Accelerators Unite ARM, IBM, X86
SAN JOSE, Calif. — Seven chip makers will define a cache-coherent interconnect for server accelerators, providing an alternative to Intel and Nvidia in a red hot sector of cloud computing. The effort is the first hardware collaboration of its type to span ARM, x86 and Power processors.
Advanced Micro Devices, ARM, Huawei, IBM, Mellanox, Qualcomm and Xilinx will define the Cache Coherent Interconnect for Accelerators (CCIX, pronounced C6). The group will release a draft specification by the end of the year, but has so far not released any technical or financial details.
The effort started after Intel bid $16.7 billion to buy Altera last year, in part to use its FPGAs as accelerators for its Xeon server CPUs. Other processor vendors approached Xilinx individually to create a cache-coherent link to their chips, and Xilinx proposed the idea of a single link to serve them all. Intel has already started shipping a device that puts a Xeon server CPU and Altera FPGA in a single package.
E-mail This Article | Printer-Friendly Page |
Related News
Breaking News
- Synopsys Showcases EDA Performance and Next-Gen Capabilities with NVIDIA Accelerated Computing, Generative AI and Omniverse
- Spectral Releases Advanced Quality Assurance & Data Analytics tool to validate advanced node Memory Compilers
- TSMC and Synopsys Bring Breakthrough NVIDIA Computational Lithography Platform to Production
- After TSMC fab in Japan, advanced packaging facility is next
- A System On Module (SoM) developed by Electra IC: BitFlex-SPB-A7 FPGA SoM
Most Popular
- After TSMC fab in Japan, advanced packaging facility is next
- HBM3 Initially Exclusively Supplied by SK Hynix, Samsung Rallies Fast After AMD Validation, Says TrendForce
- Alphawave Semi Demonstrates 3nm Silicon-Proven 24Gbps Universal Chiplet Express (UCIe) Subsystem for High-Performance AI Infrastructure
- Weebit Nano to demo its ReRAM technology on GlobalFoundries' 22FDX® platform
- We'll Need Many More Fabs to Meet $1 Trillion by 2030 Goal