Merge commit '3e6c2610' into gemm_norm

b2290854 · rocking · 253f7ef2 · 3e6c2610 · b2290854 · b2290854
Commit b2290854 authored May 27, 2022 by rocking
20 changed files
--- 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
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_f16_f16_f16.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_f16_f16_f16.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_f32_f32_b16.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_f32_f32_b16.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_f32_f32_f16.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_f32_f32_f16.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_f32_f32_f32.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_f32_f32_f32.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_f64_f64_f32.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_f64_f64_f32.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_f64_f64_f64.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_f64_f64_f64.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_i32_i32_i8.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_i32_i32_i8.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_i8_i8_i8.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_i8_i8_i8.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_impl_common.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_impl_common.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_b16_f32_f32.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_b16_f32_f32.hpp