ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-13 17:55:48 +00:00
Code Issues Packages Projects Releases Wiki Activity

Pr82 followup (#115)

Browse Source 
* Use thread cluster descriptor and explicit M_K 2d descriptor to simply Blockwise Reduction

* Change by replacing ReduceDims by NumReduceDims as Device Reduce interface template parameter

* Rename the folder name for the pool2d and reduce examples

* Update to reduction test scripts

* Add Readme for pool2d_fwd and reduce_blockwise examples

* Tiny fix in reduce profiler and tiny update in reduce testing scripts

* Tiny fix in testing script profile_reduce_no_index.sh

* Tiny change in script/profile_reduce_with_index.sh

* Renaming and refining in Reduction profiler/device layer/examples

* Renaming and refining in Reduction profiler/device layer/examples

* Renaming all NumReduceDims to NumReduceDim
This commit is contained in:
Qianfeng
2022-03-11 00:14:43 +08:00
committed by GitHub
parent 5d37d7bff4
commit 827301d95a
70 changed files with 1704 additions and 1576 deletions
Download Patch File Download Diff File Expand all files Collapse all files

38
library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16.cpp
View File

@@ -6,25 +6,25 @@ namespace device {
namespace device_reduce_instance {
// clang-format off
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | ReduceDims
ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 2, 0, 0, 4, 0, 1, 2); // for MIN
ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 2, 0, 0, 4, 0); //
ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 2, 0, 0, 2, 1); //
ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 3, 0, 0, 4, 0, 1, 2); // for MAX
ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 3, 0, 0, 4, 0); //
ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 3, 0, 0, 2, 1); //
ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 4, 0, 0, 4, 0, 1, 2); // for AMAX
ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 4, 0, 0, 4, 0); //
ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 4, 0, 0, 2, 1); //
ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 2, 0, 1, 4, 0, 1, 2); // for MIN
ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 2, 0, 1, 4, 0); //
ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 2, 0, 1, 2, 1); //
ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 3, 0, 1, 4, 0, 1, 2); // for MAX
ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 3, 0, 1, 4, 0); //
ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 3, 0, 1, 2, 1); //
ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 4, 0, 1, 4, 0, 1, 2); // for AMAX
ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 4, 0, 1, 4, 0); //
ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 4, 0, 1, 2, 1); //
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | NumReduceDim
ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 2, 0, 0, 4, 3); // for MIN
ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 2, 0, 0, 4, 1);
ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 2, 0, 0, 2, 1);
ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 3, 0, 0, 4, 3); // for MAX
ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 3, 0, 0, 4, 1);
ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 3, 0, 0, 2, 1);
ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 4, 0, 0, 4, 3); // for AMAX
ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 4, 0, 0, 4, 1);
ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 4, 0, 0, 2, 1);
ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 2, 0, 1, 4, 3); // for MIN
ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 2, 0, 1, 4, 1);
ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 2, 0, 1, 2, 1);
ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 3, 0, 1, 4, 3); // for MAX
ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 3, 0, 1, 4, 1);
ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 3, 0, 1, 2, 1);
ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 4, 0, 1, 4, 3); // for AMAX
ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 4, 0, 1, 4, 1);
ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 4, 0, 1, 2, 1);
// clang-format on
} // namespace device_reduce_instance

18
library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16.cpp
View File

@@ -6,16 +6,16 @@ namespace device {
namespace device_reduce_instance {
// clang-format off
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | ReduceDims
ADD_BLOCKWISE_INST_BY_ID(half_t, float, half_t, 0, 0, 0, 4, 0, 1, 2); // for ADD
ADD_BLOCKWISE_INST_BY_ID(half_t, float, half_t, 0, 0, 0, 4, 0);
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | NumReduceDim
ADD_BLOCKWISE_INST_BY_ID(half_t, float, half_t, 0, 0, 0, 4, 3); // for ADD
ADD_BLOCKWISE_INST_BY_ID(half_t, float, half_t, 0, 0, 0, 4, 1);
ADD_BLOCKWISE_INST_BY_ID(half_t, float, half_t, 0, 0, 0, 2, 1);
ADD_BLOCKWISE_INST_BY_ID(half_t, float, half_t, 5, 0, 0, 4, 0, 1, 2); // for AVG
ADD_BLOCKWISE_INST_BY_ID(half_t, float, half_t, 5, 0, 0, 4, 0); //
ADD_BLOCKWISE_INST_BY_ID(half_t, float, half_t, 5, 0, 0, 2, 1); //
ADD_BLOCKWISE_INST_BY_ID(half_t, float, half_t, 7, 0, 0, 4, 0, 1, 2); // for NORM2
ADD_BLOCKWISE_INST_BY_ID(half_t, float, half_t, 7, 0, 0, 4, 0); //
ADD_BLOCKWISE_INST_BY_ID(half_t, float, half_t, 7, 0, 0, 2, 1); //
ADD_BLOCKWISE_INST_BY_ID(half_t, float, half_t, 5, 0, 0, 4, 3); // for AVG
ADD_BLOCKWISE_INST_BY_ID(half_t, float, half_t, 5, 0, 0, 4, 1);
ADD_BLOCKWISE_INST_BY_ID(half_t, float, half_t, 5, 0, 0, 2, 1);
ADD_BLOCKWISE_INST_BY_ID(half_t, float, half_t, 7, 0, 0, 4, 3); // for NORM2
ADD_BLOCKWISE_INST_BY_ID(half_t, float, half_t, 7, 0, 0, 4, 1);
ADD_BLOCKWISE_INST_BY_ID(half_t, float, half_t, 7, 0, 0, 2, 1);
// clang-format on
} // namespace device_reduce_instance

54
library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32.cpp
View File

@@ -6,34 +6,34 @@ namespace device {
namespace device_reduce_instance {
// clang-format off
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | ReduceDims
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 0, 0, 0, 4, 0, 1, 2); // for ADD
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 0, 0, 0, 4, 0);
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | NumReduceDim
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 0, 0, 0, 4, 3); // for ADD
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 0, 0, 0, 4, 1);
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 0, 0, 0, 2, 1);
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 5, 0, 0, 4, 0, 1, 2); // for AVG
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 5, 0, 0, 4, 0); //
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 5, 0, 0, 2, 1); //
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 7, 0, 0, 4, 0, 1, 2); // for NORM2
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 7, 0, 0, 4, 0); //
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 7, 0, 0, 2, 1); //
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 2, 0, 0, 4, 0, 1, 2); // for MIN
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 2, 0, 0, 4, 0); //
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 2, 0, 0, 2, 1); //
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 3, 0, 0, 4, 0, 1, 2); // for MAX
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 3, 0, 0, 4, 0); //
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 3, 0, 0, 2, 1); //
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 4, 0, 0, 4, 0, 1, 2); // for AMAX
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 4, 0, 0, 4, 0); //
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 4, 0, 0, 2, 1); //
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 2, 0, 1, 4, 0, 1, 2); // for MIN
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 2, 0, 1, 4, 0); //
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 2, 0, 1, 2, 1); //
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 3, 0, 1, 4, 0, 1, 2); // for MAX
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 3, 0, 1, 4, 0); //
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 3, 0, 1, 2, 1); //
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 4, 0, 1, 4, 0, 1, 2); // for AMAX
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 4, 0, 1, 4, 0); //
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 4, 0, 1, 2, 1); //
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 5, 0, 0, 4, 3); // for AVG
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 5, 0, 0, 4, 1);
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 5, 0, 0, 2, 1);
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 7, 0, 0, 4, 3); // for NORM2
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 7, 0, 0, 4, 1);
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 7, 0, 0, 2, 1);
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 2, 0, 0, 4, 3); // for MIN
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 2, 0, 0, 4, 1);
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 2, 0, 0, 2, 1);
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 3, 0, 0, 4, 3); // for MAX
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 3, 0, 0, 4, 1);
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 3, 0, 0, 2, 1);
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 4, 0, 0, 4, 3); // for AMAX
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 4, 0, 0, 4, 1);
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 4, 0, 0, 2, 1);
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 2, 0, 1, 4, 3); // for MIN
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 2, 0, 1, 4, 1);
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 2, 0, 1, 2, 1);
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 3, 0, 1, 4, 3); // for MAX
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 3, 0, 1, 4, 1);
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 3, 0, 1, 2, 1);
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 4, 0, 1, 4, 3); // for AMAX
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 4, 0, 1, 4, 1);
ADD_BLOCKWISE_INST_BY_ID(float, float, float, 4, 0, 1, 2, 1);
// clang-format on
} // namespace device_reduce_instance

