Bartlomiej Wroblewski ad0a8e4cd2 Optimize fp16 direct load GEMM instances (#1086) ...

This PR optimizes fp16 instances of direct load GEMM kernel introduced in #999 and #1052.

Measured the performance of new instances on CDNA2 GPU and compared it against the performance of the best non-direct-load GEMM instances. Used 76 different GEMM problems.
On average, this change improves the performance of the tested problems by 47%. For cases known as latency-bound, the speedup is around 126%.

2023-12-18 11:09:10 +01:00

..

include/ck/library

disabling some fp8 gemm instances to reduce build time (#1084)

2023-12-11 17:49:27 -08:00

src

Optimize fp16 direct load GEMM instances (#1086)

2023-12-18 11:09:10 +01:00

CMakeLists.txt

Clean up conv example, Instances, profiler and test (#324)

2022-07-29 18:19:25 -05:00