tinygrad/tinygrad
George Hotz 07df14aa0e
HIP cleanups (#2843)
* move everything to code_for_op to reason about it

* loop the loopable parts

* its not that unreadable

* these are loopable too

* nitpick

* tests p1 - replace these with the actual compiler running alu ops tests

* tests p2: compile test_dtype_alu in HIP!

+add to CI

* nobody liked test_renderer

* revert test_dtypes change

* isolated mockhip tests

* dont need the WHERE hack after #2782

+ruff

* bf16 is broken in HIP

job failed in: https://github.com/tinygrad/tinygrad/actions/runs/7232101987/job/19705951290?pr=2778#step:8:73

* picking this back up

* add compile tests for unary ops and binary ops

* MOD is only in ints

* CMPLT wont work after the dtypes pr is merged because it will always be bool

* test all combinations

* Update cstyle.py

* don't use vload

* no getenv

* set seed

---------

Co-authored-by: qazal <qazal.software@gmail.com>
Co-authored-by: qazal <77887910+Qazalin@users.noreply.github.com>
2023-12-18 21:09:32 -08:00
..
codegen minor clean up in kernels (#2832) 2023-12-18 19:35:59 -05:00
features move graph to runtime, check line count with sz.py (#2842) 2023-12-18 20:30:06 -08:00
nn changes to prep for new lazy (#2748) 2023-12-13 10:28:22 -08:00
renderer HIP cleanups (#2843) 2023-12-18 21:09:32 -08:00
runtime move graph to runtime, check line count with sz.py (#2842) 2023-12-18 20:30:06 -08:00
shape hotfix: add JITGRAPH and invert sints 2023-12-18 16:33:22 -08:00
__init__.py move device to device.py (#2466) 2023-11-27 11:34:37 -08:00
device.py Fix double exception in __del__() when __init__() raises exception. (#2738) 2023-12-13 15:46:11 -08:00
graph.py ruff checks the max line length is 150 (#2734) 2023-12-12 17:34:47 -08:00
helpers.py move graph to runtime, check line count with sz.py (#2842) 2023-12-18 20:30:06 -08:00
jit.py hotfix: add JITGRAPH and invert sints 2023-12-18 16:33:22 -08:00
lazy.py remove pushing contig + fix linearizer bug (#2798) 2023-12-16 09:36:31 -08:00
mlops.py remove match_type in ops_torch and ops_cpu (#2817) 2023-12-17 15:32:30 -05:00
ops.py use least_upper_dtype mlops to upcast the output type in mlops (#2788) 2023-12-15 23:46:57 -05:00
realize.py ruff checks the max line length is 150 (#2734) 2023-12-12 17:34:47 -08:00
tensor.py dtypes.from_py to convert py types to dtypes (#2826) 2023-12-18 14:23:31 -05:00