Merge branch 'develop' into lwpck-1815

f84e2020 · Rostyslav Geyyer · GitHub · 408534d4 · 25935b57 · f84e2020
Unverified Commit f84e2020 authored Aug 26, 2024 by Rostyslav Geyyer Committed by GitHub Aug 26, 2024
20 changed files
--- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_convscale/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_convscale/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_convscale/xdl/device_grouped_conv3d_fwd_xdl_combconvscale_ndhwgc_gkzyxc_ndhwgk_f8_f8_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_convscale/xdl/device_grouped_conv3d_fwd_xdl_combconvscale_ndhwgc_gkzyxc_ndhwgk_f8_f8_f32_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_convscale_relu/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_convscale_relu/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_convscale_relu/xdl/device_grouped_conv3d_fwd_xdl_combconvscale_relu_ndhwgc_gkzyxc_ndhwgk_f8_f8_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_convscale_relu/xdl/device_grouped_conv3d_fwd_xdl_combconvscale_relu_ndhwgc_gkzyxc_ndhwgk_f8_f8_f32_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_convscale_relu/xdl/device_grouped_conv3d_fwd_xdl_convscale_relu_ndhwgc_gkzyxc_ndhwgk_f8_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_convscale_relu/xdl/device_grouped_conv3d_fwd_xdl_convscale_relu_ndhwgc_gkzyxc_ndhwgk_f8_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/permute_scale/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/permute_scale/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_6d_fp32_fp8_instances.cpp
+++ b/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_6d_fp32_fp8_instances.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_amax.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_amax.cpp
--- a/profiler/include/profiler/profile_gemm_multiply_multiply_impl.hpp
+++ b/profiler/include/profiler/profile_gemm_multiply_multiply_impl.hpp
--- a/profiler/include/profiler/profile_gemm_universal_impl.hpp
+++ b/profiler/include/profiler/profile_gemm_universal_impl.hpp
--- a/profiler/include/profiler/profile_grouped_conv_bwd_weight_impl.hpp
+++ b/profiler/include/profiler/profile_grouped_conv_bwd_weight_impl.hpp
--- a/profiler/src/profile_gemm_multiply_multiply.cpp
+++ b/profiler/src/profile_gemm_multiply_multiply.cpp
--- a/profiler/src/profile_gemm_universal.cpp
+++ b/profiler/src/profile_gemm_universal.cpp
--- a/profiler/src/profile_grouped_conv_bwd_weight.cpp
+++ b/profiler/src/profile_grouped_conv_bwd_weight.cpp
--- a/profiler/src/profile_grouped_gemm_fixed_nk.cpp
+++ b/profiler/src/profile_grouped_gemm_fixed_nk.cpp
--- a/script/convert_miopen_driver_to_profiler.py
+++ b/script/convert_miopen_driver_to_profiler.py
--- a/script/process_perf_data.py
+++ b/script/process_perf_data.py
--- a/script/process_qa_data.sh
+++ b/script/process_qa_data.sh
--- a/script/profile_conv_bwd_data.sh
+++ b/script/profile_conv_bwd_data.sh
--- a/script/profile_conv_fwd.sh
+++ b/script/profile_conv_fwd.sh