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
- Jury is out in the Arm vs Qualcomm trial
- Ceva Seeks To Exploit Synergies in Portfolio with Nano NPU
- Synopsys Responds to U.K. Competition and Markets Authority's Phase 1 Announcement Regarding Ansys Acquisition
- Alphawave Semi Scales UCIe™ to 64 Gbps Enabling >20 Tbps/mm Bandwidth Density for Die-to-Die Chiplet Connectivity
- RaiderChip Hardware NPU adds Falcon-3 LLM to its supported AI models