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

b238662a · Chao Liu · 7279e123 · e579c9e5 · b238662a · b238662a
Commit b238662a authored May 25, 2022 by Chao Liu
20 changed files
--- 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/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
--- a/library/include/ck/library/host_tensor/host_reduction.hpp
+++ b/library/include/ck/library/host_tensor/host_reduction.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16.hpp