squall/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
182 Commits 1 Branch 0 Tags 45 MiB
288af365db
Commit Graph

182 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Andrew Kerr
288af365db
Added missing synchronization to avoid WAR hazards between tiles. (#386) 2021-12-20 08:34:08 -08:00
masahi
0dc3ba60b3
Refactor GELU and Sigmoid epilogue to use a common template (and add SiLu, Hardswish epilogue) (#379) 
* Support half precision sigmoid activation

* introduce a vectorized variant using fast_tanh

* refactored sigmoid using the new interface

* refactored gelu

* add silu activation

* add hardswish

* remove sigmoid for now

* add description to silu and hardswish, and other doc update

* Do not ignore Round

* use constant N

* Set isHeavy = true in sigmoid and silu epilogue
 2021-12-18 14:58:15 -05:00
Andrew Kerr
ec4f7e5194
Updates to fused epilogue (#383) 
* Enhancements and fixes to fused GEMM and Convolution epilogue.
* Need to explicitly list cudart as unit test library dependency.
 2021-12-17 16:04:43 -05:00
Andrew Kerr
4e666e1dfd
Updated README and added issue templates. (#382) 2021-12-17 09:26:20 -05:00
Haicheng Wu
3799e12f25
Merge pull request #381 from Peter9606/update-makefile-version 
Update project version to 2.8.0 in CMakeLists.txt
 2021-12-16 21:54:57 -05:00
Peter Han
fc3bc85db8 Update project version to 2.8.0 in CMakeLists.txt 
Signed-off-by: Peter Han <fujun.han@iluvatar.ai>
 2021-12-17 02:23:31 +00:00
Matthew Nicely
49c0a58d50 Set theme jekyll-theme-minimal 2021-12-15 14:51:24 -05:00
Andrew Kerr
5fe09c2d67
Updated GEMM performance plot with CUTLASS 2.8 compiled with CUDA 11.5 Toolkit (#375) 
Updated GEMM performance plot with CUTLASS 2.8 compiled using CUDA 11.5 Toolkit.

GPUs under test:

    NVIDIA A100
    NVIDIA A2
    NVIDIA TitanV
    NVIDIA GeForce 2080 Ti
 2021-12-06 14:21:33 -05:00
Andrew Kerr
6b69c79ac3
Fixed contributor formatting. (#365) 2021-11-22 11:30:53 -08:00
Andrew Kerr
62e438f450
Listed Matthew Nicely as the CUTLASS product manager.. (#364) 2021-11-19 17:51:21 -08:00
Manish Gupta
808c25337a
CUTLASS 2.8 (#363) 
CUTLASS 2.8
 2021-11-19 13:26:35 -08:00
Haicheng Wu
6fc5008803
Update quickstart.md 
fix a broken link
 2021-11-11 09:53:46 -05:00
Haicheng Wu
a3bcc6981d
Merge pull request #331 from reed-lau/feature/fix-wmma-shape-typo 
fix wmma shape typo
 2021-09-28 10:20:29 -04:00
reed-lau
3b28642801 fix wmma shape typo 2021-09-28 19:04:09 +08:00
Manish Gupta
538592dea4
example 23 gemm operand reduction fusion (#325) 2021-09-20 13:34:47 -07:00
Manish Gupta
2e07c4cc2f
CUTLASS 2.7 (#318) 
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
 2021-09-20 11:02:22 -07:00
Haicheng Wu
9ac255863f
Merge pull request #246 from mengchihe/master 
support unalignment input for conv2d fprop stage=2 Fix for issue #242
 2021-09-08 11:40:53 -04:00
Haicheng Wu
59e2aa505a refine the implementation 2021-09-08 13:14:08 +00:00
Haicheng Wu
4e8af93da1 Merge remote-tracking branch 'origin/master' into small_alignment 2021-09-07 20:39:38 +00:00
Manish Gupta
6c2f8f2fb8
CUTLASS 2.6.1 - functional and performance enhancements to strided DGRAD, fixes, and tuning 
* cutlass 2.6 update

* remove debug prints

* cutlass 2.6.1 (minor update)

* Updated CHANGELOG.

* Minor edit to readme to indicate patch version.

* Minor edit to readme.

