squall/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
473 Commits 1 Branch 0 Tags 45 MiB
2f589ffa76
Commit Graph

473 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
mengchi.hmc
7ec3a87f22 support unalignment input for conv2d fprop stage=2 Fix for issue #242 2021-04-21 14:40:05 +08:00
KeDengMS
0b74c8f473 Address CR 2021-04-19 23:36:06 +00:00
KeDengMS
83036ed646 More clean up 2021-04-18 04:29:20 +00:00
KeDengMS
b7e43f5eb9 Clean up 2021-04-18 04:24:25 +00:00
KeDengMS
5c62d892fa Add test 2021-04-18 04:09:34 +00:00
KeDengMS
41a31b404b Fixes to Gelu for half and fusion 2021-04-17 22:10:19 +00:00
Peter Han
7320aee17d Typo fix issue#236 
Signed-off-by: Peter Han <fujun.han@iluvatar.ai>
 2021-04-15 15:08:35 +08:00
Peter Han
2142a05d9d tranpose.h update based on issue#233 
1. Add 'pragma once' preprocess directive
 2. Replace prmt PTX with __byte_perm intrinsic

Signed-off-by: Peter Han <fujun.han@iluvatar.ai>
 2021-04-14 19:58:00 +08:00
Haicheng Wu
c77a524459
Merge pull request #230 from mani-ananth/master 
Fix for issue #221
 2021-04-09 14:45:55 -04:00
Manikandan Ananth
fac6680f31 Merge branch 'master' of github.com:NVIDIA/cutlass 2021-04-09 11:36:31 -07:00
Manikandan Ananth
08993707da fixing functional bug in fused epilogue 2021-04-09 11:36:03 -07:00
Haicheng Wu
c805593ebe
Merge pull request #228 from mani-ananth/master 
Fix for issue#224 and issue#225
 2021-04-08 10:08:13 -04:00
Manikandan Ananth
26556d7206 fix a broken sparse gemm example. found by the community. 2021-04-07 13:32:55 -07:00
Manikandan Ananth
4839b6cb61 add 2stage fprop 3d into default file 2021-04-07 13:29:32 -07:00
Haicheng Wu
d97214987a
Merge pull request #220 from Peter9606/wrong-stride-array-definition 
Bugfix: typo, make reduction device cases passed
 2021-04-02 08:43:52 -04:00
Haicheng Wu
b0bbc6d548
Merge pull request #219 from mani-ananth/master 
Fix for issue #211
 2021-04-02 08:42:09 -04:00
Peter Han
7074047a54 Bugfix: typo, make reduction device cases passed 
Signed-off-by: Peter Han <fujun.han@iluvatar.ai>
 2021-04-02 09:35:23 +08:00
Manikandan Ananth
75a4737cfe Fix for public issue #211 
- Add a slice-K tile size to the profiler
- fix num warps calculations in implicit gemm header
 2021-04-01 14:42:00 -07:00
Haicheng Wu
8a3e4b8d02
Merge pull request #214 from Peter9606/separate-stream-error 
Bugfix: memsetAsync uses wrong default stream
 2021-03-24 12:09:01 -04:00
Peter Han
6a6b4028bd Revert wrong fix of params.update in GemmUniversalBase 
Signed-off-by: Peter Han <fujun.han@iluvatar.ai>
 2021-03-23 23:20:40 +08:00
Peter Han
92393b2676 Bugfix: memsetAsync uses wrong default stream 
Signed-off-by: Peter Han <fujun.han@iluvatar.ai>
 2021-03-23 21:11:42 +08:00
Haicheng Wu
50bf00e5f2
Merge pull request #193 from Peter9606/public_shape_type_from_Mma_HFMA2 
HFMA2 Convolutions for SM60 onwards
 2021-03-05 21:38:59 -05:00
Manish Gupta
4cd004ead1 fix test name to optimized and instance large tile sizes to speed unit tests 2021-03-05 13:32:36 -08:00
Peter Han
6c4539e372 Make arch tag of test cases more precisely to SM60 
Signed-off-by: Peter Han <fujun.han@iluvatar.ai>
 2021-03-05 10:53:26 +08:00
Peter Han
a3639ab1a0 Append fp16 test case to verify Mma_HFMA2 
Signed-off-by: Peter Han <fujun.han@iluvatar.ai>
 2021-03-04 18:17:57 +08:00
Peter Han
169181f30f Make Shape public from Mma_HFMA2. 
Signed-off-by: Peter Han <fujun.han@iluvatar.ai>
 2021-03-04 11:05:16 +08:00
Haicheng Wu
0f1056390d
Create PUBLICATIONS.md (#189) 2021-03-03 11:17:40 -08:00
Haicheng Wu
34a42e5620
Update generator.py (#192) 2021-03-02 12:21:48 -08:00
Dustyn Blasig
8f09b82b12
Merge pull request #187 from NVIDIA/cutlass_2.5 
CUTLASS 2.5.0
 2021-02-26 23:56:04 -06:00
Andrew Kerr
200a5a5146 Enabled reduction unit tests. 2021-02-26 15:46:57 -05:00
Andrew Kerr
746b7b3247 Enabled tensor reduction kernels. 2021-02-26 15:32:19 -05:00
Andrew Kerr
abdf16a4d9 Updated release notes. 2021-02-26 13:55:04 -05:00
Andrew Kerr
0e13748649 CUTLASS 2.5 2021-02-26 09:58:26 -05:00
Manish Gupta
ccb697bac7 cutlass 2.4 documentation only update 2020-11-23 06:59:45 -06:00
Yang Wang
e6bcdc60cf
fix broken links (#148) 2020-11-19 21:46:54 -08:00
Manish Gupta
6615010cd0
CUTLASS 2.4 (Implicit GEMM convolution) (#147) 
CUTLASS 2.4 (Implicit GEMM Convolution)

