squall/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

Enabled reduction unit tests.

Browse Source
This commit is contained in:
Andrew Kerr 2021-02-26 15:46:57 -05:00
parent 746b7b3247
commit 200a5a5146
3 changed files with 7 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
CHANGELOG.md
View File

@ -5,8 +5,8 @@
## [2.5.0](https://github.com/NVIDIA/cutlass/releases/tag/v2.5.0) (2021-02-26) ## [2.5.0](https://github.com/NVIDIA/cutlass/releases/tag/v2.5.0) (2021-02-26)
* Tensor reductions * Tensor reductions
* _m_-to-_n_ reductions of tensors with affine layout * _m_-to-_n_ reductions of tensors with affine layout
* [Specializations](/test/unit/reduction/tensor_reduce_contiguous.cu) for reductions including contiguous dimension * [Specializations](/test/unit/reduction/device/tensor_reduce_contiguous.cu) for reductions including contiguous dimension
* [Specializations](/test/unit/reduction/tensor_reduce_strided.cu) for reductions excluding contiguous dimension * [Specializations](/test/unit/reduction/device/tensor_reduce_strided.cu) for reductions excluding contiguous dimension
* Custom reduction functors such as `cutlass::logical_and` * Custom reduction functors such as `cutlass::logical_and`
* Large tensor support, up to 2^63 elements (however, each dimension is limited to an extent of 2^31) * Large tensor support, up to 2^63 elements (however, each dimension is limited to an extent of 2^31)
* Optimizations for 3-D convolution * Optimizations for 3-D convolution

2
README.md
View File

@ -36,7 +36,7 @@ supported at each level of the execution model hierarchy.
# What's New in CUTLASS 2.5 # What's New in CUTLASS 2.5
CUTLASS 2.5 is a minor update to CUTLASS adding: CUTLASS 2.5 is a minor update to CUTLASS adding:
- [Tensor reductions](/test/unit/reduction/tensor_reduce_contiguous.cu) - [Tensor reductions](/test/unit/reduction/device/tensor_reduce_contiguous.cu)
- [Optimizations for 3-D convolution](include/cutlass/conv/threadblock/conv3d_fprop_activation_tile_access_iterator_optimized.h) - [Optimizations for 3-D convolution](include/cutlass/conv/threadblock/conv3d_fprop_activation_tile_access_iterator_optimized.h)
- [Fused Convolution+Convolution example](/examples/13_two_tensor_op_fusion/README.md) - [Fused Convolution+Convolution example](/examples/13_two_tensor_op_fusion/README.md)
- See the [CHANGELOG](CHANGELOG.md) for more details - See the [CHANGELOG](CHANGELOG.md) for more details

4
test/unit/reduction/CMakeLists.txt
View File

@ -22,11 +22,14 @@
add_subdirectory(thread) add_subdirectory(thread)
add_subdirectory(kernel) add_subdirectory(kernel)
add_subdirectory(device)
add_custom_target( add_custom_target(
cutlass_test_unit_reduction cutlass_test_unit_reduction
DEPENDS DEPENDS
cutlass_test_unit_reduction_thread cutlass_test_unit_reduction_thread
cutlass_test_unit_reduction_kernel cutlass_test_unit_reduction_kernel
cutlass_test_unit_reduction_device
) )
add_custom_target( add_custom_target(
@ -34,4 +37,5 @@ add_custom_target(
DEPENDS DEPENDS
test_unit_reduction_thread test_unit_reduction_thread
test_unit_reduction_kernel test_unit_reduction_kernel
test_unit_reduction_device
) )