Commit Graph

394 Commits

Author SHA1 Message Date
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
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
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
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
Philippe Tillet
8ec9f037bb [BACKEND/CODE_GEN] Fixed float32 matmul problem (#380) 2021-11-30 22:00:56 -08:00
Philippe Tillet
e66bf76354 [RUNTIME] Bunch of bugfixes (#372) 2021-11-12 00:55:00 -08:00
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
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
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
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
5123db0b7d [LANG] Various (relatively minor) improvements (#320) 2021-10-04 18:39:40 -07:00
Philippe Tillet
2c287544cb [OPS] Faster and cleaner block-sparse implementation (#311) 2021-09-27 18:25:16 -07:00
Philippe Tillet
e22d92c63c [RUNTIME] removed obsolete putenv call (#305) 2021-09-23 17:51:58 -07:00
Philippe Tillet
ec2e7b8f48 [CODEGEN] Fixed nasty bug in coalesce pass (#303) 2021-09-23 17:05:11 -07:00
Philippe Tillet
2849e7a773 [CODEGEN] now re-coalescing before atomics (#298) 2021-09-22 13:35:53 -07:00
Philippe Tillet
6e5b0b4301 [FRONTEND] Added on-disk cache for compiled kernels (#287) 2021-09-18 22:48:26 -07:00
Philippe Tillet
313d6488f6 [CODEGEN] Fixed over-aggressive division handling in alignment pass (#280) 2021-09-15 00:40:17 -07:00
Philippe Tillet
8fdd7e7ed6 [LANG] Fixed semantics of boolean load/store (#282) 2021-09-13 17:39:06 -07:00
Philippe Tillet
3e395bc84e [LANG] Fixed semantics of NaN in float comparisons (#281) 2021-09-13 15:06:29 -07:00
Philippe Tillet
43723ccb95 [FRONTEND] Removed circular import that broke Python 3.6 support (#272) 2021-09-09 13:46:55 -07:00
Philippe Tillet
94c83d30ce [GENERAL] Removed deprecated driver files and added basic compatibility with rocm (#268)
- Removed driver module -- accelerator runtime is handled by pytorch
- Added basic support for ROCM based on @micmelesse 's PR -- now can execute empty kernel on AMD devices without any compile-time changes
- Now only using PREFER_SHARED for kernels when the size of shared memory is greater than 49k. Otherwise there can be poor L1 performance for broadcast tensors
2021-09-09 00:04:28 -07:00
Philippe Tillet
8a882b215f [CODEGEN] Fixed performance regression on vectorized loads (#259) 2021-09-02 01:07:31 -07:00
Philippe Tillet
768e0ded28 [CODEGEN] Fixed bug in pipelining pass and casting semantics analysis (#257) 2021-09-01 20:58:47 -07:00
daadaada
274d613488 [IR] Better printer (#256) 2021-09-01 09:55:12 -07:00
Philippe Tillet
4ff3714d61 [CODEGEN] Various bugfixes and stability improvements in compiler backend (#240) 2021-08-30 11:50:35 -07:00
daadaada
85426dbaf7 [DOCS] Add comments in layout.h (#249) 2021-08-28 18:07:32 -07:00
milesial
5b29da719d [DRIVER] Add CUDA P2P support (#209) 2021-08-20 21:00:54 -07:00
Philippe Tillet
226fde6ea1 [CODEGEN] Now using atomic_rmw code path for atomic_xchg (#222) 2021-08-17 16:33:23 -07:00
Philippe Tillet
bb1eebb4b4 [CODEGEN] Fixed bug for visit_reduce1d with 64-bit data-types (#207) 2021-08-14 21:07:01 -07:00
Philippe Tillet
298da78058 [CODEGEN/DRIVER] Tweaks for performance optimization (#193) 2021-08-07 16:41:44 -07:00
Philippe Tillet
e8031fe61f [DRIVER] More robust support of unsupported CUDA version (#179) 2021-08-02 09:06:55 -07:00
daadaada
c7060eadb2 [CODEGEN] Fix bug in auto-pipeline pass when a value depends on multiple phis (#164) 2021-07-31 23:40:36 -07:00
Philippe Tillet
2f0f51be50 [DRIVER] No longer crashing when encountering CUDA version >11.4 2021-07-29 11:27:55 -07:00
Philippe Tillet
76c6f24fb6 [CI] Made build-wheels compatible with system LLVM setup (#138)
This speeds up wheelhouse build time by ~10x
2021-07-27 12:38:49 -07:00
Philippe Tillet
8eb63bcb01 [CI] Various improvements to CI (#137)
Add clean-up before CI runs. Now using static LLVM-11 libraries from system rather than recompilation. Still no run-time LLVM dependencies
2021-07-27 12:38:49 -07:00
Philippe Tillet
94ce6aa80f [DRIVER] Added support for CUDA 11.4 (#135) 2021-07-27 12:38:49 -07:00
Philippe Tillet
01276b5153 [FRONTEND] Added compilation flag to force use of .nc cache modifier (#134)
in DRAM loads. /!\ USE CAREFULLY - THIS CAN BREAK CORRECTNESS IF MISUSED
/!\
2021-07-27 12:38:49 -07:00
Philippe Tillet
2824345065 [LANGUAGE] Added cos/sin (#132) 2021-07-27 12:38:49 -07:00
Philippe Tillet
8cea583109 [IR] Preliminary support for BF16 (#129)
This PR adds a BF16 data-type, along with FP32 <-> BF16 conversion instructions in the LLVM codegen. Other kinds of ops on bfloat16 are not yet supported.
2021-07-27 12:38:49 -07:00
daadaada
0b05e06c0d cu_device::max_shared_memory() now returns max dynamic shared memory size (#127) 2021-07-27 12:38:49 -07:00
daadaada
d8d6b715c8 [CODEGEN] Performance improvement on A100 (#125)
Improved codegen for the Ampere GPUs.

    * Make the layout pass recognize the multistage pipelined pattern.
    * Now the pipeline pass can automate the multistage pipelining transformation.
    * Remove extra barriers (from the prefetch pass & WAR) on Ampere.
    * Update the code generator (generator.cc) to make Triton generate n-buffered shared memory loads/stores.
2021-07-27 12:38:49 -07:00