public inbox for gcc-bugs@sourceware.org
help / color / mirror / Atom feed
* [Bug tree-optimization/19803] New: __builtin_expect doesnt modify branch prediction for power4 target
@ 2005-02-07 15:28 anton at samba dot org
  2005-02-07 17:21 ` [Bug target/19803] __builtin_expect does not modify branch prediction for power4/5 pinskia at gcc dot gnu dot org
                   ` (5 more replies)
  0 siblings, 6 replies; 7+ messages in thread
From: anton at samba dot org @ 2005-02-07 15:28 UTC (permalink / raw)
  To: gcc-bugs

gcc version 4.0.0 20050203 (experimental)

The following code snippet shows how branch prediction isnt used even when
specifying builtin_expect. flags used: -O2 -mcpu=power4

#if 1
#define likely(x)       __builtin_expect(!!(x), 1)
#else
#define likely(x) x
#endif

int i;

void foo(void)
{
        while (likely(i--)) {
                bar();
        }

}

...

        b .L2
        .p2align 4,,15
.L3:
        bl bar
        nop
.L2:
        lwz 9,0(31)
        addi 9,9,-1
        extsw 9,9
        cmpwi 7,9,-1
        stw 9,0(31)
        bne 7,.L3

-- 
           Summary: __builtin_expect doesnt modify branch prediction for
                    power4 target
           Product: gcc
           Version: 4.0.0
            Status: UNCONFIRMED
          Severity: enhancement
          Priority: P2
         Component: tree-optimization
        AssignedTo: unassigned at gcc dot gnu dot org
        ReportedBy: anton at samba dot org
                CC: gcc-bugs at gcc dot gnu dot org
GCC target triplet: powerpc64-unknown-linux-gnu


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=19803


^ permalink raw reply	[flat|nested] 7+ messages in thread

* [Bug tree-optimization/19803] __builtin_expect doesnt modify branch prediction for power4 target
  2005-02-07 15:28 [Bug tree-optimization/19803] New: __builtin_expect doesnt modify branch prediction for power4 target anton at samba dot org
  2005-02-07 17:21 ` [Bug target/19803] __builtin_expect does not modify branch prediction for power4/5 pinskia at gcc dot gnu dot org
@ 2005-02-07 17:21 ` amodra at bigpond dot net dot au
  2005-02-07 17:25 ` [Bug target/19803] __builtin_expect does not modify branch prediction for power4/5 amodra at bigpond dot net dot au
                   ` (3 subsequent siblings)
  5 siblings, 0 replies; 7+ messages in thread
From: amodra at bigpond dot net dot au @ 2005-02-07 17:21 UTC (permalink / raw)
  To: gcc-bugs


------- Additional Comments From amodra at bigpond dot net dot au  2005-02-07 03:28 -------
builtin_expect uses PROB_VERY_LIKELY.

>From predict.c
#define PROB_VERY_UNLIKELY	(REG_BR_PROB_BASE / 10 - 1)
#define PROB_EVEN		(REG_BR_PROB_BASE / 2)
#define PROB_VERY_LIKELY	(REG_BR_PROB_BASE - PROB_VERY_UNLIKELY)
#define PROB_ALWAYS		(REG_BR_PROB_BASE)

In other words, builtin_expect is using 10% / 90%

But powerpc64 only emits branch prediction hints when at 2% / 98%.  See
rs6000.c:output_cbranch

-- 
           What    |Removed                     |Added
----------------------------------------------------------------------------
             Status|UNCONFIRMED                 |NEW
     Ever Confirmed|                            |1
   Last reconfirmed|0000-00-00 00:00:00         |2005-02-07 03:28:18
               date|                            |


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=19803


^ permalink raw reply	[flat|nested] 7+ messages in thread

* [Bug target/19803] __builtin_expect does not modify branch prediction for power4/5
  2005-02-07 15:28 [Bug tree-optimization/19803] New: __builtin_expect doesnt modify branch prediction for power4 target anton at samba dot org
@ 2005-02-07 17:21 ` pinskia at gcc dot gnu dot org
  2005-02-07 17:21 ` [Bug tree-optimization/19803] __builtin_expect doesnt modify branch prediction for power4 target amodra at bigpond dot net dot au
                   ` (4 subsequent siblings)
  5 siblings, 0 replies; 7+ messages in thread
From: pinskia at gcc dot gnu dot org @ 2005-02-07 17:21 UTC (permalink / raw)
  To: gcc-bugs


------- Additional Comments From pinskia at gcc dot gnu dot org  2005-02-07 03:39 -------
(In reply to comment #1)
> builtin_expect uses PROB_VERY_LIKELY.
> 
> But powerpc64 only emits branch prediction hints when at 2% / 98%.  See
> rs6000.c:output_cbranch
This is a target problem as mentioned above.

