Philippe Tillet
|
30833c18f1
|
[codegen/tune] bugfix in heuristics for nano-tile sizes
|
2019-05-04 01:32:34 -04:00 |
|
Philippe Tillet
|
0d694445e6
|
[examples] added skeleton for pytorch wrapper
|
2019-05-03 14:30:06 -04:00 |
|
Philippe Tillet
|
208d1525de
|
[driver] added spirv-llvm dispatch functions
|
2019-05-02 10:44:29 -04:00 |
|
Philippe Tillet
|
70f49a56c1
|
[examples/python/tensorflow] better skeleton for blocksparse
|
2019-05-01 17:09:01 -04:00 |
|
Philippe Tillet
|
55866f1ef6
|
[examples/python/tensorflow] fixed ABI compatibility issue in JIT
destructor
|
2019-05-01 13:38:56 -04:00 |
|
Philippe Tillet
|
7b6efc0463
|
[examples/python/tensorflow] bugfix in tensorflow wrapper example
|
2019-04-30 21:04:30 -04:00 |
|
Philippe Tillet
|
d934d8fb40
|
[examples/python/tensorflow] improved matmul wrapper
|
2019-04-30 12:25:35 -04:00 |
|
Philippe Tillet
|
8e809a9536
|
[examples] added skeleton for tensorflow op
|
2019-04-30 10:50:54 -04:00 |
|
Philippe Tillet
|
93f53501c6
|
[triton-c] added implicit conversion to bool in while/for loops
|
2019-04-28 00:32:51 -04:00 |
|
Philippe Tillet
|
af58b8bd81
|
[triton-c] predicate in assignment statement now propagates to rhs
computations
|
2019-04-27 14:00:15 -04:00 |
|
Philippe Tillet
|
4b77b764ba
|
[triton-c] added support for while loops
|
2019-04-26 15:08:02 -04:00 |
|
Philippe Tillet
|
b6af06910d
|
[examples] deleted placeholders for not implemented examples
|
2019-04-25 16:24:16 -04:00 |
|
Philippe Tillet
|
3413aad582
|
[general] major overhaul of triton-c/triton-ir/triton-jit:
- Added alloc const
- Added atomics
- Pruning tuning space
- Added example for dot/conv/shift
- Bugfixes
|
2019-04-25 16:18:15 -04:00 |
|
Philippe Tillet
|
0c607c9392
|
[examples] normalize benchmark by max_clock / current_clock
|
2019-03-28 07:58:37 -04:00 |
|
Philippe Tillet
|
2c3ae0675e
|
[JIT] re-added nvidia compatibility
|
2019-03-27 21:12:01 -04:00 |
|
Philippe Tillet
|
fdf8559806
|
[general] added missing files
|
2019-03-27 20:01:35 -04:00 |
|
Philippe Tillet
|
bc2a257d5c
|
[code generation] more flexibility in backend selection
|
2019-03-27 11:29:42 -07:00 |
|
Philippe Tillet
|
e04253c0dd
|
[code generation] basic CPU backend
|
2019-03-27 11:13:36 -07:00 |
|
Philippe Tillet
|
9d6fc1c051
|
[code generation] bugfix in single buffering
|
2019-03-26 15:55:48 -07:00 |
|
Philippe Tillet
|
8d35c98920
|
[code generation] search space pruning
|
2019-03-25 14:10:24 -07:00 |
|
Philippe Tillet
|
deb7a1cc5c
|
Hack to make OpenCL for AMD work
|
2019-03-23 18:58:25 -07:00 |
|
Philippe Tillet
|
be55b3a081
|
saving progress
|
2019-03-23 16:52:53 -07:00 |
|
Philippe Tillet
|
9de9feff4a
|
[jit] added runtime for host but compilation still needs to be implemented
|
2019-03-23 13:40:42 -07:00 |
|
Philippe Tillet
|
49fd6ece99
|
some cleaning
|
2019-03-21 23:51:47 -07:00 |
