Vega GPU dies that have their own dedicated HBM2 stacks. With performance-segment notebooks and sleek AIO desktops building momentum for such products, Intel sees a future in building its own discrete GPUs, at least dies that can replace the AMD Radeon IP from its Core G-series processors.

With former AMD Graphics head Raja Koduri switching to Intel amidst rumors of the company investing in discrete GPUs of its own, details emerge of the company's future "Arctic Sound" and "Jupiter Sound" graphics IP, which point to the possibility of them being discrete GPU dies based on the Gen 12 and Gen 13 graphics architectures, respectively. According to Ashraf Eassa, a technology stock commentator with "The Motley Fool," both "Arctic Sound" and "Jupiter Sound" are discrete GPU dies that connect with Intel processor dies over EMIB, the company's proprietary high-density interconnect for multi-chip modules. It could be a long wait leading up to the two, since the company is still monetizing its Gen 9.5 architecture on 8th generation Core processors.