[Bug target/96339] New: [SVE] Optimise svlast[ab]

[Bug target/96339] New: [SVE] Optimise svlast[ab]

[rsandifo at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=96339

            Bug ID: 96339
           Summary: [SVE] Optimise svlast[ab]
           Product: gcc
           Version: 11.0
            Status: UNCONFIRMED
          Keywords: missed-optimization
          Severity: enhancement
          Priority: P3
         Component: target
          Assignee: unassigned at gcc dot gnu.org
          Reporter: rsandifo at gcc dot gnu.org
  Target Milestone: ---

For:

#include <arm_sve.h>
int8_t
foo (svint8_t x)
{
  return svlasta (svptrue_pat_b8 (SV_VL1), x);
}

we generate:

        ptrue   p0.b, vl1
        lasta   w0, p0, z0.b
        ret

But this is really a BIT_FIELD_REF with a constant index,
so we can generate:

        umov    w0, v0.b[0]
        ret

(works even on big-endian targets).

We should make svlast_impl fold calls to a BIT_FIELD_REF if:
(1) the predicate input is a constant,
(2) we know at compile time which element the constant selects, and
(3) the selected element ends on or before byte 64

For other cases it is probably better to keep the original call.

(2) excludes variable-length predicate constants if (a) we can't
determine the index of the final 1 bit at compile time or
(b) that index might be beyond the end of the vector

(3) restricts the optimisation to cases that can be handled by
*vec_extract<mode><Vel>_v128 and *vec_extract<mode><Vel>_dup.

[Bug target/96339] [SVE] Optimise svlast[ab]

[belagod at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=96339

Tejas Belagod <belagod at gcc dot gnu.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
                 CC|                            |belagod at gcc dot gnu.org

--- Comment #1 from Tejas Belagod <belagod at gcc dot gnu.org> ---

Small correction - the sequence translates to
          umov    w0, v0.b[1]

[Bug target/96339] [SVE] Optimise svlast[ab]

[belagod at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=96339

Tejas Belagod <belagod at gcc dot gnu.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
             Status|UNCONFIRMED                 |ASSIGNED
   Target Milestone|---                         |12.0
   Last reconfirmed|                            |2021-04-15
     Ever confirmed|0                           |1

[Bug target/96339] [SVE] Optimise svlast[ab]

[prathamesh3492 at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=96339

prathamesh3492 at gcc dot gnu.org changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
                 CC|                            |prathamesh3492 at gcc dot gnu.org

--- Comment #2 from prathamesh3492 at gcc dot gnu.org ---
(In reply to Tejas Belagod from comment #1)
> Small correction - the sequence translates to
>           umov    w0, v0.b[1]

Hi Tejas,
Are you still working on this PR ? If not, can I assign it to myself ?

Thanks,
Prathamesh

[Bug target/96339] [SVE] Optimise svlast[ab]

[belagod at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=96339

--- Comment #3 from Tejas Belagod <belagod at gcc dot gnu.org> ---
> Are you still working on this PR ? If not, can I assign it to myself ?

Yes I am - its almost done - just been busy with a few higher priority things.
I'll find some time to clean it up, test it and post it soon. Just curious - is
there some urgency for this fix?

Thanks,
Tejas.

[Bug target/96339] [SVE] Optimise svlast[ab]

[prathamesh3492 at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=96339

--- Comment #4 from prathamesh3492 at gcc dot gnu.org ---
(In reply to Tejas Belagod from comment #3)
> > Are you still working on this PR ? If not, can I assign it to myself ?
> 
> Yes I am - its almost done - just been busy with a few higher priority
> things. I'll find some time to clean it up, test it and post it soon. Just
> curious - is there some urgency for this fix?
> 
> Thanks,
> Tejas.

Hi Tejas,
Thanks for the heads up. No urgency, I was just looking around for missed
optimizations related to SVE in the bugzilla ;-)

Thanks,
Prathamesh

[Bug target/96339] [SVE] Optimise svlast[ab]

[jakub at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=96339

Jakub Jelinek <jakub at gcc dot gnu.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
   Target Milestone|12.0                        |12.2

--- Comment #5 from Jakub Jelinek <jakub at gcc dot gnu.org> ---
GCC 12.1 is being released, retargeting bugs to GCC 12.2.

