Use canonicalize_math_after_vectorization_p for FMA folds

The folds in r260348 kicked in before vectorisation, which hurts
for two reasons:

(1) the current suboptimal handling of nothrow meant that we could
    drop the flag early and so prevent if-conversion

(2) some architectures provide more scalar forms than vector forms
    (true for Advanced SIMD)

(1) is a bug in itself that needs to be fixed eventually, but delaying
the folds is still needed for (2).

2018-05-24  Richard Sandiford  <richard.sandiford@linaro.org>

gcc/
	* match.pd: Delay FMA folds until after vectorization.

gcc/testsuite/
	* gcc.dg/vect/vect-fma-1.c: New test.

From-SVN: r260639

gcc/ChangeLog

+2018-05-24  Richard Sandiford  <richard.sandiford@linaro.org>
+
+	* match.pd: Delay FMA folds until after vectorization.
+
 2018-05-24  Andre Vieira  <andre.simoesdiasvieira@arm.com>
 
 	PR target/83009

gcc/match.pd

@@ -4703,59 +4703,60 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
 		      wi::to_wide (@ipos) + isize))
     (BIT_FIELD_REF @0 @rsize @rpos)))))
 
-(for fmas (FMA)
+(if (canonicalize_math_after_vectorization_p ())
+ (for fmas (FMA)
+  (simplify
+   (fmas:c (negate @0) @1 @2)
+   (IFN_FNMA @0 @1 @2))
+  (simplify
+   (fmas @0 @1 (negate @2))
+   (IFN_FMS @0 @1 @2))
+  (simplify
+   (fmas:c (negate @0) @1 (negate @2))
+   (IFN_FNMS @0 @1 @2))
+  (simplify
+   (negate (fmas@3 @0 @1 @2))
+   (if (single_use (@3))
+    (IFN_FNMS @0 @1 @2))))
+
  (simplify
-  (fmas:c (negate @0) @1 @2)
+  (IFN_FMS:c (negate @0) @1 @2)
+  (IFN_FNMS @0 @1 @2))
+ (simplify
+  (IFN_FMS @0 @1 (negate @2))
+  (IFN_FMA @0 @1 @2))
+ (simplify
+  (IFN_FMS:c (negate @0) @1 (negate @2))
   (IFN_FNMA @0 @1 @2))
  (simplify
-  (fmas @0 @1 (negate @2))
-  (IFN_FMS @0 @1 @2))
+  (negate (IFN_FMS@3 @0 @1 @2))
+   (if (single_use (@3))
+    (IFN_FNMA @0 @1 @2)))
+
+ (simplify
+  (IFN_FNMA:c (negate @0) @1 @2)
+  (IFN_FMA @0 @1 @2))
  (simplify
-  (fmas:c (negate @0) @1 (negate @2))
+  (IFN_FNMA @0 @1 (negate @2))
   (IFN_FNMS @0 @1 @2))
  (simplify
-  (negate (fmas@3 @0 @1 @2))
+  (IFN_FNMA:c (negate @0) @1 (negate @2))
+  (IFN_FMS @0 @1 @2))
+ (simplify
+  (negate (IFN_FNMA@3 @0 @1 @2))
   (if (single_use (@3))
-   (IFN_FNMS @0 @1 @2))))
+   (IFN_FMS @0 @1 @2)))
 
