Generate vpblendd instead of vpblendw for V4SI under AVX2.

gcc/ChangeLog:

	* config/i386/i386-expand.cc (expand_vec_perm_blend): Generate
	vpblendd instead of vpblendw for V4SI under avx2.

gcc/testsuite/ChangeLog:

	* gcc.target/i386/pr88828-0.c: Adjust testcase.

diff --git a/gcc/config/i386/i386-expand.cc b/gcc/config/i386/i386-expand.cc
index 1e3ce4b7c3ff4cfbee836460f5d8786c78df30d9..76dbb3b44b0ca0c64f9ed2424884a5cb23921455 100644 (file)
--- a/gcc/config/i386/i386-expand.cc
+++ b/gcc/config/i386/i386-expand.cc
@@ -19069,10 +19069,20 @@ expand_vec_perm_blend (struct expand_vec_perm_d *d)
       goto do_subreg;
 
     case E_V4SImode:
-      for (i = 0; i < 4; ++i)
-       mask |= (d->perm[i] >= 4 ? 3 : 0) << (i * 2);
-      vmode = V8HImode;
-      goto do_subreg;
+      if (TARGET_AVX2)
+       {
+         /* Use vpblendd instead of vpblendw.  */
+         for (i = 0; i < nelt; ++i)
+           mask |= ((unsigned HOST_WIDE_INT) (d->perm[i] >= nelt)) << i;
+         break;
+       }
+      else
+       {
+         for (i = 0; i < 4; ++i)
+           mask |= (d->perm[i] >= 4 ? 3 : 0) << (i * 2);
+         vmode = V8HImode;
+         goto do_subreg;
+       }
 
     case E_V16QImode:
       /* See if bytes move in pairs so we can use pblendw with

diff --git a/gcc/testsuite/gcc.target/i386/pr88828-0.c b/gcc/testsuite/gcc.target/i386/pr88828-0.c
index 3ddb2d135260e92686fcae19bd17efe3adedeb11..441c441b51dd6c415e03324b5b6156a554d357cb 100644 (file)
--- a/gcc/testsuite/gcc.target/i386/pr88828-0.c
+++ b/gcc/testsuite/gcc.target/i386/pr88828-0.c
@@ -1,5 +1,5 @@
 /* { dg-do compile } */
-/* { dg-options "-O2 -msse4.2" } */
+/* { dg-options "-O2 -msse4.2 -mno-avx2" } */
 
 typedef int v4si __attribute__((vector_size(16)));
 typedef float v4sf __attribute__((vector_size(16)));