[PATCH 4/6] arm64/io: Provide a WC friendly __iowriteXX_copy()
Jason Gunthorpe
jgg at nvidia.com
Fri Feb 23 04:53:43 PST 2024
On Fri, Feb 23, 2024 at 11:05:29AM +0000, David Laight wrote:
> ...
> > > > > > + if ((_count % 8) >= 4) {
> > > > >
> > > > > If (_count & 4) {
> > > >
> > > > That would be obfuscating, IMHO. The compiler doesn't need such things
> > > > to generate optimal code.
> > >
> > > Try it: https://godbolt.org/z/EvvGrTxv3
> > > And it isn't that obfuscated - no more so than your version.
> >
> > The godbolt link does "n % 8 > 4" instead of "... >= 4" as in Jason's
> > original code. With ">=" the compiled code matches that for "n & 4".
>
> Bugger :-)
Yes, I already fine tuned things to get good codegen.
Jason
More information about the linux-arm-kernel
mailing list