Merge remote-tracking branch 'origin/develop' into wavelet_model

95a83c6e · Adam Osewski · 5b7c2432 · 892a8d76 · 95a83c6e · 95a83c6e
Commit 95a83c6e authored Nov 18, 2022 by Adam Osewski
20 changed files
--- 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_description/tensor_space_filling_curve.hpp
+++ b/include/ck/tensor_description/tensor_space_filling_curve.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_batched_gemm_softmax_gemm.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_batched_gemm_softmax_gemm.hpp
--- a/include/ck/tensor_operation/gpu/device/device_batched_gemm_softmax_gemm_permute.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_batched_gemm_softmax_gemm_permute.hpp
--- a/include/ck/tensor_operation/gpu/device/device_batchnorm_forward.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_batchnorm_forward.hpp
--- a/include/ck/tensor_operation/gpu/device/device_batchnorm_infer.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_batchnorm_infer.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
--- a/include/ck/tensor_operation/gpu/device/device_grouped_conv_fwd.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_grouped_conv_fwd.hpp