Merge branch 'develop' into gemm_layernorm_welford

24af0144 · Po Yen Chen · GitHub · 961f5e9e · b79bbbc2 · 24af0144
Unverified Commit 24af0144 authored Nov 12, 2022 by Po Yen Chen Committed by GitHub Nov 12, 2022
20 changed files
--- a/include/ck/tensor_operation/gpu/device/device_grouped_conv_fwd_multiple_d_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_grouped_conv_fwd_multiple_d_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/device_grouped_gemm_xdl.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_grouped_gemm_xdl.hpp
--- a/include/ck/tensor_operation/gpu/device/device_multiple_reduce_multiblock.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_multiple_reduce_multiblock.hpp
--- a/include/ck/tensor_operation/gpu/device/device_multiple_reduce_threadwise.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_multiple_reduce_threadwise.hpp
--- a/include/ck/tensor_operation/gpu/device/device_layernorm_impl.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_layernorm_impl.hpp
--- a/include/ck/tensor_operation/gpu/device/device_pool2d_fwd_nhwc_nhwc.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_pool2d_fwd_nhwc_nhwc.hpp
--- a/include/ck/tensor_operation/gpu/device/device_reduce_common.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_reduce_common.hpp
--- a/include/ck/tensor_operation/gpu/device/device_reduce_multiblock.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_reduce_multiblock.hpp
--- a/include/ck/tensor_operation/gpu/device/device_reduce_threadwise.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_reduce_threadwise.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_softmax_impl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_softmax_impl.hpp
--- a/include/ck/tensor_operation/gpu/device/device_sparse_embedding3_forward_layernorm.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_sparse_embedding3_forward_layernorm.hpp
--- a/include/ck/tensor_operation/gpu/device/masking_specialization.hpp
+++ b/include/ck/tensor_operation/gpu/device/masking_specialization.hpp
--- a/include/ck/tensor_operation/gpu/device/welford_helper.hpp
+++ b/include/ck/tensor_operation/gpu/device/welford_helper.hpp
--- a/include/ck/tensor_operation/gpu/element/element_wise_operation.hpp
+++ b/include/ck/tensor_operation/gpu/element/element_wise_operation.hpp
--- a/include/ck/tensor_operation/gpu/element/quantization_operation.hpp
+++ b/include/ck/tensor_operation/gpu/element/quantization_operation.hpp
--- a/include/ck/tensor_operation/gpu/element/unary_element_wise_operation.hpp
+++ b/include/ck/tensor_operation/gpu/element/unary_element_wise_operation.hpp
--- a/include/ck/tensor_operation/gpu/grid/batchnorm_multiblock/gridwise_multiblock_welford_first_half.hpp
+++ b/include/ck/tensor_operation/gpu/grid/batchnorm_multiblock/gridwise_multiblock_welford_first_half.hpp
--- a/include/ck/tensor_operation/gpu/grid/batchnorm_multiblock/gridwise_multiblock_welford_second_half_batchnorm_forward_final.hpp
+++ b/include/ck/tensor_operation/gpu/grid/batchnorm_multiblock/gridwise_multiblock_welford_second_half_batchnorm_forward_final.hpp
--- a/include/ck/tensor_operation/gpu/grid/block_to_ctile_map.hpp
+++ b/include/ck/tensor_operation/gpu/grid/block_to_ctile_map.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_batched_gemm_gemm_xdl_cshuffle_v1.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_batched_gemm_gemm_xdl_cshuffle_v1.hpp