Merge remote-tracking branch 'origin' into aosewski/ggemm_multi_d2

ae20247a · Adam Osewski · d1f7a3cf · a776978c · ae20247a · ae20247a
Commit ae20247a authored Feb 29, 2024 by Adam Osewski
20 changed files
--- a/example/62_conv_fwd_activ/multi_AB/convnd_fwd_activ_multi_ab_common.hpp
+++ b/example/62_conv_fwd_activ/multi_AB/convnd_fwd_activ_multi_ab_common.hpp
--- a/example/62_conv_fwd_activ/run_convnd_fwd_activ_example.inc
+++ b/example/62_conv_fwd_activ/run_convnd_fwd_activ_example.inc
--- a/example/62_conv_fwd_activ/CMakeLists.txt
+++ b/example/62_conv_fwd_activ/CMakeLists.txt
--- a/example/62_conv_fwd_activ/convnd_fwd_activ_common.hpp
+++ b/example/62_conv_fwd_activ/convnd_fwd_activ_common.hpp
--- a/example/62_convnd_activ/unary/convnd_fwd_xdl_abs_fp16.cpp
+++ b/example/62_convnd_activ/unary/convnd_fwd_xdl_abs_fp16.cpp
--- a/example/62_convnd_activ/unary/convnd_fwd_xdl_clippedrelu_fp16.cpp
+++ b/example/62_convnd_activ/unary/convnd_fwd_xdl_clippedrelu_fp16.cpp
--- a/example/62_convnd_activ/unary/convnd_fwd_xdl_elu_fp16.cpp
+++ b/example/62_convnd_activ/unary/convnd_fwd_xdl_elu_fp16.cpp
--- a/example/62_convnd_activ/unary/convnd_fwd_xdl_leakyrelu_fp16.cpp
+++ b/example/62_convnd_activ/unary/convnd_fwd_xdl_leakyrelu_fp16.cpp
--- a/example/62_convnd_activ/unary/convnd_fwd_xdl_pow_fp16.cpp
+++ b/example/62_convnd_activ/unary/convnd_fwd_xdl_pow_fp16.cpp
--- a/example/62_convnd_activ/unary/convnd_fwd_xdl_relu_fp16.cpp
+++ b/example/62_convnd_activ/unary/convnd_fwd_xdl_relu_fp16.cpp
--- a/example/62_convnd_activ/unary/convnd_fwd_xdl_sigmoid_fp16.cpp
+++ b/example/62_convnd_activ/unary/convnd_fwd_xdl_sigmoid_fp16.cpp
--- a/example/62_convnd_activ/unary/convnd_fwd_xdl_softrelu_fp16.cpp
+++ b/example/62_convnd_activ/unary/convnd_fwd_xdl_softrelu_fp16.cpp
--- a/example/62_convnd_activ/unary/convnd_fwd_xdl_tanh_fp16.cpp
+++ b/example/62_convnd_activ/unary/convnd_fwd_xdl_tanh_fp16.cpp
--- 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/impl/device_elementwise_scale_impl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_elementwise_scale_impl.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_splitk_c_shuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_splitk_c_shuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_xdl_fixed_nk.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_xdl_fixed_nk.hpp
--- a/include/ck/tensor_operation/gpu/element/binary_element_wise_operation.hpp
+++ b/include/ck/tensor_operation/gpu/element/binary_element_wise_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/gridwise_gemm_xdlops_v2r4r2.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v2r4r2.hpp