rampitec wrote:
> I've taken another look at this. The patch does not show any benefit from
> running another `SIFoldOperands` pass _after_ `SIShrinkInstructions` per se;
> you get exactly the same results (modulo a couple of add instructions that
> have their operands commuted differently) if
jayfoad wrote:
I've taken another look at this. The patch does not show any benefit from
running another `SIFoldOperands` pass _after_ `SIShrinkInstructions` per se;
you get exactly the same results (modulo a couple of add instructions that have
their operands commuted differently) if you put
jayfoad wrote:
> > > I've just tested this on 1 graphics shaders and it seems to make no
> > > difference at all. I tried gfx900 and gfx1100. Can anyone else from the
> > > graphics team confirm this?
> >
> >
> > I can confirm no difference on gfx1102
>
> gfx11 is the same as gfx10, it j
rampitec wrote:
I have measured compile time performance impact with timing
check-llvm-codegen-amdgpu on the release build:
```
before the patch: 11.06s
add folding:11.09s +0.2%
remove folding from shrink: 11.02s -0.4%
```
In general the impact smaller than run to run
rampitec wrote:
> I've just tested this on 1 graphics shaders and it seems to make no
> difference at all. I tried gfx900 and gfx1100. Can anyone else from the
> graphics team confirm this?
It seems the most impact is on the pre-gfx9 targets, very similar to
https://github.com/llvm/llvm-p
Sisyph wrote:
> I've just tested this on 1 graphics shaders and it seems to make no
> difference at all. I tried gfx900 and gfx1100. Can anyone else from the
> graphics team confirm this?
I can confirm no difference on gfx1102
https://github.com/llvm/llvm-project/pull/67878
__
jayfoad wrote:
I've just tested this on 1 graphics shaders and it seems to make no
difference at all. I tried gfx900 and gfx1100. Can anyone else from the
graphics team confirm this?
https://github.com/llvm/llvm-project/pull/67878
___
cfe-commits
