Merge branch 'gridwise_2d' of github.com:ROCmSoftwarePlatform/composable_kernel into gridwise_2d

0bff049a · Astha Rai · 33733eee · 00a6e2cd · 0bff049a · 33733eee
Commit 0bff049a authored Oct 26, 2022 by Astha Rai
20 changed files
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_amax.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_amax.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_max.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_max.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_min.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_min.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_add.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_add.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_avg.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_avg.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_norm2.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_norm2.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_add.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_add.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_amax.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_amax.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_avg.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_avg.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_max.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_max.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_min.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_min.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_norm2.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_norm2.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_add.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_add.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_avg.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_avg.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_norm2.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_norm2.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_add.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_add.cpp