public inbox for gcc-bugs@sourceware.org
help / color / mirror / Atom feed
* [Bug tree-optimization/108839] New: Option for rerolling loops
@ 2023-02-17 17:16 tkoenig at gcc dot gnu.org
2023-02-17 17:19 ` [Bug tree-optimization/108839] " pinskia at gcc dot gnu.org
2023-02-20 8:16 ` rguenth at gcc dot gnu.org
0 siblings, 2 replies; 3+ messages in thread
From: tkoenig at gcc dot gnu.org @ 2023-02-17 17:16 UTC (permalink / raw)
To: gcc-bugs
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=108839
Bug ID: 108839
Summary: Option for rerolling loops
Product: gcc
Version: unknown
Status: UNCONFIRMED
Severity: enhancement
Priority: P3
Component: tree-optimization
Assignee: unassigned at gcc dot gnu.org
Reporter: tkoenig at gcc dot gnu.org
Target Milestone: ---
Code sometimes contains manual unrolling. For example, the BLAS
reference implementation, subroutine DSCAL, has
IF (INCX.EQ.1) THEN
*
* code for increment equal to 1
*
*
* clean-up loop
*
M = MOD(N,5)
IF (M.NE.0) THEN
DO I = 1,M
DX(I) = DA*DX(I)
END DO
IF (N.LT.5) RETURN
END IF
MP1 = M + 1
DO I = MP1,N,5
DX(I) = DA*DX(I)
DX(I+1) = DA*DX(I+1)
DX(I+2) = DA*DX(I+2)
DX(I+3) = DA*DX(I+3)
DX(I+4) = DA*DX(I+4)
END DO
ELSE
While such code may have been beneficial on old architectures, by
now this disturbs the compiler's own unrolling and vectorization,
and it increases code size.
It could be beneficial to have a -freroll-loops option, which
undid the manual unrolling of the code above. This could be
stand-alone, or included in options such as -Os.
^ permalink raw reply [flat|nested] 3+ messages in thread
* [Bug tree-optimization/108839] Option for rerolling loops
2023-02-17 17:16 [Bug tree-optimization/108839] New: Option for rerolling loops tkoenig at gcc dot gnu.org
@ 2023-02-17 17:19 ` pinskia at gcc dot gnu.org
2023-02-20 8:16 ` rguenth at gcc dot gnu.org
1 sibling, 0 replies; 3+ messages in thread
From: pinskia at gcc dot gnu.org @ 2023-02-17 17:19 UTC (permalink / raw)
To: gcc-bugs
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=108839
--- Comment #1 from Andrew Pinski <pinskia at gcc dot gnu.org> ---
Note the SLP vectorizer should kick in for most cases of manually unrolled
loops.
^ permalink raw reply [flat|nested] 3+ messages in thread
* [Bug tree-optimization/108839] Option for rerolling loops
2023-02-17 17:16 [Bug tree-optimization/108839] New: Option for rerolling loops tkoenig at gcc dot gnu.org
2023-02-17 17:19 ` [Bug tree-optimization/108839] " pinskia at gcc dot gnu.org
@ 2023-02-20 8:16 ` rguenth at gcc dot gnu.org
1 sibling, 0 replies; 3+ messages in thread
From: rguenth at gcc dot gnu.org @ 2023-02-20 8:16 UTC (permalink / raw)
To: gcc-bugs
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=108839
Richard Biener <rguenth at gcc dot gnu.org> changed:
What |Removed |Added
----------------------------------------------------------------------------
Ever confirmed|0 |1
Status|UNCONFIRMED |NEW
Blocks| |53947
Last reconfirmed| |2023-02-20
--- Comment #2 from Richard Biener <rguenth at gcc dot gnu.org> ---
Note the SLP loop vectorizer could be used to re-roll loops (for -Os?) by
vectorizing with one element vectors and a "fractional" VF. I just never got
around playing with this idea (even when actually vectorizing but facing
highly manually unrolled code vectorizing with a single vector and a
"fractional" VF might be worth it for example for register pressure reasons).
Referenced Bugs:
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=53947
[Bug 53947] [meta-bug] vectorizer missed-optimizations
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2023-02-20 8:16 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2023-02-17 17:16 [Bug tree-optimization/108839] New: Option for rerolling loops tkoenig at gcc dot gnu.org
2023-02-17 17:19 ` [Bug tree-optimization/108839] " pinskia at gcc dot gnu.org
2023-02-20 8:16 ` rguenth at gcc dot gnu.org
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).