Merge remote-tracking branch 'origin/develop' into cpu_avx2

6dfb4e78 · carlushuang · 397a68f2 · 1ced00a5 · 6dfb4e78 · 6dfb4e78
Commit 6dfb4e78 authored Jun 12, 2022 by carlushuang
20 changed files
--- a/include/ck/utility/static_buffer.hpp
+++ b/include/ck/utility/static_buffer.hpp
--- a/include/ck/utility/statically_indexed_array_multi_index.hpp
+++ b/include/ck/utility/statically_indexed_array_multi_index.hpp
--- a/include/ck/utility/type.hpp
+++ b/include/ck/utility/type.hpp
--- a/library/include/ck/library/host_tensor/device.hpp
+++ b/library/include/ck/library/host_tensor/device.hpp
--- a/library/include/ck/library/host_tensor/host_common_util.hpp
+++ b/library/include/ck/library/host_tensor/host_common_util.hpp
--- a/library/include/ck/library/host_tensor/host_reduce_util.hpp
+++ b/library/include/ck/library/host_tensor/host_reduce_util.hpp
--- a/library/include/ck/library/host_tensor/host_reduction.hpp
+++ b/library/include/ck/library/host_tensor/host_reduction.hpp
--- a/library/include/ck/library/reference_tensor_operation/cpu/reference_cgemm.hpp
+++ b/library/include/ck/library/reference_tensor_operation/cpu/reference_cgemm.hpp
--- a/library/include/ck/library/reference_tensor_operation/cpu/reference_conv_backward_weight.hpp
+++ b/library/include/ck/library/reference_tensor_operation/cpu/reference_conv_backward_weight.hpp
--- a/library/include/ck/library/reference_tensor_operation/cpu/reference_gemm.hpp
+++ b/library/include/ck/library/reference_tensor_operation/cpu/reference_gemm.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f64_f32.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f64_f32.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i32_i8.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i32_i8.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i8_i8.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i8_i8.hpp