@@ -1,8 +1,8 @@
/* { dg-do compile { target { powerpc*-*-* } } } */
/* { dg-skip-if "" { powerpc*-*-darwin* } } */
/* { dg-require-effective-target powerpc_vsx_ok } */
-/* { dg-options "-O2 -ffast-math -mdejagnu-cpu=power5 -mno-altivec -mabi=altivec -fno-unroll-loops" } */
-/* { dg-final { scan-assembler-times "vaddfp" 1 } } */
+/* { dg-options "-O3 -ffast-math -mdejagnu-cpu=power5 -mno-altivec -mabi=altivec -fno-unroll-loops" } */
+/* { dg-final { scan-assembler-times "vaddfp" 2 } } */
/* { dg-final { scan-assembler-times "xvaddsp" 1 } } */
/* { dg-final { scan-assembler-times "fadds" 1 } } */
@@ -18,10 +18,6 @@
#error "__VSX__ should not be defined."
#endif
-#pragma GCC target("altivec,vsx")
-#include <altivec.h>
-#pragma GCC reset_options
-
#pragma GCC push_options
#pragma GCC target("altivec,no-vsx")
@@ -33,6 +29,7 @@
#error "__VSX__ should not be defined."
#endif
+/* Altivec build, generate vaddfp. */
void
av_add (vector float *a, vector float *b, vector float *c)
{
@@ -40,10 +37,11 @@ av_add (vector float *a, vector float *b, vector float *c)
unsigned long n = SIZE / 4;
for (i = 0; i < n; i++)
- a[i] = vec_add (b[i], c[i]);
+ a[i] = b[i] + c[i];
}
-#pragma GCC target("vsx")
+/* cpu=power7 must be used to enable VSX. */
+#pragma GCC target("cpu=power7,vsx")
#ifndef __ALTIVEC__
#error "__ALTIVEC__ should be defined."
@@ -53,6 +51,7 @@ av_add (vector float *a, vector float *b, vector float *c)
#error "__VSX__ should be defined."
#endif
+/* VSX build on power7, generate xsaddsp. */
void
vsx_add (vector float *a, vector float *b, vector float *c)
{
@@ -60,11 +59,31 @@ vsx_add (vector float *a, vector float *b, vector float *c)
unsigned long n = SIZE / 4;
for (i = 0; i < n; i++)
- a[i] = vec_add (b[i], c[i]);
+ a[i] = b[i] + c[i];
+}
+
+#pragma GCC target("cpu=power7,no-vsx")
+
+#ifndef __ALTIVEC__
+#error "__ALTIVEC__ should be defined."
+#endif
+
+#ifdef __VSX__
+#error "__VSX__ should not be defined."
+#endif
+
+/* Altivec build on power7 with no VSX, generate vaddfp. */
+void
+av2_add (vector float *a, vector float *b, vector float *c)
+{
+ unsigned long i;
+ unsigned long n = SIZE / 4;
+
+ for (i = 0; i < n; i++)
+ a[i] = b[i] + c[i];
}
#pragma GCC pop_options
-#pragma GCC target("no-vsx,no-altivec")
#ifdef __ALTIVEC__
#error "__ALTIVEC__ should not be defined."
@@ -74,6 +93,7 @@ vsx_add (vector float *a, vector float *b, vector float *c)
#error "__VSX__ should not be defined."
#endif
+/* Default power5 build, generate scalar fadds. */
void
norm_add (float *a, float *b, float *c)
{
@@ -7,7 +7,8 @@
/* Verify there is no ICE under 32 bit env. */
-__attribute__((target("vsx")))
+/* cpu=power7 must be used to enable VSX. */
+__attribute__((target("cpu=power7,vsx")))
int test (void)
{
return 0;