gaspersic/triton
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
596 Commits 14 Branches 9 Tags
keren/improve-hook
Commit Graph

416 Commits

Author SHA1 Message Date
Philippe Tillet
011bc83c1b [FRONTEND] For loops now promote initial value (#524) 2022-05-24 13:20:10 -07:00
Natalia Gimelshein
96bff90471 [FRONTEND] faster jit function launch (#523) 
With fast (200 ns) get_stream function soon to be available from pytorch this shaves off approx 25-30 us from function launch, but even without that function due to caching device properties we are saving ~15-20us.
 2022-05-24 12:08:49 -07:00
daadaada
d5eaa8dfa0 Making the generated Triton IR deterministic & a script to compare cached assembly (#522) 2022-05-24 08:56:36 -07:00
Shantanu
80f6a2698b [FRONTEND] Ensure version_key is called at most once (#519) 
Co-authored-by: hauntsaninja <>
 2022-05-23 13:40:08 -07:00
daadaada
205a493b10 [FRONTEND] Fix a bug in atomic_cas (correct cmp to val) & more tests on atomic_cas (#520) 
Fix a bug in atomic_cas (correct cmp to val) & more tests on atomic_cas
 2022-05-21 09:45:54 -07:00
Jiabao Lei
abea3dc2c6 [FRONTEND] provide device kwargs && fix fstring error for py<3.8 (#515) 
Co-authored-by: Philippe Tillet <phil@openai.com>
 2022-05-14 16:21:46 -07:00
Philippe Tillet
d35617bea1 [BACKEND][CODEGEN] Faster reduction for scanline layout (#516) 2022-05-14 15:26:13 -07:00
Jason Ansel
d954a05989 [FRONTEND] Handle torch.uint8 args (#513) 
Co-authored-by: Philippe Tillet <Phil.Tillet@gmail.com>
 2022-05-12 13:07:39 -07:00
Philippe Tillet
0835a4fb05 [TUTORIALS] Removed #noformat in layer norm tutorial 2022-05-12 12:41:25 -07:00
Philippe Tillet
c736ba7c3e [TUTORIALS] Fixed formatting 2022-05-12 12:31:23 -07:00
Philippe Tillet
cd30a99aa2 [TUTORIALS] fixed formatting 2022-05-12 12:28:22 -07:00
Philippe Tillet
d87435e536 [TUTORIALS] Layer norm tutorial now uses residency control (#510) 2022-05-05 19:53:54 -07:00
Philippe Tillet
95feb10ec9 [FRONTEND] fixup (#505) 2022-04-30 14:25:06 -07:00
Philippe Tillet
11a908655d [FRONTEND] Fixup 2022-04-29 14:35:09 -07:00
Phil Tillet
cd78ce4888 [FRONTEND] Improved error message when assigning None to non-constexpr 2022-04-29 09:17:54 -07:00
Philippe Tillet
ae2a1ab225 [BACKEND] Alignment pass improvements (#503) 2022-04-25 21:16:00 -07:00
Philippe Tillet
3ca792043f [TEST] Added test for vectorization 2022-04-24 13:50:48 -07:00
Philippe Tillet
bda209002e [BACKEND][CODEGEN] vectorization bugfix (#502) 2022-04-23 13:18:33 -07:00
Philippe Tillet
7d6c504e8d [TESTING] Added testing utilities for fixing clock and using cuda-memcheck (#500) 2022-04-21 22:40:10 -07:00
Philippe Tillet
073be1d2ee [FRONTEND] check that tensors have power-of-two number of elements (#499) 2022-04-14 19:30:02 -07:00
Philippe Tillet
5c7122004c [TUTORIALS] Tutorial shouldn't expose clock. Just removed it. 2022-04-14 17:33:44 -07:00
Philippe Tillet
dc4d40faec [FRONTEND] now mangle constexpr float containing "e-" 2022-04-14 10:26:48 -07:00
Philippe Tillet
25f6689508 [FRONTEND] rename current stream monkey patch (#495) 2022-04-13 11:45:55 -07:00
Philippe Tillet
76bfac9f15 [FRONTEND] Improved constexpr handling (#493) 2022-04-12 00:02:54 -07:00
Philippe Tillet
14b0fd4cfb [FRONTEND] Added possibility for users to customize current stream query (#492) 2022-04-07 12:11:32 -07:00
Philippe Tillet
9f08ecd684 [FRONTEND] Semantic analysis refactor (#491) 
Moved dispatch.cc to semantic.py (@ptillet)
Integer signedness analysis was moved from C++ to python (@daadaada)
Cleaner frontend types (@daadaada)
Moved SSA construction to a separate object (@ptillet)


