Post Syndicated from Patrick Kennedy original https://www.servethehome.com/broadcom-ai-compute-asic-with-optical-attach-detailed-at-hot-chips-2024/
In one of the coolest presentations at Hot Chips 2024 so far, Broadcom showed co-packaged silicon photonics for switches and AI ASICs
The post Broadcom AI Compute ASIC with Optical Attach Detailed at Hot Chips 2024 appeared first on ServeTheHome.
Post Syndicated from Patrick Kennedy original https://www.servethehome.com/amd-instinct-mi300x-architecture-at-hot-chips-2024/
AMD had a talk on its big AI GPU at Hot Chips 2024. The AMD Instinct MI300X is a multi-billion dollar product line for the company
The post AMD Instinct MI300X Architecture at Hot Chips 2024 appeared first on ServeTheHome.
Post Syndicated from Patrick Kennedy original https://www.servethehome.com/intel-gaudi-3-for-ai-training-and-inference/
We have more details of the Intel Gaudi 3 for AI training and inference at Hot Chips 2024 including generational performance gains
The post Intel Gaudi 3 for AI Training and Inference appeared first on ServeTheHome.
Post Syndicated from Patrick Kennedy original https://www.servethehome.com/everyone-reading-sth-get-excited-marvell-structera-cxl-memory-with-arm-neoverse-v2/
Marvell Structera CXL Memory Expansion modules accept DDR4 or DDR5. The line also has a 16-core Arm Neoverse V2 accelerated memory expander
The post Get Excited Marvell Structera CXL Memory with Arm Neoverse V2 appeared first on ServeTheHome.
Post Syndicated from Cliff Robinson original https://www.servethehome.com/unigen-biscotti-dual-hailo-8-ai-module-spotted-in-aic-booth-at-computex-2024/
At Computex 2024, we saw the Unigen Biscotti, a low-power dual Hailo-8 AI inference accelerator E1.S card in the AIC booth
The post Unigen Biscotti Dual Hailo-8 AI Module Spotted in AIC Booth at Computex 2024 appeared first on ServeTheHome.
Post Syndicated from Patrick Kennedy original https://www.servethehome.com/amd-instinct-mi350-288gb-gpu-offering-35x-ai-inference-performance-next-year/
AMD Instinct MI325X with 288GB of HBM3E memory is for 2024, while the MI350X with CDNA 4 offers 35x AI Inference performance in 2025
The post AMD Instinct MI350 288GB GPU Offering 35x AI Inference Performance Next Year appeared first on ServeTheHome.
Post Syndicated from Cliff Robinson original https://www.servethehome.com/intel-gaudi-2-complete-servers-from-supermicro-for-90k/
We found a hard price for an AI server configuration with Supermicro selling an 8-way Intel Gaudi 2 server for only $90K
The post Intel Gaudi 2 Complete Servers from Supermicro for $90K appeared first on ServeTheHome.
Post Syndicated from Patrick Kennedy original https://www.servethehome.com/intel-ponte-vecchio-spaceship-gpu-no-longer-hunting-new-clusters/
Intel’s spaceship GPU, Ponte Vecchio, was perhaps too far ahead of its time and the GPU is moving into a support phase ahead of Falcon Shores
The post Intel Ponte Vecchio Spaceship GPU No Longer Hunting New Clusters appeared first on ServeTheHome.
Post Syndicated from Patrick Kennedy original https://www.servethehome.com/intel-gaudi-3-24x-200gbe-ai-accelerator-short-video/
We have a quick 30 second video on the Intel Gaudi 3 AI accelerator that uses 24x 200GbE connections to scale to eight AI modules and beyond
The post Intel Gaudi 3 24x 200GbE AI Accelerator The Short Video appeared first on ServeTheHome.
Post Syndicated from Patrick Kennedy original https://www.servethehome.com/this-is-intel-gaudi-3-the-new-128gb-hbm2e-ai-chip-in-the-wild-intel-vision-2024/
This is Intel Gaudi 3 from Intel Vision 2024. The new modules are designed for scale-out AI inference and training with 24x 200GbE links
The post This is Intel Gaudi 3 the New 128GB HBM2e AI Chip in the Wild appeared first on ServeTheHome.
