diff mbox series

[5/5] libstdc++: Restore unrolling in std::find using pragma [PR116140]

Message ID ZrXhb2QnS2YSw0Mm@arm.com
State New
Headers show
Series Address std::find regression with RTL unrolling [PR116140] | expand

Commit Message

Alex Coplan Aug. 9, 2024, 9:29 a.m. UTC 
Together with the preparatory compiler patches, this patch restores
unrolling in std::__find_if, but this time relying on the compiler to do
it by using:

  #pragma GCC unroll 4

which should restore the majority of the regression relative to the
hand-unrolled version while still being vectorizable with WIP alignment
peeling enhancements.

On Neoverse V1 with LTO, this reduces the regression in xalancbmk (from
SPEC CPU 2017) from 5.8% to 1.7% (restoring ~71% of the lost
performance).

Bootstrapped/regtested on aarch64-linux-gnu, OK for trunk?

Thanks,
Alex

libstdc++-v3/ChangeLog:

	PR libstdc++/116140
	* include/bits/stl_algobase.h (std::__find_if): Add #pragma to
	request GCC to unroll the loop.
---
 libstdc++-v3/include/bits/stl_algobase.h | 1 +
 1 file changed, 1 insertion(+)

Comments

Jonathan Wakely Aug. 20, 2024, 1:25 p.m. UTC | #1 
On Fri, 9 Aug 2024 at 10:29, Alex Coplan <alex.coplan@arm.com> wrote:
>
> Together with the preparatory compiler patches, this patch restores
> unrolling in std::__find_if, but this time relying on the compiler to do
> it by using:
>
>   #pragma GCC unroll 4
>
> which should restore the majority of the regression relative to the
> hand-unrolled version while still being vectorizable with WIP alignment
> peeling enhancements.
>
> On Neoverse V1 with LTO, this reduces the regression in xalancbmk (from
> SPEC CPU 2017) from 5.8% to 1.7% (restoring ~71% of the lost
> performance).
>
> Bootstrapped/regtested on aarch64-linux-gnu, OK for trunk?

Yes, OK - thanks.

>
> Thanks,
> Alex
>
> libstdc++-v3/ChangeLog:
>
>         PR libstdc++/116140
>         * include/bits/stl_algobase.h (std::__find_if): Add #pragma to
>         request GCC to unroll the loop.
> ---
>  libstdc++-v3/include/bits/stl_algobase.h | 1 +
>  1 file changed, 1 insertion(+)
>
diff mbox series

Patch

diff --git a/libstdc++-v3/include/bits/stl_algobase.h b/libstdc++-v3/include/bits/stl_algobase.h
index 27f6c377ad6..f13662fc448 100644
--- a/libstdc++-v3/include/bits/stl_algobase.h
+++ b/libstdc++-v3/include/bits/stl_algobase.h
@@ -2104,6 +2104,7 @@  _GLIBCXX_END_NAMESPACE_ALGO
     inline _Iterator
     __find_if(_Iterator __first, _Iterator __last, _Predicate __pred)
     {
+#pragma GCC unroll 4
       while (__first != __last && !__pred(__first))
 	++__first;
       return __first;