Co-authored-by: Yan Da <dyanab@connect.ust.hk>
 2022-04-06 16:13:53 -07:00
Philippe Tillet
2bed6fc850 [LANG] Added support for device functions (#484) 2022-04-03 20:58:16 -07:00
Philippe Tillet
bace26143d [TUTORIALS] Removed leftover print 2022-03-28 16:53:23 -07:00
Philippe Tillet
e0cc488055 [FRONTEND] Added tl.clock and tl.globaltimer (#485) 2022-03-28 16:15:43 -07:00
Philippe Tillet
76a9ee50a8 Revert "[FRONTEND] Semantic analysis refactor (#473)" (#483) 
This reverts commit 539961072c.
 2022-03-24 17:16:50 -07:00
Keren Zhou
a4f68165cd [FRONTEND] Hot fix for lineno (#481) 
Override __reduce__ to make CompilationError pickable and print out error messages
 2022-03-22 22:09:49 -07:00
daadaada
539961072c [FRONTEND] Semantic analysis refactor (#473) 
Moved dispatch.cc to semantic.py
Integer signedness now moved from C++ to python
Cleaner frontend type

Co-authored-by: Phil Tillet <phil@openai.com>
 2022-03-16 21:25:30 -07:00
Yongjik Kim
0dd2ec2e3a [FRONTEND] Add an assert in case we get a CPU tensor. (#478) 2022-03-16 14:38:56 -07:00
Philippe Tillet
d4d8eaf6c0 [FRONTEND] improved caching mechanism (#474) 
Co-authored-by: Greg Brockman <gdb@gregbrockman.com>
Co-authored-by: Christopher Hesse <christopherhesse@users.noreply.github.com>
 2022-03-15 12:20:51 -07:00
Philippe Tillet
98ed7db8c1 [CODEGEN] Improvements and bugfixes (#463) 2022-02-24 14:56:24 -08:00
daadaada
a9dfdcaaa9 [FRONTEND] Make the performance model work for int8, tf32, and fp32 (#456) 2022-02-11 22:34:42 -08:00
Philippe Tillet
9b100302d3 [FRONTEND] Now using pybind11 to release GIL (#458) 2022-02-10 01:57:39 -08:00
Philippe Tillet
7b48340ffd [CI] Some fixes for the build (#451) 2022-02-06 19:11:33 -08:00
Philippe Tillet
5a8a544d10 [OPS][BLOCKSPARSE] Improved robustness, clarity and performance (#450) 
* dds layout now internally re-uses dsd code path for increased code 
* at_mask and kp_mask related things are now dropped from the softmax API. I couldn't think of any case where it was needed beyond is_causal. And if there is any, we should probably find a way to get it implemented statically so that users don't have to materialize masks.
 * fixed bug in blocksparse matmul that caused troubles when layout had a full row/col of zeros
 * blocksparse softmax now no longer modifies any data in-place
 * blocksparse softmax now takes an is_dense arguments that provides better performance. Passing is_dense=True, is_causal=True is the best way to achieve triangular attention.
  * unit tests now test backward pass
 2022-02-06 18:00:45 -08:00
TC
137bb67fad [LANG] Add fp16 to fp8 conversion (#444) 2022-02-02 20:42:09 -08:00
Philippe Tillet
b0d6e2f322 [STYLE] run autopep 2022-01-30 20:27:44 -08:00
Philippe Tillet
2922dc141c Merge branch 'master' into v2.0 2022-01-30 20:25:01 -08:00
Philippe Tillet
807d8a1945 [ALL] Merge master (#447) 2022-01-30 20:21:20 -08:00
Philippe Tillet
bef76b142a [BACKEND] float division is now approximate by default (#446) 2022-01-29 18:29:29 -08:00
Philippe Tillet
bd52e530a0 [OPS][BLOCKSPARSE] Fix padding issue in DSD LUT (#445) 2022-01-28 21:40:30 -08:00
daadaada
59d371c6eb [BACKEND] Added Int8 mma (#440) 2022-01-27 09:12:44 -08:00
Philippe Tillet
ccf9abe0ba [FRONTEND][RANDOM] Improved backward compatibility of RNG (#438) 
The unsigned int PR definitely improved our RNG. However, it requires
different floating point arithmetics which, means the results are not
bit-wise identical to how they were before. This commit revives backward
compatibility, but we should change it back to the "right" way later.
 2022-01-21 18:05:55 -08:00
Philippe Tillet
4c97d1ecd7 [FRONTEND] Bunch of fixes here and there (#436) 2022-01-20 10:55:59 -08:00
daadaada
2a944ded53 [TESTS] Added bfloat16 tests (#430) 2022-01-13 23:38:32 -08:00
Philippe Tillet
4c94359199 [FRONTEND] Alignment fix-up (#428) 2022-01-11 23:11:58 -08:00