Post Syndicated from Patrick Kennedy original https://www.servethehome.com/new-meta-ai-accelerator-mtia-2-revealed/
The new Meta MTIA 2 AI accelerator optimizes for memory capacity/ W or memory capacity/ compute unit making it a very different AI design
The post New Meta AI Accelerator MTIA 2 Revealed appeared first on ServeTheHome.
Post Syndicated from Patrick Kennedy original https://www.servethehome.com/nvidia-gtc-2024-keynote-coverage-new-cpus-gpus-and-more/
We are covering the NVIDIA GTC 2024 keynote live from San Jose California with tons of new product launches from the AI company
The post NVIDIA GTC 2024 Keynote Coverage New CPUs GPUs and More appeared first on ServeTheHome.
Post Syndicated from Patrick Kennedy original https://www.servethehome.com/cerebras-wse-3-ai-chip-launched-56x-larger-than-nvidia-h100-vertiv-supermicro-hpe-qualcomm/
The Cerebras WSE-3 is a giant AI training engineering marvel with 44GB of on-chip memory, 900,000 cores, and 125PF of AI compute
The post Cerebras WSE-3 AI Chip Launched 56x Larger than NVIDIA H100 appeared first on ServeTheHome.
Post Syndicated from Patrick Kennedy original https://www.servethehome.com/amd-infinity-fabric-afl-scale-up-competitor-to-nvidia-nvlink-coming-to-broadcom-switches-in-pcie-gen7/
AMD’s AFL Infinity Fabric scale-up competitor to NVIDIA NVLink is coming to Broadcom switches in the PCIe Gen7 era
The post AMD Infinity Fabric AFL Scale Up Competitor to NVIDIA NVLink Coming to Broadcom Switches in PCIe Gen7 appeared first on ServeTheHome.
Post Syndicated from Patrick Kennedy original https://www.servethehome.com/nvidia-l40s-vs-h100-vs-a100-the-video/
We have a video on the NIVIDA L40S vs NVIDIA H100 vs NVIDIA A100 and why the new L40S is a different GPU option for AI inference and more
The post NVIDIA L40S vs H100 vs A100 The Video appeared first on ServeTheHome.
Post Syndicated from John Lee original https://www.servethehome.com/touring-the-ai-servers-at-the-asus-sc23-booth-nvidia/
We tour the NVIDIA AI servers in the ASUS SC23 booth. This includes HGX H100 platforms, L40S platforms, and a special liquid cooling option
The post Touring the NVIDIA AI Servers at the ASUS SC23 Booth appeared first on ServeTheHome.
Post Syndicated from Patrick Kennedy original https://www.servethehome.com/marvell-octeon-cn103-dpu-50gbps-encryption-on-one-core-arm/
We saw a demo of the new Marvell Octeon 10 DPU. The demo had two Marvell CN103 DPUs in new low profile PCIe cards offloading IPsec crypto
The post Marvell Octeon CN103 DPU 50Gbps Encryption on One Core appeared first on ServeTheHome.
Post Syndicated from Cliff Robinson original https://www.servethehome.com/google-tpu-v5p-ai-chip-launches-alongside-gemini/
The Google TPU v5p scales to pods of up to 8960 chips with huge interconnect bandwidth. This is a chip used to train Gemini
The post Google TPU v5p AI Chip Launches Alongside Gemini appeared first on ServeTheHome.
Post Syndicated from Patrick Kennedy original https://www.servethehome.com/amd-instinct-mi300x-gpu-and-mi300a-apus-launched-for-ai-era/
We delve into the new AMD Instinct MI300X GPU, MI300A APU, and see how AMD has built packages to go head-to-head with the NVIDIA H100 and win
The post AMD Instinct MI300X GPU and MI300A APUs Launched for AI Era appeared first on ServeTheHome.
Post Syndicated from Cliff Robinson original https://www.servethehome.com/aws-graviton4-is-an-even-bigger-arm-server-processor-and-tranium2-for-ai-nvidia/
Today AWS made the much-anticipated announcement of Graviton4 which should be available in 2024. This is AWS’s latest Graviton processor and the fourth generation launched in the last five years. The company also announced its second-generation Tranium2 processor for AI workloads. AWS Graviton4 is an Even Bigger Arm Server Processor AWS is continuing on its […]
The post AWS Graviton4 is an Even Bigger Arm Server Processor and Tranium2 for AI appeared first on ServeTheHome.