leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 26 Packages Projects Releases Wiki Activity
547 Commits 1 Branch 1 Tag
0837a2a00a02cf53ff2a36bb9630a39dbf772b5c
Commit Graph
8 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Manish Gupta 033d9efd2d [Documentation] Fixes the confusion between concatenated vs. composed layout in CuTe documentation (#1498) 
* Update 02_layout_algebra.md

* Update 02_layout_algebra.md
 2024-05-02 15:35:12 -04:00
Manish Gupta 5ae8133cfa Doc only change changelog 3.3 (#1180) 2023-11-13 13:29:22 -05:00
Manish Gupta 757275f279 Adding more Threadblock Tiles for Mixed-input TensorOp (BF16 * S8) in cutlass_library (#1132) 
* Adding more tiles in the cutlass_library for mixed-input support.

* fix rebase issue

* more tiles to upcast a
 2023-10-13 11:33:15 -04:00
Manish Gupta ff02da2667 Fx parallel split-k (#1116) 2023-10-06 12:02:40 -04:00
Manish Gupta 7d8317a63e Support for Mixed Input TensorOp (#1084) 
* 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
 2023-09-27 11:18:30 -04:00
Manish Gupta 5cd735c48e Fix Parallel Split-K on Gemm Operation Profiler (#1109) 
* Debug and fix for parallel split-k in profiler

* restore debug files and remove prints
 2023-09-26 17:28:00 -04:00
Manish Gupta b97404837e Adding 128x256 tile for 16b input datatype WGMMA gemm (#950) 2023-05-17 17:13:23 -04:00
Manish Gupta 660a05f581 fix split_k_mode and add reduction kernel for f16 input/accum/output (#896) 2023-03-30 15:31:08 -04:00