leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 29 Packages Projects Releases Wiki Activity

CUTLASS 2.7 (#318)

Browse Source 
CUTLASS 2.7

Mainloop fusion for GEMM: summation over A or B
Strided DGRAD (optimized iterators)
Half-precision GELU_taylor activation functions
Use these when accumulation and epilogue compute types are all cutlass::half_t
Tuning and bug fixes to fused GEMM + GEMM example
Support for smaller than 128b aligned Convolutions: see examples
Caching of results to accelerate Convolution unit tests
Can be enabled or disabled by running cmake .. -DCUTLASS_TEST_ENABLE_CACHED_RESULTS=OFF
Corrections and bug fixes reported by the CUTLASS community
Thank you for filing these issues!

authored-by: Haicheng Wu haichengw@nvidia.com, Manish Gupta manigupta@nvidia.com, Dustyn Blasig dblasig@nvidia.com, Andrew Kerr akerr@nvidia.com
This commit is contained in:
Manish Gupta
2021-09-20 11:02:22 -07:00
committed by GitHub
parent 9ac255863f
commit 2e07c4cc2f
62 changed files with 5611 additions and 186 deletions
Download Patch File Download Diff File Expand all files Collapse all files
CHANGELOG.md
+11 -1
View File
@@ -1,6 +1,16 @@
# NVIDIA CUTLASS Changelog
# CUTLASS 2.x
## [2.7.0](https://github.com/NVIDIA/cutlass/releases/tag/v2.7.0) (2021-09-24)
* Mainloop fusion for GEMM: [summation over A or B](/examples/23_ampere_gemm_operand_reduction_fusion/ampere_gemm_operand_reduction_fusion.cu)
* [Strided DGRAD (optimized iterators)](/include/cutlass/conv/kernel/default_conv2d_dgrad.h)
* [Half-precision GELU_taylor activation functions](/include/cutlass/epilogue/thread/activation.h#L196)
* Use these when accumulation and epilogue compute types are all `cutlass::half_t`
* Tuning and bug fixes to [fused GEMM + GEMM example](/examples/13_two_tensor_op_fusion/)
* Support for smaller than 128b aligned Convolutions: [see examples](test/unit/conv/device/conv2d_fprop_implicit_gemm_f16nhwc_f16nhwc_f16nhwc_tensor_op_f16_sm80.cu#L272)
* Caching of results to accelerate Convolution [unit tests](test/unit/conv/device/cache_testbed_output.h)
* Can be enabled or disabled by running `cmake .. -DCUTLASS_TEST_ENABLE_CACHED_RESULTS=OFF`
* Corrections and bug fixes reported by the CUTLASS community
* Thank you for filing these issues!
## [2.6.1](https://github.com/NVIDIA/cutlass/releases/tag/v2.6.1) (2021-09-03)
* Arbitrary padding and striding for CUTLASS Strided DGRAD Convolution operator (Analytic Iterators)