merge develop and resolve conflict

bccc6d8b · wangshaojie6 · c6b52884 · 91d8b7d6 · bccc6d8b · bccc6d8b
Commit bccc6d8b authored May 30, 2022 by wangshaojie6
20 changed files
--- a/include/ck/tensor_operation/gpu/grid/gridwise_binary_elementwise_1d.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_binary_elementwise_1d.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_dlops_v1r3.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_dlops_v1r3.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_reduce_xdl_cshuffle_v1.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_reduce_xdl_cshuffle_v1.hpp
@@ -306,7 +306,7 @@ struct GridwiseGemmReduce_k0mk1_k0nk1_mn_xdl_cshuffle_v1
    __host__ __device__ static constexpr auto
    MakeDefaultBlock2CTileMap(const CGridDesc_M_N& c_grid_desc_m_n)
    {
-        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);
    }

--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_cshuffle_v1.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_cshuffle_v1.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v2r3.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v2r3.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v2r4.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v2r4.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v2r4r2.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v2r4r2.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r1.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r1.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r2.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r2.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r3.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r3.hpp
--- a/include/ck/tensor_operation/gpu/thread/threadwise_contraction_dlops.hpp
+++ b/include/ck/tensor_operation/gpu/thread/threadwise_contraction_dlops.hpp
--- a/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v5r1.hpp
+++ b/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v5r1.hpp
--- 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/generic_memory_space_atomic.hpp
+++ b/include/ck/utility/generic_memory_space_atomic.hpp
--- a/include/ck/utility/inner_product.hpp
+++ b/include/ck/utility/inner_product.hpp
--- a/include/ck/utility/reduction_operator.hpp
+++ b/include/ck/utility/reduction_operator.hpp
--- a/include/ck/utility/static_buffer.hpp
+++ b/include/ck/utility/static_buffer.hpp
--- a/library/include/ck/library/host_tensor/host_common_util.hpp
+++ b/library/include/ck/library/host_tensor/host_common_util.hpp
--- a/library/include/ck/library/host_tensor/host_reduce_util.hpp
+++ b/library/include/ck/library/host_tensor/host_reduce_util.hpp