mirrors/tinygrad
2
0
Fork 0
mirror of https://github.com/tinygrad/tinygrad.git synced 2026-06-24 02:14:17 +00:00
Code Issues Projects Releases Packages Wiki Activity

gep should look at count, not vcount (#9698)

Browse source 
* gep should look at count, not vcount

* gep in order is a rule

* min change

* gep on void
This commit is contained in:
George Hotz 2025-04-02 18:10:57 +08:00 • committed by GitHub
commit ea5caefef0
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 4 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

4
tinygrad/codegen/symbolic.py
View file

@ -180,6 +180,10 @@ gep_pushing = PatternMatcher([
lambda gep, vec: UOp(Ops.VECTORIZE, gep.dtype, tuple(vec.src[i] for i in gep.arg)) if len(gep.arg) > 1 else vec.src[gep.arg[0]]),
(UPat(Ops.GEP, src=(UPat.cvar("c", vec=False),), name="gep"), lambda gep, c: gep.const_like(c.arg)),
(UPat(Ops.GEP, src=(UPat(Ops.VCONST, name="c"),), name="gep"), lambda gep, c: gep.const_like(tuple(c.arg[x] for x in gep.arg))),
# GEP on void is skipped
(UPat(Ops.GEP, src=(UPat(dtype=dtypes.void, name="x"),)), lambda x: x),
# GEP in order is removed
(UPat(Ops.GEP, name="g"), lambda g: g.src[0] if not isinstance(g.dtype, PtrDType) and g.arg == tuple(range(g.src[0].dtype.count)) else None),
# push all GEPs through ALUs (fix arange stuff)
(UPat(Ops.GEP, src=(UPat((*GroupOp.ALU, Ops.CAST, Ops.BITCAST), name='alu'),), name='gep'),
lambda gep,alu: UOp(alu.op, alu.dtype.scalar().vec(gep.dtype.count), tuple(x.gep(gep.arg) for x in alu.src), alu.arg) \

1
tinygrad/ops.py
View file

@ -387,7 +387,6 @@ class UOp(MathTrait, metaclass=UOpMetaClass):
if self.op is Ops.VCONST: return UOp.const(self.dtype.scalar(), self.arg[i])
if self.op is Ops.CONST: return UOp.const(self.dtype.scalar(), self.arg)
i = (i,)
if (self.dtype.vcount == len(i) and i == tuple(range(len(i)))) or self.dtype == dtypes.void: return self
return UOp(Ops.GEP, self.dtype.scalar().vec(len(i)) if len(i) > 1 else self.dtype.scalar(), (self,), i)
def load(self, *src:UOp, **kwargs): return UOp(Ops.LOAD, src=(self,)+src, **kwargs)
def store(self, *src:UOp, **kwargs): return UOp(Ops.STORE, dtypes.void, (self,)+src, **kwargs)