* [PATCH 3/3] Increase iterations for autofdo tests
2019-01-14 8:20 ` [PATCH 2/3] Fix autoprofiledbootstrap Andi Kleen
@ 2019-01-14 8:20 ` Andi Kleen
2019-01-14 9:08 ` Richard Biener
2019-01-14 9:04 ` [PATCH 2/3] Fix autoprofiledbootstrap Richard Biener
2019-01-14 9:11 ` Bin.Cheng
2 siblings, 1 reply; 7+ messages in thread
From: Andi Kleen @ 2019-01-14 8:20 UTC (permalink / raw)
To: gcc-patches; +Cc: amker.cheng, Andi Kleen
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(-)
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
^ permalink raw reply [flat|nested] 7+ messages in thread* Re: [PATCH 3/3] Increase iterations for autofdo tests
2019-01-14 8:20 ` [PATCH 3/3] Increase iterations for autofdo tests Andi Kleen
@ 2019-01-14 9:08 ` Richard Biener
0 siblings, 0 replies; 7+ messages in thread
From: Richard Biener @ 2019-01-14 9:08 UTC (permalink / raw)
To: Andi Kleen; +Cc: GCC Patches, Amker.Cheng, Andi Kleen
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
>
^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: [PATCH 2/3] Fix autoprofiledbootstrap
2019-01-14 8:20 ` [PATCH 2/3] Fix autoprofiledbootstrap Andi Kleen
2019-01-14 8:20 ` [PATCH 3/3] Increase iterations for autofdo tests Andi Kleen
@ 2019-01-14 9:04 ` Richard Biener
2019-01-14 9:11 ` Bin.Cheng
2 siblings, 0 replies; 7+ messages in thread
From: Richard Biener @ 2019-01-14 9:04 UTC (permalink / raw)
To: Andi Kleen; +Cc: GCC Patches, Amker.Cheng, Andi Kleen
On Mon, Jan 14, 2019 at 9:20 AM Andi Kleen <andi@firstfloor.org> wrote:
>
> From: Andi Kleen <ak@linux.intel.com>
>
> autoprofiledbootstrap fails currently with
>
> In file included from ../../gcc/gcc/hash-table.h:236,
> from ../../gcc/gcc/coretypes.h:440,
> from ../../gcc/gcc/ipa-devirt.c:110:
> In static member function 'static void va_heap::release(vec<T, va_heap, vl_embed>*&) [with T = tree_node*]',
> inlined from 'void vec<T>::release() [with T = tree_node*]' at ../../gcc/gcc/vec.h:1679:20,
> inlined from 'auto_vec<T, N>::~auto_vec() [with T = tree_node*; long unsigned int N = 8]' at ../../gcc/gcc/vec.h:1436:5,
> inlined from 'vec<cgraph_node*> possible_polymorphic_call_targets(tree, long int, ipa_polymorphic_call_context, bool*, void**, bool)' at ../../gcc/gcc/ipa-devirt.c:3099:22:
> ../../gcc/gcc/vec.h:311:10: error: attempt to free a non-heap object 'bases_to_consider' [-Werror=free-nonheap-object]
> 311 | ::free (v);
> | ~~~~~~~^~~
> ../../gcc/gcc/vec.h:311:10: error: attempt to free a non-heap object 'bases_to_consider' [-Werror=free-nonheap-object]
> cc1plus: all warnings being treated as errors
>
> The problem is that auto_vec uses a variable to keep track if the vector
> is on the heap or auto. Normally this gets constant resolved, but only
> when the right functions are inlined. With autofdo for some reason
> the compiler decides to not inline these vec functions, even though
> they are marked as "inline"
>
> Mark them as ALWAYS_INLINE instead.
This might fix your case but I think it only papers over the issue. Consider
auto_vec<...> vec;
not-inlined-foo (vec);
where the function can end up re-allocating the vector. I think the more
appropriate fix is to add #pragma GCC diagnostic pus/pop and
ignored "-Wfree-nonheap-object" around the inline function (and hope
for the best that works in the inlined contexts...)
Richard.
> gcc/:
>
> 2019-01-14 Andi Kleen <ak@linux.intel.com>
>
> * vec.h (using_auto_storage, release): Mark as ALWAYS_INLINE.
