Re:Unweaving warp specialization on modern tensor core GPUs
by rohany on Monday September 22, 2025 @05:37PM
(#45339821)
> I always assumed that when one warp waits for results from a long latency instruction, another warp, potentially from another block can be scheduled in.
Yes, that is correct. However, most MMA-style kernels that utilize the Tensor Core usually need enough resources per block that only 1 block fits on each SM.
Yes, that is correct. However, most MMA-style kernels that utilize the Tensor Core usually need enough resources per block that only 1 block fits on each SM.