Hmm, I thought there was a patch floating around to fix this but I could be wrong.

Also note this changed back in 2002 for power4:
<http://gcc.gnu.org/ml/gcc-patches/2002-08/msg00149.html> so in a way it could be considered a 
regression.
It also effects power5 also (and ppc970).

-- 
           What    |Removed                     |Added
----------------------------------------------------------------------------
                 CC|                            |pinskia at gcc dot gnu dot
                   |                            |org
          Component|tree-optimization           |target
 GCC target triplet|powerpc64-unknown-linux-gnu |powerpc*-*-*
            Summary|__builtin_expect doesnt     |__builtin_expect does not
                   |modify branch prediction for|modify branch prediction for
                   |power4 target               |power4/5


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=19803


^ permalink raw reply	[flat|nested] 7+ messages in thread

* [Bug target/19803] __builtin_expect does not modify branch prediction for power4/5
  2005-02-07 15:28 [Bug tree-optimization/19803] New: __builtin_expect doesnt modify branch prediction for power4 target anton at samba dot org
  2005-02-07 17:21 ` [Bug target/19803] __builtin_expect does not modify branch prediction for power4/5 pinskia at gcc dot gnu dot org
  2005-02-07 17:21 ` [Bug tree-optimization/19803] __builtin_expect doesnt modify branch prediction for power4 target amodra at bigpond dot net dot au
@ 2005-02-07 17:25 ` amodra at bigpond dot net dot au
  2005-02-08  9:18 ` cvs-commit at gcc dot gnu dot org
                   ` (2 subsequent siblings)
  5 siblings, 0 replies; 7+ messages in thread
From: amodra at bigpond dot net dot au @ 2005-02-07 17:25 UTC (permalink / raw)
  To: gcc-bugs


------- Additional Comments From amodra at bigpond dot net dot au  2005-02-07 04:47 -------
patch http://gcc.gnu.org/ml/gcc-patches/2005-02/msg00225.html

-- 
           What    |Removed                     |Added
----------------------------------------------------------------------------
           Severity|enhancement                 |normal
           Keywords|                            |patch


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=19803


^ permalink raw reply	[flat|nested] 7+ messages in thread

* [Bug target/19803] __builtin_expect does not modify branch prediction for power4/5
  2005-02-07 15:28 [Bug tree-optimization/19803] New: __builtin_expect doesnt modify branch prediction for power4 target anton at samba dot org
                   ` (2 preceding siblings ...)
  2005-02-07 17:25 ` [Bug target/19803] __builtin_expect does not modify branch prediction for power4/5 amodra at bigpond dot net dot au
@ 2005-02-08  9:18 ` cvs-commit at gcc dot gnu dot org
  2005-02-08  9:19 ` cvs-commit at gcc dot gnu dot org
  2005-02-08  9:25 ` amodra at bigpond dot net dot au
  5 siblings, 0 replies; 7+ messages in thread
From: cvs-commit at gcc dot gnu dot org @ 2005-02-08  9:18 UTC (permalink / raw)
  To: gcc-bugs


------- Additional Comments From cvs-commit at gcc dot gnu dot org  2005-02-07 21:12 -------
Subject: Bug 19803

CVSROOT:	/cvs/gcc
Module name:	gcc
Changes by:	amodra@gcc.gnu.org	2005-02-07 21:11:45

Modified files:
	gcc            : ChangeLog predict.c 

Log message:
	PR target/19803
	* predict.c (PROB_VERY_UNLIKELY): Use 1% instead of 10%.

