fixed block_sync_lds

ae3d6cb6 · Jing Zhang · 760b0c75 · b62926dc · ae3d6cb6 · ae3d6cb6
Commit ae3d6cb6 authored Feb 27, 2024 by Jing Zhang
20 changed files
--- 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/example/64_fpAintB_gemm/CMakeLists.txt
+++ b/example/64_fpAintB_gemm/CMakeLists.txt
+if(GPU_TARGETS MATCHES "gfx1100" OR GPU_TARGETS MATCHES "gfx1101" OR GPU_TARGETS MATCHES "gfx1102")
+  add_custom_target(example_fpAintB_gemm_wmma)
+  add_example_executable(example_fp16int8_gemm_wmma fp16int8_gemm_wmma.cpp)
+  add_dependencies(example_fpAintB_gemm_wmma example_fp16int8_gemm_wmma)
+endif()
--- a/example/64_fpAintB_gemm/common.hpp
+++ b/example/64_fpAintB_gemm/common.hpp
--- a/example/64_fpAintB_gemm/fp16int8_gemm_wmma.cpp
+++ b/example/64_fpAintB_gemm/fp16int8_gemm_wmma.cpp
--- a/example/64_fpAintB_gemm/run_gemm_example.inc
+++ b/example/64_fpAintB_gemm/run_gemm_example.inc
--- a/include/ck/tensor_operation/gpu/block/blockwise_gemm_wmma.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_gemm_wmma.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/block/thread_group_tensor_slice_transfer_v4r1_dequant.hpp
+++ b/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v4r1_dequant.hpp
--- a/include/ck/tensor_operation/gpu/device/device_gemm_dequantB.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_gemm_dequantB.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_batched_contraction_multiple_d_wmma_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_batched_contraction_multiple_d_wmma_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_softmax_gemm_permute_wmma_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_softmax_gemm_permute_wmma_cshuffle.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_fpAintB_gemm_wmma.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_fpAintB_gemm_wmma.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_wmma_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_wmma_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_gemm_wmma.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_gemm_wmma.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_conv_bwd_data_multiple_d_wmma_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_data_multiple_d_wmma_cshuffle.hpp