Merge remote-tracking branch 'origin/develop' into cpu_avx2

b134b7d6 · carlushuang · 090ba885 · 9f71ff48 · b134b7d6 · b134b7d6
Commit b134b7d6 authored May 16, 2022 by carlushuang
20 changed files
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_v1.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_v1.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
--- 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_tensor_slice_transfer.hpp
+++ b/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer.hpp
--- a/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v6r1.hpp
+++ b/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v6r1.hpp
--- a/include/ck/utility/amd_xdlops.hpp
+++ b/include/ck/utility/amd_xdlops.hpp
--- a/include/ck/utility/common_header.hpp
+++ b/include/ck/utility/common_header.hpp
@@ -28,6 +28,7 @@
 #include "transpose_vectors.hpp"
 #include "inner_product.hpp"
 // #include "element_wise_operation.hpp"
+#include "thread_group.hpp"
 #include "debug.hpp"
 #include "amd_buffer_addressing.hpp"

--- a/include/ck/utility/get_id.hpp
+++ b/include/ck/utility/get_id.hpp
--- a/include/ck/utility/number.hpp
+++ b/include/ck/utility/number.hpp
--- a/include/ck/utility/static_buffer.hpp
+++ b/include/ck/utility/static_buffer.hpp
--- a/include/ck/utility/thread_group.hpp
+++ b/include/ck/utility/thread_group.hpp
--- a/include/ck/utility/tuple.hpp
+++ b/include/ck/utility/tuple.hpp
--- a/library/include/ck/library/host/host_interface.hpp
+++ b/library/include/ck/library/host/host_interface.hpp
--- a/library/include/ck/library/host_tensor/device.hpp
+++ b/library/include/ck/library/host_tensor/device.hpp