Madeleine Thompson
5cdb948c05
[FRONTEND] signed-integer math fixes and testing ( #395 )
...
- Promote 16-bit floating-point `/` and `%` to 32-bit; we have to anyway.
- Do not force result of integer binary operations to be the LHS type. There used to be a bug in pytorch that did this, which Triton matched, but that bug is fixed now.
- When testing signed integer operations, use random numbers from the full range of the type.
- Add an optional `seed` argument to `triton.testing.random` so binary operations are not tested with both sides equal when the LHS and RHS have the same type.
- Fix a bad `CompilationError` invocation.
- Fix a warning suppression that causes tests to fail if you run them with `-W error` on python 3.8.
2021-12-21 09:46:05 -08:00
daadaada
4a8953efa3
[FRONTEND] Replace the legacy print call in triton.cc with the SlotTracker-based one. ( #396 )
...
The legacy print call will assign names (e.g., %10) to values, which can be undesirable in some cases.
2021-12-18 18:03:22 -08:00
Madeleine Thompson
fa62b4a8f6
[FRONTEND] better stringification ( #394 )
...
- Don't override `self.args` in `CompilationError`, and show the line number and column in error messages. This causes it to generate an easier-to-read backtrace.
- Better `__str__` on `TensorWrapper`, `dtype`, and `block`.
2021-12-17 20:11:45 -08:00
Philippe Tillet
4e93b41c52
[GENERAL] Some minor fixups ( #393 )
...
* [RUNTIME] Now displaying error message when generated PTX is invalid
* [CODEGEN] Now converting `if` condition to bool implicitly
2021-12-17 18:06:21 -08:00
Philippe Tillet
e062812969
[CODEGEN] Disabled peephole for masked load + select -- masked_load
...
doesn't work as expected when vectorized
2021-12-17 12:44:47 -08:00
Victor
eb077fc993
[RUNTIME] fixed NVidia DLL names on Windows ( #392 )
2021-12-16 22:09:52 -08:00
Philippe Tillet
e0b92c1380
[FRONTEND] Reverted from .random import *
. There are still some
...
namespace errors in the Triton frontend apparently
2021-12-16 18:37:51 -08:00
Philippe Tillet
558555630f
[FRONTEND] Added xor_sum
2021-12-16 17:55:35 -08:00
Madeleine Thompson
e575ae3443
[FRONTEND] Minor accumulated style and warning fixes ( #388 )
...
- Fix some whitespace.
- Make an undeclared dependency on `pytest` explicit.
- Fix deprecated `description-file` use.
- `#ifdef` out a deprecated `PyEval_InitThreads` call.
- Use a slightly different numpy invocation in `test_random.py` to quiet down overflow warnings in tests.
- Fix a deprecated cast in `test_core.py`.
- Suppress a warning about `visit_Constant` in Python 3.9+; we can't migrate yet because it'd break Python 3.6 and 3.7.
- Use chained exceptions for `CompilationError` rather than rolling our own; it makes the error messages nicer.
- Add a `__str__` for `tl.dtype` to make debugging kernels easier; it lets you `print` a dtype to see what type was inferred.
- Fix a few bad escapes.
2021-12-10 15:19:20 -08:00
Philippe Tillet
9def2424ab
[RUNTIME] Fix typo in IfExp
2021-12-09 15:14:41 -08:00
Philippe Tillet
e31b9b4e66
[RUNTIME] Better support for None
( #387 )
...
* regression test fails but it doesn't make sense to me.
2021-12-09 13:21:22 -08:00
Victor
73b04d71b2
Fixes for building on Windows ( #382 )
...
* make C++ code compatible with Windows + MSVC
* added dlfcn-win32 for cross-platform dlopen
* fixed building and pip install on Windows
* fixed shared library file name under Windows
2021-12-07 14:10:58 -08:00
Victor
0ff1a26b70
fixed p2p tests failing when there are no supported p2p devices ( #386 )
2021-12-06 18:14:03 -08:00
Philippe Tillet
f23bf55f15
[RUNTIME] release the gil on launch ( #383 )
2021-12-03 13:01:01 -08:00
Philippe Tillet
8ec9f037bb
[BACKEND/CODE_GEN] Fixed float32 matmul problem ( #380 )
2021-11-30 22:00:56 -08:00
Philippe Tillet
c86ad9c9ab
[FRONTEND] Added default arguments to non-kernel @triton.jit'd function ( #379 )
2021-11-29 19:11:26 -08:00
daadaada
1296eb877b
[RUNTIME] Config hook v2.0 ( #373 )
...
* Add pre_hook to triton.Config
* Use argument names in triton.heuristics
* Update base perf
* Remove meta from heuristics
2021-11-21 11:20:59 -08:00
Philippe Tillet
5693b582ea
[RUNTIME] Now using pybind11 to avoid memory leaks ( #377 )
2021-11-21 02:30:22 -08:00
Philippe Tillet
edd4b0c8b7
[CODEGEN] Fixed issue with jit function passed as constexpr
2021-11-16 09:53:34 -08:00
Philippe Tillet
5b7ba3eb96
[CODEGEN] Reverted to old launch method (memory leak?)
