* Allow per-column bias in EpilogueTensorBroadcast
EpilogueTensorBroadcast only supports per-row vector broadcast, because
the bias stride is hardcoded.
It can easily support both if the bias stride is made conditional, and
the original behavior is maintained by defaulting to per-row.
* Add unit test for EpilogueTensorBroadcast with per-col bias
---------
Co-authored-by: Ali Hassani <ahassanijr@gmail.com>
Co-authored-by: Ali Hassani <ali@hippoml.com>
* Remove unused variables
* Qualify calls to make_fragment_? from templated base class.
Fixes clang build error.
* Add missing `#include <cstdio>`
* Various changes to fix clang compile errors.
* More changes to fix clang build.
Remaining issues:
- `params` initializer of `CollectiveEpilogue`.
- `ops` initializer of `Sm90VisitorImplBase`.
- `__usAtomicCAS` needs to be added to clang upstream.
* Fix remaining clang build issues.
* Qualify `cute::rank()` calls.
* Qualify some more calls that are otherwise ambiguous between `cute` and `std` namespace.
* Double-escape special registers in inline asm.
* small change
---------
Co-authored-by: Haicheng Wu <haichengw@nvidia.com>
* Release 3.3.0
Adds support for mixed precision GEMMs On Hopper and Ampere
Adds support for < 16B aligned GEMMs on Hopper
Enhancements to EVT
Enhancements to Python interface
Enhancements to Sub-byte type handling in CuTe
Several other bug-fixes and performance improvements.
* minor doc update
* Passing warp-level mixed input F16*(S8/U8) tests
* passing device-level mixed input F16*(S8/U8) tests
* add to profiler - I8 (111 TFLOPs), U (123 TFLOPs)
* fast numeric conversions (I8 = 132 TFLOPs, U8 = 148 TFLOPs)
* Speedup reference compilation (REVERT THIS COMMIT)
* wider_add.u32_packed_sub.f16x2 (I8 = 132TFLOP/s, U8 = 170 TFLOP/s)
* Improve s8->f16 cvt and support bf16*u8 @158 TFLOPs
* BF16 * S8 (142 TFLOPs)
* Handle mixed-input upcast on OperandA (Support [S8|U8]*[F16|BF16]
* rename OpMultiplyAddMixedInput to OpMultiplyAddMixedInputUpcast
* Add device-level test and profiler support for upcast on operand A
* Move shfl before the cvt and reduce #shfls by 1/2
* fix smem_usage calculation for mixed_input types
* uncomment the stuff (getting ready for merge)
* profiler changes and mixed-input reference
* mixed input reference are in a new file
* use platform instead of std
* comments and typo only
* Use CreateGemmOperator and delete CreateMixedInputGemmOperator
* copyright for new files
* rebase follow-up
* Remove redundant <fstream> includes
* Fix fstream in examples/
* Fix <fstream> in test/
* Use consistent order for <fstream> (always after <iostream>)
* Remove an unneeded include in a file where std::ofstream usage is commented out
Co-authored-by: Ivan Komarov <dfyz@yandex-team.ru>
* Actually use float accumulation in gemm_f16t_f16t_f16t_wmma_tensor_op_f32_sm70.cu
As title
* Update gemm_f16t_f16t_f16t_wmma_tensor_op_f32_sm70.cu
change the missing one
Co-authored-by: Haicheng Wu <57973641+hwu36@users.noreply.github.com>
* Add epilogue functor for residual block fusion
* Do not run split-k tests when ActivationOp is not Identity
* explain TestSplitK param
* return early
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
