>
> optimize_function_for_speed ()?
>
Yes, updated patch with optimize_function_for_speed_p()
gcc/ChangeLog:
PR target/105034
* config/i386/i386-features.cc (pass_stv::gate()): Add
optimize_function_for_speed_p ().
gcc/testsuite/ChangeLog:
PR target/105034
* gcc.target/i386/pr105034.c: New test.
---
gcc/config/i386/i386-features.cc | 3 ++-
gcc/testsuite/gcc.target/i386/pr105034.c | 23 +++++++++++++++++++++++
2 files changed, 25 insertions(+), 1 deletion(-)
create mode 100644 gcc/testsuite/gcc.target/i386/pr105034.c
diff --git a/gcc/config/i386/i386-features.cc b/gcc/config/i386/i386-features.cc
index 6fe41c3c24f..a49c3aa1525 100644
--- a/gcc/config/i386/i386-features.cc
+++ b/gcc/config/i386/i386-features.cc
@@ -1911,7 +1911,8 @@ public:
virtual bool gate (function *)
{
return ((!timode_p || TARGET_64BIT)
- && TARGET_STV && TARGET_SSE2 && optimize > 1);
+ && TARGET_STV && TARGET_SSE2 && optimize > 1
+ && optimize_function_for_speed_p (cfun));
}
virtual unsigned int execute (function *)
diff --git a/gcc/testsuite/gcc.target/i386/pr105034.c
b/gcc/testsuite/gcc.target/i386/pr105034.c
new file mode 100644
index 00000000000..d997e26e9ed
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr105034.c
@@ -0,0 +1,23 @@
+/* PR target/105034 */
+/* { dg-do compile } */
+/* { dg-options "-Os -msse4.1" } */
+
+#define max(a,b) (((a) > (b))? (a) : (b))
+#define min(a,b) (((a) < (b))? (a) : (b))
+
+int foo(int x)
+{
+ return max(x,0);
+}
+
+int bar(int x)
+{
+ return min(x,0);
+}
+
+unsigned int baz(unsigned int x)
+{
+ return min(x,1);
+}
+
+/* { dg-final { scan-assembler-not "xmm" } } */
--
2.18.1
Richard Biener via Gcc-patches <[email protected]> 于2022年4月14日周四 14:56写道：
>
> On Thu, Apr 14, 2022 at 3:18 AM Hongyu Wang via Gcc-patches
> <[email protected]> wrote:
> >
> > Hi,
> >
> > From -Os point of view, stv converts scalar register to vector mode
> > which introduces extra reg conversion and increase instruction size.
> > Disabling stv under optimize_size would avoid such code size increment
> > and no need to touch ix86_size_cost that has not been tuned for long
> > time.
> >
> > Bootstrapped/regtested on x86_64-pc-linux-gnu{-m32,},
> >
> > Ok for master?
> >
> > gcc/ChangeLog:
> >
> > PR target/105034
> > * config/i386/i386-features.cc (pass_stv::gate()): Block out
> > optimize_size.
> >
> > gcc/testsuite/ChangeLog:
> >
> > PR target/105034
> > * gcc.target/i386/pr105034.c: New test.
> > ---
> > gcc/config/i386/i386-features.cc | 3 ++-
> > gcc/testsuite/gcc.target/i386/pr105034.c | 23 +++++++++++++++++++++++
> > 2 files changed, 25 insertions(+), 1 deletion(-)
> > create mode 100644 gcc/testsuite/gcc.target/i386/pr105034.c
> >
> > diff --git a/gcc/config/i386/i386-features.cc
> > b/gcc/config/i386/i386-features.cc
> > index 6fe41c3c24f..f57281e672f 100644
> > --- a/gcc/config/i386/i386-features.cc
> > +++ b/gcc/config/i386/i386-features.cc
> > @@ -1911,7 +1911,8 @@ public:
> > virtual bool gate (function *)
> > {
> > return ((!timode_p || TARGET_64BIT)
> > - && TARGET_STV && TARGET_SSE2 && optimize > 1);
> > + && TARGET_STV && TARGET_SSE2 && optimize > 1
> > + && !optimize_size);
>
> optimize_function_for_speed ()?
>
> > }
> >
> > virtual unsigned int execute (function *)
> > diff --git a/gcc/testsuite/gcc.target/i386/pr105034.c
> > b/gcc/testsuite/gcc.target/i386/pr105034.c
> > new file mode 100644
> > index 00000000000..d997e26e9ed
> > --- /dev/null
> > +++ b/gcc/testsuite/gcc.target/i386/pr105034.c
> > @@ -0,0 +1,23 @@
> > +/* PR target/105034 */
> > +/* { dg-do compile } */
> > +/* { dg-options "-Os -msse4.1" } */
> > +
> > +#define max(a,b) (((a) > (b))? (a) : (b))
> > +#define min(a,b) (((a) < (b))? (a) : (b))
> > +
> > +int foo(int x)
> > +{
> > + return max(x,0);
> > +}
> > +
> > +int bar(int x)
> > +{
> > + return min(x,0);
> > +}
> > +
> > +unsigned int baz(unsigned int x)
> > +{
> > + return min(x,1);
> > +}
> > +
> > +/* { dg-final { scan-assembler-not "xmm" } } */
> > --
> > 2.18.1
> >
