gaspersic/triton
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
366 Commits 14 Branches 9 Tags
4a69af08e77c5fe59f62a38a6ea24b7d86de7630
Commit Graph

71 Commits

Author SHA1 Message Date
Philippe Tillet
0ff81badac [driver] added TRITON_LIBCUDA environment variable to specify libcuda 
path if not in LD_LIBRARY_PATH
 2019-09-06 13:26:51 -04:00
Philippe Tillet
18848cbb71 [driver] now passing std::unique_ptr<> instead of cloning LLVM module 
when compiling it
 2019-09-05 17:25:58 -04:00
Philippe Tillet
b747959a57 trying to work around tensorflow limitations 2019-09-04 01:54:43 -04:00
Philippe Tillet
2ccc915011 [python][examples] added template for blocksparse 2019-09-03 20:44:27 -04:00
Philippe Tillet
97fdb5b6be [tests] added missing files 2019-09-03 12:44:35 -04:00
Philippe Tillet
a842d337c5 [general] various cleaning and bugfix: 
* added copy1d and copy2d benchmark
* fixed issue in reassociation pass
 2019-09-02 23:00:49 -04:00
Philippe Tillet
7e0af2118c [codegen] worked around bug seemingly from nvptx/ptxas by simplifying multiplications by 1: 
- Generated LLVM-IR looked correct
- Illegal addressing disappeared when running cuda-memcheck
- Illegal addressing disappeared when using nvptx-short-pointer
 2019-08-30 16:45:14 -07:00
Philippe Tillet
d457482539 [codegen] fixed issue in double buffering pointer update 2019-08-28 17:50:45 -07:00
Philippe Tillet
37cbcfabd0 [examples] back to 96 TFLOPS on V100 2019-08-26 22:49:14 -07:00
Philippe Tillet
b4ae06a714 tracking down performance regression 2019-08-26 20:38:39 -07:00
Philippe Tillet
7cb73f66e2 testing some register gradient 2019-08-26 19:25:58 -07:00
Philippe Tillet
cb04ec0b3b some more cleaning 2019-08-23 19:22:38 -07:00
Philippe Tillet
732156b942 [general] rename *.cpp -> *.cc 2019-08-23 19:06:39 -07:00
Philippe Tillet
f98b0b8e2a [general] deleted the old compiler frontend 2019-08-23 17:28:02 -07:00
Philippe Tillet
8798d240dc matmul test passes 2019-08-23 17:13:30 -07:00
Philippe Tillet
845c0e5b93 adding tunable parameters 2019-08-22 19:21:01 -07:00
Philippe Tillet
b58b0d8b27 [general] removed unnecessary includes 2019-08-18 00:34:30 -07:00
Philippe Tillet
38a8b0ab19 [runtime] overall of the run-time API 2019-08-14 20:26:11 -07:00
Philippe Tillet
1400d960a6 [auto-tuning] much smaller parameters space 2019-08-12 21:15:21 -07:00
Philippe Tillet
7578c27d3d [general][filesystem] added structure and namespace to code generation files 2019-08-07 21:17:17 -07:00
Philippe Tillet
392b55280d [codegen] some cleaning for batched matmul 2019-08-07 21:17:17 -07:00
Philippe Tillet
7b75b68edc dirty but working warp-splitting 2019-08-06 21:07:13 -07:00
Philippe Tillet
5af7e5adac Made sure it works for FP16 2019-07-30 20:02:16 -07:00
Philippe Tillet
2a377bc8b1 [ir] deleted mask/merge instructions; will be replaced by masked_load/store and select 2019-07-25 15:06:15 -07:00
Philippe Tillet
38b3771c26 some reassociation 2019-07-23 14:43:18 -07:00
Philippe Tillet
c448876178 better benchmarking 2019-07-22 19:26:12 -07:00
Philippe Tillet
5215fb0424 [codegen] some more optimizations 2019-07-19 20:29:03 -07:00
Philippe Tillet
f74dcb7e30 [dnn/batchnorm]: added some more code in Triton-C batchnorm implementations 2019-07-08 20:18:20 -07:00
Philippe Tillet
f9db0449b7 [dnn] Adding batchnorm 2019-07-08 18:44:37 -07:00
Philippe Tillet
1d88f0a36b stuff 2019-07-03 19:25:16 -07:00
Philippe Tillet
c172bd518b more stuff 2019-06-30 16:55:02 -07:00
Philippe Tillet
64513fb407 [codegen] added fallback when tensor cores cannot be used 2019-06-25 15:49:58 -07:00
Philippe Tillet
d52abc9379 [codegen] bugfix in alignment inference 2019-06-25 15:06:15 -07:00
Philippe Tillet
72867d17d4 more cleaning 2019-06-24 12:37:13 -07:00
Philippe Tillet
f7dcea1187 Now doing double-buffering 2019-06-13 19:48:02 -07:00
Philippe Tillet
21a9b92c87 disabling interleaving 2019-06-13 17:16:00 -07:00
Philippe Tillet
d487cf31ce trying 128 bits loads 2019-06-12 21:07:01 -07:00
Philippe Tillet
a6b580ec05 interleaving fails with B 2019-06-12 19:46:43 -07:00
Philippe Tillet
1b5a742a88 [triton/codegen] added shared memory padding for HMMA arguments and vectorized loads 2019-06-11 19:51:08 -07:00
Philippe Tillet
7d50b87681 [selection/codegen] bugfix in distributed tile indices initialization 2019-06-11 10:45:19 -07:00
Philippe Tillet
06b5992509 [feature] added basic tensor core support 2019-06-11 10:24:49 -07:00
Philippe Tillet
5f3d48c1d0 [tensor cores] added basic codegen template for using wmma 2019-06-07 21:19:47 -07:00
Philippe Tillet
ec4c6aaaaa Added inline PTX for mma.sync 2019-06-07 19:39:33 -07:00
Philippe Tillet
f58c9a4d2b [general] hmma baseline setup 2019-06-05 14:43:38 -07:00
Philippe Tillet
a9d078c06f [triton/dnn/conv] merged optimizations branch 
- Added forward/backward support for strided convolution
- Added support for bias
- Added support for reduction splitting
 2019-05-28 14:04:53 -04:00
Philippe Tillet
e8f23bcade [dnn/conv] Added bias and forward stride 2019-05-22 13:27:08 -04:00
Philippe Tillet
b2b55c52c9 [triton/python/conv]: Added cache for compiled kernels 2019-05-18 11:51:49 -04:00
Philippe Tillet
208d1525de [driver] added spirv-llvm dispatch functions 2019-05-02 10:44:29 -04:00
Philippe Tillet
7b6efc0463 [examples/python/tensorflow] bugfix in tensorflow wrapper example 2019-04-30 21:04:30 -04:00
Philippe Tillet
af58b8bd81 [triton-c] predicate in assignment statement now propagates to rhs 
computations
 2019-04-27 14:00:15 -04:00