Skip to content

GitLab

Commit a30c626b authored by Bartlomiej Wroblewski's avatar Bartlomiej Wroblewski
Browse files

Make ComputeDataType an optional argument

parent b019d839
Hide whitespace changes
Inline Side-by-side
Showing with 40 additions and 40 deletions
library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f16_f16_f16_compute_f32_kkn_instance.cpp
View file @ a30c626b
...@@ -41,10 +41,10 @@ void add_device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f16_f16_f16_compute_f32 ...@@ -41,10 +41,10 @@ void add_device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f16_f16_f16_compute_f32
F16, F16,
Empty_Tuple, Empty_Tuple,
F16, F16,
F32,
PassThrough, PassThrough,
PassThrough, PassThrough,
Scale>>>& instances) Scale,
F32>>>& instances)
{ {
add_device_operation_instances( add_device_operation_instances(
instances, instances,
......
library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f16_f16_f16_compute_f32_knn_instance.cpp
View file @ a30c626b
...@@ -41,10 +41,10 @@ void add_device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f16_f16_f16_compute_f32 ...@@ -41,10 +41,10 @@ void add_device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f16_f16_f16_compute_f32
F16, F16,
Empty_Tuple, Empty_Tuple,
F16, F16,
F32,
PassThrough, PassThrough,
PassThrough, PassThrough,
Scale>>>& instances) Scale,
F32>>>& instances)
{ {
add_device_operation_instances( add_device_operation_instances(
instances, instances,
......
library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f16_f16_f16_compute_f32_mkn_instance.cpp
View file @ a30c626b
...@@ -41,10 +41,10 @@ void add_device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f16_f16_f16_compute_f32 ...@@ -41,10 +41,10 @@ void add_device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f16_f16_f16_compute_f32
F16, F16,
Empty_Tuple, Empty_Tuple,
F16, F16,
F32,
PassThrough, PassThrough,
PassThrough, PassThrough,
Scale>>>& instances) Scale,
F32>>>& instances)
{ {
add_device_operation_instances( add_device_operation_instances(
instances, instances,
......
library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f16_f16_f16_compute_f32_mnn_instance.cpp
View file @ a30c626b
...@@ -41,10 +41,10 @@ void add_device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f16_f16_f16_compute_f32 ...@@ -41,10 +41,10 @@ void add_device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f16_f16_f16_compute_f32
F16, F16,
Empty_Tuple, Empty_Tuple,
F16, F16,
F32,
PassThrough, PassThrough,
PassThrough, PassThrough,
Scale>>>& instances) Scale,
F32>>>& instances)
{ {
add_device_operation_instances( add_device_operation_instances(
instances, instances,
......
library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_compute_bf16_kkn_instance.cpp
View file @ a30c626b
...@@ -41,10 +41,10 @@ void add_device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_compute_bf1 ...@@ -41,10 +41,10 @@ void add_device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_compute_bf1
F32, F32,
Empty_Tuple, Empty_Tuple,
F32, F32,
BF16,
PassThrough, PassThrough,
PassThrough, PassThrough,
Scale>>>& instances) Scale,
BF16>>>& instances)
{ {
add_device_operation_instances( add_device_operation_instances(
instances, instances,
......
library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_compute_bf16_knn_instance.cpp
View file @ a30c626b
...@@ -41,10 +41,10 @@ void add_device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_compute_bf1 ...@@ -41,10 +41,10 @@ void add_device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_compute_bf1
F32, F32,
Empty_Tuple, Empty_Tuple,
F32, F32,
BF16,
PassThrough, PassThrough,
PassThrough, PassThrough,
Scale>>>& instances) Scale,
BF16>>>& instances)
{ {
add_device_operation_instances( add_device_operation_instances(
instances, instances,
......
library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_compute_bf16_mkn_instance.cpp
View file @ a30c626b
...@@ -41,10 +41,10 @@ void add_device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_compute_bf1 ...@@ -41,10 +41,10 @@ void add_device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_compute_bf1
F32, F32,
Empty_Tuple, Empty_Tuple,
F32, F32,
BF16,
PassThrough, PassThrough,
PassThrough, PassThrough,
Scale>>>& instances) Scale,
BF16>>>& instances)
{ {
add_device_operation_instances( add_device_operation_instances(
instances, instances,
......
library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_compute_bf16_mnn_instance.cpp
View file @ a30c626b
...@@ -41,10 +41,10 @@ void add_device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_compute_bf1 ...@@ -41,10 +41,10 @@ void add_device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_compute_bf1
F32, F32,
Empty_Tuple, Empty_Tuple,
F32, F32,
BF16,
PassThrough, PassThrough,
PassThrough, PassThrough,
Scale>>>& instances) Scale,
BF16>>>& instances)
{ {
add_device_operation_instances( add_device_operation_instances(
instances, instances,
......
library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_compute_f16_kkn_instance.cpp
View file @ a30c626b
...@@ -41,10 +41,10 @@ void add_device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_compute_f16 ...@@ -41,10 +41,10 @@ void add_device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_compute_f16
F32, F32,
Empty_Tuple, Empty_Tuple,
F32, F32,
F16,
PassThrough, PassThrough,
PassThrough, PassThrough,
Scale>>>& instances) Scale,
F16>>>& instances)
{ {
add_device_operation_instances( add_device_operation_instances(
instances, instances,
......
library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_compute_f16_knn_instance.cpp
View file @ a30c626b
...@@ -41,10 +41,10 @@ void add_device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_compute_f16 ...@@ -41,10 +41,10 @@ void add_device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_compute_f16
F32, F32,
Empty_Tuple, Empty_Tuple,
F32, F32,
F16,
PassThrough, PassThrough,
PassThrough, PassThrough,
Scale>>>& instances) Scale,
F16>>>& instances)
{ {
add_device_operation_instances( add_device_operation_instances(
instances, instances,
......
library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_compute_f16_mkn_instance.cpp
View file @ a30c626b
