Merge branch 'develop' into codegen_target

76cf795a · Astha Rai · f42a8811 · f16ebf82 · 76cf795a · 76cf795a
Commit 76cf795a authored Sep 24, 2024 by Astha Rai
20 changed files
--- a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/device_grouped_conv2d_fwd_xdl_ngchw_gkyxc_ngkhw_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/device_grouped_conv2d_fwd_xdl_ngchw_gkyxc_ngkhw_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/device_grouped_conv2d_fwd_xdl_ngchw_gkyxc_ngkhw_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/device_grouped_conv2d_fwd_xdl_ngchw_gkyxc_ngkhw_f32_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/mem/device_grouped_conv2d_fwd_xdl_ngchw_gkyxc_ngkhw_f16_mem_inter_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/mem/device_grouped_conv2d_fwd_xdl_ngchw_gkyxc_ngkhw_f16_mem_inter_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/mem/device_grouped_conv2d_fwd_xdl_ngchw_gkyxc_ngkhw_f16_mem_intra_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/mem/device_grouped_conv2d_fwd_xdl_ngchw_gkyxc_ngkhw_f16_mem_intra_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/mem/device_grouped_conv2d_fwd_xdl_ngchw_gkyxc_ngkhw_f32_mem_inter_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/mem/device_grouped_conv2d_fwd_xdl_ngchw_gkyxc_ngkhw_f32_mem_inter_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/mem/device_grouped_conv2d_fwd_xdl_ngchw_gkyxc_ngkhw_f32_mem_intra_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/mem/device_grouped_conv2d_fwd_xdl_ngchw_gkyxc_ngkhw_f32_mem_intra_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/merged_groups/device_grouped_conv2d_fwd_xdl_merged_groups_ngchw_gkyxc_ngkhw_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/merged_groups/device_grouped_conv2d_fwd_xdl_merged_groups_ngchw_gkyxc_ngkhw_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/merged_groups/device_grouped_conv2d_fwd_xdl_merged_groups_ngchw_gkyxc_ngkhw_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/merged_groups/device_grouped_conv2d_fwd_xdl_merged_groups_ngchw_gkyxc_ngkhw_f32_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/max_pool_bwd/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/max_pool_bwd/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/max_pool_bwd/device_max_pool_bwd_f8_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/max_pool_bwd/device_max_pool_bwd_f8_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/max_pool_bwd/device_max_pool_bwd_int8_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/max_pool_bwd/device_max_pool_bwd_int8_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/max_pool_bwd/max_pool_bwd_instance_common.hpp
+++ b/library/src/tensor_operation_instance/gpu/max_pool_bwd/max_pool_bwd_instance_common.hpp
--- a/library/src/tensor_operation_instance/gpu/mha/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/mha/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/pool2d_fwd/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/pool2d_fwd/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/pool2d_fwd/device_avg_pool2d_fwd_nhwc_bf16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/pool2d_fwd/device_avg_pool2d_fwd_nhwc_bf16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/pool2d_fwd/device_avg_pool2d_fwd_nhwc_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/pool2d_fwd/device_avg_pool2d_fwd_nhwc_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/pool2d_fwd/device_avg_pool2d_fwd_nhwc_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/pool2d_fwd/device_avg_pool2d_fwd_nhwc_f32_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/pool2d_fwd/device_avg_pool2d_fwd_nhwc_f8_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/pool2d_fwd/device_avg_pool2d_fwd_nhwc_f8_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/pool2d_fwd/device_avg_pool2d_fwd_nhwc_i8_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/pool2d_fwd/device_avg_pool2d_fwd_nhwc_i8_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/pool2d_fwd/device_max_pool2d_fwd_nhwc_bf16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/pool2d_fwd/device_max_pool2d_fwd_nhwc_bf16_instance.cpp