merge develop

b5ada11b · Jing Zhang · cee92951 · b6eaf3eb · b5ada11b · b5ada11b
Commit b5ada11b authored Jun 01, 2022 by Jing Zhang
20 changed files
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r3.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r3.hpp
@@ -316,11 +316,11 @@ struct GridwiseGemm_k0mk1_k0nk1_mn_xdlops_v3r3
    }
    // return block_id to C matrix tile idx (m0, n0) mapping
-    __host__ __device__ static constexpr auto
+    __host__ __device__ static constexpr auto MakeDefaultBlock2CTileMap(
-    MakeDefaultBlock2CTileMap(const CGridDesc_M_N& c_grid_desc_m_n, index_t M01, index_t N01)
+        const CGridDesc_M_N& c_grid_desc_m_n, index_t /* M01 */, index_t /* N01 */)
    {
-        return BlockToCTileMap_M00_N00_M01_N01<MPerBlock, NPerBlock, CGridDesc_M_N>(
+        return BlockToCTileMap_M00_N0_M01Adapt<MPerBlock, NPerBlock, CGridDesc_M_N>(
-            c_grid_desc_m_n, M01, N01);
+            c_grid_desc_m_n);
    }
    using CGridDescriptor_MBlock_MXdlPerWave_MWaveMPerXdl_NBlock_NXdlPerWave_NWaveNPerXdl =
        remove_cvref_t<decltype(

--- a/include/ck/tensor_operation/gpu/warp/xdlops_gemm.hpp
+++ b/include/ck/tensor_operation/gpu/warp/xdlops_gemm.hpp
--- a/include/ck/utility/amd_xdlops.hpp
+++ b/include/ck/utility/amd_xdlops.hpp
--- a/include/ck/utility/dynamic_buffer.hpp
+++ b/include/ck/utility/dynamic_buffer.hpp
--- a/library/include/ck/library/reference_tensor_operation/cpu/reference_cgemm.hpp
+++ b/library/include/ck/library/reference_tensor_operation/cpu/reference_cgemm.hpp
--- a/library/include/ck/library/reference_tensor_operation/cpu/reference_gemm.hpp
+++ b/library/include/ck/library/reference_tensor_operation/cpu/reference_gemm.hpp
--- a/library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gkm_gkn_gmn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gkm_gkn_gmn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gkm_gnk_gmn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gkm_gnk_gmn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gmk_gkn_gmn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gmk_gkn_gmn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gmk_gnk_gmn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gmk_gnk_gmn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/gemm/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f64_f64_f64_km_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f64_f64_f64_km_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f64_f64_f64_km_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f64_f64_f64_km_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f64_f64_f64_mk_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f64_f64_f64_mk_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f64_f64_f64_mk_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f64_f64_f64_mk_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_km_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_km_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_km_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_km_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_mk_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_mk_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_mk_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_mk_nk_mn_instance.cpp
--- a/profiler/include/profile_gemm_impl.hpp
+++ b/profiler/include/profile_gemm_impl.hpp