Patches:
http://gcc.gnu.org/cgi-bin/cvsweb.cgi/gcc/gcc/ChangeLog.diff?cvsroot=gcc&r1=2.7414&r2=2.7415
http://gcc.gnu.org/cgi-bin/cvsweb.cgi/gcc/gcc/predict.c.diff?cvsroot=gcc&r1=1.137&r2=1.138



-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=19803


^ permalink raw reply	[flat|nested] 7+ messages in thread

* [Bug target/19803] __builtin_expect does not modify branch prediction for power4/5
  2005-02-07 15:28 [Bug tree-optimization/19803] New: __builtin_expect doesnt modify branch prediction for power4 target anton at samba dot org
                   ` (3 preceding siblings ...)
  2005-02-08  9:18 ` cvs-commit at gcc dot gnu dot org
@ 2005-02-08  9:19 ` cvs-commit at gcc dot gnu dot org
  2005-02-08  9:25 ` amodra at bigpond dot net dot au
  5 siblings, 0 replies; 7+ messages in thread
From: cvs-commit at gcc dot gnu dot org @ 2005-02-08  9:19 UTC (permalink / raw)
  To: gcc-bugs


------- Additional Comments From cvs-commit at gcc dot gnu dot org  2005-02-07 21:18 -------
Subject: Bug 19803

CVSROOT:	/cvs/gcc
Module name:	gcc
Branch: 	gcc-3_4-branch
Changes by:	amodra@gcc.gnu.org	2005-02-07 21:18:33

Modified files:
	gcc            : ChangeLog predict.c 

Log message:
	PR target/19803
	* predict.c (PROB_VERY_UNLIKELY): Use 1% instead of 10%.

Patches:
http://gcc.gnu.org/cgi-bin/cvsweb.cgi/gcc/gcc/ChangeLog.diff?cvsroot=gcc&only_with_tag=gcc-3_4-branch&r1=2.2326.2.794&r2=2.2326.2.795
http://gcc.gnu.org/cgi-bin/cvsweb.cgi/gcc/gcc/predict.c.diff?cvsroot=gcc&only_with_tag=gcc-3_4-branch&r1=1.98&r2=1.98.2.1



-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=19803


^ permalink raw reply	[flat|nested] 7+ messages in thread

* [Bug target/19803] __builtin_expect does not modify branch prediction for power4/5
  2005-02-07 15:28 [Bug tree-optimization/19803] New: __builtin_expect doesnt modify branch prediction for power4 target anton at samba dot org
                   ` (4 preceding siblings ...)
  2005-02-08  9:19 ` cvs-commit at gcc dot gnu dot org
@ 2005-02-08  9:25 ` amodra at bigpond dot net dot au
  5 siblings, 0 replies; 7+ messages in thread
From: amodra at bigpond dot net dot au @ 2005-02-08  9:25 UTC (permalink / raw)
  To: gcc-bugs


------- Additional Comments From amodra at bigpond dot net dot au  2005-02-07 21:23 -------
Fixed.

-- 
           What    |Removed                     |Added
----------------------------------------------------------------------------
             Status|NEW                         |RESOLVED
         Resolution|                            |FIXED
   Target Milestone|---                         |4.0.0


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=19803


^ permalink raw reply	[flat|nested] 7+ messages in thread

end of thread, other threads:[~2005-02-07 21:24 UTC | newest]

Thread overview: 7+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2005-02-07 15:28 [Bug tree-optimization/19803] New: __builtin_expect doesnt modify branch prediction for power4 target anton at samba dot org
2005-02-07 17:21 ` [Bug target/19803] __builtin_expect does not modify branch prediction for power4/5 pinskia at gcc dot gnu dot org
2005-02-07 17:21 ` [Bug tree-optimization/19803] __builtin_expect doesnt modify branch prediction for power4 target amodra at bigpond dot net dot au
2005-02-07 17:25 ` [Bug target/19803] __builtin_expect does not modify branch prediction for power4/5 amodra at bigpond dot net dot au
2005-02-08  9:18 ` cvs-commit at gcc dot gnu dot org
2005-02-08  9:19 ` cvs-commit at gcc dot gnu dot org
2005-02-08  9:25 ` amodra at bigpond dot net dot au

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).