| Message ID | 20190114081942.9088-3-andi@firstfloor.org |
|---|---|
| State | New |
| Headers | show |
| Series | [1/3] Lower sampling rate for autofdo bootstrap | expand |
On Mon, Jan 14, 2019 at 9:20 AM Andi Kleen <andi@firstfloor.org> wrote: > > From: Andi Kleen <ak@linux.intel.com> > > Bin cheng pointed out that the autofdo tests are unstable because they > don't have enough iterations for the perf sampling to get enough data. > > Increase the iterations, but only for autofdo. This avoids any impact > on targets that use a slow emulator, which will never run the host > only autofdo tests. Can you instead use sth like AFDO_ITER_FACTOR #defined to 1 if not defined? > gcc/testsuite/: > > 2019-01-14 Andi Kleen <ak@linux.intel.com> > > * g++.dg/tree-prof/morefunc.C (ITER): Add. > (test1): Use. > (test2): Use. > * gcc.dg/tree-prof/cold_partition_label.c (ITER): Add. > (main): Use. > * gcc.dg/tree-prof/crossmodule-indircall-1.c (ITER): Add. > (main): Use > * gcc.dg/tree-prof/indir-call-prof.c (ITER): Add. > (main): Use. > * gcc.dg/tree-prof/peel-1.c (ITER): Add. > (t): Use. > (main): Use. > * gcc.dg/tree-prof/pr52027.c (ITER): Add. > (main): Use. > * gcc.dg/tree-prof/tracer-1.c (ITER): Add. > (main): Use. > * gcc.dg/tree-prof/unroll-1.c (ITER): Add. > (t): Use. > (main): Use. > * gcc.dg/tree-prof/update-cunroll-2.c (ITER): Add. > (main): Use. > * lib/profopt.exp: Pass -DITER to autofdo compilations. > --- > gcc/testsuite/g++.dg/tree-prof/morefunc.C | 8 ++++++-- > gcc/testsuite/gcc.dg/tree-prof/cold_partition_label.c | 6 +++++- > .../gcc.dg/tree-prof/crossmodule-indircall-1.c | 10 +++++++--- > gcc/testsuite/gcc.dg/tree-prof/indir-call-prof.c | 6 +++++- > gcc/testsuite/gcc.dg/tree-prof/peel-1.c | 10 +++++++--- > gcc/testsuite/gcc.dg/tree-prof/pr52027.c | 6 +++++- > gcc/testsuite/gcc.dg/tree-prof/tracer-1.c | 7 ++++++- > gcc/testsuite/gcc.dg/tree-prof/unroll-1.c | 10 +++++++--- > gcc/testsuite/gcc.dg/tree-prof/update-cunroll-2.c | 8 ++++++-- > gcc/testsuite/lib/profopt.exp | 4 ++-- > 10 files changed, 56 insertions(+), 19 deletions(-) > > diff --git a/gcc/testsuite/g++.dg/tree-prof/morefunc.C b/gcc/testsuite/g++.dg/tree-prof/morefunc.C > index a9bdc167f45..02b01c073e9 100644 > --- a/gcc/testsuite/g++.dg/tree-prof/morefunc.C > +++ b/gcc/testsuite/g++.dg/tree-prof/morefunc.C > @@ -2,6 +2,10 @@ > #include "reorder_class1.h" > #include "reorder_class2.h" > > +#ifndef ITER > +#define ITER 1000 > +#endif > + > int g; > > #ifdef _PROFILE_USE > @@ -19,7 +23,7 @@ static __attribute__((always_inline)) > void test1 (A *tc) > { > int i; > - for (i = 0; i < 1000; i++) > + for (i = 0; i < ITER; i++) > g += tc->foo(); > if (g<100) g++; > } > @@ -28,7 +32,7 @@ static __attribute__((always_inline)) > void test2 (B *tc) > { > int i; > - for (i = 0; i < 1000000; i++) > + for (i = 0; i < ITER; i++) > g += tc->foo(); > } > > diff --git a/gcc/testsuite/gcc.dg/tree-prof/cold_partition_label.c b/gcc/testsuite/gcc.dg/tree-prof/cold_partition_label.c > index 450308d6407..099069da6a7 100644 > --- a/gcc/testsuite/gcc.dg/tree-prof/cold_partition_label.c > +++ b/gcc/testsuite/gcc.dg/tree-prof/cold_partition_label.c > @@ -9,6 +9,10 @@ const char *sarr[SIZE]; > const char *buf_hot; > const char *buf_cold; > > +#ifndef ITER > +#define ITER 1000000 > +#endif > + > __attribute__((noinline)) > void > foo (int path) > @@ -32,7 +36,7 @@ main (int argc, char *argv[]) > int i; > buf_hot = "hello"; > buf_cold = "world"; > - for (i = 0; i < 1000000; i++) > + for (i = 0; i < ITER; i++) > foo (argc); > return 0; > } > diff --git a/gcc/testsuite/gcc.dg/tree-prof/crossmodule-indircall-1.c b/gcc/testsuite/gcc.dg/tree-prof/crossmodule-indircall-1.c > index 58109d54dc7..32d22c69c6c 100644 > --- a/gcc/testsuite/gcc.dg/tree-prof/crossmodule-indircall-1.c > +++ b/gcc/testsuite/gcc.dg/tree-prof/crossmodule-indircall-1.c > @@ -2,6 +2,10 @@ > /* { dg-additional-sources "crossmodule-indircall-1a.c" } */ > /* { dg-options "-O3 -flto -DDOJOB=1" } */ > > +#ifndef ITER > +#define ITER 1000 > +#endif > + > int a; > extern void (*p[2])(int n); > void abort (void); > @@ -10,12 +14,12 @@ main() > { int i; > > /* This call shall be converted. */ > - for (i = 0;i<1000;i++) > + for (i = 0;i<ITER;i++) > p[0](1); > /* This call shall not be converted. */ > - for (i = 0;i<1000;i++) > + for (i = 0;i<ITER;i++) > p[i%2](2); > - if (a != 1000) > + if (a != ITER) > abort (); > > return 0; > diff --git a/gcc/testsuite/gcc.dg/tree-prof/indir-call-prof.c b/gcc/testsuite/gcc.dg/tree-prof/indir-call-prof.c > index 53063c3e7fa..8b9dfbb78c7 100644 > --- a/gcc/testsuite/gcc.dg/tree-prof/indir-call-prof.c > +++ b/gcc/testsuite/gcc.dg/tree-prof/indir-call-prof.c > @@ -1,5 +1,9 @@ > /* { dg-options "-O2 -fdump-tree-optimized -fdump-ipa-profile -fdump-ipa-afdo" } */ > > +#ifndef ITER > +#define ITER 100000 > +#endif > + > static int a1 (void) > { > return 10; > @@ -28,7 +32,7 @@ main (void) > int (*p) (void); > int i; > > - for (i = 0; i < 10000000; i ++) > + for (i = 0; i < ITER*100; i++) > { > setp (&p, i); > p (); > diff --git a/gcc/testsuite/gcc.dg/tree-prof/peel-1.c b/gcc/testsuite/gcc.dg/tree-prof/peel-1.c > index 7245b68c1ee..b6ed178e1ad 100644 > --- a/gcc/testsuite/gcc.dg/tree-prof/peel-1.c > +++ b/gcc/testsuite/gcc.dg/tree-prof/peel-1.c > @@ -1,13 +1,17 @@ > /* { dg-options "-O3 -fdump-tree-cunroll-details -fno-unroll-loops -fpeel-loops" } */ > void abort(); > > -int a[1000]; > +#ifndef ITER > +#define ITER 1000 > +#endif > + > +int a[ITER]; > int > __attribute__ ((noinline)) > t() > { > int i; > - for (i=0;i<1000;i++) > + for (i=0;i<ITER;i++) > if (!a[i]) > return 1; > abort (); > @@ -16,7 +20,7 @@ int > main() > { > int i; > - for (i=0;i<1000;i++) > + for (i=0;i<ITER;i++) > t(); > return 0; > } > diff --git a/gcc/testsuite/gcc.dg/tree-prof/pr52027.c b/gcc/testsuite/gcc.dg/tree-prof/pr52027.c > index c46a14b2e86..bf2a83a336d 100644 > --- a/gcc/testsuite/gcc.dg/tree-prof/pr52027.c > +++ b/gcc/testsuite/gcc.dg/tree-prof/pr52027.c > @@ -2,6 +2,10 @@ > /* { dg-require-effective-target freorder } */ > /* { dg-options "-O2 -freorder-blocks-and-partition -fno-reorder-functions" } */ > > +#ifndef ITER > +#define ITER 1000 > +#endif > + > void > foo (int len) > { > @@ -13,7 +17,7 @@ int > main () > { > int i; > - for (i = 0; i < 1000; i++) > + for (i = 0; i < ITER; i++) > foo (8); > return 0; > } > diff --git a/gcc/testsuite/gcc.dg/tree-prof/tracer-1.c b/gcc/testsuite/gcc.dg/tree-prof/tracer-1.c > index 1e64f284ac0..65570a5e96d 100644 > --- a/gcc/testsuite/gcc.dg/tree-prof/tracer-1.c > +++ b/gcc/testsuite/gcc.dg/tree-prof/tracer-1.c > @@ -1,9 +1,14 @@ > /* { dg-options "-O2 -ftracer -fdump-tree-tracer" } */ > + > +#ifndef ITER > +#define ITER 1000 > +#endif > + > volatile int a, b, c; > int main () > { > int i; > - for (i = 0; i < 1000; i++) > + for (i = 0; i < ITER; i++) > { > if (i % 17) > a++; > diff --git a/gcc/testsuite/gcc.dg/tree-prof/unroll-1.c b/gcc/testsuite/gcc.dg/tree-prof/unroll-1.c > index 3ad0cf019b3..3027e75a241 100644 > --- a/gcc/testsuite/gcc.dg/tree-prof/unroll-1.c > +++ b/gcc/testsuite/gcc.dg/tree-prof/unroll-1.c > @@ -1,13 +1,17 @@ > /* { dg-options "-O3 -fdump-rtl-loop2_unroll-details -funroll-loops -fno-peel-loops" } */ > void abort (); > > -int a[1000]; > +#ifndef ITER > +#define ITER 1000 > +#endif > + > +int a[ITER]; > int > __attribute__ ((noinline)) > t() > { > int i; > - for (i=0;i<1000;i++) > + for (i=0;i<ITER;i++) > if (!a[i]) > return 1; > abort (); > @@ -16,7 +20,7 @@ int > main() > { > int i; > - for (i=0;i<1000;i++) > + for (i=0;i<ITER;i++) > t(); > return 0; > } > diff --git a/gcc/testsuite/gcc.dg/tree-prof/update-cunroll-2.c b/gcc/testsuite/gcc.dg/tree-prof/update-cunroll-2.c > index c286816cdf8..de2d03ebaee 100644 > --- a/gcc/testsuite/gcc.dg/tree-prof/update-cunroll-2.c > +++ b/gcc/testsuite/gcc.dg/tree-prof/update-cunroll-2.c > @@ -1,5 +1,9 @@ > - > /* { dg-options "-O2 -fdump-tree-optimized-blocks" } */ > + > +#ifndef ITER > +#define ITER 1000 > +#endif > + > int a[8]; > __attribute__ ((noinline)) > int t() > @@ -14,7 +18,7 @@ int > main () > { > int i; > - for (i = 0; i < 1000; i++) > + for (i = 0; i < ITER; i++) > t (); > return 0; > } > diff --git a/gcc/testsuite/lib/profopt.exp b/gcc/testsuite/lib/profopt.exp > index 