Merge branch 'develop' into aosewski/ggemm_multi_d2

defa2071 · Adam Osewski · 28a68428 · f2398f61 · defa2071 · defa2071
Commit defa2071 authored Nov 15, 2023 by Adam Osewski
20 changed files
--- a/library/src/tensor_operation_instance/gpu/normalization_fwd/normalization_fwd_instance_common.hpp
+++ b/library/src/tensor_operation_instance/gpu/normalization_fwd/normalization_fwd_instance_common.hpp
--- a/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_bias_perchannel_quantization_int8_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_bias_perchannel_quantization_int8_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_bias_perlayer_quantization_int8_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_bias_perlayer_quantization_int8_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_perchannel_quantization_int8_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_perchannel_quantization_int8_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_perlayer_quantization_int8_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_perlayer_quantization_int8_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_bias_perchannel_quantization_int8_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_bias_perchannel_quantization_int8_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_bias_perlayer_quantization_int8_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_bias_perlayer_quantization_int8_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_int8_instance.hpp
+++ b/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_int8_instance.hpp
--- a/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_perchannel_quantization_int8_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_perchannel_quantization_int8_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_perlayer_quantization_int8_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_xdl_perlayer_quantization_int8_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/transpose/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/transpose/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/transpose/device_transpose_instances_3d.cpp
+++ b/library/src/tensor_operation_instance/gpu/transpose/device_transpose_instances_3d.cpp
--- a/profiler/README.md
+++ b/profiler/README.md
--- a/profiler/include/profiler/profile_contraction_impl.hpp
+++ b/profiler/include/profiler/profile_contraction_impl.hpp
--- a/profiler/include/profiler/profile_contraction_utils.hpp
+++ b/profiler/include/profiler/profile_contraction_utils.hpp
--- a/profiler/include/profiler/profile_conv_tensor_rearrange_impl.hpp
+++ b/profiler/include/profiler/profile_conv_tensor_rearrange_impl.hpp
--- a/profiler/include/profiler/profile_gemm_impl.hpp
+++ b/profiler/include/profiler/profile_gemm_impl.hpp
--- a/profiler/include/profiler/profile_gemm_splitk_impl.hpp
+++ b/profiler/include/profiler/profile_gemm_splitk_impl.hpp
--- a/profiler/include/profiler/profile_grouped_conv_fwd_impl.hpp
+++ b/profiler/include/profiler/profile_grouped_conv_fwd_impl.hpp
--- a/profiler/include/profiler/profile_groupnorm_impl.hpp
+++ b/profiler/include/profiler/profile_groupnorm_impl.hpp