> ---
> gcc/vec.h | 4 ++--
> 1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/gcc/vec.h b/gcc/vec.h
> index 407269c5ad3..1f5b78b1fac 100644
> --- a/gcc/vec.h
> +++ b/gcc/vec.h
> @@ -1664,7 +1664,7 @@ vec<T, va_heap, vl_ptr>::create (unsigned nelems MEM_STAT_DECL)
> /* Free the memory occupied by the embedded vector. */
>
> template<typename T>
> -inline void
> +ALWAYS_INLINE void
> vec<T, va_heap, vl_ptr>::release (void)
> {
> if (!m_vec)
> @@ -1940,7 +1940,7 @@ vec<T, va_heap, vl_ptr>::reverse (void)
> }
>
> template<typename T>
> -inline bool
> +ALWAYS_INLINE bool
> vec<T, va_heap, vl_ptr>::using_auto_storage () const
> {
> return m_vec->m_vecpfx.m_using_auto_storage;
> --
> 2.19.1
>
^ permalink raw reply [flat|nested] 7+ messages in thread* Re: [PATCH 2/3] Fix autoprofiledbootstrap
2019-01-14 8:20 ` [PATCH 2/3] Fix autoprofiledbootstrap Andi Kleen
2019-01-14 8:20 ` [PATCH 3/3] Increase iterations for autofdo tests Andi Kleen
2019-01-14 9:04 ` [PATCH 2/3] Fix autoprofiledbootstrap Richard Biener
@ 2019-01-14 9:11 ` Bin.Cheng
2 siblings, 0 replies; 7+ messages in thread
From: Bin.Cheng @ 2019-01-14 9:11 UTC (permalink / raw)
To: Andi Kleen; +Cc: gcc-patches List, Andi Kleen
On Mon, Jan 14, 2019 at 4:20 PM Andi Kleen <andi@firstfloor.org> wrote:
>
> From: Andi Kleen <ak@linux.intel.com>
>
> autoprofiledbootstrap fails currently with
>
> In file included from ../../gcc/gcc/hash-table.h:236,
> from ../../gcc/gcc/coretypes.h:440,
> from ../../gcc/gcc/ipa-devirt.c:110:
> In static member function 'static void va_heap::release(vec<T, va_heap, vl_embed>*&) [with T = tree_node*]',
> inlined from 'void vec<T>::release() [with T = tree_node*]' at ../../gcc/gcc/vec.h:1679:20,
> inlined from 'auto_vec<T, N>::~auto_vec() [with T = tree_node*; long unsigned int N = 8]' at ../../gcc/gcc/vec.h:1436:5,
> inlined from 'vec<cgraph_node*> possible_polymorphic_call_targets(tree, long int, ipa_polymorphic_call_context, bool*, void**, bool)' at ../../gcc/gcc/ipa-devirt.c:3099:22:
> ../../gcc/gcc/vec.h:311:10: error: attempt to free a non-heap object 'bases_to_consider' [-Werror=free-nonheap-object]
> 311 | ::free (v);
> | ~~~~~~~^~~
> ../../gcc/gcc/vec.h:311:10: error: attempt to free a non-heap object 'bases_to_consider' [-Werror=free-nonheap-object]
> cc1plus: all warnings being treated as errors
>
> The problem is that auto_vec uses a variable to keep track if the vector
> is on the heap or auto. Normally this gets constant resolved, but only
> when the right functions are inlined. With autofdo for some reason
> the compiler decides to not inline these vec functions, even though
> they are marked as "inline"
A comment not closely related to this patch. We observed the same
inline behavior in which perf data is inadequate, sometime it has
non-trivial impact on kernel compilation. We have patch fall back to
guessed profile count if the profiled count is of low quality. Will
send it out in GCC10.
Thanks,
bin
>
> Mark them as ALWAYS_INLINE instead.
>
> gcc/:
>
> 2019-01-14 Andi Kleen <ak@linux.intel.com>
>
> * vec.h (using_auto_storage, release): Mark as ALWAYS_INLINE.
> ---
> gcc/vec.h | 4 ++--
> 1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/gcc/vec.h b/gcc/vec.h
> index 407269c5ad3..1f5b78b1fac 100644
> --- a/gcc/vec.h
> +++ b/gcc/vec.h
> @@ -1664,7 +1664,7 @@ vec<T, va_heap, vl_ptr>::create (unsigned nelems MEM_STAT_DECL)
> /* Free the memory occupied by the embedded vector. */
>
> template<typename T>
> -inline void
> +ALWAYS_INLINE void
> vec<T, va_heap, vl_ptr>::release (void)
> {
> if (!m_vec)
> @@ -1940,7 +1940,7 @@ vec<T, va_heap, vl_ptr>::reverse (void)
> }
>
> template<typename T>
> -inline bool
> +ALWAYS_INLINE bool
> vec<T, va_heap, vl_ptr>::using_auto_storage () const
> {
> return m_vec->m_vecpfx.m_using_auto_storage;
> --
> 2.19.1
>
^ permalink raw reply [flat|nested] 7+ messages in thread