Max Podkorytov 2b4f8a85b2 Convert CK (GeMM MulMul Weight Preshuffle) instances to use 16x16 xdl tile (#2229) ...

* compile profiler only for gemm-mulmul-weight-preshuffle

* m/n xdl; m/n xdl per wave; cshuffle block transfer cluster length m per block

* process all p1 instances

* process all p2 instances

* process all p3 instances

* convert p4 instance

* modify compute p1 instances

* modify compute p2 instances

* relax p4 instance c block transfer cluster len

* fix c block transfer cluster lengths comment

* add mfma (without 16x16) instances to the profiler

* roll back profiling cmakelists change

* clang-format

* re-add (now unused) 32x32 xdl-tile instances

* clang-format

* add more instances

* fit c block transfer lengths into block

* copy and write over the instance definitions from bf16 to fp16

* add instances to profiler

* unify instance tuple alias

[ROCm/composable_kernel commit: e6b5e31c20]

2025-06-10 09:37:14 -07:00

..

reference_tensor_operation

Optimized GEMMs for MX FP4/8 (#2294)

2025-06-05 13:54:15 -06:00

tensor_operation_instance

Convert CK (GeMM MulMul Weight Preshuffle) instances to use 16x16 xdl tile (#2229)

2025-06-10 09:37:14 -07:00