* add split k wgrad example
* wgrad done
* begin transposed conv2d example
* update transposed conv2d example and add ref check
* update doc for conv2d transpose example
* add license
* add wgrad doc
* more clarification on GEMM output type
* typo fix
* clean up indent
* address comments
* rename example numbers to 34 and 35
* GEMM -> Implicit GEMM
* Revert "rename example numbers to 34 and 35"
This reverts commit 551a808c227216e9e38d4472ba8ff020557b8500.
* transposed_conv2d is 34
* add compiler and device version check to exit gracefully
Co-authored-by: Haicheng Wu <haichengw@nvidia.com>
When split-k is enabled, we should set alpha to 1 and beta to 0 for the
split-k gemm kernel.
The fix was from hwu36. I only did fixed some minor typos along with his
fix.
* Removed trivial copy constructors on parameter classes to enable device-side launch of CUTLASS kernels
* Added SFINAE to the `TensorRef(NonConstTensorRef const&)` constructor to avoid making it a copy-constructor for device code
* std => platform
* fix affine2
* really fix affine2
Co-authored-by: Haicheng Wu <haichengw@nvidia.com>
* Fix the build of cutlass/gemm/device/gemm_array.h and add a demo for GemmArray
* Add a reference to GemmArray to the docs
Co-authored-by: Ivan Komarov <dfyz@yandex-team.ru>
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
CUTLASS 2.3 adds GEMMs targeting Sparse Tensor Cores on the NVIDIA Ampere Architecture, fast SGEMM, and small matrix classes, bug fixes, and performance enhancements.
* Updated documentation of fused GEMM example and removed UNITY BUILD batch size. The default batch size when unity build is enabled tends to be favorable.
- Updated mma_sm80.h to avoid perf penalty due to reinterpret_cast<>.
- Enhancement to CUTLASS Utility Library's HostTensorPlanarComplex template to support copy-in and copy-out
- Added test_examples target to build and test all CUTLASS examples
- Minor edits to documentation to point to GTC 2020 webinar
CUTLASS 2.1 contributes:
- BLAS-style host-side API added to CUTLASS Library
- Planar Complex GEMM kernels targeting Volta and Turing Tensor Cores
- Minor enhancements and bug fixes
CUTLASS 2.0
Substantially refactored for
- Better performance, particularly for native Turing Tensor Cores
- Robust and durable templates spanning the design space
- Encapsulated functionality embodying modern C++11 programming techniques
- Optimized containers and data types for efficient, generic, portable device code
Updates to:
- Quick start guide
- Documentation
- Utilities
- CUTLASS Profiler
Native Turing Tensor Cores
- Efficient GEMM kernels targeting Turing Tensor Cores
- Mixed-precision floating point, 8-bit integer, 4-bit integer, and binarized operands
Coverage of existing CUTLASS functionality:
- GEMM kernels targeting CUDA and Tensor Cores in NVIDIA GPUs
- Volta Tensor Cores through native mma.sync and through WMMA API
- Optimizations such as parallel reductions, threadblock rasterization, and intra-threadblock reductions
- Batched GEMM operations
- Complex-valued GEMMs
Note: this commit and all that follow require a host compiler supporting C++11 or greater.