18
library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f64_f32.cpp
View File

@@ -6,16 +6,16 @@ namespace device {
namespace device_reduce_instance {
// clang-format off
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | ReduceDims
ADD_BLOCKWISE_INST_BY_ID(float, double, float, 0, 0, 0, 4, 0, 1, 2); // for ADD
ADD_BLOCKWISE_INST_BY_ID(float, double, float, 0, 0, 0, 4, 0);
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | NumReduceDim
ADD_BLOCKWISE_INST_BY_ID(float, double, float, 0, 0, 0, 4, 3); // for ADD
ADD_BLOCKWISE_INST_BY_ID(float, double, float, 0, 0, 0, 4, 1);
ADD_BLOCKWISE_INST_BY_ID(float, double, float, 0, 0, 0, 2, 1);
ADD_BLOCKWISE_INST_BY_ID(float, double, float, 5, 0, 0, 4, 0, 1, 2); // for AVG
ADD_BLOCKWISE_INST_BY_ID(float, double, float, 5, 0, 0, 4, 0); //
ADD_BLOCKWISE_INST_BY_ID(float, double, float, 5, 0, 0, 2, 1); //
ADD_BLOCKWISE_INST_BY_ID(float, double, float, 7, 0, 0, 4, 0, 1, 2); // for NORM2
ADD_BLOCKWISE_INST_BY_ID(float, double, float, 7, 0, 0, 4, 0); //
ADD_BLOCKWISE_INST_BY_ID(float, double, float, 7, 0, 0, 2, 1); //
ADD_BLOCKWISE_INST_BY_ID(float, double, float, 5, 0, 0, 4, 3); // for AVG
ADD_BLOCKWISE_INST_BY_ID(float, double, float, 5, 0, 0, 4, 1);
ADD_BLOCKWISE_INST_BY_ID(float, double, float, 5, 0, 0, 2, 1);
ADD_BLOCKWISE_INST_BY_ID(float, double, float, 7, 0, 0, 4, 3); // for NORM2
ADD_BLOCKWISE_INST_BY_ID(float, double, float, 7, 0, 0, 4, 1);
ADD_BLOCKWISE_INST_BY_ID(float, double, float, 7, 0, 0, 2, 1);
// clang-format on
} // namespace device_reduce_instance

54
library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64.cpp
View File

@@ -6,34 +6,34 @@ namespace device {
namespace device_reduce_instance {
// clang-format off
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | ReduceDims
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 0, 0, 0, 4, 0, 1, 2); // for ADD
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 0, 0, 0, 4, 0);
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | NumReduceDim
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 0, 0, 0, 4, 3); // for ADD
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 0, 0, 0, 4, 1);
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 0, 0, 0, 2, 1);
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 5, 0, 0, 4, 0, 1, 2); // for AVG
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 5, 0, 0, 4, 0); //
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 5, 0, 0, 2, 1); //
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 7, 0, 0, 4, 0, 1, 2); // for NORM2
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 7, 0, 0, 4, 0); //
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 7, 0, 0, 2, 1); //
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 2, 0, 0, 4, 0, 1, 2); // for MIN
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 2, 0, 0, 4, 0); //
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 2, 0, 0, 2, 1); //
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 3, 0, 0, 4, 0, 1, 2); // for MAX
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 3, 0, 0, 4, 0); //
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 3, 0, 0, 2, 1); //
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 4, 0, 0, 4, 0, 1, 2); // for AMAX
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 4, 0, 0, 4, 0); //
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 4, 0, 0, 2, 1); //
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 2, 0, 1, 4, 0, 1, 2); // for MIN
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 2, 0, 1, 4, 0); //
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 2, 0, 1, 2, 1); //
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 3, 0, 1, 4, 0, 1, 2); // for MAX
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 3, 0, 1, 4, 0); //
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 3, 0, 1, 2, 1); //
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 4, 0, 1, 4, 0, 1, 2); // for AMAX
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 4, 0, 1, 4, 0); //
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 4, 0, 1, 2, 1); //
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 5, 0, 0, 4, 3); // for AVG
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 5, 0, 0, 4, 1);
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 5, 0, 0, 2, 1);
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 7, 0, 0, 4, 3); // for NORM2
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 7, 0, 0, 4, 1);
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 7, 0, 0, 2, 1);
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 2, 0, 0, 4, 3); // for MIN
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 2, 0, 0, 4, 1);
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 2, 0, 0, 2, 1);
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 3, 0, 0, 4, 3); // for MAX
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 3, 0, 0, 4, 1);
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 3, 0, 0, 2, 1);
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 4, 0, 0, 4, 3); // for AMAX
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 4, 0, 0, 4, 1);
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 4, 0, 0, 2, 1);
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 2, 0, 1, 4, 3); // for MIN
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 2, 0, 1, 4, 1);
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 2, 0, 1, 2, 1);
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 3, 0, 1, 4, 3); // for MAX
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 3, 0, 1, 4, 1);
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 3, 0, 1, 2, 1);
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 4, 0, 1, 4, 3); // for AMAX
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 4, 0, 1, 4, 1);
ADD_BLOCKWISE_INST_BY_ID(double, double, double, 4, 0, 1, 2, 1);
// clang-format on
} // namespace device_reduce_instance

38
library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_f16_f16_f16.cpp
View File

@@ -6,25 +6,25 @@ namespace device {
namespace device_reduce_instance {
// clang-format off
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | ReduceDims
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 2, 0, 0, 4, 0, 1, 2); // for MIN
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 2, 0, 0, 4, 0); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 2, 0, 0, 2, 1); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 3, 0, 0, 4, 0, 1, 2); // for MAX
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 3, 0, 0, 4, 0); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 3, 0, 0, 2, 1); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 4, 0, 0, 4, 0, 1, 2); // for AMAX
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 4, 0, 0, 4, 0); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 4, 0, 0, 2, 1); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 2, 0, 1, 4, 0, 1, 2); // for MIN
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 2, 0, 1, 4, 0); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 2, 0, 1, 2, 1); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 3, 0, 1, 4, 0, 1, 2); // for MAX
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 3, 0, 1, 4, 0); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 3, 0, 1, 2, 1); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 4, 0, 1, 4, 0, 1, 2); // for AMAX
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 4, 0, 1, 4, 0); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 4, 0, 1, 2, 1); //
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | NumReduceDim
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 2, 0, 0, 4, 3); // for MIN
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 2, 0, 0, 4, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 2, 0, 0, 2, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 3, 0, 0, 4, 3); // for MAX
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 3, 0, 0, 4, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 3, 0, 0, 2, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 4, 0, 0, 4, 3); // for AMAX
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 4, 0, 0, 4, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 4, 0, 0, 2, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 2, 0, 1, 4, 3); // for MIN
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 2, 0, 1, 4, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 2, 0, 1, 2, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 3, 0, 1, 4, 3); // for MAX
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 3, 0, 1, 4, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 3, 0, 1, 2, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 4, 0, 1, 4, 3); // for AMAX
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 4, 0, 1, 4, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 4, 0, 1, 2, 1);
// clang-format on
} // namespace device_reduce_instance

