Compute_Express_Link
en.wikipedia.org · 2,861 words · saved by 1 readers
Couldn't find lead section for Compute_Express_Link
Compute Express Link - Wikipedia Jump to content From Wikipedia, the free encyclopedia Open standard processor interconnection for data centers Compute Express Link Year created 2019 ; 7 years ago  ( 2019 ) Created by Intel No. of devices 4096 Speed Full duplex 1.x - 2.0 (32 GT/s ): 3.938 GB/s (×1) 63.015 GB/s (×16) 3.x (64 GT/s ): 7.563 GB/s (×1) 121.0 GB/s (×16) 4.0 (128 GT/s ): 15.126 GB/s (×1) 242.0 GB/s (×16) Style Serial Website www .computeexpresslink .org Compute Express Link ( CXL ) is an open standard interconnect for high-speed, high capacity CPU -to-device and CPU
saved by
related reading
- AI Chip Architecturesjepeake.com
- China’s CXMT Is Set to Challenge DRAM Incumbentsnewsletter.semianalysis.com
- Are you a memory_man, Part 2 - by Investing with Martinmartinbradstreet.substack.com
- TPU Inference Externalization Full Steam Ahead - InferenceXnewsletter.semianalysis.com
- Meta harness makes 10 times better Kimi K3 chipluoluo.ai
- AI Chip Architecturesjacobpeake.com
- Another Giant Leap: The Rubin CPX Specialized Accelerator & Rack – SemiAnalysissemianalysis.com
- MatX: High-throughput chips for LLMsmatx.com
- How to Think About TPUs | How To Scale Your Modeljax-ml.github.io
- ⭐️ Fast LLM Inference From Scratchandrewkchan.dev
- Mixture-of-Kittens: our open-source MoE megakernel for NVL72scursor.com
- 1. Introduction — PTX ISA 9.3 documentationdocs.nvidia.com