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

Update README.md

Browse Source
This commit is contained in:
Haicheng Wu 2022-06-27 23:25:26 -04:00 committed by GitHub
parent 9ab9110168
commit ba18ea9c32
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 11 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
README.md
View File

@ -46,12 +46,13 @@ CUTLASS 2.9 is an update to CUTLASS adding:
- [CUTLASS Python](/examples/40_cutlass_py) demonstrating JIT compilation of CUTLASS kernels and a Python-based runtime using [CUDA Python](https://developer.nvidia.com/cuda-python)
- [GEMM + Softmax example](/examples/35_gemm_softmax)
- [Gather and Scatter Fusion with GEMM](/examples/36_gather_scatter_fusion) can gather inputs and scatters outputs based on indices vectors in the same GEMM kernel.
- [Back-to-back GEMM/CONV](examples/13_two_tensor_op_fusion) fully supports buffering the previous GEMM/CONV results in the shared memory for the latter one to use.
- [Back-to-back GEMM/CONV](examples/13_two_tensor_op_fusion) fully supports buffering the first GEMM/CONV results in the shared memory for the latter one to use. Bias Vector add is also supported in the first GEMM/CONV.
- [Transposed Convolution](/examples/34_transposed_conv2d) (a.k.a Deconvolution) support which reuses Dgrad implementation.
- [Utility functions](/tools/util/include/cutlass/util) that can pad NHWC and convert between NCHW and NHWC.
- [Small alignment implicit gemm](https://github.com/NVIDIA/cutlass/issues/242) support for Fprop/Dgrad/Wgrad so that padding is no longer mandated to use tensor cores.
- Epilogue enhancement with performance improvement, more activation functions, and more fusion patterns.
- Optimal performance using [CUDA 11.6u2](https://developer.nvidia.com/cuda-downloads)
- [Group GEMM](/examples/24_gemm_grouped) thread block number calculation fix.
- Optimal performance using [CUDA 11.7](https://developer.nvidia.com/cuda-downloads)
- [Parallel GEMM splitk](https://github.com/NVIDIA/cutlass/pull/277) support in the CUTLASS profiler.
- Updates and bugfixes from the community (thanks!)
- **Deprecation announcement:** CUTLASS plans to deprecate the following:
@ -75,6 +76,13 @@ and an [NVIDIA GeForce 2080 Ti](https://www.nvidia.com/en-us/geforce/graphics-ca
compiled with the [CUDA 11.5 Toolkit](https://developer.nvidia.com/cuda-downloads). Tensor Core operations are implemented using CUDA's
[mma instruction](https://docs.nvidia.com/cuda/parallel-thread-execution/index.html#warp-level-matrix-instructions-mma).
<p align="center"><img src=/media/images/cutlass-2.9-implicit-gemm-performance.png></p>
When using CUTLASS building blocks to construct device-wide implicit gemm (Fprop, Dgrad, and Wgrad)
kernels, CUTLASS performance is also comparable to cuDNN when running Resnet-50 layers on an [NVIDIA A100](https://www.nvidia.com/en-us/data-center/a100/)
as shown in the above figure. Tensor Core operations are still implemented using CUDA's
[mma instruction](https://docs.nvidia.com/cuda/parallel-thread-execution/index.html#warp-level-matrix-instructions-mma).
# Compatibility
CUTLASS requires a C++11 host compiler and