18
library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_f32_f32_f16.cpp
View File

@@ -6,16 +6,16 @@ namespace device {
namespace device_reduce_instance {
// clang-format off
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | ReduceDims
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, half_t, 0, 0, 0, 4, 0, 1, 2); // for ADD
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, half_t, 0, 0, 0, 4, 0);
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | NumReduceDim
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, half_t, 0, 0, 0, 4, 3); // for ADD
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, half_t, 0, 0, 0, 4, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, half_t, 0, 0, 0, 2, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, half_t, 5, 0, 0, 4, 0, 1, 2); // for AVG
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, half_t, 5, 0, 0, 4, 0); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, half_t, 5, 0, 0, 2, 1); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, half_t, 7, 0, 0, 4, 0, 1, 2); // for NORM2
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, half_t, 7, 0, 0, 4, 0); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, half_t, 7, 0, 0, 2, 1); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, half_t, 5, 0, 0, 4, 3); // for AVG
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, half_t, 5, 0, 0, 4, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, half_t, 5, 0, 0, 2, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, half_t, 7, 0, 0, 4, 3); // for NORM2
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, half_t, 7, 0, 0, 4, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, half_t, 7, 0, 0, 2, 1);
// clang-format on
} // namespace device_reduce_instance

54
library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_f32_f32_f32.cpp
View File

@@ -6,34 +6,34 @@ namespace device {
namespace device_reduce_instance {
// clang-format off
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | ReduceDims
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 0, 0, 0, 4, 0, 1, 2); // for ADD
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 0, 0, 0, 4, 0);
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | NumReduceDim
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 0, 0, 0, 4, 3); // for ADD
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 0, 0, 0, 4, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 0, 0, 0, 2, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 5, 0, 0, 4, 0, 1, 2); // for AVG
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 5, 0, 0, 4, 0); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 5, 0, 0, 2, 1); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 7, 0, 0, 4, 0, 1, 2); // for NORM2
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 7, 0, 0, 4, 0); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 7, 0, 0, 2, 1); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 2, 0, 0, 4, 0, 1, 2); // for MIN
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 2, 0, 0, 4, 0); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 2, 0, 0, 2, 1); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 3, 0, 0, 4, 0, 1, 2); // for MAX
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 3, 0, 0, 4, 0); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 3, 0, 0, 2, 1); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 4, 0, 0, 4, 0, 1, 2); // for AMAX
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 4, 0, 0, 4, 0); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 4, 0, 0, 2, 1); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 2, 0, 1, 4, 0, 1, 2); // for MIN
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 2, 0, 1, 4, 0); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 2, 0, 1, 2, 1); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 3, 0, 1, 4, 0, 1, 2); // for MAX
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 3, 0, 1, 4, 0); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 3, 0, 1, 2, 1); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 4, 0, 1, 4, 0, 1, 2); // for AMAX
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 4, 0, 1, 4, 0); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 4, 0, 1, 2, 1); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 5, 0, 0, 4, 3); // for AVG
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 5, 0, 0, 4, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 5, 0, 0, 2, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 7, 0, 0, 4, 3); // for NORM2
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 7, 0, 0, 4, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 7, 0, 0, 2, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 2, 0, 0, 4, 3); // for MIN
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 2, 0, 0, 4, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 2, 0, 0, 2, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 3, 0, 0, 4, 3); // for MAX
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 3, 0, 0, 4, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 3, 0, 0, 2, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 4, 0, 0, 4, 3); // for AMAX
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 4, 0, 0, 4, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 4, 0, 0, 2, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 2, 0, 1, 4, 3); // for MIN
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 2, 0, 1, 4, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 2, 0, 1, 2, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 3, 0, 1, 4, 3); // for MAX
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 3, 0, 1, 4, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 3, 0, 1, 2, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 4, 0, 1, 4, 3); // for AMAX
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 4, 0, 1, 4, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 4, 0, 1, 2, 1);
// clang-format on
} // namespace device_reduce_instance

18
library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_f64_f64_f32.cpp
View File

@@ -6,16 +6,16 @@ namespace device {
namespace device_reduce_instance {
// clang-format off
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | ReduceDims
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, float, 0, 0, 0, 4, 0, 1, 2); // for ADD
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, float, 0, 0, 0, 4, 0);
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | NumReduceDim
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, float, 0, 0, 0, 4, 3); // for ADD
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, float, 0, 0, 0, 4, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, float, 0, 0, 0, 2, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, float, 5, 0, 0, 4, 0, 1, 2); // for AVG
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, float, 5, 0, 0, 4, 0); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, float, 5, 0, 0, 2, 1); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, float, 7, 0, 0, 4, 0, 1, 2); // for NORM2
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, float, 7, 0, 0, 4, 0); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, float, 7, 0, 0, 2, 1); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, float, 5, 0, 0, 4, 3); // for AVG
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, float, 5, 0, 0, 4, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, float, 5, 0, 0, 2, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, float, 7, 0, 0, 4, 3); // for NORM2
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, float, 7, 0, 0, 4, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, float, 7, 0, 0, 2, 1);
// clang-format on
} // namespace device_reduce_instance

54
library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_f64_f64_f64.cpp
View File

@@ -6,34 +6,34 @@ namespace device {
namespace device_reduce_instance {
// clang-format off
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | ReduceDims
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 0, 0, 0, 4, 0, 1, 2); // for ADD
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 0, 0, 0, 4, 0);
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | NumReduceDim
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 0, 0, 0, 4, 3); // for ADD
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 0, 0, 0, 4, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 0, 0, 0, 2, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 5, 0, 0, 4, 0, 1, 2); // for AVG
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 5, 0, 0, 4, 0); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 5, 0, 0, 2, 1); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 7, 0, 0, 4, 0, 1, 2); // for NORM2
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 7, 0, 0, 4, 0); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 7, 0, 0, 2, 1); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 2, 0, 0, 4, 0, 1, 2); // for MIN
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 2, 0, 0, 4, 0); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 2, 0, 0, 2, 1); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 3, 0, 0, 4, 0, 1, 2); // for MAX
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 3, 0, 0, 4, 0); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 3, 0, 0, 2, 1); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 4, 0, 0, 4, 0, 1, 2); // for AMAX
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 4, 0, 0, 4, 0); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 4, 0, 0, 2, 1); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 2, 0, 1, 4, 0, 1, 2); // for MIN
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 2, 0, 1, 4, 0); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 2, 0, 1, 2, 1); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 3, 0, 1, 4, 0, 1, 2); // for MAX
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 3, 0, 1, 4, 0); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 3, 0, 1, 2, 1); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 4, 0, 1, 4, 0, 1, 2); // for AMAX
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 4, 0, 1, 4, 0); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 4, 0, 1, 2, 1); //
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 5, 0, 0, 4, 3); // for AVG
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 5, 0, 0, 4, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 5, 0, 0, 2, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 7, 0, 0, 4, 3); // for NORM2
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 7, 0, 0, 4, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 7, 0, 0, 2, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 2, 0, 0, 4, 3); // for MIN
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 2, 0, 0, 4, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 2, 0, 0, 2, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 3, 0, 0, 4, 3); // for MAX
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 3, 0, 0, 4, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 3, 0, 0, 2, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 4, 0, 0, 4, 3); // for AMAX
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 4, 0, 0, 4, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 4, 0, 0, 2, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 2, 0, 1, 4, 3); // for MIN
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 2, 0, 1, 4, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 2, 0, 1, 2, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 3, 0, 1, 4, 3); // for MAX
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 3, 0, 1, 4, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 3, 0, 1, 2, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 4, 0, 1, 4, 3); // for AMAX
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 4, 0, 1, 4, 1);
ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, double, 4, 0, 1, 2, 1);
// clang-format on
} // namespace device_reduce_instance

