onnxruntime

78e355fd · gaoqiong · fae08684 · 78e355fd · 78e355fd · 78e355fd
Commit 78e355fd authored Dec 20, 2022 by gaoqiong
20 changed files
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_add.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_add.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_amax.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_amax.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_avg.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_avg.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_max.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_max.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_min.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_min.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_norm2.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_norm2.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_add.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_add.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_avg.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_avg.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_norm2.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_norm2.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_add.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_add.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_amax.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_amax.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_avg.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_avg.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_max.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_max.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_min.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_min.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_norm2.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_norm2.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i32_i8_add.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i32_i8_add.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i32_i8_avg.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i32_i8_avg.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8_amax.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8_amax.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8_max.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8_max.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8_min.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8_min.hpp