Wojciech Laskowski b25d4d684a WMMA support for GEMM reduce (#2823) ...

Added gemm + reduce instance library for RDNA4. This includes:

- New device implementation running GEMM and reduction kernel
- instances for wmma (xdl parity)
- examples for wmma (xdl parity)
- tests for existing xdl and wmma

2025-09-12 21:36:43 +02:00

..

CMakeLists.txt

WMMA support for GEMM reduce (#2823)

2025-09-12 21:36:43 +02:00

common.hpp

WMMA support for GEMM reduce (#2823)

2025-09-12 21:36:43 +02:00

gemm_wmma_splitk_reduce_bf16.cpp

WMMA support for GEMM reduce (#2823)

2025-09-12 21:36:43 +02:00

gemm_wmma_splitk_reduce_bf16A_i8B.cpp

WMMA support for GEMM reduce (#2823)

2025-09-12 21:36:43 +02:00

gemm_wmma_splitk_reduce_multi_d_bf16.cpp

WMMA support for GEMM reduce (#2823)

2025-09-12 21:36:43 +02:00

gemm_wmma_splitk_reduce_multi_d_fp16.cpp

WMMA support for GEMM reduce (#2823)

2025-09-12 21:36:43 +02:00

gemm_xdl_splitk_reduce_bf16.cpp

Universal gemm splitk using reduce (with multi-d) (#1341)

2024-07-19 22:01:22 +08:00

gemm_xdl_splitk_reduce_bf16A_i8B.cpp

Universal gemm splitk using reduce (with multi-d) (#1341)

2024-07-19 22:01:22 +08:00

gemm_xdl_splitk_reduce_multi_d_bf16.cpp

Universal gemm splitk using reduce (with multi-d) (#1341)

2024-07-19 22:01:22 +08:00

gemm_xdl_splitk_reduce_multi_d_fp16.cpp

Universal gemm splitk using reduce (with multi-d) (#1341)

2024-07-19 22:01:22 +08:00

run_gemm_splitk_reduce_multi_d_example.inc

WMMA support for GEMM reduce (#2823)

2025-09-12 21:36:43 +02:00

run_gemm_wmma_splitk_reduce_example.inc

WMMA support for GEMM reduce (#2823)

2025-09-12 21:36:43 +02:00

run_gemm_wmma_splitk_reduce_multi_d_example.inc

WMMA support for GEMM reduce (#2823)

2025-09-12 21:36:43 +02:00

run_splitK_gemm_example.inc

OCP FP8 support for gfx12. (#1710)

2024-12-03 08:42:55 -08:00

splitK_gemm_xdl_bf16.cpp

Extend XDL kernel to Support RDNA3/4 - Part 4 (#2724)

2025-09-12 08:17:07 -07:00

splitK_gemm_xdl_fp16_fp8.cpp

Extend XDL kernel to Support RDNA3/4 - Part 4 (#2724)

2025-09-12 08:17:07 -07:00

splitK_gemm_xdl_fp16.cpp

Extend XDL kernel to Support RDNA3/4 - Part 4 (#2724)

2025-09-12 08:17:07 -07:00

splitK_gemm_xdl_fp32.cpp

Extend XDL kernel to Support RDNA3/4 - Part 4 (#2724)

2025-09-12 08:17:07 -07:00

splitK_gemm_xdl_int4.cpp

Extend XDL kernel to Support RDNA3/4 - Part 4 (#2724)

2025-09-12 08:17:07 -07:00

splitK_gemm_xdl_int8.cpp

Extend XDL kernel to Support RDNA3/4 - Part 4 (#2724)

2025-09-12 08:17:07 -07:00

splitK_gemm_xdl_lds_direct_load_fp16.cpp

Extend XDL kernel to Support RDNA3/4 - Part 4 (#2724)

2025-09-12 08:17:07 -07:00