12
library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f16_f32_f32.cpp
View File

@@ -6,13 +6,13 @@ namespace device {
namespace device_reduce_instance {
// clang-format off
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | ReduceDims
ADD_MULTIBLOCK_ATOMIC_ADD_INST_BY_ID(half_t, float, float, 0, 0, 0, 4, 0, 1, 2); // for ADD
ADD_MULTIBLOCK_ATOMIC_ADD_INST_BY_ID(half_t, float, float, 0, 0, 0, 4, 0);
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | NumReduceDim
ADD_MULTIBLOCK_ATOMIC_ADD_INST_BY_ID(half_t, float, float, 0, 0, 0, 4, 3); // for ADD
ADD_MULTIBLOCK_ATOMIC_ADD_INST_BY_ID(half_t, float, float, 0, 0, 0, 4, 1);
ADD_MULTIBLOCK_ATOMIC_ADD_INST_BY_ID(half_t, float, float, 0, 0, 0, 2, 1);
ADD_MULTIBLOCK_ATOMIC_ADD_INST_BY_ID(half_t, float, float, 5, 0, 0, 4, 0, 1, 2); // for AVG
ADD_MULTIBLOCK_ATOMIC_ADD_INST_BY_ID(half_t, float, float, 5, 0, 0, 4, 0); //
ADD_MULTIBLOCK_ATOMIC_ADD_INST_BY_ID(half_t, float, float, 5, 0, 0, 2, 1); //
ADD_MULTIBLOCK_ATOMIC_ADD_INST_BY_ID(half_t, float, float, 5, 0, 0, 4, 3); // for AVG
ADD_MULTIBLOCK_ATOMIC_ADD_INST_BY_ID(half_t, float, float, 5, 0, 0, 4, 1);
ADD_MULTIBLOCK_ATOMIC_ADD_INST_BY_ID(half_t, float, float, 5, 0, 0, 2, 1);
// clang-format on
} // namespace device_reduce_instance

12
library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f32_f32.cpp
View File

@@ -6,13 +6,13 @@ namespace device {
namespace device_reduce_instance {
// clang-format off
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | ReduceDims
ADD_MULTIBLOCK_ATOMIC_ADD_INST_BY_ID(float, float, float, 0, 0, 0, 4, 0, 1, 2); // for ADD
ADD_MULTIBLOCK_ATOMIC_ADD_INST_BY_ID(float, float, float, 0, 0, 0, 4, 0);
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | NumReduceDim
ADD_MULTIBLOCK_ATOMIC_ADD_INST_BY_ID(float, float, float, 0, 0, 0, 4, 3); // for ADD
ADD_MULTIBLOCK_ATOMIC_ADD_INST_BY_ID(float, float, float, 0, 0, 0, 4, 1);
ADD_MULTIBLOCK_ATOMIC_ADD_INST_BY_ID(float, float, float, 0, 0, 0, 2, 1);
ADD_MULTIBLOCK_ATOMIC_ADD_INST_BY_ID(float, float, float, 5, 0, 0, 4, 0, 1, 2); // for AVG
ADD_MULTIBLOCK_ATOMIC_ADD_INST_BY_ID(float, float, float, 5, 0, 0, 4, 0); //
ADD_MULTIBLOCK_ATOMIC_ADD_INST_BY_ID(float, float, float, 5, 0, 0, 2, 1); //
ADD_MULTIBLOCK_ATOMIC_ADD_INST_BY_ID(float, float, float, 5, 0, 0, 4, 3); // for AVG
ADD_MULTIBLOCK_ATOMIC_ADD_INST_BY_ID(float, float, float, 5, 0, 0, 4, 1);
ADD_MULTIBLOCK_ATOMIC_ADD_INST_BY_ID(float, float, float, 5, 0, 0, 2, 1);
// clang-format on
} // namespace device_reduce_instance

12
library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f64_f32.cpp
View File

@@ -6,13 +6,13 @@ namespace device {
namespace device_reduce_instance {
// clang-format off
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | ReduceDims
ADD_MULTIBLOCK_ATOMIC_ADD_INST_BY_ID(float, double, float, 0, 0, 0, 4, 0, 1, 2); // for ADD
ADD_MULTIBLOCK_ATOMIC_ADD_INST_BY_ID(float, double, float, 0, 0, 0, 4, 0);
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | NumReduceDim
ADD_MULTIBLOCK_ATOMIC_ADD_INST_BY_ID(float, double, float, 0, 0, 0, 4, 3); // for ADD
ADD_MULTIBLOCK_ATOMIC_ADD_INST_BY_ID(float, double, float, 0, 0, 0, 4, 1);
ADD_MULTIBLOCK_ATOMIC_ADD_INST_BY_ID(float, double, float, 0, 0, 0, 2, 1);
ADD_MULTIBLOCK_ATOMIC_ADD_INST_BY_ID(float, double, float, 5, 0, 0, 4, 0, 1, 2); // for AVG
ADD_MULTIBLOCK_ATOMIC_ADD_INST_BY_ID(float, double, float, 5, 0, 0, 4, 0); //
ADD_MULTIBLOCK_ATOMIC_ADD_INST_BY_ID(float, double, float, 5, 0, 0, 2, 1); //
ADD_MULTIBLOCK_ATOMIC_ADD_INST_BY_ID(float, double, float, 5, 0, 0, 4, 3); // for AVG
ADD_MULTIBLOCK_ATOMIC_ADD_INST_BY_ID(float, double, float, 5, 0, 0, 4, 1);
ADD_MULTIBLOCK_ATOMIC_ADD_INST_BY_ID(float, double, float, 5, 0, 0, 2, 1);
// clang-format on
} // namespace device_reduce_instance

38
library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_partial_reduce_f16_f16_f16.cpp
View File

@@ -6,25 +6,25 @@ namespace device {
namespace device_reduce_instance {
// clang-format off
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | ReduceDims
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, half_t, half_t, 2, 0, 0, 4, 0, 1, 2); // for MIN
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, half_t, half_t, 2, 0, 0, 4, 0); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, half_t, half_t, 2, 0, 0, 2, 1); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, half_t, half_t, 3, 0, 0, 4, 0, 1, 2); // for MAX
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, half_t, half_t, 3, 0, 0, 4, 0); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, half_t, half_t, 3, 0, 0, 2, 1); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, half_t, half_t, 4, 0, 0, 4, 0, 1, 2); // for AMAX
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, half_t, half_t, 4, 0, 0, 4, 0); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, half_t, half_t, 4, 0, 0, 2, 1); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, half_t, half_t, 2, 0, 1, 4, 0, 1, 2); // for MIN
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, half_t, half_t, 2, 0, 1, 4, 0); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, half_t, half_t, 2, 0, 1, 2, 1); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, half_t, half_t, 3, 0, 1, 4, 0, 1, 2); // for MAX
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, half_t, half_t, 3, 0, 1, 4, 0); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, half_t, half_t, 3, 0, 1, 2, 1); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, half_t, half_t, 4, 0, 1, 4, 0, 1, 2); // for AMAX
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, half_t, half_t, 4, 0, 1, 4, 0); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, half_t, half_t, 4, 0, 1, 2, 1); //
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | NumReduceDim
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, half_t, half_t, 2, 0, 0, 4, 3); // for MIN
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, half_t, half_t, 2, 0, 0, 4, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, half_t, half_t, 2, 0, 0, 2, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, half_t, half_t, 3, 0, 0, 4, 3); // for MAX
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, half_t, half_t, 3, 0, 0, 4, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, half_t, half_t, 3, 0, 0, 2, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, half_t, half_t, 4, 0, 0, 4, 3); // for AMAX
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, half_t, half_t, 4, 0, 0, 4, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, half_t, half_t, 4, 0, 0, 2, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, half_t, half_t, 2, 0, 1, 4, 3); // for MIN
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, half_t, half_t, 2, 0, 1, 4, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, half_t, half_t, 2, 0, 1, 2, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, half_t, half_t, 3, 0, 1, 4, 3); // for MAX
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, half_t, half_t, 3, 0, 1, 4, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, half_t, half_t, 3, 0, 1, 2, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, half_t, half_t, 4, 0, 1, 4, 3); // for AMAX
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, half_t, half_t, 4, 0, 1, 4, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, half_t, half_t, 4, 0, 1, 2, 1);
// clang-format on
} // namespace device_reduce_instance

