sse.md (*ssse3_palignr<mode>_perm): Add avx512bw alternative.

	* config/i386/sse.md (*ssse3_palignr<mode>_perm): Add avx512bw
	alternative.  Formatting fix.

	* gcc.target/i386/avx512bw-vpalignr-4.c: New test.
	* gcc.target/i386/avx512vl-vpalignr-4.c: New test.

From-SVN: r236764

gcc/ChangeLog

 2016-05-26  Jakub Jelinek  <jakub@redhat.com>
 
+	* config/i386/sse.md (*ssse3_palignr<mode>_perm): Add avx512bw
+	alternative.  Formatting fix.
+
 	* config/i386/sse.md
 	(<mask_codefor>avx512vl_shuf_<shuffletype>32x4_1<mask_name>): Rename
 	to ...

gcc/config/i386/sse.md

@@ -17783,33 +17783,34 @@
    (set_attr "mode" "<sseinsnmode>")])
 
 (define_insn "*ssse3_palignr<mode>_perm"
-  [(set (match_operand:V_128 0 "register_operand" "=x,x")
+  [(set (match_operand:V_128 0 "register_operand" "=x,x,v")
       (vec_select:V_128
-	(match_operand:V_128 1 "register_operand" "0,x")
+	(match_operand:V_128 1 "register_operand" "0,x,v")
 	(match_parallel 2 "palignr_operand"
-	  [(match_operand 3 "const_int_operand" "n, n")])))]
+	  [(match_operand 3 "const_int_operand" "n,n,n")])))]
   "TARGET_SSSE3"
 {
-  operands[2] =
-   GEN_INT (INTVAL (operands[3]) * GET_MODE_UNIT_SIZE (GET_MODE (operands[0])));
+  operands[2] = (GEN_INT (INTVAL (operands[3])
+		 * GET_MODE_UNIT_SIZE (GET_MODE (operands[0]))));
 
   switch (which_alternative)
     {
     case 0:
       return "palignr\t{%2, %1, %0|%0, %1, %2}";
     case 1:
+    case 2:
       return "vpalignr\t{%2, %1, %1, %0|%0, %1, %1, %2}";
     default:
       gcc_unreachable ();
     }
 }
-  [(set_attr "isa" "noavx,avx")
+  [(set_attr "isa" "noavx,avx,avx512bw")
    (set_attr "type" "sseishft")
    (set_attr "atom_unit" "sishuf")
-   (set_attr "prefix_data16" "1,*")
+   (set_attr "prefix_data16" "1,*,*")
    (set_attr "prefix_extra" "1")
    (set_attr "length_immediate" "1")
-   (set_attr "prefix" "orig,vex")])
+   (set_attr "prefix" "orig,vex,evex")])
 
 (define_expand "avx512vl_vinsert<mode>"
   [(match_operand:VI48F_256 0 "register_operand")

gcc/testsuite/ChangeLog

 2016-05-26  Jakub Jelinek  <jakub@redhat.com>
 
+	* gcc.target/i386/avx512bw-vpalignr-4.c: New test.
+	* gcc.target/i386/avx512vl-vpalignr-4.c: New test.
+
 	* gcc.target/i386/avx512vl-vbroadcast-3.c: New test.
 
 2016-05-26  Jiong Wang  <jiong.wang@arm.com>

gcc/testsuite/gcc.target/i386/avx512bw-vpalignr-4.c

+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-O2 -mavx512vl -mavx512bw -masm=att" } */
+
+typedef char V1 __attribute__((vector_size (16)));
+
+void
+f1 (V1 x)
+{
+  register V1 a __asm ("xmm16");
+  a = x;
+  asm volatile ("" : "+v" (a));
+  a = __builtin_shuffle (a, (V1) { 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 0, 1, 2, 3, 4, 5 });
+  asm volatile ("" : "+v" (a));
+}
+
+/* { dg-final { scan-assembler-times "vpalignr\[^\n\r]*\\\$6\[^\n\r]*%xmm16\[^\n\r]*%xmm16\[^\n\r]*%xmm16" 1 } } */
+
+typedef short V2 __attribute__((vector_size (16)));
+
+void
+f2 (V2 x)
+{
+  register V2 a __asm ("xmm16");
+  a = x;
+  asm volatile ("" : "+v" (a));
+  a = __builtin_shuffle (a, (V2) { 5, 6, 7, 0, 1, 2, 3, 4 });
+  asm volatile ("" : "+v" (a));
+}
+
+/* { dg-final { scan-assembler-times "vpalignr\[^\n\r]*\\\$10\[^\n\r]*%xmm16\[^\n\r]*%xmm16\[^\n\r]*%xmm16" 1 } } */
+
+typedef int V3 __attribute__((vector_size (16)));
+
+void
+f3 (V3 x)
+{
+  register V3 a __asm ("xmm16");
+  a = x;
+  asm volatile ("" : "+v" (a));
+  a = __builtin_shuffle (a, (V3) { 3, 0, 1, 2 });
+  asm volatile ("" : "+v" (a));
+}
+
+/* { dg-final { scan-assembler-times "vpshufd\[^\n\r]*\\\$147\[^\n\r]*%xmm16\[^\n\r]*%xmm16" 1 } } */
+
+typedef long long V4 __attribute__((vector_size (16)));
+
+void
+f4 (V4 x)
+{
+  register V4 a __asm ("xmm16");
+  a = x;
+  asm volatile ("" : "+v" (a));
+  a = __builtin_shuffle (a, (V4) { 1, 0 });
+  asm volatile ("" : "+v" (a));
+}
+
+/* { dg-final { scan-assembler-times "vpalignr\[^\n\r]*\\\$8\[^\n\r]*%xmm16\[^\n\r]*%xmm16\[^\n\r]*%xmm16" 1 } } */
+
+typedef float V5 __attribute__((vector_size (16)));
+
+void
+f5 (V5 x)
+{
+  register V5 a __asm ("xmm16");
+  a = x;
+  asm volatile ("" : "+v" (a));
+  a = __builtin_shuffle (a, (V3) { 3, 0, 1, 2 });
+  asm volatile ("" : "+v" (a));
+}
+
+/* { dg-final { scan-assembler-times "vpermilps\[^\n\r]*\\\$147\[^\n\r]*%xmm16\[^\n\r]*%xmm16" 1 } } */
+
+typedef double V6 __attribute__((vector_size (16)));
+
+void
+f6 (V6 x)
+{
+  register V6 a __asm ("xmm16");
+  a = x;
+  asm volatile ("" : "+v" (a));
+  a = __builtin_shuffle (a, (V4) { 1, 0 });
+  asm volatile ("" : "+v" (a));
+}
+
+/* { dg-final { scan-assembler-times "vpermilpd\[^\n\r]*\\\$1\[^\n\r]*%xmm16\[^\n\r]*%xmm16" 1 } } */