-(simplify
- (IFN_FMS:c (negate @0) @1 @2)
- (IFN_FNMS @0 @1 @2))
-(simplify
- (IFN_FMS @0 @1 (negate @2))
- (IFN_FMA @0 @1 @2))
-(simplify
- (IFN_FMS:c (negate @0) @1 (negate @2))
- (IFN_FNMA @0 @1 @2))
-(simplify
- (negate (IFN_FMS@3 @0 @1 @2))
+ (simplify
+  (IFN_FNMS:c (negate @0) @1 @2)
+  (IFN_FMS @0 @1 @2))
+ (simplify
+  (IFN_FNMS @0 @1 (negate @2))
+  (IFN_FNMA @0 @1 @2))
+ (simplify
+  (IFN_FNMS:c (negate @0) @1 (negate @2))
+  (IFN_FMA @0 @1 @2))
+ (simplify
+  (negate (IFN_FNMS@3 @0 @1 @2))
   (if (single_use (@3))
-   (IFN_FNMA @0 @1 @2)))
-
-(simplify
- (IFN_FNMA:c (negate @0) @1 @2)
- (IFN_FMA @0 @1 @2))
-(simplify
- (IFN_FNMA @0 @1 (negate @2))
- (IFN_FNMS @0 @1 @2))
-(simplify
- (IFN_FNMA:c (negate @0) @1 (negate @2))
- (IFN_FMS @0 @1 @2))
-(simplify
- (negate (IFN_FNMA@3 @0 @1 @2))
- (if (single_use (@3))
-  (IFN_FMS @0 @1 @2)))
-
-(simplify
- (IFN_FNMS:c (negate @0) @1 @2)
- (IFN_FMS @0 @1 @2))
-(simplify
- (IFN_FNMS @0 @1 (negate @2))
- (IFN_FNMA @0 @1 @2))
-(simplify
- (IFN_FNMS:c (negate @0) @1 (negate @2))
- (IFN_FMA @0 @1 @2))
-(simplify
- (negate (IFN_FNMS@3 @0 @1 @2))
- (if (single_use (@3))
-  (IFN_FMA @0 @1 @2)))
+   (IFN_FMA @0 @1 @2))))

gcc/testsuite/ChangeLog

+2018-05-24  Richard Sandiford  <richard.sandiford@linaro.org>
+
+	* gcc.dg/vect/vect-fma-1.c: New test.
+
 2018-05-24  Rainer Orth  <ro@CeBiTec.Uni-Bielefeld.DE>
 
 	* gcc.dg/tree-prof/update-loopch.c: Fix dumpfile name in

gcc/testsuite/gcc.dg/vect/vect-fma-1.c

+/* { dg-require-effective-target scalar_all_fma } */
+
+#include "tree-vect.h"
+
+#define N (VECTOR_BITS * 11 / 64 + 3)
+
+#define DEF(INV)					\
+  void __attribute__ ((noipa))				\
+  f_##INV (double *restrict a, double *restrict b,	\
+	   double *restrict c, double *restrict d)	\
+  {							\
+    for (int i = 0; i < N; ++i)				\
+      {							\
+	double mb = (INV & 1 ? -b[i] : b[i]);		\
+	double mc = c[i];				\
+	double md = (INV & 2 ? -d[i] : d[i]);		\
+	double fma = __builtin_fma (mb, mc, md);	\
+	a[i] = (INV & 4 ? -fma : fma);			\
+      }							\
+  }
+
+#define TEST(INV)					\
+  {							\
+    f_##INV (a, b, c, d);				\
+    for (int i = 0; i < N; ++i)				\
+      {							\
+	double mb = (INV & 1 ? -b[i] : b[i]);		\
+	double mc = c[i];				\
+	double md = (INV & 2 ? -d[i] : d[i]);		\
+	double fma = __builtin_fma (mb, mc, md);	\
+	double expected = (INV & 4 ? -fma : fma);	\
+	if (a[i] != expected)				\
+	  __builtin_abort ();				\
+	asm volatile ("" ::: "memory");			\
+      }							\
+  }
+
+#define FOR_EACH_INV(T)	\
+  T (0) T (1) T (2) T (3) T (4) T (5) T (6) T (7)
+
+FOR_EACH_INV (DEF)
+
+int
+main (void)
+{
+  double a[N], b[N], c[N], d[N];
+  for (int i = 0; i < N; ++i)
+    {
+      b[i] = i % 17;
+      c[i] = i % 9 + 11;
+      d[i] = i % 13 + 14;
+      asm volatile ("" ::: "memory");
+    }
+  FOR_EACH_INV (TEST)
+  return 0;
+}
+
+/* { dg-final { scan-tree-dump-times "LOOP VECTORIZED" 8 "vect" { target vect_double } } } */