i386: prefer vpermilpd over vpermpd [PR93395]

In Agner Fog's tables, vpermilp[sd] with immediates seem to be
much faster than vpermpd with immediate, for a good reason,
the former only permute something within the lanes and don't do anything
intra-lane, while vpermpd can.  So, functionality-wise, vpermilpd
is more efficient subset of vpermpd.  We use the same RTL for those
though (and also for certain broadcast).

Now, the problem was that the vpermpd pattern appeared first in sse.md,
followed by the broadcast patterns, followed by the vpermilp[sd].
Which means unless -mavx -mno-avx2, we'd emit vpermpd instead of the
more efficient alternatives.

The following patch reorders them, so that vpermpd comes last, if we
can match a broadcast, we do, if we can match a vpermilp[sd] that is not a
broadcast, we will, otherwise fall back (of course only if -mavx2) to
vpermpd.

2020-01-24  Jakub Jelinek  <jakub@redhat.com>

	PR target/93395
	* config/i386/sse.md (*avx_vperm_broadcast_v4sf,
	*avx_vperm_broadcast_<mode>,
	<sse2_avx_avx512f>_vpermil<mode><mask_name>,
	*<sse2_avx_avx512f>_vpermilp<mode><mask_name>):
	Move before avx2_perm<mode>/avx512f_perm<mode>.

	* gcc.target/i386/pr93395.c: New test.
	* gcc.target/i386/avx512vl-vpermilpdi-1.c: Remove xfail.

gcc/ChangeLog

 2020-01-24  Jakub Jelinek  <jakub@redhat.com>
 
+	PR target/93395
+	* config/i386/sse.md (*avx_vperm_broadcast_v4sf,
+	*avx_vperm_broadcast_<mode>,
+	<sse2_avx_avx512f>_vpermil<mode><mask_name>,
+	*<sse2_avx_avx512f>_vpermilp<mode><mask_name>):
+	Move before avx2_perm<mode>/avx512f_perm<mode>.
+
 	PR target/93376
 	* simplify-rtx.c (simplify_const_unary_operation,
 	simplify_const_binary_operation): Punt for mode precision above

gcc/testsuite/ChangeLog

+2020-01-24  Jakub Jelinek  <jakub@redhat.com>
+
+	PR target/93395
+	* gcc.target/i386/pr93395.c: New test.
+	* gcc.target/i386/avx512vl-vpermilpdi-1.c: Remove xfail.
+
 2020-01-24  Marek Polacek  <polacek@redhat.com>
 
 	PR c++/93299 - ICE in tsubst_copy with parenthesized expression.

gcc/testsuite/gcc.target/i386/avx512vl-vpermilpdi-1.c

 /* { dg-do compile } */
 /* { dg-options "-mavx512vl -O2" } */
-/* { dg-final { scan-assembler-times "vpermilpd\[ \\t\]+\[^\{\n\]*13\[^\n\]*%ymm\[0-9\]+\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)" 1 { xfail *-*-* } } } */
-/* { dg-final { scan-assembler-times "vpermilpd\[ \\t\]+\[^\{\n\]*13\[^\n\]*%ymm\[0-9\]+\{%k\[1-7\]\}\{z\}(?:\n|\[ \\t\]+#)" 1 { xfail *-*-* } } } */
+/* { dg-final { scan-assembler-times "vpermilpd\[ \\t\]+\[^\{\n\]*13\[^\n\]*%ymm\[0-9\]+\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vpermilpd\[ \\t\]+\[^\{\n\]*13\[^\n\]*%ymm\[0-9\]+\{%k\[1-7\]\}\{z\}(?:\n|\[ \\t\]+#)" 1 } } */
 /* { dg-final { scan-assembler-times "vpermilpd\[ \\t\]+\[^\{\n\]*3\[^\n\]*%xmm\[0-9\]+\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)" 1 } } */
 /* { dg-final { scan-assembler-times "vpermilpd\[ \\t\]+\[^\{\n\]*3\[^\n\]*%xmm\[0-9\]+\{%k\[1-7\]\}\{z\}(?:\n|\[ \\t\]+#)" 1 } } */
 

gcc/testsuite/gcc.target/i386/pr93395.c

+/* PR target/93395 */
+/* { dg-do compile } */
+/* { dg-options "-O2 -mavx512f -masm=att" } */
+/* { dg-final { scan-assembler-times "vpermilpd\t.5, %ymm" 3 } } */
+/* { dg-final { scan-assembler-times "vpermilpd\t.85, %zmm" 3 } } */
+/* { dg-final { scan-assembler-not "vpermpd\t" } } */
+
+#include <immintrin.h>
+
+__m256d
+foo1 (__m256d a)
+{
+  return _mm256_permute4x64_pd (a, 177);
+}
+
+__m256d
+foo2 (__m256d a)
+{
+  return _mm256_permute_pd (a, 5);
+}
+
+__m256d
+foo3 (__m256d a)
+{
+  return __builtin_shuffle (a, (__v4di) { 1, 0, 3, 2 });
+}
+
+__m512d
+foo4 (__m512d a)
+{
+  return _mm512_permutex_pd (a, 177);
+}
+
+__m512d
+foo5 (__m512d a)
+{
+  return _mm512_permute_pd (a, 85);
+}
+
+__m512d
+foo6 (__m512d a)
+{
+  return __builtin_shuffle (a, (__v8di) { 1, 0, 3, 2, 5, 4, 7, 6 });
+}