Merge branch 'develop' into mi300

f8a6c69c · Illia Silin · GitHub · 56599d67 · 52f64967 · f8a6c69c
Unverified Commit f8a6c69c authored Mar 13, 2023 by Illia Silin Committed by GitHub Mar 13, 2023
20 changed files
--- a/example/26_contraction/CMakeLists.txt
+++ b/example/26_contraction/CMakeLists.txt
 add_example_executable(example_contraction_bilinear_xdl_fp32 contraction_bilinear_xdl_fp32.cpp)
 add_example_executable(example_contraction_scale_xdl_fp32 contraction_scale_xdl_fp32.cpp)
+add_example_executable(example_contraction_bilinear_xdl_fp64 contraction_bilinear_xdl_fp64.cpp)
+add_example_executable(example_contraction_scale_xdl_fp64 contraction_scale_xdl_fp64.cpp)
--- a/example/26_contraction/contraction_bilinear_xdl_fp64.cpp
+++ b/example/26_contraction/contraction_bilinear_xdl_fp64.cpp
--- a/example/26_contraction/contraction_scale_xdl_fp64.cpp
+++ b/example/26_contraction/contraction_scale_xdl_fp64.cpp
--- a/example/27_layernorm/layernorm_blockwise.cpp
+++ b/example/27_layernorm/layernorm_blockwise.cpp
--- a/example/29_batched_gemm_bias_e_permute/CMakeLists.txt
+++ b/example/29_batched_gemm_bias_e_permute/CMakeLists.txt
--- a/example/29_batched_gemm_bias_e_permute/batched_gemm_bias_e_permute_wmma_fp16.cpp
+++ b/example/29_batched_gemm_bias_e_permute/batched_gemm_bias_e_permute_wmma_fp16.cpp
--- a/example/30_grouped_conv_fwd_multiple_d/CMakeLists.txt
+++ b/example/30_grouped_conv_fwd_multiple_d/CMakeLists.txt
--- a/example/30_grouped_conv_fwd_multiple_d/common.hpp
+++ b/example/30_grouped_conv_fwd_multiple_d/common.hpp
--- a/example/30_grouped_conv_fwd_multiple_d/common_wmma.hpp
+++ b/example/30_grouped_conv_fwd_multiple_d/common_wmma.hpp
--- a/example/30_grouped_conv_fwd_multiple_d/grouped_conv_fwd_bias_relu_add_wmma_fp16.cpp
+++ b/example/30_grouped_conv_fwd_multiple_d/grouped_conv_fwd_bias_relu_add_wmma_fp16.cpp
--- a/example/30_grouped_conv_fwd_multiple_d/run_grouped_conv_fwd_bias_relu_add_wmma_example.inc
+++ b/example/30_grouped_conv_fwd_multiple_d/run_grouped_conv_fwd_bias_relu_add_wmma_example.inc
--- a/example/42_groupnorm/groupnorm_sigmoid_fp16.cpp
+++ b/example/42_groupnorm/groupnorm_sigmoid_fp16.cpp
--- a/example/46_gemm_add_multiply/run_gemm_add_multiply_example.inc
+++ b/example/46_gemm_add_multiply/run_gemm_add_multiply_example.inc
--- a/example/47_gemm_bias_softmax_gemm_permute/CMakeLists.txt
+++ b/example/47_gemm_bias_softmax_gemm_permute/CMakeLists.txt
+add_example_executable(example_gemm_bias_softmax_gemm_permute gemm_bias_softmax_gemm_permute.cpp)
--- a/example/47_gemm_bias_softmax_gemm_permute/gemm_bias_softmax_gemm_permute.cpp
+++ b/example/47_gemm_bias_softmax_gemm_permute/gemm_bias_softmax_gemm_permute.cpp
--- a/include/ck/ck.hpp
+++ b/include/ck/ck.hpp
--- a/include/ck/host_utility/kernel_launch.hpp
+++ b/include/ck/host_utility/kernel_launch.hpp
--- a/include/ck/tensor_operation/gpu/device/device_batched_gemm_softmax_gemm_permute.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_batched_gemm_softmax_gemm_permute.hpp
--- a/include/ck/tensor_operation/gpu/device/device_normalization.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_normalization.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_batched_contraction_multiple_d_wmma_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_batched_contraction_multiple_d_wmma_cshuffle.hpp