nimlgen/tinygrad
1
0
Fork 0
forked from tinygrad/tinygrad
Code Pull Requests Activity

fix ptx

Browse Source
This commit is contained in:
geohot
2025-08-12 10:55:37 -07:00
parent 27396b8eed
commit d319a044a6
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tinygrad/renderer/ptx.py
+1
View File
@@ -38,6 +38,7 @@ doesnt_support_half: tuple[Ops, ...] = tuple(op for op in asm_for_op.keys() if o
ptx_matcher = PatternMatcher([
# bool CMPNE is XOR, bool CMPLT is XOR+AND (universal makes this slow, this is for renderer only)
(UPat.var('x', dtype=dtypes.bool).ne(UPat.var('y')), lambda x,y: x^y),
(UPat.var('x', dtype=dtypes.bool).alu(Ops.CMPEQ, UPat.var('y')), lambda x,y: (x^y)^True),
(UPat.var('x', dtype=dtypes.bool)<UPat.var('y'), lambda x,y: (x^True)&y),
# upcast to float32 all the ops that don't support half
(UPat(doesnt_support_half, dtype=dtypes.half, name="x"),