AMD's ROCm to support Xilinx's FPGAs

[igormp]

Summary

Xilinx's announced that their FPGAs will also work under ROCm, enabling an open source stack capable of doing the integration between GPUs and FPGAs seamlessly

 

Quotes

Quote

 Xilinx is presenting a technology demonstration showcasing the integration of Xilinx Alveo accelerator cards with the AMD ROCm™ open software platform. The technology preview builds on AMD leadership in high-performance computing technology, specifically leveraging user-mode queueing and shared-virtual memory, to offer direct, low-latency dispatch of work on Alveo accelerators.   

[...]

The technology demonstration showcases:

• Unified discovery and reservation of AMD and Xilinx accelerators using a converged runtime in the AMD ROCm open software platform;
• Dispatch of work to Alveo accelerators using the same user-space queues used for low-latency work dispatch to AMD Instinct accelerators;
• Peer-to-peer synchronization between GPU and FPGA devices; and
• Access to memory on GPU, CPU, and FPGA devices using a common, shared virtual address space  

 

My thoughts

This now brings AMD to be on par with Intel's oneAPI, with the advantage of having much more powerful GPUs.

A stack that allows seamless communication between a GPU and a FPGA is a dream for HPC scenarios.

 

Sources

https://forums.xilinx.com/t5/Xilinx-Xclusive-Blog/AMD-and-Xilinx-Demonstrate-Converged-ROCm-Runtime-Technology/ba-p/1175091