|
Philippe Tillet
|
907bbb1ad2
|
[driver] now debugging AMD runtime
|
2019-03-20 17:32:17 -07:00 |
|
Philippe Tillet
|
b6305f4388
|
[driver] added more genericity for opencl support
|
2019-03-20 00:25:08 -07:00 |
|
Philippe Tillet
|
02775a226e
|
[driver] adding opencl in the driver API
|
2019-03-18 23:12:14 -07:00 |
|
Philippe Tillet
|
b73c3bdd25
|
[examples] removed dependency on isaac for auto-tuning
|
2019-03-11 22:22:43 -04:00 |
|
Philippe Tillet
|
87c85ed50d
|
[code generation] reparameterization
|
2019-03-11 19:30:21 -04:00 |
|
Philippe Tillet
|
614f83baee
|
[jit] basic auto-tuning support
|
2019-03-11 12:00:50 -04:00 |
|
Philippe Tillet
|
94e315ea8a
|
Reparameterized in terms of micro- and nano- tiles
|
2019-03-10 23:10:17 -04:00 |
|
Philippe Tillet
|
c96a263896
|
[jit] changed default metaparameter ranges
|
2019-03-10 10:45:21 -04:00 |
|
Philippe Tillet
|
d2e7d7890d
|
[jit] preparing auto-tuning
|
2019-03-10 00:42:36 -05:00 |
|
Philippe Tillet
|
9e2cfddf4c
|
[examples] some cleaning
|
2019-03-09 17:17:55 -05:00 |
|
Philippe Tillet
|
9a3537662d
|
[jit] can now infer launch parameters from triton module
|
2019-03-09 14:44:13 -05:00 |
|
Philippe Tillet
|
b721202812
|
[code generation] uniformized shape and layout metaparameters
|
2019-03-09 12:31:21 -05:00 |
|
Philippe Tillet
|
5f29263044
|
[code generation] now using ir::metaparameter* for all tunable
metaparameters
|
2019-03-09 12:05:12 -05:00 |
|
Philippe Tillet
|
d049679aa2
|
[general] added simple jit interface
|
2019-03-08 23:58:42 -05:00 |
|
Philippe Tillet
|
c5073a5af6
|
[abstract syntax tree] better error messages
|
2019-03-05 23:45:58 -05:00 |
|
Philippe Tillet
|
20ff9543ac
|
[abstract syntax tree] improved the grammar
|
2019-03-05 21:03:19 -05:00 |
|
Philippe Tillet
|
4189e130bf
|
[general] added support for constant memory declaration
|
2019-03-03 23:16:33 -05:00 |
|
Philippe Tillet
|
1f30e111ec
|
[code generation] more optimizations
|
2019-03-02 16:03:26 -05:00 |
|
Philippe Tillet
|
2467c5e504
|
[code generation] added ternary operator
|
2019-03-01 21:53:35 -05:00 |
|
Philippe Tillet
|
08fcfbca47
|
[code generation] better predication
|
2019-03-01 14:36:17 -05:00 |
|
Philippe Tillet
|
36acf22fd3
|
better masking
|
2019-02-28 23:46:11 -05:00 |
|
Philippe Tillet
|
017702590b
|
[intermediate representation] added ternary_inst
|
2019-02-26 14:20:58 -05:00 |
|
Philippe Tillet
|
68dea75aa0
|
[syntax tree] more fixes in lowering phi nodes
|
2019-02-26 12:36:37 -05:00 |
|
Philippe Tillet
|
338f291835
|
[code generation] now ordered iterations across distributed tiles
|
2019-02-25 11:41:45 -05:00 |
|
Philippe Tillet
|
6dc88878ac
|
[code generation] bugfix in double-buffering
|
2019-02-24 23:22:28 -05:00 |
|
Philippe Tillet
|
daa828ec18
|
[general] rename namespace tdl -> triton
|
2019-02-24 14:35:16 -05:00 |
|