Co-authored-by:  Haicheng Wu <haichengw@nvidia.com>, Andrew Kerr <akerr@nvidia.com>
 2021-09-03 10:26:15 -07:00
Haicheng Wu
598e35401c Merge remote-tracking branch 'origin/master' into small_alignment 2021-08-16 07:49:08 -07:00
Manish Gupta
a01feb93d9
Merge pull request #308 from dongxiao92/patch-1 
fix typo in doc
 2021-08-08 11:54:42 -07:00
dongxiao
d36f331b44
fix typo in doc 
fix typo
 2021-08-08 16:44:22 +08:00
Haicheng Wu
69abafb85a
Merge pull request #306 from NVIDIA/fix-profiler-cmd-doc 
Fix profiler cmd doc
 2021-07-30 14:36:54 -04:00
Haicheng Wu
68a078fbbf cleanup 2021-07-30 11:27:21 -07:00
Haicheng Wu
10709dbb64 clean profiler cmd and doc 2021-07-30 11:02:17 -07:00
Manish Gupta
1227351079
Merge pull request #305 from NVIDIA/fix_epilogue_spill 
fix epilogue register spill
 2021-07-29 14:30:11 -07:00
Haicheng Wu
a77c658439 fix epilogue register spill 2021-07-29 14:25:48 -07:00
Haicheng Wu
4516b833ce
Merge pull request #303 from Peter9606/doc_typo 
Doc typo
 2021-07-28 20:49:06 -04:00
Peter Han
64dd1e1915 Doc typo 
Signed-off-by: Peter Han <fujun.han@iluvatar.ai>
 2021-07-29 08:45:59 +08:00
Manish Gupta
1ac4559d12
Cutlass 2.6 Update 1 (#301) 
* cutlass 2.6 update

* remove debug prints
 2021-07-27 17:58:30 -07:00
Manish Gupta
e5d51840e8
CUTLASS 2.6 (#298) 
CUTLASS 2.6
 2021-07-23 00:40:53 -04:00
Haicheng Wu
6c29fe20ba
Merge pull request #285 from tjingrant/patch-1 
Typo Fixes
 2021-07-05 22:51:19 -04:00
Tian Jin
e3c56b0d6b
Update predicated_tile_iterator.h 2021-07-05 12:11:53 -04:00
Tian Jin
4647c57243
Update predicated_tile_iterator.h 2021-07-05 12:06:41 -04:00
Haicheng Wu
856d4db3fb
Update basic_gemm.cu 
fix the matrix malloc size
 2021-06-15 09:08:36 -04:00
Haicheng Wu
6a1064093f
Merge pull request #274 from mani-ananth/master 
Some pending Bug fixes
 2021-06-02 13:17:39 -04:00
Manikandan Ananth
c5f1ef4dff update contributors 2021-06-02 10:11:42 -07:00
Manikandan Ananth
47ebfccbec bug fixes 2021-06-02 10:08:25 -07:00
Haicheng Wu
ad9486684f
Merge pull request #272 from BernardoCovas/master 
Bug in reference conv3d
 2021-05-28 17:18:27 -04:00
Bernardo Covas
1d8372a8e2 fix typo in reference conv3d 2021-05-28 21:06:59 +01:00
Haicheng Wu
9cb7d63424
Merge pull request #266 from mani-ananth/master 
Fixes for public issue #265
 2021-05-19 15:15:22 -04:00
Manikandan Ananth
da2f110906 Fixes for public issue #265 2021-05-19 10:16:52 -07:00
Haicheng Wu
b68113f5be
Merge pull request #264 from zheng95z/patch-3 
Adds `NoBetaScaling` for `LinearCombination`
 2021-05-17 10:03:30 -04:00
Zheng Zeng
a68d7cd6f1
Adds NoBetaScaling for LinearCombination 2021-05-12 22:23:55 +08:00
Haicheng Wu
38e8b29f56
Merge pull request #259 from hzfan/ignore_pr 
Add gitignore
 2021-05-10 20:07:53 -04:00
Haozheng Fan
ee7349c94f fix 2021-05-10 16:39:04 +08:00
Haozheng Fan
8cdd4293d4 add gitignore 2021-05-10 16:37:59 +08:00
Haicheng Wu
f58b843951
Merge pull request #239 from KeDengMS/kedeng/gelu 
Fixes to Gelu for half and fusion
 2021-05-08 12:51:42 -04:00
Haicheng Wu
5fc142296f
Merge pull request #237 from Peter9606/issue_236_typo 
Typo fix issue#236
 2021-05-08 07:51:19 -04:00