18
library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_partial_reduce_f16_f32_f16.cpp
View File

@@ -6,16 +6,16 @@ namespace device {
namespace device_reduce_instance {
// clang-format off
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | ReduceDims
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, float, half_t, 0, 0, 0, 4, 0, 1, 2); // for ADD
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, float, half_t, 0, 0, 0, 4, 0);
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | NumReduceDim
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, float, half_t, 0, 0, 0, 4, 3); // for ADD
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, float, half_t, 0, 0, 0, 4, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, float, half_t, 0, 0, 0, 2, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, float, half_t, 5, 0, 0, 4, 0, 1, 2); // for AVG
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, float, half_t, 5, 0, 0, 4, 0); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, float, half_t, 5, 0, 0, 2, 1); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, float, half_t, 7, 0, 0, 4, 0, 1, 2); // for NORM2
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, float, half_t, 7, 0, 0, 4, 0); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, float, half_t, 7, 0, 0, 2, 1); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, float, half_t, 5, 0, 0, 4, 3); // for AVG
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, float, half_t, 5, 0, 0, 4, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, float, half_t, 5, 0, 0, 2, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, float, half_t, 7, 0, 0, 4, 3); // for NORM2
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, float, half_t, 7, 0, 0, 4, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(half_t, float, half_t, 7, 0, 0, 2, 1);
// clang-format on
} // namespace device_reduce_instance

44
library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_partial_reduce_f32_f32_f32.cpp
View File

@@ -6,29 +6,29 @@ namespace device {
namespace device_reduce_instance {
// clang-format off
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | ReduceDims
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, float, float, 2, 0, 0, 4, 0, 1, 2); // for MIN
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, float, float, 2, 0, 0, 4, 0); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, float, float, 2, 0, 0, 2, 1); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, float, float, 3, 0, 0, 4, 0, 1, 2); // for MAX
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, float, float, 3, 0, 0, 4, 0); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, float, float, 3, 0, 0, 2, 1); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, float, float, 4, 0, 0, 4, 0, 1, 2); // for AMAX
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, float, float, 4, 0, 0, 4, 0); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, float, float, 4, 0, 0, 2, 1); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, float, float, 2, 0, 1, 4, 0, 1, 2); // for MIN
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, float, float, 2, 0, 1, 4, 0); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, float, float, 2, 0, 1, 2, 1); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, float, float, 3, 0, 1, 4, 0, 1, 2); // for MAX
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, float, float, 3, 0, 1, 4, 0); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, float, float, 3, 0, 1, 2, 1); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, float, float, 4, 0, 1, 4, 0, 1, 2); // for AMAX
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, float, float, 4, 0, 1, 4, 0); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, float, float, 4, 0, 1, 2, 1); //
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | NumReduceDim
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, float, float, 2, 0, 0, 4, 3); // for MIN
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, float, float, 2, 0, 0, 4, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, float, float, 2, 0, 0, 2, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, float, float, 3, 0, 0, 4, 3); // for MAX
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, float, float, 3, 0, 0, 4, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, float, float, 3, 0, 0, 2, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, float, float, 4, 0, 0, 4, 3); // for AMAX
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, float, float, 4, 0, 0, 4, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, float, float, 4, 0, 0, 2, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, float, float, 2, 0, 1, 4, 3); // for MIN
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, float, float, 2, 0, 1, 4, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, float, float, 2, 0, 1, 2, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, float, float, 3, 0, 1, 4, 3); // for MAX
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, float, float, 3, 0, 1, 4, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, float, float, 3, 0, 1, 2, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, float, float, 4, 0, 1, 4, 3); // for AMAX
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, float, float, 4, 0, 1, 4, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, float, float, 4, 0, 1, 2, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, float, float, 7, 0, 0, 4, 0, 1, 2); // for NORM2
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, float, float, 7, 0, 0, 4, 0); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, float, float, 7, 0, 0, 2, 1); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, float, float, 7, 0, 0, 4, 3); // for NORM2
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, float, float, 7, 0, 0, 4, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, float, float, 7, 0, 0, 2, 1);
// clang-format on
} // namespace device_reduce_instance

8
library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_partial_reduce_f32_f64_f32.cpp
View File

@@ -6,10 +6,10 @@ namespace device {
namespace device_reduce_instance {
// clang-format off
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | ReduceDims
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, double, float, 7, 0, 0, 4, 0, 1, 2); // for NORM2
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, double, float, 7, 0, 0, 4, 0); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, double, float, 7, 0, 0, 2, 1); //
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | NumReduceDim
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, double, float, 7, 0, 0, 4, 3); // for NORM2
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, double, float, 7, 0, 0, 4, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(float, double, float, 7, 0, 0, 2, 1);
// clang-format on
} // namespace device_reduce_instance

56
library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_partial_reduce_f64_f64_f64.cpp
View File

@@ -6,37 +6,37 @@ namespace device {
namespace device_reduce_instance {
// clang-format off
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | ReduceDims
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 2, 0, 0, 4, 0, 1, 2); // for MIN
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 2, 0, 0, 4, 0); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 2, 0, 0, 2, 1); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 3, 0, 0, 4, 0, 1, 2); // for MAX
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 3, 0, 0, 4, 0); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 3, 0, 0, 2, 1); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 4, 0, 0, 4, 0, 1, 2); // for AMAX
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 4, 0, 0, 4, 0); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 4, 0, 0, 2, 1); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 2, 0, 1, 4, 0, 1, 2); // for MIN
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 2, 0, 1, 4, 0); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 2, 0, 1, 2, 1); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 3, 0, 1, 4, 0, 1, 2); // for MAX
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 3, 0, 1, 4, 0); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 3, 0, 1, 2, 1); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 4, 0, 1, 4, 0, 1, 2); // for AMAX
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 4, 0, 1, 4, 0); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 4, 0, 1, 2, 1); //
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | NumReduceDim
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 2, 0, 0, 4, 3); // for MIN
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 2, 0, 0, 4, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 2, 0, 0, 2, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 3, 0, 0, 4, 3); // for MAX
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 3, 0, 0, 4, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 3, 0, 0, 2, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 4, 0, 0, 4, 3); // for AMAX
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 4, 0, 0, 4, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 4, 0, 0, 2, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 2, 0, 1, 4, 3); // for MIN
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 2, 0, 1, 4, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 2, 0, 1, 2, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 3, 0, 1, 4, 3); // for MAX
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 3, 0, 1, 4, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 3, 0, 1, 2, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 4, 0, 1, 4, 3); // for AMAX
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 4, 0, 1, 4, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 4, 0, 1, 2, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 7, 0, 0, 4, 0, 1, 2); // for NORM2
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 7, 0, 0, 4, 0); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 7, 0, 0, 2, 1); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 7, 0, 0, 4, 3); // for NORM2
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 7, 0, 0, 4, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 7, 0, 0, 2, 1);
// Will be moved to use MultiBlockAtomicAdd
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 0, 0, 0, 4, 0, 1, 2); // for ADD
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 0, 0, 0, 4, 0); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 0, 0, 0, 2, 1); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 5, 0, 0, 4, 0, 1, 2); // for AVG
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 5, 0, 0, 4, 0); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 5, 0, 0, 2, 1); //
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 0, 0, 0, 4, 3); // for ADD
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 0, 0, 0, 4, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 0, 0, 0, 2, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 5, 0, 0, 4, 3); // for AVG
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 5, 0, 0, 4, 1);
ADD_MULTIBLOCK_PARTIAL_REDUCE_INST_BY_ID(double, double, double, 5, 0, 0, 2, 1);
// clang-format on
} // namespace device_reduce_instance

