leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 26 Packages Projects Releases Wiki Activity

Updates for CUTLASS 3.5.0 (#1468)

Browse Source
This commit is contained in:
Vijay Thakkar
2024-04-11 21:33:40 -04:00
committed by GitHub
parent a40e08e9d5
commit 7d49e6c7e2
171 changed files with 7526 additions and 1888 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+7 -4
View File
@@ -2,7 +2,7 @@
# CUTLASS 3.5
_CUTLASS 3.5 - March 2024_
_CUTLASS 3.5 - April 2024_
CUTLASS is a collection of CUDA C++ template abstractions for implementing
high-performance matrix-matrix multiplication (GEMM) and related computations at all levels
@@ -45,18 +45,21 @@ In addition to GEMMs, CUTLASS implements high-performance convolution via the im
CUTLASS 3.5 is an update to CUTLASS adding:
- Implicit GEMM Convolutions targeting Hopper SM90A via WGMMA + [TMA im2col](./include/cute/atom/copy_traits_sm90_im2col.hpp)
- Implicit GEMM Convolutions targeting Hopper SM90A via WGMMA + [TMA im2col](./include/cute/atom/copy_traits_sm90_im2col.hpp).
+ Native implementation in CUTLASS 3.x using CuTe, mirroring the [same design hierarchy as that of GEMMs](./media/docs/gemm_api_3x.md).
+ Support for 1D, 2D, and 3D convolutions in a [rank-agnostic fashion](./include/cutlass/conv/convnd_problem_shape.hpp).
+ Support for [Fprop](./test/unit/conv/device_3x/fprop/sm90_conv3d_fprop_implicit_gemm_s8_s8_s32_tensorop_s32.cu), [Dgrad](./test/unit/conv/device_3x/dgrad/sm90_conv2d_dgrad_implicit_gemm_f16_f16_f32_tensorop_f16.cu), and [Wgrad](./test/unit/conv/device_3x/wgrad/sm90_conv1d_wgrad_implicit_gemm_f16_f16_f32_tensorop_f16.cu) algorithms
+ Support for [Fprop](./test/unit/conv/device_3x/fprop/sm90_conv3d_fprop_implicit_gemm_s8_s8_s32_tensorop_s32.cu), [Dgrad](./test/unit/conv/device_3x/dgrad/sm90_conv2d_dgrad_implicit_gemm_f16_f16_f32_tensorop_f16.cu), and [Wgrad](./test/unit/conv/device_3x/wgrad/sm90_conv1d_wgrad_implicit_gemm_f16_f16_f32_tensorop_f16.cu) algorithms.
+ [CUTLASS profiler support](./python/cutlass_library/conv3x_emitter.py) for 2D and 3D convolutions implemented via the 3.x API.
+ NOTE: this is a beta release. Further updates to CUTLASS will include major performance improvements, feature enablement, and possible breaking changes to the API until 3.7 release. Your feedback is welcome on the design!
- Support for [Ada (SM89) FP8 tensor cores via the 2.x API](./examples/58_ada_fp8_gemm/ada_fp8_gemm.cu). Requires CUDA 12.4 or newer.
- [Ampere gather/scatter convolution example](./examples/59_ampere_gather_scatter_gemm/README.md) in CuTe and CUTLASS 3.x
- [Ampere gather/scatter convolution example](./examples/59_ampere_gather_scatter_gemm/README.md) in CuTe and CUTLASS 3.x.
+ Showcasing how custom kernels can be written and optimized using CUTLASS 3.x and CuTe and the general strategy for implementing convolutions as specializations of GETTs.
+ Implementation of a coarse grained sparse gather/scatter kernel achieving peak performance on Ampere class tensor cores.
- 32x and 16x tile sizes are added to CUTLASS 2.x to improve the performance of narrow-tall and wide-short matrices.
- Updates to CuTe documentation for [`cute::Tensor<>`](./media/docs/cute/03_tensor.md), [MMA atoms](./media/docs/cute/0t_mma_atom.md), and an overhauled [CuTe GEMM tutorial series](./examples/cute/tutorial).
- Extensions to CuTe to support [L2 prefetching](./include/cute/algorithm/prefetch.hpp) and [TMA store+reductions](./include/cute/arch/copy_sm90_tma.hpp#L1337).
- Remove C++11 requirement on a few CUTLASS 2.x API header files. All CUTLASS files now require C++17.
- Fixes to greatly reduce build warnings.
- Updates and bugfixes from the community (thanks!)
Minimum requirements: