提交FT和CK交叉编译代码

acd8b8ea · liuhy · c95fe99a · acd8b8ea · acd8b8ea · acd8b8ea
Commit acd8b8ea authored Aug 24, 2023 by liuhy
20 changed files
--- a/3rdparty/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_max.hpp
+++ b/3rdparty/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_max.hpp
--- a/3rdparty/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_min.hpp
+++ b/3rdparty/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_min.hpp
--- a/3rdparty/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_add.hpp
+++ b/3rdparty/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_add.hpp
--- a/3rdparty/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_avg.hpp
+++ b/3rdparty/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_avg.hpp
--- a/3rdparty/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_norm2.hpp
+++ b/3rdparty/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_norm2.hpp
--- a/3rdparty/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_add.hpp
+++ b/3rdparty/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_add.hpp
--- a/3rdparty/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_amax.hpp
+++ b/3rdparty/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_amax.hpp
--- a/3rdparty/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_avg.hpp
+++ b/3rdparty/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_avg.hpp
--- a/3rdparty/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_max.hpp
+++ b/3rdparty/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_max.hpp
--- a/3rdparty/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_min.hpp
+++ b/3rdparty/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_min.hpp
--- a/3rdparty/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_norm2.hpp
+++ b/3rdparty/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32_norm2.hpp
--- a/3rdparty/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_add.hpp
+++ b/3rdparty/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_add.hpp
--- a/3rdparty/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_avg.hpp
+++ b/3rdparty/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_avg.hpp
--- a/3rdparty/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_norm2.hpp
+++ b/3rdparty/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32_norm2.hpp
--- a/3rdparty/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_add.hpp
+++ b/3rdparty/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_add.hpp
--- a/3rdparty/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_amax.hpp
+++ b/3rdparty/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_amax.hpp
--- a/3rdparty/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_avg.hpp
+++ b/3rdparty/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_avg.hpp
--- a/3rdparty/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_max.hpp
+++ b/3rdparty/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_max.hpp
--- a/3rdparty/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_min.hpp
+++ b/3rdparty/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_min.hpp
--- a/3rdparty/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_norm2.hpp
+++ b/3rdparty/composable_kernel/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_norm2.hpp