gcc/testsuite/gcc.target/i386/avx512vl-vpalignr-4.c

+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-O2 -mavx512vl -mno-avx512bw -masm=att" } */
+
+typedef char V1 __attribute__((vector_size (16)));
+
+void
+f1 (V1 x)
+{
+  register V1 a __asm ("xmm16");
+  a = x;
+  asm volatile ("" : "+v" (a));
+  a = __builtin_shuffle (a, (V1) { 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 0, 1, 2, 3, 4, 5 });
+  asm volatile ("" : "+v" (a));
+}
+
+/* { dg-final { scan-assembler-not "vpalignr\[^\n\r]*\\\$6\[^\n\r]*%xmm16\[^\n\r]*%xmm16\[^\n\r]*%xmm16" } } */
+
+typedef short V2 __attribute__((vector_size (16)));
+
+void
+f2 (V2 x)
+{
+  register V2 a __asm ("xmm16");
+  a = x;
+  asm volatile ("" : "+v" (a));
+  a = __builtin_shuffle (a, (V2) { 5, 6, 7, 0, 1, 2, 3, 4 });
+  asm volatile ("" : "+v" (a));
+}
+
+/* { dg-final { scan-assembler-not "vpalignr\[^\n\r]*\\\$10\[^\n\r]*%xmm16\[^\n\r]*%xmm16\[^\n\r]*%xmm16" } } */
+
+typedef int V3 __attribute__((vector_size (16)));
+
+void
+f3 (V3 x)
+{
+  register V3 a __asm ("xmm16");
+  a = x;
+  asm volatile ("" : "+v" (a));
+  a = __builtin_shuffle (a, (V3) { 3, 0, 1, 2 });
+  asm volatile ("" : "+v" (a));
+}
+
+/* { dg-final { scan-assembler-times "vpshufd\[^\n\r]*\\\$147\[^\n\r]*%xmm16\[^\n\r]*%xmm16" 1 } } */
+
+typedef long long V4 __attribute__((vector_size (16)));
+
+void
+f4 (V4 x)
+{
+  register V4 a __asm ("xmm16");
+  a = x;
+  asm volatile ("" : "+v" (a));
+  a = __builtin_shuffle (a, (V4) { 1, 0 });
+  asm volatile ("" : "+v" (a));
+}
+
+/* { dg-final { scan-assembler-not "vpalignr\[^\n\r]*\\\$8\[^\n\r]*%xmm16\[^\n\r]*%xmm16\[^\n\r]*%xmm16" } } */
+
+typedef float V5 __attribute__((vector_size (16)));
+
+void
+f5 (V5 x)
+{
+  register V5 a __asm ("xmm16");
+  a = x;
+  asm volatile ("" : "+v" (a));
+  a = __builtin_shuffle (a, (V3) { 3, 0, 1, 2 });
+  asm volatile ("" : "+v" (a));
+}
+
+/* { dg-final { scan-assembler-times "vpermilps\[^\n\r]*\\\$147\[^\n\r]*%xmm16\[^\n\r]*%xmm16" 1 } } */
+
+typedef double V6 __attribute__((vector_size (16)));
+
+void
+f6 (V6 x)
+{
+  register V6 a __asm ("xmm16");
+  a = x;
+  asm volatile ("" : "+v" (a));
+  a = __builtin_shuffle (a, (V4) { 1, 0 });
+  asm volatile ("" : "+v" (a));
+}
+
+/* { dg-final { scan-assembler-times "vpermilpd\[^\n\r]*\\\$1\[^\n\r]*%xmm16\[^\n\r]*%xmm16" 1 } } */