[committed] i386: Optimize pinsrq of 0 with index 1 into movq [PR94866]

[Uros Bizjak via Gcc-patches]

Add new pattern involving vec_merge RTX that is produced by combine from the
combination of sse4_1_pinsrq and *movdi_internal:

    7: r86:DI=0
    8: r85:V2DI=vec_merge(vec_duplicate(r86:DI),r87:V2DI,0x2)
      REG_DEAD r87:V2DI
      REG_DEAD r86:DI
Successfully matched this instruction:
(set (reg:V2DI 85 [ a ])
    (vec_merge:V2DI (reg:V2DI 87)
        (const_vector:V2DI [
                (const_int 0 [0]) repeated x2
            ])
        (const_int 1 [0x1])))

    PR target/94866

gcc/ChangeLog:

    * config/i386/sse.md (*sse2_movq128_<mode>_1): New insn pattern.

gcc/testsuite/ChangeLog:

    * g++.target/i386/pr94866.C: New test.

Bootstrapped and regression tested on x86_64-linux-gnu {,-m32}.

Uros.

diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index da85223a9b4..52104f8d1c9 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -1770,6 +1770,18 @@ (define_insn "*sse2_movq128_<mode>"
    (set_attr "prefix" "maybe_vex")
    (set_attr "mode" "TI")])
 
+(define_insn "*sse2_movq128_<mode>_1"
+  [(set (match_operand:VI8F_128 0 "register_operand" "=v")
+       (vec_merge:VI8F_128
+         (match_operand:VI8F_128 1 "nonimmediate_operand" "vm")
+         (match_operand:VI8F_128 2 "const0_operand")
+         (const_int 1)))]
+  "TARGET_SSE2"
+  "%vmovq\t{%1, %0|%0, %q1}"
+  [(set_attr "type" "ssemov")
+   (set_attr "prefix" "maybe_vex")
+   (set_attr "mode" "TI")])
+
 ;; Move a DI from a 32-bit register pair (e.g. %edx:%eax) to an xmm.
 ;; We'd rather avoid this entirely; if the 32-bit reg pair was loaded
 ;; from memory, we'd prefer to load the memory directly into the %xmm
diff --git a/gcc/testsuite/g++.target/i386/pr94866.C 
b/gcc/testsuite/g++.target/i386/pr94866.C
new file mode 100644
index 00000000000..eb0f5ef11c5
--- /dev/null
+++ b/gcc/testsuite/g++.target/i386/pr94866.C
@@ -0,0 +1,13 @@
+// PR target/94866
+// { dg-do compile }
+// { dg-options "-O2 -msse4.1" }
+// { dg-require-effective-target c++11 }
+
+typedef long long v2di __attribute__((vector_size(16)));
+
+v2di _mm_move_epi64(v2di a)
+{
+    return v2di{a[0], 0LL};
+}
+
+// { dg-final { scan-assembler-times "movq\[ \\t\]+\[^\n\]*%xmm" 1 } }