Masahiro Masuda 53d163c968 [TIR, CUDA] Add pass to replace global to shared memory copy with cp.async (#11658) ...

* [TIR, CUDA] Add pass to replace global to shared memory copy with cp.async

* add missing doc

* black

* missing src

* clang format

* clang format

* check against nested async scope

2022-06-09 19:05:18 -07:00

..

__init__.py

[TVMScript] Add for loop syntax sugar (#9620)

2021-12-07 19:19:47 -05:00

_ffi_api.py

[TIR] Use PopenPool instead of multiprocessing.pool (#8492)

2021-08-12 13:35:04 -07:00

aot.py

[microTVM][ARM] Add Relay tests for conv2d registered schedules (#11250)

2022-05-19 16:09:51 -07:00

auto_scheduler.py

[TIR] Use PopenPool instead of multiprocessing.pool (#8492)

2021-08-12 13:35:04 -07:00

autotvm.py

[FIX] Pad feature vectors to the same size in xgboost cost model (#11479)

2022-06-02 16:47:20 -07:00

plugin.py

[CI] Refactor of tvm.testing.requires_* annotations (#11313)

2022-06-03 14:03:08 -07:00

popen_pool.py

[FFI][CYTHON] Release GIL when calling into long running functions (#11461)

2022-05-27 11:14:50 -07:00

tir.py

[Software pipeline] Fix hardcoded index in access_ptr rewriting, add a GPU test with depth 4 (#11495)

2022-05-28 09:47:45 +09:00

usmp.py

[Hexagon] Add USMP tests (#11279)

2022-05-13 15:38:20 -07:00

utils.py

[TIR, CUDA] Add pass to replace global to shared memory copy with cp.async (#11658)

2022-06-09 19:05:18 -07:00