[PATCH, rs6000] Disable gimple fold for float or double vec_minmax when fast-math is not set

[HAO CHEN GUI]

Hi,

  This patch disables gimple folding for VSX_BUILTIN_XVMINDP, VSX_BUILTIN_XVMAXDP, ALTIVEC_BUILTIN_VMINFP and  ALTIVEC_BUILTIN_VMAXFP when fast-math is not set.  With the gimple folding is enabled, the four built-ins will be implemented by c-type instructions - xs[min|max]cdp on P9 and P10 if they can be converted to scalar comparisons.  While they are implemented by xv[min|max][s|d]p on P8 and P7 as P8 and P7 don't have corresponding scalar comparison instructions.  The patch binds these four built-ins to xv[min|max][s|d]p when fast-math is not set. The two new test cases illustrate it. 

  ALTIVEC_BUILTIN_VMINFP and  ALTIVEC_BUILTIN_VMAXFP are not implemented by vminfp or vmaxfp.

rs6000-builtin.def:BU_ALTIVEC_2 (VMAXFP,              "vmaxfp",         CONST, smaxv4sf3)

rs6000-builtin.def:BU_ALTIVEC_2 (VMINFP,              "vminfp",         CONST, sminv4sf3)

Bootstrapped and tested on powerpc64le-linux with no regressions. Is this okay for trunk? Any recommendations? Thanks a lot.


ChangeLog

2021-11-01 Haochen Gui <guihaoc@linux.ibm.com>

gcc/
        * config/rs6000/rs6000-call.c (rs6000_gimple_fold_builtin): Disable
        gimple fold for VSX_BUILTIN_XVMINDP, ALTIVEC_BUILTIN_VMINFP,
        VSX_BUILTIN_XVMAXDP, ALTIVEC_BUILTIN_VMAXFP when fast-math is not
        set.

gcc/testsuite/
        * gcc.target/powerpc/vec-minmax-1.c: New test.
        * gcc.target/powerpc/vec-minmax-2.c: Likewise.


patch.diff

diff --git a/gcc/testsuite/gcc.target/powerpc/vec-minmax-1.c b/gcc/testsuite/gcc.target/powerpc/vec-minmax-1.c
new file mode 100644
index 00000000000..e238659c9be
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/vec-minmax-1.c
@@ -0,0 +1,52 @@
+/* { dg-require-effective-target powerpc_p9vector_ok } */
+/* { dg-options "-O2 -mdejagnu-cpu=power9" } */
+/* { dg-final { scan-assembler-times {\mxvmaxdp\M} 1 } } */
+/* { dg-final { scan-assembler-times {\mxvmaxsp\M} 1 } } */
+/* { dg-final { scan-assembler-times {\mxvmindp\M} 1 } } */
+/* { dg-final { scan-assembler-times {\mxvminsp\M} 1 } } */
+
+/* This test verifies that float or double vec_min/max are bound to
+   xv[min|max][d|s]p instructions when fast-math is not set.  */
+
+
+#include <altivec.h>
+
+#ifdef _BIG_ENDIAN
+   const int PREF_D = 0;
+#else
+   const int PREF_D = 1;
+#endif
+
+double vmaxd (double a, double b)
+{
+  vector double va = vec_promote (a, PREF_D);
+  vector double vb = vec_promote (b, PREF_D);
+  return vec_extract (vec_max (va, vb), PREF_D);
+}
+
+double vmind (double a, double b)
+{
+  vector double va = vec_promote (a, PREF_D);
+  vector double vb = vec_promote (b, PREF_D);
+  return vec_extract (vec_min (va, vb), PREF_D);
+}
+
+#ifdef _BIG_ENDIAN
+   const int PREF_F = 0;
+#else
+   const int PREF_F = 3;
+#endif
+
+float vmaxf (float a, float b)
+{
+  vector float va = vec_promote (a, PREF_F);
+  vector float vb = vec_promote (b, PREF_F);
+  return vec_extract (vec_max (va, vb), PREF_F);
+}
+
+float vminf (float a, float b)
+{
+  vector float va = vec_promote (a, PREF_F);
+  vector float vb = vec_promote (b, PREF_F);
+  return vec_extract (vec_min (va, vb), PREF_F);
+}
diff --git a/gcc/testsuite/gcc.target/powerpc/vec-minmax-2.c b/gcc/testsuite/gcc.target/powerpc/vec-minmax-2.c
new file mode 100644
index 00000000000..149275d8709
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/vec-minmax-2.c
@@ -0,0 +1,50 @@
+/* { dg-require-effective-target powerpc_p9vector_ok } */
+/* { dg-options "-O2 -mdejagnu-cpu=power9 -ffast-math" } */
+/* { dg-final { scan-assembler-times {\mxsmaxcdp\M} 2 } } */
+/* { dg-final { scan-assembler-times {\mxsmincdp\M} 2 } } */
+
+/* This test verifies that float or double vec_min/max can be converted
+   to scalar comparison when fast-math is set.  */
+
+
+#include <altivec.h>
+
+#ifdef _BIG_ENDIAN
+   const int PREF_D = 0;
+#else
+   const int PREF_D = 1;
+#endif
+
+double vmaxd (double a, double b)
+{
+  vector double va = vec_promote (a, PREF_D);
+  vector double vb = vec_promote (b, PREF_D);
+  return vec_extract (vec_max (va, vb), PREF_D);
+}
+
+double vmind (double a, double b)
+{
+  vector double va = vec_promote (a, PREF_D);
+  vector double vb = vec_promote (b, PREF_D);
+  return vec_extract (vec_min (va, vb), PREF_D);
+}
+
+#ifdef _BIG_ENDIAN
+   const int PREF_F = 0;
+#else
+   const int PREF_F = 3;
+#endif
+
+float vmaxf (float a, float b)
+{
+  vector float va = vec_promote (a, PREF_F);
+  vector float vb = vec_promote (b, PREF_F);
+  return vec_extract (vec_max (va, vb), PREF_F);
+}
+
+float vminf (float a, float b)
+{
+  vector float va = vec_promote (a, PREF_F);
+  vector float vb = vec_promote (b, PREF_F);
+  return vec_extract (vec_min (va, vb), PREF_F);
+}
-------------- next part --------------
2021-11-01 Haochen Gui <guihaoc@linux.ibm.com>