2021-11-16 01:21:03 -08:00
Philippe Tillet
791b953b21
[CODEGEN] Reverted to old way to query current stream
2021-11-16 00:17:27 -08:00
Philippe Tillet
b908095872
[VERSION] Bumped triton.__version__ to 2.0.0
2021-11-12 15:10:36 -08:00
Philippe Tillet
01cc3d4503
[RUNTIME] Restored do_not_specialize
( #374 )
2021-11-12 15:06:55 -08:00
Philippe Tillet
e66bf76354
[RUNTIME] Bunch of bugfixes ( #372 )
2021-11-12 00:55:00 -08:00
Philippe Tillet
f7ab96cfd7
[FRONTEND] Fixed some issues with constexpr
2021-11-09 13:03:09 -08:00
daadaada
9a02dddf29
Fix sdd_lut ( #368 )
2021-11-08 08:25:05 -08:00
Philippe Tillet
5d54352164
[FRONTEND] Significantly reduce kernel launch time ( #367 )
2021-11-04 13:25:24 -07:00
Philippe Tillet
2acaa4d0dd
[LANG] Added support for constexpr ( #361 )
2021-10-30 00:32:58 -07:00
Philippe Tillet
b7f0e87dc2
[DRIVER] Removed std::cout log message
2021-10-29 10:42:10 -07:00
Philippe Tillet
770ea96cca
[PACKAGING] Bumped dev version to 2.0.0
2021-10-29 01:28:17 -07:00
Philippe Tillet
969d6de8a2
[PACKAGING] Bumped dev version to 1.1.2
2021-10-29 01:26:21 -07:00
Philippe Tillet
2d6df9b518
[PACKAGING] Bumped dev version to 1.1.2
v1.1.2
2021-10-29 01:24:19 -07:00
Philippe Tillet
1b842f8e5e
[CI] Now running integration tests on pull requests on branch v2.0
2021-10-29 01:11:12 -07:00
Philippe Tillet
d3e584d4ba
Revert "[DRIVER] Fixed CUDA 10.1 bug ( #357 )" ( #358 )
...
This reverts commit d35014ba47
.
2021-10-26 15:04:49 -07:00
Philippe Tillet
d35014ba47
[DRIVER] Fixed CUDA 10.1 bug ( #357 )
2021-10-26 11:17:06 -07:00
Philippe Tillet
5ce1b726dc
[CODEGEN] Various bugfixes that make it possible to fuse RNG in a matmul epilogue ( #356 )
2021-10-24 02:30:46 -07:00
daadaada
858dec8372
[CODEGEN] Add cache modifier to tl.load ( #351 )
...
* Add cache modifier to tl.load
* Add comment to cache_modifier
* Remove force_nc_cache
* Update test
2021-10-17 22:14:04 -07:00
Philippe Tillet
90ded16c32
[DOCS] Added placeholder docstring for layernorm tutorial
2021-10-15 19:04:01 -07:00
Philippe Tillet
abbc554838
[VERSION] Bumped version to 1.1.1 ( #350 )
v1.1.1
2021-10-14 18:09:39 -07:00
Philippe Tillet
9b32075062
[CODEGEN] Some compiler improvements ( #349 )
2021-10-13 17:49:39 -07:00
Stephen McGroarty
c2e6b90ff1
[CODEGEN] Fixes masked load exception ( #342 )
2021-10-13 13:31:52 -07:00
Philippe Tillet
bfacc191b3
[FRONTEND] Now cache re-compiles when language
changes ( #348 )
2021-10-13 12:29:57 -07:00
Shantanu
f5ad168686
[PYTHON] Fix up __version__ ( #345 )
...
Co-authored-by: hauntsaninja <>
2021-10-13 00:09:00 -07:00
Philippe Tillet
c3c0ff0552
[LANGUAGE] Fixed issue with duplicates in large arrays of random uniform numbers ( #338 )
2021-10-10 15:22:34 -07:00
daadaada
9e9d781912
[CODEGEN] Pipeline fixup ( #336 )
2021-10-10 01:47:11 -07:00
daadaada
d5f20dbce0
[IR] Fix error when building in debug mode ( #331 )
2021-10-08 21:40:20 -07:00
Philippe Tillet
d4baad426d
[DOCS] Added layer norm example ( #326 )
2021-10-08 11:02:10 -07:00
Philippe Tillet
5123db0b7d
[LANG] Various (relatively minor) improvements ( #320 )
2021-10-04 18:39:40 -07:00
Min Xu
12b6158c5c
[DOCS] Minor fix ( #317 )
...
Co-authored-by: Min Xu <min.xu.public@gmail.com >
2021-09-30 17:33:08 -07:00
Philippe Tillet
b352b16567
[DOCS] Installation documentation now doesn't suggest to run regression
...
tests
2021-09-29 18:32:33 -07:00