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/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f16_f32_f32_add.cpp
+++ b/3rdparty/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f16_f32_f32_add.cpp
--- a/3rdparty/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f16_f32_f32_avg.cpp
+++ b/3rdparty/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f16_f32_f32_avg.cpp
--- a/3rdparty/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f32_f32_add.cpp
+++ b/3rdparty/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f32_f32_add.cpp
--- a/3rdparty/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f32_f32_avg.cpp
+++ b/3rdparty/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f32_f32_avg.cpp
--- a/3rdparty/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f64_f32_add.cpp
+++ b/3rdparty/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f64_f32_add.cpp
--- a/3rdparty/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f64_f32_avg.cpp
+++ b/3rdparty/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f64_f32_avg.cpp
--- a/3rdparty/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f64_f64_f64_add.cpp
+++ b/3rdparty/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f64_f64_f64_add.cpp
--- a/3rdparty/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f64_f64_f64_avg.cpp
+++ b/3rdparty/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f64_f64_f64_avg.cpp
--- a/3rdparty/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_add.cpp
+++ b/3rdparty/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_add.cpp
--- a/3rdparty/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_amax.cpp
+++ b/3rdparty/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_amax.cpp
--- a/3rdparty/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_avg.cpp
+++ b/3rdparty/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_avg.cpp
--- a/3rdparty/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_max.cpp
+++ b/3rdparty/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_max.cpp
--- a/3rdparty/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_min.cpp
+++ b/3rdparty/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_min.cpp
--- a/3rdparty/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_norm2.cpp
+++ b/3rdparty/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16_norm2.cpp
--- a/3rdparty/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_amax.cpp
+++ b/3rdparty/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_amax.cpp
--- a/3rdparty/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_max.cpp
+++ b/3rdparty/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_max.cpp
--- a/3rdparty/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_min.cpp
+++ b/3rdparty/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16_min.cpp
--- a/3rdparty/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_add.cpp
+++ b/3rdparty/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_add.cpp
--- a/3rdparty/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_avg.cpp
+++ b/3rdparty/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_avg.cpp
--- a/3rdparty/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_norm2.cpp
+++ b/3rdparty/composable_kernel/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16_norm2.cpp