38
library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16.cpp
View File

@@ -6,25 +6,25 @@ namespace device {
namespace device_reduce_instance {
// clang-format off
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | ReduceDims
ADD_THREADWISE_INST_BY_ID(half_t, half_t, half_t, 2, 0, 0, 4, 0, 1, 2); // for MIN
ADD_THREADWISE_INST_BY_ID(half_t, half_t, half_t, 2, 0, 0, 4, 0); //
ADD_THREADWISE_INST_BY_ID(half_t, half_t, half_t, 2, 0, 0, 2, 1); //
ADD_THREADWISE_INST_BY_ID(half_t, half_t, half_t, 3, 0, 0, 4, 0, 1, 2); // for MAX
ADD_THREADWISE_INST_BY_ID(half_t, half_t, half_t, 3, 0, 0, 4, 0); //
ADD_THREADWISE_INST_BY_ID(half_t, half_t, half_t, 3, 0, 0, 2, 1); //
ADD_THREADWISE_INST_BY_ID(half_t, half_t, half_t, 4, 0, 0, 4, 0, 1, 2); // for AMAX
ADD_THREADWISE_INST_BY_ID(half_t, half_t, half_t, 4, 0, 0, 4, 0); //
ADD_THREADWISE_INST_BY_ID(half_t, half_t, half_t, 4, 0, 0, 2, 1); //
ADD_THREADWISE_INST_BY_ID(half_t, half_t, half_t, 2, 0, 1, 4, 0, 1, 2); // for MIN
ADD_THREADWISE_INST_BY_ID(half_t, half_t, half_t, 2, 0, 1, 4, 0); //
ADD_THREADWISE_INST_BY_ID(half_t, half_t, half_t, 2, 0, 1, 2, 1); //
ADD_THREADWISE_INST_BY_ID(half_t, half_t, half_t, 3, 0, 1, 4, 0, 1, 2); // for MAX
ADD_THREADWISE_INST_BY_ID(half_t, half_t, half_t, 3, 0, 1, 4, 0); //
ADD_THREADWISE_INST_BY_ID(half_t, half_t, half_t, 3, 0, 1, 2, 1); //
ADD_THREADWISE_INST_BY_ID(half_t, half_t, half_t, 4, 0, 1, 4, 0, 1, 2); // for AMAX
ADD_THREADWISE_INST_BY_ID(half_t, half_t, half_t, 4, 0, 1, 4, 0); //
ADD_THREADWISE_INST_BY_ID(half_t, half_t, half_t, 4, 0, 1, 2, 1); //
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | NumReduceDim
ADD_THREADWISE_INST_BY_ID(half_t, half_t, half_t, 2, 0, 0, 4, 3); // for MIN
ADD_THREADWISE_INST_BY_ID(half_t, half_t, half_t, 2, 0, 0, 4, 1);
ADD_THREADWISE_INST_BY_ID(half_t, half_t, half_t, 2, 0, 0, 2, 1);
ADD_THREADWISE_INST_BY_ID(half_t, half_t, half_t, 3, 0, 0, 4, 3); // for MAX
ADD_THREADWISE_INST_BY_ID(half_t, half_t, half_t, 3, 0, 0, 4, 1);
ADD_THREADWISE_INST_BY_ID(half_t, half_t, half_t, 3, 0, 0, 2, 1);
ADD_THREADWISE_INST_BY_ID(half_t, half_t, half_t, 4, 0, 0, 4, 3); // for AMAX
ADD_THREADWISE_INST_BY_ID(half_t, half_t, half_t, 4, 0, 0, 4, 1);
ADD_THREADWISE_INST_BY_ID(half_t, half_t, half_t, 4, 0, 0, 2, 1);
ADD_THREADWISE_INST_BY_ID(half_t, half_t, half_t, 2, 0, 1, 4, 3); // for MIN
ADD_THREADWISE_INST_BY_ID(half_t, half_t, half_t, 2, 0, 1, 4, 1);
ADD_THREADWISE_INST_BY_ID(half_t, half_t, half_t, 2, 0, 1, 2, 1);
ADD_THREADWISE_INST_BY_ID(half_t, half_t, half_t, 3, 0, 1, 4, 3); // for MAX
ADD_THREADWISE_INST_BY_ID(half_t, half_t, half_t, 3, 0, 1, 4, 1);
ADD_THREADWISE_INST_BY_ID(half_t, half_t, half_t, 3, 0, 1, 2, 1);
ADD_THREADWISE_INST_BY_ID(half_t, half_t, half_t, 4, 0, 1, 4, 3); // for AMAX
ADD_THREADWISE_INST_BY_ID(half_t, half_t, half_t, 4, 0, 1, 4, 1);
ADD_THREADWISE_INST_BY_ID(half_t, half_t, half_t, 4, 0, 1, 2, 1);
// clang-format on
} // namespace device_reduce_instance

18
library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16.cpp
View File

@@ -6,16 +6,16 @@ namespace device {
namespace device_reduce_instance {
// clang-format off
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | ReduceDims
ADD_THREADWISE_INST_BY_ID(half_t, float, half_t, 0, 0, 0, 4, 0, 1, 2); // for ADD
ADD_THREADWISE_INST_BY_ID(half_t, float, half_t, 0, 0, 0, 4, 0);
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | NumReduceDim
ADD_THREADWISE_INST_BY_ID(half_t, float, half_t, 0, 0, 0, 4, 3); // for ADD
ADD_THREADWISE_INST_BY_ID(half_t, float, half_t, 0, 0, 0, 4, 1);
ADD_THREADWISE_INST_BY_ID(half_t, float, half_t, 0, 0, 0, 2, 1);
ADD_THREADWISE_INST_BY_ID(half_t, float, half_t, 5, 0, 0, 4, 0, 1, 2); // for AVG
ADD_THREADWISE_INST_BY_ID(half_t, float, half_t, 5, 0, 0, 4, 0); //
ADD_THREADWISE_INST_BY_ID(half_t, float, half_t, 5, 0, 0, 2, 1); //
ADD_THREADWISE_INST_BY_ID(half_t, float, half_t, 7, 0, 0, 4, 0, 1, 2); // for NORM2
ADD_THREADWISE_INST_BY_ID(half_t, float, half_t, 7, 0, 0, 4, 0); //
ADD_THREADWISE_INST_BY_ID(half_t, float, half_t, 7, 0, 0, 2, 1); //
ADD_THREADWISE_INST_BY_ID(half_t, float, half_t, 5, 0, 0, 4, 3); // for AVG
ADD_THREADWISE_INST_BY_ID(half_t, float, half_t, 5, 0, 0, 4, 1);
ADD_THREADWISE_INST_BY_ID(half_t, float, half_t, 5, 0, 0, 2, 1);
ADD_THREADWISE_INST_BY_ID(half_t, float, half_t, 7, 0, 0, 4, 3); // for NORM2
ADD_THREADWISE_INST_BY_ID(half_t, float, half_t, 7, 0, 0, 4, 1);
ADD_THREADWISE_INST_BY_ID(half_t, float, half_t, 7, 0, 0, 2, 1);
// clang-format on
} // namespace device_reduce_instance

