[Bug target/114481] New: [14 Regression] 14% exec time slowdown of 433.milc on aarch64

[Bug target/114481] New: [14 Regression] 14% exec time slowdown of 433.milc on aarch64

[pheeck at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=114481

            Bug ID: 114481
           Summary: [14 Regression] 14% exec time slowdown of 433.milc on
                    aarch64
           Product: gcc
           Version: 14.0
            Status: UNCONFIRMED
          Keywords: missed-optimization, needs-bisection
          Severity: normal
          Priority: P3
         Component: target
          Assignee: unassigned at gcc dot gnu.org
          Reporter: pheeck at gcc dot gnu.org
            Blocks: 26163
  Target Milestone: ---
              Host: aarch64-gnu-linux
            Target: aarch64-gnu-linux

As seen here

https://lnt.opensuse.org/db_default/v4/SPEC/graph?plot.0=686.70.0

between the commits

g:8b483cd5521de79c
g:81ee1298b47d3f3b

there was an 14% runtime slowdown of 433.milc on aarch64. The CPU is Ampere
Altra Neoverse N1. The compilation options were -O2 -flto PGO.

---

Btw here is a plot that also includes GCC13 and GCC12.

https://lnt.opensuse.org/db_default/v4/SPEC/graph?plot.0=686.70.0&plot.4=749.70.0&plot.5=869.70.0


Referenced Bugs:

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=26163
[Bug 26163] [meta-bug] missed optimization in SPEC (2k17, 2k and 2k6 and 95)

[Bug target/114481] [14 Regression] 14% exec time slowdown of 433.milc on aarch64

[pheeck at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=114481

Filip Kastl <pheeck at gcc dot gnu.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
   Target Milestone|---                         |14.0

[Bug target/114481] [14 Regression] 14% exec time slowdown of 433.milc on aarch64

[rguenth at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=114481

--- Comment #1 from Richard Biener <rguenth at gcc dot gnu.org> ---
Looks like speed is back to 12/13, so possibly not a regression.

[Bug target/114481] 14% exec time slowdown of 433.milc on aarch64

[pheeck at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=114481

Filip Kastl <pheeck at gcc dot gnu.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
            Summary|[14 Regression] 14% exec    |14% exec time slowdown of
                   |time slowdown of 433.milc   |433.milc on aarch64
                   |on aarch64                  |

--- Comment #2 from Filip Kastl <pheeck at gcc dot gnu.org> ---
(In reply to Richard Biener from comment #1)
> Looks like speed is back to 12/13, so possibly not a regression.

Ah, I misunderstood what [14 Regression] means exactly. I'll remove it from the
bug's name.

[Bug target/114481] 14% exec time slowdown of 433.milc on aarch64

[rguenth at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=114481

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

           What    |Removed                     |Added
----------------------------------------------------------------------------
   Target Milestone|14.0                        |14.2

--- Comment #3 from Richard Biener <rguenth at gcc dot gnu.org> ---
GCC 14.1 is being released, retargeting bugs to GCC 14.2.