65494cfd4f6..13e7828bf32 100644 > --- a/gcc/testsuite/lib/profopt.exp > +++ b/gcc/testsuite/lib/profopt.exp > @@ -289,8 +289,8 @@ proc auto-profopt-execute { src } { > return > } > set profile_wrapper [profopt-perf-wrapper] > - set profile_option "-g" > - set feedback_option "-fauto-profile" > + set profile_option "-g -DITER=1000000" > + set feedback_option "-fauto-profile -DITER=1000000" > set run_autofdo 1 > profopt-execute $src > unset profile_wrapper > -- > 2.19.1 >
diff --git a/gcc/testsuite/g++.dg/tree-prof/morefunc.C b/gcc/testsuite/g++.dg/tree-prof/morefunc.C index a9bdc167f45..02b01c073e9 100644 --- a/gcc/testsuite/g++.dg/tree-prof/morefunc.C +++ b/gcc/testsuite/g++.dg/tree-prof/morefunc.C @@ -2,6 +2,10 @@ #include "reorder_class1.h" #include "reorder_class2.h" +#ifndef ITER +#define ITER 1000 +#endif + int g; #ifdef _PROFILE_USE @@ -19,7 +23,7 @@ static __attribute__((always_inline)) void test1 (A *tc) { int i; - for (i = 0; i < 1000; i++) + for (i = 0; i < ITER; i++) g += tc->foo(); if (g<100) g++; } @@ -28,7 +32,7 @@ static __attribute__((always_inline)) void test2 (B *tc) { int i; - for (i = 0; i < 1000000; i++) + for (i = 0; i < ITER; i++) g += tc->foo(); } diff --git a/gcc/testsuite/gcc.dg/tree-prof/cold_partition_label.c b/gcc/testsuite/gcc.dg/tree-prof/cold_partition_label.c index 450308d6407..099069da6a7 100644 --- a/gcc/testsuite/gcc.dg/tree-prof/cold_partition_label.c +++ b/gcc/testsuite/gcc.dg/tree-prof/cold_partition_label.c @@ -9,6 +9,10 @@ const char *sarr[SIZE]; const char *buf_hot; const char *buf_cold; +#ifndef ITER +#define ITER 1000000 +#endif + __attribute__((noinline)) void foo (int path) @@ -32,7 +36,7 @@ main (int argc, char *argv[]) int i; buf_hot = "hello"; buf_cold = "world"; - for (i = 0; i < 1000000; i++) + for (i = 0; i < ITER; i++) foo (argc); return 0; } diff --git a/gcc/testsuite/gcc.dg/tree-prof/crossmodule-indircall-1.c b/gcc/testsuite/gcc.dg/tree-prof/crossmodule-indircall-1.c index 58109d54dc7..32d22c69c6c 100644 --- a/gcc/testsuite/gcc.dg/tree-prof/crossmodule-indircall-1.c +++ b/gcc/testsuite/gcc.dg/tree-prof/crossmodule-indircall-1.c @@ -2,6 +2,10 @@ /* { dg-additional-sources "crossmodule-indircall-1a.c" } */ /* { dg-options "-O3 -flto -DDOJOB=1" } */ +#ifndef ITER +#define ITER 1000 +#endif + int a; extern void (*p[2])(int n); void abort (void); @@ -10,12 +14,12 @@ main() { int i; /* This call shall be converted. */ - for (i = 0;i<1000;i++) + for (i = 0;i<ITER;i++) p[0](1); /* This call shall not be converted. */ - for (i = 0;i<1000;i++) + for (i = 0;i<ITER;i++) p[i%2](2); - if (a != 1000) + if (a != ITER) abort (); return 0; diff --git a/gcc/testsuite/gcc.dg/tree-prof/indir-call-prof.c b/gcc/testsuite/gcc.dg/tree-prof/indir-call-prof.c index 