Merge pull request #64 from ROCm/merge_from_public

Merge from public

Merge pull request #64 from ROCm/merge_from_public
Merge from public
12d70ff3 · Illia Silin · GitHub · 5dbbf5d6 · 6422c23b · 12d70ff3
Unverified Commit 12d70ff3 authored May 15, 2024 by Illia Silin Committed by GitHub May 15, 2024
20 changed files
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_convolution_forward_xdl.inc
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_convolution_forward_xdl.inc
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm_multi_abd_fixed_nk.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm_multi_abd_fixed_nk.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm_tile_loop.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm_tile_loop.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm_tile_loop_multply.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm_tile_loop_multply.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/permute_scale.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/permute_scale.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/permute_scale/device_permute_scale_instances.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/permute_scale/device_permute_scale_instances.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/transpose/device_transpose_instance.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/transpose/device_transpose_instance.hpp
--- a/library/include/ck/library/utility/host_tensor.hpp
+++ b/library/include/ck/library/utility/host_tensor.hpp
--- a/library/include/ck/library/utility/host_tensor_generator.hpp
+++ b/library/include/ck/library/utility/host_tensor_generator.hpp
--- a/library/src/tensor_operation_instance/gpu/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/batched_gemm/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/batched_gemm/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/batched_gemm_add_relu_gemm_add/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/batched_gemm_add_relu_gemm_add/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/batched_gemm_bias_permute/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/batched_gemm_bias_permute/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/batched_gemm_gemm/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/batched_gemm_gemm/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/batched_gemm_reduce/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/batched_gemm_reduce/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_infer_bf16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_infer_bf16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_infer_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_infer_f16_instance.cpp