gaspersic/triton
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
512 Commits 14 Branches 9 Tags
af85f5fa468b5d43d637a1ddf3f69ff984fb7ee0
Commit Graph

512 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Keren Zhou
af85f5fa46 [FRONTEND] Refresh cache when the source code of outlined functions are changed (#590) 2022-07-20 17:34:07 -07:00
daadaada
9b2bc88d11 [BACKEND] Better bf16 support (#588) 2022-07-19 21:22:37 -07:00
Philippe Tillet
86cab58d89 [CI] Changed dev wheel date to UTC time to match CRON schedule (#587) 2022-07-18 14:54:13 -07:00
Phil Tillet
5b04331dd2 [TUTORIALS] Added more credits in fused attention tutorial 2022-07-13 23:48:58 -07:00
Jason Ansel
0a3f3d5f25 [PACKAGING] Include triton/language/libdevice.10.bc in package data (#582) 2022-07-13 23:45:27 -07:00
Keren Zhou
4912916c11 [FRONTEND] Added support for element-wise function defined in external LLVM bitcode (e.g., libdevice) (#562) 2022-07-13 15:52:21 -07:00
Phil Tillet
971f5782b4 [tutorials] Added flash attention credits in tutorial 2022-07-11 18:56:48 -07:00
Philippe Tillet
d5eb9bc230 [tutorial] Added bwd in fused attention example (#579) 
Doesn't work on V100
 2022-07-11 15:43:46 -07:00
Jason Ansel
c9a2b9c7d4 [FRONTEND] Add missing args to get_simd_tflops() (#578) 2022-07-11 14:37:59 -07:00
Philippe Tillet
4a399a7e40 [BACKEND] Fix some bugs (atomics, a segfault...) (#577) 
This should fix #558 , #573 and #574
 2022-07-06 20:03:04 -07:00
vesuppi
22105bc33b [FRONTEND] Added type check in semantic arange (#572) 2022-07-03 15:25:37 -07:00
Keren Zhou
4bf509889b [BUILD] Change the default build type to Release (#571) 2022-07-01 12:17:22 -07:00
Keren Zhou
a74cce375f [FRONTEND] Raise broadcast error (#555) 2022-06-30 17:32:07 -07:00
Philippe Tillet
f733327ba4 [BACKEND][CODEGEN] Disabling L2 residency control by default (#570) 2022-06-29 17:05:13 -07:00
Natalia Gimelshein
1bbb2430d9 [TUTORIALS] adjust heuristics for dwdb kernel (#565) 2022-06-29 17:00:22 -07:00
Kashif Rasul
1895ceaa2d [TUTORIAL] Fix f-string for older python (#569) 
fixes issue #568
 2022-06-29 09:39:10 -07:00
Philippe Tillet
feb7a2a0dc [FRONTEND] Hotfix for store argument order (#567) 2022-06-28 00:24:02 -07:00
Philippe Tillet
5b4c8f221e [BACKEND] Compiler improvements (#557) 
This PR adds several optimization capabilities in the compiler backend:
- Now using inline PTX for `tl.store`, making it possible to use things like evict_last
- For A100, mma layout can be directly converted to shared memory
- For A100, an additional "transpose" argument in `dot` allows tensors to be loaded once and used both row- and col- major.
- Fixed liveness analysis; this was broken.
- Now can load/store directly mma layout without converting. Useful for when tl.dot accumulator is initialized with DRAM data inside of an inner loop.
- `tl.dot` can now take LHS inputs in registers when it comes from a previous `tl.dot` instruction. Useful for e.g. fused attention.
 2022-06-27 11:49:19 -07:00
Keren Zhou
87413bc925 [BACKEND] Fix layout convert for non-contiguous input (#564) 2022-06-25 23:12:03 -07:00
Keren Zhou
d345ddf837 [DOCS] Separate atomic cas from other atomic operations since operands are very different (#559) 2022-06-22 17:51:17 -07:00
Keren Zhou
b02bac41ba [CI] Change cache dir (#561) 2022-06-22 11:44:35 -07:00
Keren Zhou
a428cf0bb2 [FRONTEND] Fix pytorch warning. (#560) 
UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc').
 2022-06-20 20:12:09 -07:00
Keren Zhou
b5e728cb14 Add argmin argmax (#552) 2022-06-15 13:55:20 -07:00
Jason Ansel
6b9756532f [BACKEND] Remove print in coalesce.cc (#551) 2022-06-15 13:13:20 -07:00
Madeleine Thompson
8ce2c12e33 [PYTHON] move ephemeral files to homedir (#549) 
This prevents potential conflicts with other users on shared machines.
 2022-06-13 19:37:52 -07:00
Keren Zhou
93209c07e0 [BACKEND][CODEGEN] Fix reduce uint (#547) 2022-06-13 16:43:57 -07:00
Philippe Tillet
58c8889235 [FRONTEND] Fix scanline layout (#548) 2022-06-13 16:21:10 -07:00
Natalia Gimelshein
7094657aa9 [FRONTEND] fix bool conversion of floating types (#545) 2022-06-13 15:52:37 -07:00
Keren Zhou
38573d1261 [FRONTEND] Return allocated registers and spilled registers for users (#541) 2022-06-07 18:37:12 -07:00
Mengchi Zhang
2cdc6d35c4 [FRONTEND] Give col_per_thread an initial value to make the compiler happy (#535) 
Signed-off-by: Mengchi Zhang <mengchi@fb.com>
 2022-06-06 12:48:23 -07:00
TC
f13cbaab9f [FRONTEND] assert that num_warps is a power of 2 (#539) 2022-06-06 11:37:08 -07:00
Philippe Tillet
751e325d2e [TUTORIALS] Fixed typo 2022-06-05 13:33:21 -07:00
Philippe Tillet
801c8a4c92 [TUTORIALS] Fixed typo 2022-06-05 12:32:07 -07:00
Philippe Tillet
8876e53206 [BACKEND] Restored reduction bugfixes 2022-06-03 11:38:52 -07:00
Philippe Tillet
a60374a597 Revert "[BACKEND] Various bug fixes; making reductions faster (#533)". 
This is a more stable commit that produce bitwise identical code to earlier
versions. Using commits after this one may lead to slightly different numerics
 2022-06-03 11:36:06 -07:00
Philippe Tillet
efa04cac1f [FRONTEND] A couple of bugfixes (#534) 2022-06-02 16:57:37 -07:00
Philippe Tillet
3e7500dfe6 [BACKEND] Various bug fixes; making reductions faster (#533) 2022-05-31 17:14:44 -07:00
Bert Maher
37037bb3be [FRONTEND] Default cache dir to /tmp/triton_$USER (#527) 2022-05-27 13:51:05 -07:00
Philippe Tillet
c82a206684 [FRONTEND] Better dot error message (#531) 2022-05-26 17:41:09 -07:00
Philippe Tillet
0e2883020a [BACKEND] Fixed typo in alignment analysis (#528) 2022-05-25 20:01:19 -07:00
Bert Maher
43fec2adca [FRONTEND] Add binding for create_int_to_ptr (#526) 2022-05-25 15:26:18 -07:00
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
Mengchi Zhang
d1a22a94e6 [FRONTEND] Add empty return value and remove protect to open the access to contained_tys_vec_t (#514) 
Signed-off-by: Mengchi Zhang <mengchi@fb.com>
 2022-05-13 11:46:12 -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