Co-authored-by: Manish Gupta <manigupta@nvidia.com>, Haicheng Wu <haichengw@nvidia.com>, Dustyn Blasig <dblasig@nvidia.com>, Andrew Kerr <akerr@nvidia.com>
 2020-11-19 21:25:25 -08:00
Dustyn Blasig
c2b80ad4e4
Merge pull request #135 from NVIDIA/cutlass_2.3_final 
CUTLASS 2.3.0
 2020-09-25 13:25:26 -05:00
akerr
37a8f9e598 CUTLASS 2.3.0 final. 2020-09-25 10:34:46 -07:00
Andrew Kerr
c53f3339bb
CUTLASS 2.3 initial commit (#134) 
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.
 2020-09-23 14:00:58 -07:00
hwu36
4dac7490e6
Typoes (#107) 
* Update splitk_gemm.cu

* Update gemm_bias_relu.cu

* Update mma_sm75.h
 2020-07-13 14:25:52 -07:00
Andrew Kerr
fd7e058d0c
Added examples to enable the unity build (#102) 
* 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.
 2020-06-17 07:09:18 -07:00
Andrew Kerr
1ab1027954
Updated mma_sm80.h to avoid perf penalty due to reinterpret_cast<>. (#100) 
- 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
 2020-06-15 10:47:01 -07:00
Andrew Kerr
86931fef85
CUTLASS 2.2 (#96) 
Adds support for NVIDIA Ampere Architecture features. CUDA 11 Toolkit recommended.
 2020-06-08 16:17:35 -07:00
Vijay Thakkar
e33d90b361
update tools/library/CMakeLists to require python 3.6 according to #70 (#82) 
#70 only updates the documentation. This commit reflects this bump in python version to the CMake configuration as well.
 2020-04-08 10:54:36 -07:00
Andrew Kerr
96dab34ad9
CUTLASS 2.1 (#83) 
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
 2020-04-07 13:51:25 -07:00
Andrew Kerr
7c0cd26d13
Need Python 3.6 to use enum.auto() (#70) 2019-11-22 09:39:12 -08:00
Andrew Kerr
45ecbc885b
Removed redundant conjugation operations from matrix_traits. (#65) 2019-11-20 11:27:13 -08:00
Andrew Kerr
8aca98f9a7
Improved formatting, clarity, and content of several documents. (#64) 
* Improved formatting, clarity, and content of several documents.
 2019-11-20 10:42:15 -08:00
Dustyn Blasig
f4d9c8f755 Clang GPU compilation requires explicit CUDACC version flags (#63) 2019-11-20 09:52:11 -08:00
Andrew Kerr
fb335f6a5f
CUTLASS 2.0 (#62) 
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.
 2019-11-19 16:55:34 -08:00