Merge branch 'develop' into bnorm_bwd_pr

a781d078 · Qianfeng Zhang · fd76c787 · 4c4c7328 · a781d078 · a781d078
Commit a781d078 authored Nov 16, 2022 by Qianfeng Zhang
20 changed files
--- a/example/39_permute/run_permute_bundle_example.inc
+++ b/example/39_permute/run_permute_bundle_example.inc
--- a/example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_bf16.cpp
+++ b/example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_bf16.cpp
--- a/example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_fp16.cpp
+++ b/example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_fp16.cpp
--- a/example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_fp32.cpp
+++ b/example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_fp32.cpp
--- a/example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_int4.cpp
+++ b/example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_int4.cpp
--- a/example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_int8.cpp
+++ b/example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_int8.cpp
--- a/example/41_grouped_conv_conv_fwd/run_grouped_conv_conv_fwd_example.inc
+++ b/example/41_grouped_conv_conv_fwd/run_grouped_conv_conv_fwd_example.inc
--- a/example/42_groupnorm/groupnorm_sigmoid_fp16.cpp
+++ b/example/42_groupnorm/groupnorm_sigmoid_fp16.cpp
--- a/example/44_conv2d_fwd_quant/CMakeLists.txt
+++ b/example/44_conv2d_fwd_quant/CMakeLists.txt
--- a/example/44_conv2d_fwd_quant/conv2d_fwd_xdl_bias_relu_perlayer_quantization_int8.cpp
+++ b/example/44_conv2d_fwd_quant/conv2d_fwd_xdl_bias_relu_perlayer_quantization_int8.cpp
--- a/example/44_conv2d_fwd_quant/conv2d_fwd_xdl_perlayer_quantization_int8.cpp
+++ b/example/44_conv2d_fwd_quant/conv2d_fwd_xdl_perlayer_quantization_int8.cpp
--- a/example/44_elementwise_permute/elementwise_permute_4D_fp16.cpp
+++ b/example/44_elementwise_permute/elementwise_permute_4D_fp16.cpp
--- a/example/45_elementwise_normalization/CMakeLists.txt
+++ b/example/45_elementwise_normalization/CMakeLists.txt
--- a/example/45_elementwise_normalization/elementwise_layernorm_blockwise.cpp
+++ b/example/45_elementwise_normalization/elementwise_layernorm_blockwise.cpp
--- a/example/CMakeLists.txt
+++ b/example/CMakeLists.txt
--- a/include/ck/ck.hpp
+++ b/include/ck/ck.hpp
--- a/include/ck/tensor_operation/gpu/block/blockwise_gemm_xdlops.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_gemm_xdlops.hpp
--- a/include/ck/tensor_operation/gpu/device/device_elementwise_normalization.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_elementwise_normalization.hpp
--- a/include/ck/tensor_operation/gpu/device/device_grouped_conv_bwd_data_multiple_d.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_grouped_conv_bwd_data_multiple_d.hpp
--- a/include/ck/tensor_operation/gpu/device/device_conv_bwd_weight.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_conv_bwd_weight.hpp