Under Dr. Su’s leadership, the company has assembled a comprehensive suite of silicon solutions for the lucrative cloud data center, HPC and AI markets.
AMD 4Th Gen EPYC Bergamo Performance Claims Per Server RackAt a high level, Bergamo has the same L1 and L2 cache complement but less L3 shared cache at up to 256MB total, versus AMD’s Genoa CPU arch at 384MB. That smaller shared cache is also divided amongst more cores at 16MB per CCX , versus 32MB per CCX in the traditional Zen 4 Genoa design. Clock speeds are scaled back a bit as well, with base clocks as low as 2.2GHz and boost at 3.1GHz, whereas Genoa tops out at 3.7GHz.
Gen EPYC processors with 3D V-Cache have just been unveiled as well, with up to a massive 1.1GB of L3 cache per chip. The Genoa-X platform is specifically optimized for what the company refers to as technical computing requirements of design, modeling and simulation. This market segment has as much more compute-intensive demands with massive data sets, processing and bandwidth demands that are more costly to go off-chip into system memory.
AMD’s MI300A is a combo CPU+GPU design, with 24 Zen 4 CPU cores on board with an AMD CDNA 3 GPU with 128GB of HMB3 memory in a single package and unified memory access across CPU and GPU resources, which can be particularly efficient in HPC workloads. AMD notes MI300A has been slated for deployment in the El Capitan supercomputer at Lawrence Livermore National Labs in California.
In addition, there will be a GPU-only version of MI300 called MI300X. This GPU is designed to go toe to toe with NVIDIA’s H100 Hopper AI accelerator, and is optimized for large language models and generative AI. MI300X will have a total of 192GB of HBM3 memory on board delivering 5.2 TB/s of bandwidth and is comprised of 153 billion transistors across a 12 chiplet design. With MI300X, AMD is claiming a 2.4X HBM density and a 1.
There will, however, be a lot of software and platform support that will be required to foster development on and adoption of these various technologies. In fact, I think that will likely be the longer pole in the tent for AMD moving forward with respect to AI especially, as the company unifies its ROCm GPU, ZenDNN CPU and Vitis AI software tools into an optimized stack for the developer ecosystem from cloud to edge.
United States Latest News, United States Headlines
Similar News:You can also read news stories similar to this one that we have collected from other news sources.
AMD likely to offer details on AI chip in challenge to NvidiaAdvanced Micro Devices on Tuesday is expected to reveal new details about an AI 'superchip' that analysts believe will be a strong challenger to Nvidia Corp , whose chips dominate the fast-growing artificial intelligence market.
Read more »
AMD launches new Bergamo data-center CPU to go up against Nvidia, IntelAdvanced Micro Devices Inc. officially launched its next-generation data-center central processing unit at its Data Center & AI Technology Premiere event in...
Read more »
In challenge to Nvidia, AMD will ramp up AI chip production this yearAdvanced Micro Devices' production of a new artificial intelligence chip to challenge market leader Nvidia Corp will ramp up in the fourth quarter, the company said on Tuesday.
Read more »
Fueled by family, Tucson native Montañez chasing ’24 OlympicsOne of America's elite runners, Nico Montañez credits his past and present coaches, as well as his family, for putting him on the right track.
Read more »
Exhibition at National Museum of Mexican Art Places Native Mexican Culture Front and CenterWhat does it mean to be a native Mexican after centuries of colonization? And how do those cultures present themselves today, despite efforts at their erasure? Those are the questions at the heart of “Los Huecos del Agua” at ExploreNMMA.
Read more »
Native American protesters shut down Biden admin event over oil leasing banA scheduled event hosted by the Biden administration was derailed Sunday after Native American protesters blocked top officials from crossing into their territory.
Read more »