54
library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32.cpp
View File

@@ -6,34 +6,34 @@ namespace device {
namespace device_reduce_instance {
// clang-format off
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | ReduceDims
ADD_THREADWISE_INST_BY_ID(float, float, float, 0, 0, 0, 4, 0, 1, 2); // for ADD
ADD_THREADWISE_INST_BY_ID(float, float, float, 0, 0, 0, 4, 0);
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | NumReduceDim
ADD_THREADWISE_INST_BY_ID(float, float, float, 0, 0, 0, 4, 3); // for ADD
ADD_THREADWISE_INST_BY_ID(float, float, float, 0, 0, 0, 4, 1);
ADD_THREADWISE_INST_BY_ID(float, float, float, 0, 0, 0, 2, 1);
ADD_THREADWISE_INST_BY_ID(float, float, float, 5, 0, 0, 4, 0, 1, 2); // for AVG
ADD_THREADWISE_INST_BY_ID(float, float, float, 5, 0, 0, 4, 0); //
ADD_THREADWISE_INST_BY_ID(float, float, float, 5, 0, 0, 2, 1); //
ADD_THREADWISE_INST_BY_ID(float, float, float, 7, 0, 0, 4, 0, 1, 2); // for NORM2
ADD_THREADWISE_INST_BY_ID(float, float, float, 7, 0, 0, 4, 0); //
ADD_THREADWISE_INST_BY_ID(float, float, float, 7, 0, 0, 2, 1); //
ADD_THREADWISE_INST_BY_ID(float, float, float, 2, 0, 0, 4, 0, 1, 2); // for MIN
ADD_THREADWISE_INST_BY_ID(float, float, float, 2, 0, 0, 4, 0); //
ADD_THREADWISE_INST_BY_ID(float, float, float, 2, 0, 0, 2, 1); //
ADD_THREADWISE_INST_BY_ID(float, float, float, 3, 0, 0, 4, 0, 1, 2); // for MAX
ADD_THREADWISE_INST_BY_ID(float, float, float, 3, 0, 0, 4, 0); //
ADD_THREADWISE_INST_BY_ID(float, float, float, 3, 0, 0, 2, 1); //
ADD_THREADWISE_INST_BY_ID(float, float, float, 4, 0, 0, 4, 0, 1, 2); // for AMAX
ADD_THREADWISE_INST_BY_ID(float, float, float, 4, 0, 0, 4, 0); //
ADD_THREADWISE_INST_BY_ID(float, float, float, 4, 0, 0, 2, 1); //
ADD_THREADWISE_INST_BY_ID(float, float, float, 2, 0, 1, 4, 0, 1, 2); // for MIN
ADD_THREADWISE_INST_BY_ID(float, float, float, 2, 0, 1, 4, 0); //
ADD_THREADWISE_INST_BY_ID(float, float, float, 2, 0, 1, 2, 1); //
ADD_THREADWISE_INST_BY_ID(float, float, float, 3, 0, 1, 4, 0, 1, 2); // for MAX
ADD_THREADWISE_INST_BY_ID(float, float, float, 3, 0, 1, 4, 0); //
ADD_THREADWISE_INST_BY_ID(float, float, float, 3, 0, 1, 2, 1); //
ADD_THREADWISE_INST_BY_ID(float, float, float, 4, 0, 1, 4, 0, 1, 2); // for AMAX
ADD_THREADWISE_INST_BY_ID(float, float, float, 4, 0, 1, 4, 0); //
ADD_THREADWISE_INST_BY_ID(float, float, float, 4, 0, 1, 2, 1); //
ADD_THREADWISE_INST_BY_ID(float, float, float, 5, 0, 0, 4, 3); // for AVG
ADD_THREADWISE_INST_BY_ID(float, float, float, 5, 0, 0, 4, 1);
ADD_THREADWISE_INST_BY_ID(float, float, float, 5, 0, 0, 2, 1);
ADD_THREADWISE_INST_BY_ID(float, float, float, 7, 0, 0, 4, 3); // for NORM2
ADD_THREADWISE_INST_BY_ID(float, float, float, 7, 0, 0, 4, 1);
ADD_THREADWISE_INST_BY_ID(float, float, float, 7, 0, 0, 2, 1);
ADD_THREADWISE_INST_BY_ID(float, float, float, 2, 0, 0, 4, 3); // for MIN
ADD_THREADWISE_INST_BY_ID(float, float, float, 2, 0, 0, 4, 1);
ADD_THREADWISE_INST_BY_ID(float, float, float, 2, 0, 0, 2, 1);
ADD_THREADWISE_INST_BY_ID(float, float, float, 3, 0, 0, 4, 3); // for MAX
ADD_THREADWISE_INST_BY_ID(float, float, float, 3, 0, 0, 4, 1);
ADD_THREADWISE_INST_BY_ID(float, float, float, 3, 0, 0, 2, 1);
ADD_THREADWISE_INST_BY_ID(float, float, float, 4, 0, 0, 4, 3); // for AMAX
ADD_THREADWISE_INST_BY_ID(float, float, float, 4, 0, 0, 4, 1);
ADD_THREADWISE_INST_BY_ID(float, float, float, 4, 0, 0, 2, 1);
ADD_THREADWISE_INST_BY_ID(float, float, float, 2, 0, 1, 4, 3); // for MIN
ADD_THREADWISE_INST_BY_ID(float, float, float, 2, 0, 1, 4, 1);
ADD_THREADWISE_INST_BY_ID(float, float, float, 2, 0, 1, 2, 1);
ADD_THREADWISE_INST_BY_ID(float, float, float, 3, 0, 1, 4, 3); // for MAX
ADD_THREADWISE_INST_BY_ID(float, float, float, 3, 0, 1, 4, 1);
ADD_THREADWISE_INST_BY_ID(float, float, float, 3, 0, 1, 2, 1);
ADD_THREADWISE_INST_BY_ID(float, float, float, 4, 0, 1, 4, 3); // for AMAX
ADD_THREADWISE_INST_BY_ID(float, float, float, 4, 0, 1, 4, 1);
ADD_THREADWISE_INST_BY_ID(float, float, float, 4, 0, 1, 2, 1);
// clang-format on
} // namespace device_reduce_instance