gcc/
	* config/rs6000/rs6000-call.c (rs6000_gimple_fold_builtin): Disable
	gimple fold for VSX_BUILTIN_XVMINDP, ALTIVEC_BUILTIN_VMINFP,
	VSX_BUILTIN_XVMAXDP, ALTIVEC_BUILTIN_VMAXFP when fast-math is not
	set.

gcc/testsuite/
	* gcc.target/powerpc/vec-minmax-1.c: New test.
	* gcc.target/powerpc/vec-minmax-2.c: Likewise.
-------------- next part --------------
diff --git a/gcc/testsuite/gcc.target/powerpc/vec-minmax-1.c b/gcc/testsuite/gcc.target/powerpc/vec-minmax-1.c
new file mode 100644
index 00000000000..e238659c9be
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/vec-minmax-1.c
@@ -0,0 +1,52 @@
+/* { dg-require-effective-target powerpc_p9vector_ok } */
+/* { dg-options "-O2 -mdejagnu-cpu=power9" } */
+/* { dg-final { scan-assembler-times {\mxvmaxdp\M} 1 } } */
+/* { dg-final { scan-assembler-times {\mxvmaxsp\M} 1 } } */
+/* { dg-final { scan-assembler-times {\mxvmindp\M} 1 } } */
+/* { dg-final { scan-assembler-times {\mxvminsp\M} 1 } } */
+
+/* This test verifies that float or double vec_min/max are bound to
+   xv[min|max][d|s]p instructions when fast-math is not set.  */
+
+
+#include <altivec.h>
+
+#ifdef _BIG_ENDIAN
+   const int PREF_D = 0;
+#else
+   const int PREF_D = 1;
+#endif
+
+double vmaxd (double a, double b)
+{
+  vector double va = vec_promote (a, PREF_D);
+  vector double vb = vec_promote (b, PREF_D);
+  return vec_extract (vec_max (va, vb), PREF_D);
+}
+
+double vmind (double a, double b)
+{
+  vector double va = vec_promote (a, PREF_D);
+  vector double vb = vec_promote (b, PREF_D);
+  return vec_extract (vec_min (va, vb), PREF_D);
+}
+
+#ifdef _BIG_ENDIAN
+   const int PREF_F = 0;
+#else
+   const int PREF_F = 3;
+#endif
+
+float vmaxf (float a, float b)
+{
+  vector float va = vec_promote (a, PREF_F);
+  vector float vb = vec_promote (b, PREF_F);
+  return vec_extract (vec_max (va, vb), PREF_F);
+}
+
+float vminf (float a, float b)
+{
+  vector float va = vec_promote (a, PREF_F);
+  vector float vb = vec_promote (b, PREF_F);
+  return vec_extract (vec_min (va, vb), PREF_F);
+}
diff --git a/gcc/testsuite/gcc.target/powerpc/vec-minmax-2.c b/gcc/testsuite/gcc.target/powerpc/vec-minmax-2.c
new file mode 100644
index 00000000000..149275d8709
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/vec-minmax-2.c
@@ -0,0 +1,50 @@
+/* { dg-require-effective-target powerpc_p9vector_ok } */
+/* { dg-options "-O2 -mdejagnu-cpu=power9 -ffast-math" } */
+/* { dg-final { scan-assembler-times {\mxsmaxcdp\M} 2 } } */
+/* { dg-final { scan-assembler-times {\mxsmincdp\M} 2 } } */
+
+/* This test verifies that float or double vec_min/max can be converted
+   to scalar comparison when fast-math is set.  */
+
+
+#include <altivec.h>
+
+#ifdef _BIG_ENDIAN
+   const int PREF_D = 0;
+#else
+   const int PREF_D = 1;
+#endif
+
+double vmaxd (double a, double b)
+{
+  vector double va = vec_promote (a, PREF_D);
+  vector double vb = vec_promote (b, PREF_D);
+  return vec_extract (vec_max (va, vb), PREF_D);
+}
+
+double vmind (double a, double b)
+{
+  vector double va = vec_promote (a, PREF_D);
+  vector double vb = vec_promote (b, PREF_D);
+  return vec_extract (vec_min (va, vb), PREF_D);
+}
+
+#ifdef _BIG_ENDIAN
+   const int PREF_F = 0;
+#else
+   const int PREF_F = 3;
+#endif
+
+float vmaxf (float a, float b)
+{
+  vector float va = vec_promote (a, PREF_F);
+  vector float vb = vec_promote (b, PREF_F);
+  return vec_extract (vec_max (va, vb), PREF_F);
+}
+
+float vminf (float a, float b)
+{
+  vector float va = vec_promote (a, PREF_F);
+  vector float vb = vec_promote (b, PREF_F);
+  return vec_extract (vec_min (va, vb), PREF_F);
+}