Don't fold __builtin_ia32_blendvpd w/o sse4.2.

__builtin_ia32_blendvpd is defined under sse4.1 and gimple folded
to ((v2di) c) < 0 ? b : a where vec_cmpv2di is under sse4.2 w/o which
it's veclowered to scalar operations and not combined back in rtl.

gcc/ChangeLog:

	PR target/104946
	* config/i386/i386-builtin.def (BDESC): Add
	CODE_FOR_sse4_1_blendvpd for IX86_BUILTIN_BLENDVPD.
	* config/i386/i386.cc (ix86_gimple_fold_builtin): Don't fold
	__builtin_ia32_blendvpd w/o sse4.2

gcc/testsuite/ChangeLog:

	* gcc.target/i386/sse4_1-blendvpd-1.c: New test.

diff --git a/gcc/config/i386/i386-builtin.def b/gcc/config/i386/i386-builtin.def
index ea32755..b410102 100644 (file)
--- a/gcc/config/i386/i386-builtin.def
+++ b/gcc/config/i386/i386-builtin.def
@@ -906,7 +906,7 @@ BDESC (OPTION_MASK_ISA_SSSE3 | OPTION_MASK_ISA_MMX, 0, CODE_FOR_ssse3_palignrdi,
 /* SSE4.1 */
 BDESC (OPTION_MASK_ISA_SSE4_1, 0, CODE_FOR_sse4_1_blendpd, "__builtin_ia32_blendpd", IX86_BUILTIN_BLENDPD, UNKNOWN, (int) V2DF_FTYPE_V2DF_V2DF_INT)
 BDESC (OPTION_MASK_ISA_SSE4_1, 0, CODE_FOR_sse4_1_blendps, "__builtin_ia32_blendps", IX86_BUILTIN_BLENDPS, UNKNOWN, (int) V4SF_FTYPE_V4SF_V4SF_INT)
-BDESC (OPTION_MASK_ISA_SSE4_1, 0, CODE_FOR_nothing, "__builtin_ia32_blendvpd", IX86_BUILTIN_BLENDVPD, UNKNOWN, (int) V2DF_FTYPE_V2DF_V2DF_V2DF)
+BDESC (OPTION_MASK_ISA_SSE4_1, 0, CODE_FOR_sse4_1_blendvpd, "__builtin_ia32_blendvpd", IX86_BUILTIN_BLENDVPD, UNKNOWN, (int) V2DF_FTYPE_V2DF_V2DF_V2DF)
 BDESC (OPTION_MASK_ISA_SSE4_1, 0, CODE_FOR_nothing, "__builtin_ia32_blendvps", IX86_BUILTIN_BLENDVPS, UNKNOWN, (int) V4SF_FTYPE_V4SF_V4SF_V4SF)
 BDESC (OPTION_MASK_ISA_SSE4_1, 0, CODE_FOR_sse4_1_dppd, "__builtin_ia32_dppd", IX86_BUILTIN_DPPD, UNKNOWN, (int) V2DF_FTYPE_V2DF_V2DF_INT)
 BDESC (OPTION_MASK_ISA_SSE4_1, 0, CODE_FOR_sse4_1_dpps, "__builtin_ia32_dpps", IX86_BUILTIN_DPPS, UNKNOWN, (int) V4SF_FTYPE_V4SF_V4SF_INT)

diff --git a/gcc/config/i386/i386.cc b/gcc/config/i386/i386.cc
index d77ad83..5a56196 100644 (file)
--- a/gcc/config/i386/i386.cc
+++ b/gcc/config/i386/i386.cc
@@ -18368,10 +18368,16 @@ ix86_gimple_fold_builtin (gimple_stmt_iterator *gsi)
        }
       break;
 
+    case IX86_BUILTIN_BLENDVPD:
+      /* blendvpd is under sse4.1 but pcmpgtq is under sse4.2,
+        w/o sse4.2, it's veclowered to scalar operations and
+        not combined back.  */
+      if (!TARGET_SSE4_2)
+       break;
+      /* FALLTHRU.  */
     case IX86_BUILTIN_PBLENDVB128:
     case IX86_BUILTIN_PBLENDVB256:
     case IX86_BUILTIN_BLENDVPS:
-    case IX86_BUILTIN_BLENDVPD:
     case IX86_BUILTIN_BLENDVPS256:
     case IX86_BUILTIN_BLENDVPD256:
       gcc_assert (n_args == 3);

diff --git a/gcc/testsuite/gcc.target/i386/sse4_1-blendvpd-1.c b/gcc/testsuite/gcc.target/i386/sse4_1-blendvpd-1.c
new file mode 100644 (file)
index 0000000..c25d3fb
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/sse4_1-blendvpd-1.c
@@ -0,0 +1,11 @@
+/* { dg-do compile } */
+/* { dg-options "-msse4.1 -O2 -mno-sse4.2" } */
+/* { dg-final { scan-assembler-times {(?n)blendvpd[ \t]+%xmm[0-9]+} 1 } } */
+
+#include <immintrin.h>
+
+__m128d
+foo (__m128d a, __m128d b, __m128d c)
+{
+  return _mm_blendv_pd (a, b, c);
+}