github/ROCm
1
1
Fork 0
mirror of https://github.com/ROCm/ROCm.git synced 2026-04-05 03:01:17 -04:00
Code Issues Packages Projects Releases Wiki Activity
138 Commits 337 Branches 76 Tags
269ebc12e5f96355e5ebee510cf882ceed73502f
Commit Graph

38 Commits

Author SHA1 Message Date
Philippe Tillet
269ebc12e5 [PYTHON][TESTS][DOC] Various improvement of the API and code quality: 
* Simplified `triton.kernel` API to achieve lower latency:
  > .data_ptr() must now be passed as kernel argument. No more implicit
conversion from torch.tensor
  > compilation options are now constant attributes, i.e., opt.d('VAR')
becomes opt.VAR
  > torch.device must now be passed explicitly to triton.kernel (no
longer inferred from torch.tensor arguments)
* C++ tests moved to `python/tests/`
* C++ tutorial created in `tutorials/`
* Python tutorial created in python/tutorials/
* Version changed to 1.0alpha
* No longer copying C++ headers into the Python package
* added python/triton/ops/ package for pre-written Triton ops
 2021-07-27 12:38:48 -07:00
Philippe Tillet
083bbd1e8d [GENERAL] Merged v1.0alpha into master. Added features are: 
- A100 support via mma.16816
- Thread swizzling for conflict-free shared memory accesses without
padding
- Complete overhaul of the LLVM code generation in
codegen/selection/generator.cc to remove overengineering
- Added debugging capabilities in the Python binding
- Compilation error for kernels that spill
 2021-07-27 12:38:48 -07:00
Philippe Tillet
c0bc7ed8b0 [PYTHON] Added TRITON_DEBUG_MODE which reallocates input tensors outside of the pytorch memory pool to spot out-of-bounds accesses more easily 2021-07-27 12:38:48 -07:00
Philippe Tillet
a77c925dfd [DRIVER] Improved performance of Host driver code 2021-07-27 12:38:48 -07:00
Philippe Tillet
8f8d36c7a4 [GENERAL] Various bugfixes 2021-07-27 12:38:48 -07:00
Philippe Tillet
8f3ee53f24 [PYTHON] Added option to show PTX source code in Python 2021-07-27 12:38:48 -07:00
Philippe Tillet
f152150e7d [LANG] Added log intrinsic 2021-07-27 12:38:48 -07:00
Philippe Tillet
02a6e81b88 [PYTHON] Cleaning C++ bindings 2021-07-27 12:38:48 -07:00
Philippe Tillet
049ab989b5 [GENERAL] Various improvements: 
* Sparse einsum in triton.ops.einsum
* Hacky support for fixed-tile-size atomic-add
* Various bugfixes in parser
 2021-07-27 12:38:48 -07:00
Philippe Tillet
840308ab5d [CODEGEN] More work on the CPU backend 2021-07-27 12:38:48 -07:00
Philippe Tillet
acff1b5e05 [RUNTIME] Lower-level interface for executing functions 2021-07-27 12:38:48 -07:00
Philippe Tillet
ba9955ae39 [CODEGEN][ANALYSIS] Fixed issue in layout inference 2021-07-27 12:38:48 -07:00
Philippe Tillet
c33d6d15f5 [TRITON][PYTHON] Reverted back to distutils 2021-07-27 12:38:48 -07:00
Philippe Tillet
955b027103 [TRITON][KERNEL] Fixed issue for concurrent compilation of torch 
extensions
 2021-07-27 12:38:48 -07:00
Philippe Tillet
f35b9100e2 [PYTHON] Restored compatibility with powerpc 2021-07-27 12:38:48 -07:00
Philippe Tillet
1426b103e9 [PYTHON] Removed -std=gnu++11 in extra_cflags 2021-07-27 12:38:48 -07:00
Philippe Tillet
04a9ea060b [GENERAL] Added compatibility with pytorch 1.2.0 and powerpc 2021-07-27 12:38:48 -07:00
Philippe Tillet
609ef3a24d [CORE] Fixed bug for Multi-GPU 2021-07-27 12:38:48 -07:00
Philippe Tillet
5bb977173f [PYTHON][EINSUM] re-established auto-tuning 2021-07-27 12:38:48 -07:00
Philippe Tillet
4ae0e28b32 [PYTHON][KERNEL] Added thread-safety when caching custom torch op 2021-07-27 12:38:48 -07:00
Philippe Tillet
94e8ee7f01 [PYTHON][KERNEL] Better handling of case where cache directory already 
exists
 2021-07-27 12:38:48 -07:00
Philippe Tillet
3304629de9 [CORE] Fixed several issues that arose in the development of the 
torch-blocksparse package:

* Now using warp shuffle in reductions when possible
* Various bugfixes in layout inference
* Added INFINITY, exponential and select
* Better error messages for unimplemented constructs
 2021-07-27 12:38:48 -07:00
Philippe Tillet
268894a5ce [PYTHON] Merged blocksparse branch: 
* Example for blocksparse matrix multiplication
* Simplified Triton kernel API
* Revived auto-tuning in einsum
 2021-07-27 12:38:48 -07:00
Philippe Tillet
ea37ba5d35 [PYTHON][OPS] Fixed typo in einsum 2021-07-27 12:38:48 -07:00
Philippe Tillet
926acc2e28 [TRITON][NN][CONV] Renamed input -> x to not modify built-in functions 2021-07-27 12:38:48 -07:00
Philippe Tillet
420e36a038 [PYTHON][NN][CONV] Fixed typo in dx computation 2021-07-27 12:38:48 -07:00
Philippe Tillet
ecb0d81b2d [PYTHON] Added missing files for nn submodule 2021-07-27 12:38:48 -07:00
Philippe Tillet
3d769b57e2 [PYTHON] Better packaging 2021-07-27 12:38:48 -07:00
Philippe Tillet
dfb844bf41 [GENERAL] Improved caching mechanism: 
* Now computing hash in libtriton
* Now only compiling a single pytorch hook per function signature
 2021-07-27 12:38:48 -07:00
Philippe Tillet
30f77e9ec5 [PYTHON][OPS][EINSUM] Now throwing error for automatic differentiation 
of extended einsum
 2021-07-27 12:38:48 -07:00
Philippe Tillet
4e50ef4076 [PYTHON][OP][EINSUM] simplified API 2021-07-27 12:38:48 -07:00
Philippe Tillet
26fd884d96 [PYTHON][OPS][EINSUM] Added support for inner tensor strides 2021-07-27 12:38:48 -07:00
Philippe Tillet
4181f9f2af [CODEGEN][TRANSFORM][PEEPHOLE] Fixed bug in *1 multiplication 2021-07-27 12:38:48 -07:00
Philippe Tillet
3816f2f259 [PYTHON][EINSUM] Now handling reduction sizes that are not a multiple of 
TK
 2021-07-27 12:38:48 -07:00
Philippe Tillet
fa4ec7ea65 [PYTHON][OPS][EINSUM] Added support for masked accumulator 2021-07-27 12:38:48 -07:00
Philippe Tillet
404dd18333 [PYTHON][CORE] Deprecating Tensorflow support 2021-07-27 12:38:48 -07:00
Philippe Tillet
558422c18a [PYTHON][EXAMPLES] Changed shape of einsum examples 2021-07-27 12:38:48 -07:00
Philippe Tillet
6d7cf35123 History prior to this date belonged to the now deprecated ISAAC project, and was deleted to save space 2021-07-27 12:38:38 -07:00