https://gcc.gnu.org/bugzilla/show_bug.cgi?id=86702
Bug ID: 86702
Summary: [8/9 Regression] SPEC CPU2006 400.perlbench, CPU2017
500.perlbench_r ~3% performance drop after r262247
Product: gcc
Version: unknown
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: tree-optimization
Assignee: unassigned at gcc dot gnu.org
Reporter: alexander.nesterovskiy at intel dot com
Target Milestone: ---
Created attachment 44453
--> https://gcc.gnu.org/bugzilla/attachment.cgi?id=44453&action=edit
reproducer
It looks like some branch probabilities information is being lost in some cases
after r262247 during tree-switchlower1.
As a result there are performance drops of ~3% for SPEC CPU2006/2017 perlbench
with some particular compilation options/HW configurations because of a more
heavy spilling/filling in hot block.
It can be illustrated with a small example:
---
$ cat > reproducer.c
int foo(int bar)
{
switch (bar)
{
case 0:
return bar + 5;
case 1:
return bar - 4;
case 2:
return bar + 3;
case 3:
return bar - 2;
case 4:
return bar + 1;
case 5:
return bar;
default:
return 0;
}
}
^Z
[2]+ Stopped cat > reproducer.c
$ ./r262246/bin/gcc -m64 -c -o /dev/null -O1
-fdump-tree-switchlower1=r262246_168t.switchlower1 reproducer.c
$ ./r262247/bin/gcc -m64 -c -o /dev/null -O1
-fdump-tree-switchlower1=r262247_168t.switchlower1 reproducer.c
$ cat r262246_168t.switchlower1
;; Function foo (foo, funcdef_no=0, decl_uid=2007, cgraph_uid=1,
symbol_order=0)
beginning to process the following SWITCH statement (reproducer.c:3) : -------
switch (bar_2(D)) <default: <L6> [14.29%], case 0: <L9> [57.14%], case 1: <L8>
[14.29%], case 2: <L9> [57.14%], case 3: <L3> [14.29%], case 4 ... 5: <L9>
[57.14%]>
;; GIMPLE switch case clusters: JT:0-5
Removing basic block 9
Merging blocks 2 and 8
Merging blocks 2 and 7
Symbols to be put in SSA form
{ D.2019 }
Incremental SSA update started at block: 0
Number of blocks in CFG: 7
Number of blocks to update: 6 ( 86%)
foo (int bar)
{
int _1;
<bb 2> [local count: 1073419798]:
switch (bar_2(D)) <default: <L6> [14.29%], case 0: <L9> [57.14%], case 1:
<L8> [14.29%], case 2: <L9> [57.14%], case 3: <L3> [14.29%], case 4 ... 5: <L9>
[57.14%]>
<bb 3> [local count: 613382737]:
<L9>:
goto <bb 6>; [100.00%]
<bb 4> [local count: 153391689]:
<L3>:
goto <bb 6>; [100.00%]
<bb 5> [local count: 153391689]:
<L6>:
<bb 6> [local count: 1073741825]:
# _1 = PHI <0(5), -3(2), 1(4), 5(3)>
<L8>:
return _1;
}
$ cat r262247_168t.switchlower1
;; Function foo (foo, funcdef_no=0, decl_uid=2007, cgraph_uid=1,
symbol_order=0)
beginning to process the following SWITCH statement (reproducer.c:3) : -------
switch (bar_2(D)) <default: <L6> [14.29%], case 0: <L9> [57.14%], case 1: <L8>
[14.29%], case 2: <L9> [57.14%], case 3: <L3> [14.29%], case 4 ... 5: <L9>
[57.14%]>
;; GIMPLE switch case clusters: JT:0-5
Removing basic block 7
Merging blocks 2 and 8
Merging blocks 2 and 9
Symbols to be put in SSA form
{ D.2019 }
Incremental SSA update started at block: 0
Number of blocks in CFG: 7
Number of blocks to update: 6 ( 86%)
foo (int bar)
{
int _1;
<bb 2> [local count: 1073419798]:
switch (bar_2(D)) <default: <L6> [INV], case 0: <L9> [INV], case 1: <L8>
[INV], case 2: <L9> [INV], case 3: <L3> [INV], case 4 ... 5: <L9> [INV]>
<bb 3> [local count: 613382737]:
<L9>:
goto <bb 6>; [100.00%]
<bb 4> [local count: 153391689]:
<L3>:
goto <bb 6>; [100.00%]
<bb 5> [local count: 153391689]:
<L6>:
<bb 6> [local count: 1073741825]:
# _1 = PHI <0(5), -3(2), 1(4), 5(3)>
<L8>:
return _1;
}
---
Same for a current trunk (I tried r263027).
