bzs1118 commented on PR #3144:
URL: https://github.com/apache/brpc/pull/3144#issuecomment-6758520497

   当前 GDR 接收路径固定从 GPU block pool 按 gdr_block_size_kb(默认 512KB)分配,导致大消息被切成多个 
block。对于接收端已有预分配连续 buffer 的场景(例如推理引擎的固定 shape 显存),应用只能用 
copy_from_gpu(to_gpu=true) 再做一次 D2D,抵消了 GDR 的一部分收益。
   
   而 DoPostRecvGDR(void* block, size_t block_size, uint32_t lkey) 本身已经支持任意 
buffer。是否可以在 PostRecv 层增加一个可选的 allocator 回调,允许调用方提供自己的显存块?


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]


---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to