Post Syndicated from Ryan Smith original https://www.servethehome.com/marvell-shows-dense-sram-custom-hbm-and-cxl-with-arm-compute-at-hot-chips-2025/
Marvell showed its massively dense SRAM, its custom HBM solution, and how it is adding Arm cores to CXL memory controllers at Hot Chips 2025
The post Marvell Shows Dense SRAM Custom HBM and CXL with Arm Compute at Hot Chips 2025 appeared first on ServeTheHome.
Post Syndicated from Cliff Robinson original https://www.servethehome.com/new-faster-amd-alveo-v80-accelerator-with-hbm2e-and-fast-networking/
The new, faster, AMD Alveo V80 packs 32GB of HBM2e memory, four QSFP56 200G ports, and many other features with the SoC on a pre-built card
The post New Faster AMD Alveo V80 Accelerator with HBM2e and Fast Networking appeared first on ServeTheHome.
Post Syndicated from Patrick Kennedy original https://www.servethehome.com/broadcom-3-5d-xdsip-with-face-to-face-3-5d-for-2026-xpus-and-beyond/
Broadcom 3.5D XDSiP with Face-to-Face 3.5D packaging already has a number of design wins for big custom 2026 XPUs
The post Broadcom 3.5D XDSiP with Face-To-Face 3.5D For 2026 XPUs and Beyond appeared first on ServeTheHome.
Post Syndicated from Cliff Robinson original https://www.servethehome.com/new-36gb-sk-hynix-hbm3e-12-high-in-volume-production/
SK hynix joins the 36GB HBM3E 12-high stack club announcing that its HBM modules are now in volume production
The post New 36GB SK hynix HBM3E 12-High in Volume Production appeared first on ServeTheHome.
Post Syndicated from Cliff Robinson original https://www.servethehome.com/micron-hbm3e-12-high-36gb-higher-capacity-ai-accelerators-shipping/
Micron HBM3E 12-High will bring 36GB packages for higher capacity AI accelerators in the coming months as it starts to ship
The post Micron HBM3E 12-High 36GB Higher Capacity AI Accelerators Shipping appeared first on ServeTheHome.
Post Syndicated from Patrick Kennedy original https://www.servethehome.com/cerebras-enters-ai-inference-blows-away-tiny-nvidia-h100-gpus-by-besting-hbm/
Cerebras enters AI inference and uses its giant chip to run circles around NVIDIA HGX H100 platform performance
The post Cerebras Enters AI Inference Blows Away Tiny NVIDIA H100 GPUs by Besting HBM appeared first on ServeTheHome.
Post Syndicated from Patrick Kennedy original https://www.servethehome.com/sambanova-sn40l-rdu-for-trillion-parameter-ai-models/
This is the SambaNova SN40L a dataflow architecture AI accelerator with 520MB of SRAM, 64GB of HBM, and 1.5TB of DDR memory
The post SambaNova SN40L RDU for Trillion Parameter AI Models appeared first on ServeTheHome.
Post Syndicated from Cliff Robinson original https://www.servethehome.com/samsung-hbm3e-12h-36gb-in-production-q2-2024/
Samsung has new HBM slated for Q2 2024 production. Samsung HBM3E 12H will bring 36GB packages to the market in a few months
The post Samsung HBM3E 12H 36GB In Production Q2 2024 appeared first on ServeTheHome.
Post Syndicated from Patrick Kennedy original https://www.servethehome.com/quanta-qct-qoolrack-liquid-cooling-intel-xeon-max-overview/
We take you for a tour of the QCT QoolRack which is the company’s integrated liquid cooling solution for high-performance computing
The post Quanta QCT QoolRack Liquid Cooling Intel Xeon Max Overview appeared first on ServeTheHome.
Post Syndicated from Patrick Kennedy original https://www.servethehome.com/sk-hynix-hbm3e-cxl-computational-memory-mcrdimm-and-more-ocp-summit-2023/
At OCP Summit 2023, we saw SK hynix HBM3e, CXL Computational Memory, MCRDIMM for 2024, PCIe Gen5 NVMe SSDs, and Accelerator in Memory modules
The post SK hynix HBM3e CXL Computational Memory MCRDIMM and More OCP Summit 2023 appeared first on ServeTheHome.
Post Syndicated from Patrick Kennedy original https://www.servethehome.com/intel-xeon-max-9480-deep-dive-intel-has-64gb-hbm2e-onboard-like-a-gpu-or-ai-accelerator/
We deep-dive into the Intel Xeon MAX 9480 and see several surprises when combining Xeon cores and HBM2e memory (like a GPU uses)
The post Intel Xeon MAX 9480 Deep-Dive 64GB HBM2e Onboard Like a GPU or AI Accelerator appeared first on ServeTheHome.
Post Syndicated from Patrick Kennedy original https://www.servethehome.com/samsung-processing-in-memory-technology-at-hot-chips-2023/
At Hot Chips 2023, Samsung showed its Processing in/near Memory ranging from PIM-HBM in AMD MI100 test GPUs to LPDDR-PIM and CXL-PNM modules
The post Samsung Processing in Memory Technology at Hot Chips 2023 appeared first on ServeTheHome.
Post Syndicated from Cliff Robinson original https://www.servethehome.com/micron-hbm3-gen2-with-higher-capacity-and-bandwidth/
Micron HBM3 Gen2 offers higher capacity and more bandwidth making 200GB+ GPUs and AI accelerators possible in 2024
The post Micron HBM3 Gen2 with Higher Capacity and Bandwidth appeared first on ServeTheHome.
Post Syndicated from Cliff Robinson original https://www.servethehome.com/sk-hynix-introduces-new-12-layer-hbm3-memory/
SK hynix has new 12-layer HBM3 memory increasing capacity from 8-layer 16GB stacks to 12-layer 24GB stacks
The post SK hynix Introduces New 12-layer HBM3 Memory appeared first on ServeTheHome.
Post Syndicated from John Lee original https://www.servethehome.com/amd-talks-stacking-compute-and-dram-at-isscc-2023/
At ISSCC 2023, Dr. Lisa Su CEO of AMD discusses why stacking compute and DRAM can lead to enormous efficiency gains
The post AMD Talks Stacking Compute and DRAM at ISSCC 2023 appeared first on ServeTheHome.