[Bug target/96339] [SVE] Optimise svlast[ab]

[rguenth at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=96339

Richard Biener <rguenth at gcc dot gnu.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
   Target Milestone|12.3                        |12.4

--- Comment #7 from Richard Biener <rguenth at gcc dot gnu.org> ---
GCC 12.3 is being released, retargeting bugs to GCC 12.4.

[Bug target/96339] [SVE] Optimise svlast[ab]

[cvs-commit at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=96339

--- Comment #8 from CVS Commits <cvs-commit at gcc dot gnu.org> ---
The master branch has been updated by Tejas Belagod <belagod@gcc.gnu.org>:

https://gcc.gnu.org/g:22d85c10a004f4f5eaf6b68b62a0792faf048bf8

commit r14-1744-g22d85c10a004f4f5eaf6b68b62a0792faf048bf8
Author: Tejas Belagod <tbelagod@arm.com>
Date:   Tue May 11 11:09:03 2021 +0100

    AArch64: [PR96339] Optimise svlast[ab]

      This PR optimizes an SVE intrinsics sequence where
        svlasta (svptrue_pat_b8 (SV_VL1), x)
      a scalar is selected based on a constant predicate and a variable vector.
      This sequence is optimized to return the correspoding element of a NEON
      vector. For eg.
        svlasta (svptrue_pat_b8 (SV_VL1), x)
      returns
        umov    w0, v0.b[1]
      Likewise,
        svlastb (svptrue_pat_b8 (SV_VL1), x)
      returns
         umov    w0, v0.b[0]
      This optimization only works provided the constant predicate maps to a
range
      that is within the bounds of a 128-bit NEON register.

    gcc/ChangeLog:

            PR target/96339
            * config/aarch64/aarch64-sve-builtins-base.cc (svlast_impl::fold):
Fold sve
            calls that have a constant input predicate vector.
            (svlast_impl::is_lasta): Query to check if intrinsic is svlasta.
            (svlast_impl::is_lastb): Query to check if intrinsic is svlastb.
            (svlast_impl::vect_all_same): Check if all vector elements are
equal.

    gcc/testsuite/ChangeLog:

            PR target/96339
            * gcc.target/aarch64/sve/acle/general-c/svlast.c: New.
            * gcc.target/aarch64/sve/acle/general-c/svlast128_run.c: New.
            * gcc.target/aarch64/sve/acle/general-c/svlast256_run.c: New.
            * gcc.target/aarch64/sve/pcs/return_4.c (caller_bf16): Fix asm
            to expect optimized code for function body.
            * gcc.target/aarch64/sve/pcs/return_4_128.c (caller_bf16):
Likewise.
            * gcc.target/aarch64/sve/pcs/return_4_256.c (caller_bf16):
Likewise.
            * gcc.target/aarch64/sve/pcs/return_4_512.c (caller_bf16):
Likewise.
            * gcc.target/aarch64/sve/pcs/return_4_1024.c (caller_bf16):
Likewise.
            * gcc.target/aarch64/sve/pcs/return_4_2048.c (caller_bf16):
Likewise.
            * gcc.target/aarch64/sve/pcs/return_5.c (caller_bf16): Likewise.
            * gcc.target/aarch64/sve/pcs/return_5_128.c (caller_bf16):
Likewise.
            * gcc.target/aarch64/sve/pcs/return_5_256.c (caller_bf16):
Likewise.
            * gcc.target/aarch64/sve/pcs/return_5_512.c (caller_bf16):
Likewise.
            * gcc.target/aarch64/sve/pcs/return_5_1024.c (caller_bf16):
Likewise.
            * gcc.target/aarch64/sve/pcs/return_5_2048.c (caller_bf16):
Likewise.

[Bug target/96339] [SVE] Optimise svlast[ab]

[belagod at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=96339

Tejas Belagod <belagod at gcc dot gnu.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
         Resolution|---                         |FIXED
             Status|ASSIGNED                    |RESOLVED
   Target Milestone|12.4                        |14.0

--- Comment #9 from Tejas Belagod <belagod at gcc dot gnu.org> ---
Now fixed on master.