53063c3e7fa..8b9dfbb78c7 100644 --- a/gcc/testsuite/gcc.dg/tree-prof/indir-call-prof.c +++ b/gcc/testsuite/gcc.dg/tree-prof/indir-call-prof.c @@ -1,5 +1,9 @@ /* { dg-options "-O2 -fdump-tree-optimized -fdump-ipa-profile -fdump-ipa-afdo" } */ +#ifndef ITER +#define ITER 100000 +#endif + static int a1 (void) { return 10; @@ -28,7 +32,7 @@ main (void) int (*p) (void); int i; - for (i = 0; i < 10000000; i ++) + for (i = 0; i < ITER*100; i++) { setp (&p, i); p (); diff --git a/gcc/testsuite/gcc.dg/tree-prof/peel-1.c b/gcc/testsuite/gcc.dg/tree-prof/peel-1.c index 7245b68c1ee..b6ed178e1ad 100644 --- a/gcc/testsuite/gcc.dg/tree-prof/peel-1.c +++ b/gcc/testsuite/gcc.dg/tree-prof/peel-1.c @@ -1,13 +1,17 @@ /* { dg-options "-O3 -fdump-tree-cunroll-details -fno-unroll-loops -fpeel-loops" } */ void abort(); -int a[1000]; +#ifndef ITER +#define ITER 1000 +#endif + +int a[ITER]; int __attribute__ ((noinline)) t() { int i; - for (i=0;i<1000;i++) + for (i=0;i<ITER;i++) if (!a[i]) return 1; abort (); @@ -16,7 +20,7 @@ int main() { int i; - for (i=0;i<1000;i++) + for (i=0;i<ITER;i++) t(); return 0; } diff --git a/gcc/testsuite/gcc.dg/tree-prof/pr52027.c b/gcc/testsuite/gcc.dg/tree-prof/pr52027.c index c46a14b2e86..bf2a83a336d 100644 --- a/gcc/testsuite/gcc.dg/tree-prof/pr52027.c +++ b/gcc/testsuite/gcc.dg/tree-prof/pr52027.c @@ -2,6 +2,10 @@ /* { dg-require-effective-target freorder } */ /* { dg-options "-O2 -freorder-blocks-and-partition -fno-reorder-functions" } */ +#ifndef ITER +#define ITER 1000 +#endif + void foo (int len) { @@ -13,7 +17,7 @@ int main () { int i; - for (i = 0; i < 1000; i++) + for (i = 0; i < ITER; i++) foo (8); return 0; } diff --git a/gcc/testsuite/gcc.dg/tree-prof/tracer-1.c b/gcc/testsuite/gcc.dg/tree-prof/tracer-1.c index 1e64f284ac0..65570a5e96d 100644 --- a/gcc/testsuite/gcc.dg/tree-prof/tracer-1.c +++ b/gcc/testsuite/gcc.dg/tree-prof/tracer-1.c @@ -1,9 +1,14 @@ /* { dg-options "-O2 -ftracer -fdump-tree-tracer" } */ + +#ifndef ITER +#define ITER 1000 +#endif + volatile int a, b, c; int main () { int i; - for (i = 0; i < 1000; i++) + for (i = 0; i < ITER; i++) { if (i % 17) a++; diff --git a/gcc/testsuite/gcc.dg/tree-prof/unroll-1.c b/gcc/testsuite/gcc.dg/tree-prof/unroll-1.c index 3ad0cf019b3..3027e75a241 100644 --- a/gcc/testsuite/gcc.dg/tree-prof/unroll-1.c +++ b/gcc/testsuite/gcc.dg/tree-prof/unroll-1.c @@ -1,13 +1,17 @@ /* { dg-options "-O3 -fdump-rtl-loop2_unroll-details -funroll-loops -fno-peel-loops" } */ void abort (); -int a[1000]; +#ifndef ITER +#define ITER 1000 +#endif + +int a[ITER]; int __attribute__ ((noinline)) t() { int i; - for (i=0;i<1000;i++) + for (i=0;i<ITER;i++) if (!a[i]) return 1; abort (); @@ -16,7 +20,7 @@ int main() { int i; - for (i=0;i<1000;i++) + for (i=0;i<ITER;i++) t(); return 0; } diff --git a/gcc/testsuite/gcc.dg/tree-prof/update-cunroll-2.c b/gcc/testsuite/gcc.dg/tree-prof/update-cunroll-2.c index c286816cdf8..de2d03ebaee 100644 --- a/gcc/testsuite/gcc.dg/tree-prof/update-cunroll-2.c +++ b/gcc/testsuite/gcc.dg/tree-prof/update-cunroll-2.c @@ -1,5 +1,9 @@ - /* { dg-options "-O2 -fdump-tree-optimized-blocks" } */ + +#ifndef ITER +#define ITER 1000 +#endif + int a[8]; __attribute__ ((noinline)) int t() @@ -14,7 +18,7 @@ int main () { int i; - for (i = 0; i < 1000; i++) + for (i = 0; i < ITER; i++) t (); return 0; } diff --git a/gcc/testsuite/lib/profopt.exp b/gcc/testsuite/lib/profopt.exp index 65494cfd4f6..13e7828bf32 100644 --- a/gcc/testsuite/lib/profopt.exp +++ b/gcc/testsuite/lib/profopt.exp @@ -289,8 +289,8 @@ proc auto-profopt-execute { src } { return } set profile_wrapper [profopt-perf-wrapper] - set profile_option "-g" - set feedback_option "-fauto-profile" + set profile_option "-g -DITER=1000000" + set feedback_option "-fauto-profile -DITER=1000000" set run_autofdo 1 profopt-execute $src unset profile_wrapper
From: Andi Kleen <ak@linux.intel.com> Bin cheng pointed out that the autofdo tests are unstable because they don't have enough iterations for the perf sampling to get enough data. Increase the iterations, but only for autofdo. This avoids any impact on targets that use a slow emulator, which will never run the host only autofdo tests. gcc/testsuite/: 2019-01-14 Andi Kleen <ak@linux.intel.com> * g++.dg/tree-prof/morefunc.C (ITER): Add. (test1): Use. (test2): Use. * gcc.dg/tree-prof/cold_partition_label.c (ITER): Add. (main): Use. * gcc.dg/tree-prof/crossmodule-indircall-1.c (ITER): Add. (main): Use * gcc.dg/tree-prof/indir-call-prof.c (ITER): Add. (main): Use. * gcc.dg/tree-prof/peel-1.c (ITER): Add. (t): Use. (main): Use. * gcc.dg/tree-prof/pr52027.c (ITER): Add. (main): Use. * gcc.dg/tree-prof/tracer-1.c (ITER): Add. (main): Use. * gcc.dg/tree-prof/unroll-1.c (ITER): Add. (t): Use. (main): Use. * gcc.dg/tree-prof/update-cunroll-2.c (ITER): Add. (main): Use. * lib/profopt.exp: Pass -DITER to autofdo compilations. --- gcc/testsuite/g++.dg/tree-prof/morefunc.C | 8 ++++++-- gcc/testsuite/gcc.dg/tree-prof/cold_partition_label.c | 6 +++++- .../gcc.dg/tree-prof/crossmodule-indircall-1.c | 10 +++++++--- gcc/testsuite/gcc.dg/tree-prof/indir-call-prof.c | 6 +++++- gcc/testsuite/gcc.dg/tree-prof/peel-1.c | 10 +++++++--- gcc/testsuite/gcc.dg/tree-prof/pr52027.c | 6 +++++- gcc/testsuite/gcc.dg/tree-prof/tracer-1.c | 7 ++++++- gcc/testsuite/gcc.dg/tree-prof/unroll-1.c | 10 +++++++--- gcc/testsuite/gcc.dg/tree-prof/update-cunroll-2.c | 8 ++++++-- gcc/testsuite/lib/profopt.exp | 4 ++-- 10 files changed, 56 insertions(+), 19 deletions(-)