re PR target/88278 (Fails to elide zeroing of upper vector register)

	PR target/88278
	* config/i386/sse.md (*vec_concatv4sf_0, *vec_concatv4si_0): New insns.

	* gcc.target/i386/pr88278.c: New test.
	* gcc.target/i386/pr53759.c: Don't expect vmovlps insn, expect vmovq
	instead.
	* gcc.target/i386/pr53759-2.c: New test.

From-SVN: r266728

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 204a9fa27c0762d7554894fb3eadf4ad68360572..d74c1a990248a8e70ff1934a0dcd54fa3ee33d5c 100644 (file)
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,8 @@
+2018-12-02  Jakub Jelinek  <jakub@redhat.com>
+
+       PR target/88278
+       * config/i386/sse.md (*vec_concatv4sf_0, *vec_concatv4si_0): New insns.
+
 2018-12-02  Jeff Law  <law@redhat.com>
 
        * config/h8300/h8300.md (call, call_value): Drop mode from 

diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index e2cae71d44a1e7d6f20736e59a279b2f9f1acde5..1415c36930b727aad218418d719bbb30c20edbea 100644 (file)
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -7248,6 +7248,17 @@
    (set_attr "prefix" "orig,maybe_evex,orig,maybe_evex")
    (set_attr "mode" "V4SF,V4SF,V2SF,V2SF")])
 
+(define_insn "*vec_concatv4sf_0"
+  [(set (match_operand:V4SF 0 "register_operand"       "=v")
+       (vec_concat:V4SF
+         (match_operand:V2SF 1 "nonimmediate_operand" "xm")
+         (match_operand:V2SF 2 "const0_operand"       " C")))]
+  "TARGET_SSE2"
+  "%vmovq\t{%1, %0|%0, %1}"
+  [(set_attr "type" "ssemov")
+   (set_attr "prefix" "maybe_vex")
+   (set_attr "mode" "DF")])
+
 ;; Avoid combining registers from different units in a single alternative,
 ;; see comment above inline_secondary_memory_needed function in i386.c
 (define_insn "vec_set<mode>_0"
@@ -14409,6 +14420,23 @@
    (set_attr "prefix" "orig,maybe_evex,orig,orig,maybe_evex")
    (set_attr "mode" "TI,TI,V4SF,V2SF,V2SF")])
 
+(define_insn "*vec_concatv4si_0"
+  [(set (match_operand:V4SI 0 "register_operand"       "=v,x")
+       (vec_concat:V4SI
+         (match_operand:V2SI 1 "nonimmediate_operand" "xm,?!*y")
+         (match_operand:V2SI 2 "const0_operand"       " C,C")))]
+  "TARGET_SSE2"
+  "@
+   %vmovq\t{%1, %0|%0, %1}
+   movq2dq\t{%1, %0|%0, %1}"
+  [(set_attr "type" "ssemov")
+   (set_attr "prefix" "maybe_vex,orig")
+   (set_attr "mode" "TI")
+   (set (attr "preferred_for_speed")
+     (if_then_else (eq_attr "alternative" "1")
+       (symbol_ref "TARGET_INTER_UNIT_MOVES_FROM_VEC")
+       (symbol_ref "true")))])
+
 ;; movd instead of movq is required to handle broken assemblers.
 (define_insn "vec_concatv2di"
   [(set (match_operand:V2DI 0 "register_operand"

diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 89dc430c1dc4db2eb348a29bb46f80f4213726df..a28b73ca5a71d180f59ecbac6a81452ff51fadab 100644 (file)
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,5 +1,11 @@
 2018-12-02  Jakub Jelinek  <jakub@redhat.com>
 
+       PR target/88278
+       * gcc.target/i386/pr88278.c: New test.
+       * gcc.target/i386/pr53759.c: Don't expect vmovlps insn, expect vmovq
+       instead.
+       * gcc.target/i386/pr53759-2.c: New test.
+
        * c-c++-common/gomp/cancel-1.c (f2): Add various taskloop related
        tests.
 

diff --git a/gcc/testsuite/gcc.target/i386/pr53759-2.c b/gcc/testsuite/gcc.target/i386/pr53759-2.c
new file mode 100644 (file)
index 0000000..ddabb84
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr53759-2.c
@@ -0,0 +1,16 @@
+/* PR target/53759 */
+/* { dg-do compile } */
+/* { dg-options "-O2 -mavx" } */
+
+#include <xmmintrin.h>
+
+void
+foo (__m128 *x, __m64 *y)
+{
+  __m128 a = _mm_add_ps (x[1], x[2]);
+  __m128 b = _mm_loadl_pi (a, y);
+  *x = _mm_add_ps (b, b);
+}
+
+/* { dg-final { scan-assembler "vmovlps\[ \\t\]" } } */
+/* { dg-final { scan-assembler-not "vshufps\[ \\t\]" } } */

diff --git a/gcc/testsuite/gcc.target/i386/pr53759.c b/gcc/testsuite/gcc.target/i386/pr53759.c
index d55316a79d4e49baf25fb5c24b3d4ca9e18fb155..c30592daf10d5aa885b41721133fd6d2d1dfeaeb 100644 (file)
--- a/gcc/testsuite/gcc.target/i386/pr53759.c
+++ b/gcc/testsuite/gcc.target/i386/pr53759.c
@@ -12,5 +12,6 @@ foo (__m128 *x, __m64 *y)
   *x = _mm_add_ps (b, b);
 }
 
-/* { dg-final { scan-assembler "vmovlps\[ \\t\]" } } */
+/* { dg-final { scan-assembler "vmovq\[ \\t\]" } } */
+/* { dg-final { scan-assembler-not "vmovlps\[ \\t\]" } } */
 /* { dg-final { scan-assembler-not "vshufps\[ \\t\]" } } */

diff --git a/gcc/testsuite/gcc.target/i386/pr88278.c b/gcc/testsuite/gcc.target/i386/pr88278.c
new file mode 100644 (file)
index 0000000..84d6e26
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr88278.c
@@ -0,0 +1,34 @@
+/* PR target/88278 */
+/* { dg-do compile } */
+/* { dg-options "-O2 -msse2 -mno-sse3 -fgimple -masm=att" } */
+/* { dg-final { scan-assembler-times "movq\[ \t]+\\(" 2 } } */
+/* { dg-final { scan-assembler-not "punpcklqdq\[ \t]+" } } */
+/* { dg-final { scan-assembler-not "pxor\[ \t]+" } } */
+
+typedef unsigned char v16qi __attribute__((vector_size(16)));
+typedef unsigned char v8qi __attribute__((vector_size(8)));
+typedef unsigned int v4si __attribute__((vector_size(16)));
+typedef unsigned int v2si __attribute__((vector_size(8)));
+
+v16qi __GIMPLE foo (unsigned char *p)
+{
+  v8qi _2;
+  v16qi _3;
+
+bb_2:
+  _2 = __MEM <v8qi, 8> (p_1(D));
+  _3 = _Literal (v16qi) { _2, _Literal (v8qi) { _Literal (unsigned char) 0, _Literal (unsigned char) 0, _Literal (unsigned char) 0, _Literal (unsigned char) 0, _Literal (unsigned char) 0, _Literal (unsigned char) 0, _Literal (unsigned char) 0 } };
+  return _3;
+}
+
+
+v4si __GIMPLE bar (unsigned int *p)
+{
+  v2si _2;
+  v4si _3;
+
+bb_2:
+  _2 = __MEM <v2si, 32> (p_1(D));
+  _3 = _Literal (v4si) { _2, _Literal (v2si) { 0u, 0u } };
+  return _3;
+}