...@@ -41,10 +41,10 @@ void add_device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_compute_f16 ...@@ -41,10 +41,10 @@ void add_device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_compute_f16
F32, F32,
Empty_Tuple, Empty_Tuple,
F32, F32,
F16,
PassThrough, PassThrough,
PassThrough, PassThrough,
Scale>>>& instances) Scale,
F16>>>& instances)
{ {
add_device_operation_instances( add_device_operation_instances(
instances, instances,
......
library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_compute_f16_mnn_instance.cpp
View file @ a30c626b
...@@ -41,10 +41,10 @@ void add_device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_compute_f16 ...@@ -41,10 +41,10 @@ void add_device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_compute_f16
F32, F32,
Empty_Tuple, Empty_Tuple,
F32, F32,
F16,
PassThrough, PassThrough,
PassThrough, PassThrough,
Scale>>>& instances) Scale,
F16>>>& instances)
{ {
add_device_operation_instances( add_device_operation_instances(
instances, instances,
......
library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_kkn_instance.cpp
View file @ a30c626b
...@@ -41,10 +41,10 @@ void add_device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_kkn_instanc ...@@ -41,10 +41,10 @@ void add_device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_kkn_instanc
F32, F32,
Empty_Tuple, Empty_Tuple,
F32, F32,
F32,
PassThrough, PassThrough,
PassThrough, PassThrough,
Scale>>>& instances) Scale,
F32>>>& instances)
{ {
add_device_operation_instances( add_device_operation_instances(
instances, device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_kkn_instance{}); instances, device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_kkn_instance{});
......
library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_knn_instance.cpp
View file @ a30c626b
...@@ -41,10 +41,10 @@ void add_device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_knn_instanc ...@@ -41,10 +41,10 @@ void add_device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_knn_instanc
F32, F32,
Empty_Tuple, Empty_Tuple,
F32, F32,
F32,
PassThrough, PassThrough,
PassThrough, PassThrough,
Scale>>>& instances) Scale,
F32>>>& instances)
{ {
add_device_operation_instances( add_device_operation_instances(
instances, device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_knn_instance{}); instances, device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_knn_instance{});
......
library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_mkn_instance.cpp
View file @ a30c626b
...@@ -41,10 +41,10 @@ void add_device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_mkn_instanc ...@@ -41,10 +41,10 @@ void add_device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_mkn_instanc
F32, F32,
Empty_Tuple, Empty_Tuple,
F32, F32,
F32,
PassThrough, PassThrough,
PassThrough, PassThrough,
Scale>>>& instances) Scale,
F32>>>& instances)
{ {
add_device_operation_instances( add_device_operation_instances(
instances, device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_mkn_instance{}); instances, device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_mkn_instance{});
......
library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_mnn_instance.cpp
View file @ a30c626b
...@@ -41,10 +41,10 @@ void add_device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_mnn_instanc ...@@ -41,10 +41,10 @@ void add_device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_mnn_instanc
F32, F32,
Empty_Tuple, Empty_Tuple,
F32, F32,
F32,
PassThrough, PassThrough,
PassThrough, PassThrough,
Scale>>>& instances) Scale,
F32>>>& instances)
{ {
add_device_operation_instances( add_device_operation_instances(
instances, device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_mnn_instance{}); instances, device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f32_f32_f32_mnn_instance{});
......
library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_compute_f32_kkn_instance.cpp
View file @ a30c626b
...@@ -41,10 +41,10 @@ void add_device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_compute_f32 ...@@ -41,10 +41,10 @@ void add_device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_compute_f32
F64, F64,
Empty_Tuple, Empty_Tuple,
F64, F64,
F32,
PassThrough, PassThrough,
PassThrough, PassThrough,
Scale>>>& instances) Scale,
F32>>>& instances)
{ {
add_device_operation_instances( add_device_operation_instances(
instances, instances,
......
library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_compute_f32_knn_instance.cpp
View file @ a30c626b
...@@ -41,10 +41,10 @@ void add_device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_compute_f32 ...@@ -41,10 +41,10 @@ void add_device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_compute_f32
F64, F64,
Empty_Tuple, Empty_Tuple,
F64, F64,
F32,
PassThrough, PassThrough,
PassThrough, PassThrough,
Scale>>>& instances) Scale,
F32>>>& instances)
{ {
add_device_operation_instances( add_device_operation_instances(
instances, instances,
......
library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_compute_f32_mkn_instance.cpp
View file @ a30c626b
...@@ -41,10 +41,10 @@ void add_device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_compute_f32 ...@@ -41,10 +41,10 @@ void add_device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_compute_f32
F64, F64,
Empty_Tuple, Empty_Tuple,
F64, F64,
F32,
PassThrough, PassThrough,
PassThrough, PassThrough,
Scale>>>& instances) Scale,
F32>>>& instances)
{ {
add_device_operation_instances( add_device_operation_instances(
instances, instances,
......
library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_compute_f32_mnn_instance.cpp
View file @ a30c626b
...@@ -41,10 +41,10 @@ void add_device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_compute_f32 ...@@ -41,10 +41,10 @@ void add_device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_compute_f32
F64, F64,
Empty_Tuple, Empty_Tuple,
F64, F64,
F32,
PassThrough, PassThrough,
PassThrough, PassThrough,
Scale>>>& instances) Scale,
F32>>>& instances)
{ {
add_device_operation_instances( add_device_operation_instances(
instances, instances,
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment