Merge branch 'develop' into lwpck-759

9efb5cc4 · Rostyslav Geyyer · GitHub · af52fe33 · 40365904 · 9efb5cc4
Unverified Commit 9efb5cc4 authored Jun 05, 2023 by Rostyslav Geyyer Committed by GitHub Jun 05, 2023
20 changed files
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_min.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_min.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_norm2.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16_norm2.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16_amax.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16_amax.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16_max.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16_max.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16_min.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16_min.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16_add.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16_add.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16_avg.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16_avg.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16_norm2.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16_norm2.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_add.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_add.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_amax.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_amax.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_avg.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_avg.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_max.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_max.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_min.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_min.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_norm2.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_norm2.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f64_f32_add.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f64_f32_add.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f64_f32_avg.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f64_f32_avg.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f64_f32_norm2.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f64_f32_norm2.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_add.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_add.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_amax.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_amax.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_avg.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64_avg.hpp