Merge branch 'develop' into max-pool-bwd

8c2c1114 · rocking · GitHub · cf9114fd · 016ebaa7 · 8c2c1114
Unverified Commit 8c2c1114 authored Jun 09, 2023 by rocking Committed by GitHub Jun 09, 2023
20 changed files
--- a/library/src/tensor_operation_instance/gpu/normalization/device_groupnorm_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/normalization/device_groupnorm_f32_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/normalization/device_groupnorm_swish_f16_f32_f32_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/normalization/device_groupnorm_swish_f16_f32_f32_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/normalization/device_groupnorm_swish_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/normalization/device_groupnorm_swish_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/normalization/device_groupnorm_swish_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/normalization/device_groupnorm_swish_f32_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/normalization/device_layernorm2d_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/normalization/device_layernorm2d_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/normalization/device_layernorm2d_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/normalization/device_layernorm2d_f32_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/normalization/device_layernorm4d_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/normalization/device_layernorm4d_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/normalization/device_layernorm4d_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/normalization/device_layernorm4d_f32_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/normalization/normalization_instance_common.hpp
+++ b/library/src/tensor_operation_instance/gpu/normalization/normalization_instance_common.hpp
--- a/library/src/tensor_operation_instance/gpu/pool_fwd/device_avg_pool2d_fwd_nhwc_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/pool_fwd/device_avg_pool2d_fwd_nhwc_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/pool_fwd/device_avg_pool2d_fwd_nhwc_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/pool_fwd/device_avg_pool2d_fwd_nhwc_f32_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/pool_fwd/device_avg_pool3d_fwd_ndhwc_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/pool_fwd/device_avg_pool3d_fwd_ndhwc_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/pool_fwd/device_avg_pool3d_fwd_ndhwc_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/pool_fwd/device_avg_pool3d_fwd_ndhwc_f32_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/pool_fwd/device_max_pool2d_fwd_nhwc_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/pool_fwd/device_max_pool2d_fwd_nhwc_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/pool_fwd/device_max_pool2d_fwd_nhwc_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/pool_fwd/device_max_pool2d_fwd_nhwc_f32_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/pool_fwd/device_max_pool3d_fwd_ndhwc_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/pool_fwd/device_max_pool3d_fwd_ndhwc_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/pool_fwd/device_max_pool3d_fwd_ndhwc_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/pool_fwd/device_max_pool3d_fwd_ndhwc_f32_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/pool_fwd/pool_fwd_instance_common.hpp
+++ b/library/src/tensor_operation_instance/gpu/pool_fwd/pool_fwd_instance_common.hpp
--- a/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/conv2d_quantization_common.hpp
+++ b/library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/conv2d_quantization_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