18
library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32.cpp
View File

@@ -6,16 +6,16 @@ namespace device {
namespace device_reduce_instance {
// clang-format off
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | ReduceDims
ADD_THREADWISE_INST_BY_ID(float, double, float, 0, 0, 0, 4, 0, 1, 2); // for ADD
ADD_THREADWISE_INST_BY_ID(float, double, float, 0, 0, 0, 4, 0);
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | NumReduceDim
ADD_THREADWISE_INST_BY_ID(float, double, float, 0, 0, 0, 4, 3); // for ADD
ADD_THREADWISE_INST_BY_ID(float, double, float, 0, 0, 0, 4, 1);
ADD_THREADWISE_INST_BY_ID(float, double, float, 0, 0, 0, 2, 1);
ADD_THREADWISE_INST_BY_ID(float, double, float, 5, 0, 0, 4, 0, 1, 2); // for AVG
ADD_THREADWISE_INST_BY_ID(float, double, float, 5, 0, 0, 4, 0); //
ADD_THREADWISE_INST_BY_ID(float, double, float, 5, 0, 0, 2, 1); //
ADD_THREADWISE_INST_BY_ID(float, double, float, 7, 0, 0, 4, 0, 1, 2); // for NORM2
ADD_THREADWISE_INST_BY_ID(float, double, float, 7, 0, 0, 4, 0); //
ADD_THREADWISE_INST_BY_ID(float, double, float, 7, 0, 0, 2, 1); //
ADD_THREADWISE_INST_BY_ID(float, double, float, 5, 0, 0, 4, 3); // for AVG
ADD_THREADWISE_INST_BY_ID(float, double, float, 5, 0, 0, 4, 1);
ADD_THREADWISE_INST_BY_ID(float, double, float, 5, 0, 0, 2, 1);
ADD_THREADWISE_INST_BY_ID(float, double, float, 7, 0, 0, 4, 3); // for NORM2
ADD_THREADWISE_INST_BY_ID(float, double, float, 7, 0, 0, 4, 1);
ADD_THREADWISE_INST_BY_ID(float, double, float, 7, 0, 0, 2, 1);
// clang-format on
} // namespace device_reduce_instance

54
library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64.cpp
View File

@@ -6,34 +6,34 @@ namespace device {
namespace device_reduce_instance {
// clang-format off
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | ReduceDims
ADD_THREADWISE_INST_BY_ID(double, double, double, 0, 0, 0, 4, 0, 1, 2); // for ADD
ADD_THREADWISE_INST_BY_ID(double, double, double, 0, 0, 0, 4, 0);
// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | NumReduceDim
ADD_THREADWISE_INST_BY_ID(double, double, double, 0, 0, 0, 4, 3); // for ADD
ADD_THREADWISE_INST_BY_ID(double, double, double, 0, 0, 0, 4, 1);
ADD_THREADWISE_INST_BY_ID(double, double, double, 0, 0, 0, 2, 1);
ADD_THREADWISE_INST_BY_ID(double, double, double, 5, 0, 0, 4, 0, 1, 2); // for AVG
ADD_THREADWISE_INST_BY_ID(double, double, double, 5, 0, 0, 4, 0); //
ADD_THREADWISE_INST_BY_ID(double, double, double, 5, 0, 0, 2, 1); //
ADD_THREADWISE_INST_BY_ID(double, double, double, 7, 0, 0, 4, 0, 1, 2); // for NORM2
ADD_THREADWISE_INST_BY_ID(double, double, double, 7, 0, 0, 4, 0); //
ADD_THREADWISE_INST_BY_ID(double, double, double, 7, 0, 0, 2, 1); //
ADD_THREADWISE_INST_BY_ID(double, double, double, 2, 0, 0, 4, 0, 1, 2); // for MIN
ADD_THREADWISE_INST_BY_ID(double, double, double, 2, 0, 0, 4, 0); //
ADD_THREADWISE_INST_BY_ID(double, double, double, 2, 0, 0, 2, 1); //
ADD_THREADWISE_INST_BY_ID(double, double, double, 3, 0, 0, 4, 0, 1, 2); // for MAX
ADD_THREADWISE_INST_BY_ID(double, double, double, 3, 0, 0, 4, 0); //
ADD_THREADWISE_INST_BY_ID(double, double, double, 3, 0, 0, 2, 1); //
ADD_THREADWISE_INST_BY_ID(double, double, double, 4, 0, 0, 4, 0, 1, 2); // for AMAX
ADD_THREADWISE_INST_BY_ID(double, double, double, 4, 0, 0, 4, 0); //
ADD_THREADWISE_INST_BY_ID(double, double, double, 4, 0, 0, 2, 1); //
ADD_THREADWISE_INST_BY_ID(double, double, double, 2, 0, 1, 4, 0, 1, 2); // for MIN
ADD_THREADWISE_INST_BY_ID(double, double, double, 2, 0, 1, 4, 0); //
ADD_THREADWISE_INST_BY_ID(double, double, double, 2, 0, 1, 2, 1); //
ADD_THREADWISE_INST_BY_ID(double, double, double, 3, 0, 1, 4, 0, 1, 2); // for MAX
ADD_THREADWISE_INST_BY_ID(double, double, double, 3, 0, 1, 4, 0); //
ADD_THREADWISE_INST_BY_ID(double, double, double, 3, 0, 1, 2, 1); //
ADD_THREADWISE_INST_BY_ID(double, double, double, 4, 0, 1, 4, 0, 1, 2); // for AMAX
ADD_THREADWISE_INST_BY_ID(double, double, double, 4, 0, 1, 4, 0); //
ADD_THREADWISE_INST_BY_ID(double, double, double, 4, 0, 1, 2, 1); //
ADD_THREADWISE_INST_BY_ID(double, double, double, 5, 0, 0, 4, 3); // for AVG
ADD_THREADWISE_INST_BY_ID(double, double, double, 5, 0, 0, 4, 1);
ADD_THREADWISE_INST_BY_ID(double, double, double, 5, 0, 0, 2, 1);
ADD_THREADWISE_INST_BY_ID(double, double, double, 7, 0, 0, 4, 3); // for NORM2
ADD_THREADWISE_INST_BY_ID(double, double, double, 7, 0, 0, 4, 1);
ADD_THREADWISE_INST_BY_ID(double, double, double, 7, 0, 0, 2, 1);
ADD_THREADWISE_INST_BY_ID(double, double, double, 2, 0, 0, 4, 3); // for MIN
ADD_THREADWISE_INST_BY_ID(double, double, double, 2, 0, 0, 4, 1);
ADD_THREADWISE_INST_BY_ID(double, double, double, 2, 0, 0, 2, 1);
ADD_THREADWISE_INST_BY_ID(double, double, double, 3, 0, 0, 4, 3); // for MAX
ADD_THREADWISE_INST_BY_ID(double, double, double, 3, 0, 0, 4, 1);
ADD_THREADWISE_INST_BY_ID(double, double, double, 3, 0, 0, 2, 1);
ADD_THREADWISE_INST_BY_ID(double, double, double, 4, 0, 0, 4, 3); // for AMAX
ADD_THREADWISE_INST_BY_ID(double, double, double, 4, 0, 0, 4, 1);
ADD_THREADWISE_INST_BY_ID(double, double, double, 4, 0, 0, 2, 1);
ADD_THREADWISE_INST_BY_ID(double, double, double, 2, 0, 1, 4, 3); // for MIN
ADD_THREADWISE_INST_BY_ID(double, double, double, 2, 0, 1, 4, 1);
ADD_THREADWISE_INST_BY_ID(double, double, double, 2, 0, 1, 2, 1);
ADD_THREADWISE_INST_BY_ID(double, double, double, 3, 0, 1, 4, 3); // for MAX
ADD_THREADWISE_INST_BY_ID(double, double, double, 3, 0, 1, 4, 1);
ADD_THREADWISE_INST_BY_ID(double, double, double, 3, 0, 1, 2, 1);
ADD_THREADWISE_INST_BY_ID(double, double, double, 4, 0, 1, 4, 3); // for AMAX
ADD_THREADWISE_INST_BY_ID(double, double, double, 4, 0, 1, 4, 1);
ADD_THREADWISE_INST_BY_ID(double, double, double, 4, 0, 1, 2, 1);
// clang-format on
} // namespace device_reduce_instance