vec: don't select partial vectors when unnecessary

gcc/ChangeLog

2020-09-09  Andrea Corallo  <andrea.corallo@arm.com>

	* tree-vect-loop.c (vect_need_peeling_or_partial_vectors_p): New
	function.
	(vect_analyze_loop_2): Make use of it not to select partial
	vectors if no peel is required.
	(determine_peel_for_niter): Move out some logic into
	'vect_need_peeling_or_partial_vectors_p'.

gcc/testsuite/ChangeLog

2020-09-09  Andrea Corallo  <andrea.corallo@arm.com>

	* gcc.target/aarch64/sve/cost_model_10.c: New test.
	* gcc.target/aarch64/sve/clastb_8.c: Update test for new
	vectorization strategy.
	* gcc.target/aarch64/sve/cost_model_5.c: Likewise.
	* gcc.target/aarch64/sve/struct_vect_14.c: Likewise.
	* gcc.target/aarch64/sve/struct_vect_15.c: Likewise.
	* gcc.target/aarch64/sve/struct_vect_16.c: Likewise.
	* gcc.target/aarch64/sve/struct_vect_17.c: Likewise.

8 files changed, 80 insertions, 58 deletions

diff --git a/gcc/testsuite/gcc.target/aarch64/sve/clastb_8.c b/gcc/testsuite/gcc.target/aarch64/sve/clastb_8.c
index 57c4208..e61ff4a 100644
--- a/gcc/testsuite/gcc.target/aarch64/sve/clastb_8.c
+++ b/gcc/testsuite/gcc.target/aarch64/sve/clastb_8.c
@@ -23,7 +23,4 @@ TEST_TYPE (uint64_t);
 /* { dg-final { scan-assembler {\tclastb\t(h[0-9]+), p[0-7], \1, z[0-9]+\.h\n} } } */
 /* { dg-final { scan-assembler {\tclastb\t(s[0-9]+), p[0-7], \1, z[0-9]+\.s\n} } } */
 /* { dg-final { scan-assembler {\tclastb\t(d[0-9]+), p[0-7], \1, z[0-9]+\.d\n} } } */
-/* { dg-final { scan-assembler {\twhilelo\tp[0-9]+\.b,} } } */
-/* { dg-final { scan-assembler {\twhilelo\tp[0-9]+\.h,} } } */
-/* { dg-final { scan-assembler {\twhilelo\tp[0-9]+\.s,} } } */
-/* { dg-final { scan-assembler {\twhilelo\tp[0-9]+\.d,} } } */
+/* { dg-final { scan-assembler {\tptrue\tp[0-9]+\.b,} 4 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/cost_model_10.c b/gcc/testsuite/gcc.target/aarch64/sve/cost_model_10.c
new file mode 100644
index 0000000..bfac09e
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/cost_model_10.c
@@ -0,0 +1,12 @@
+/* { dg-options "-O3 -msve-vector-bits=256" } */
+
+void
+f (int *restrict x, int *restrict y, unsigned int n)
+{
+  for (unsigned int i = 0; i < n * 8; ++i)
+    x[i] += y[i];
+}
+
+/* { dg-final { scan-assembler-not {\twhilelo\t} } } */
+/* { dg-final { scan-assembler {\tptrue\tp} } } */
+/* { dg-final { scan-assembler {\tcmp\tx[0-9]+, x[0-9]+\n} } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/cost_model_5.c b/gcc/testsuite/gcc.target/aarch64/sve/cost_model_5.c
index 250ca83..f3a29fc 100644
--- a/gcc/testsuite/gcc.target/aarch64/sve/cost_model_5.c
+++ b/gcc/testsuite/gcc.target/aarch64/sve/cost_model_5.c
@@ -9,5 +9,5 @@ vset (int *restrict dst, int *restrict src, int count)
       *dst++ = 1;
 }
 
-/* { dg-final { scan-assembler-not {\tst1w\tz} } } */
-/* { dg-final { scan-assembler-times {\tstp\tq} 2 } } */
+/* { dg-final { scan-assembler-times {\tst1w\tz} 2 } } */
+/* { dg-final { scan-assembler-not {\tstp\tq} } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/struct_vect_14.c b/gcc/testsuite/gcc.target/aarch64/sve/struct_vect_14.c
index a16a79e..45644b6 100644
--- a/gcc/testsuite/gcc.target/aarch64/sve/struct_vect_14.c
+++ b/gcc/testsuite/gcc.target/aarch64/sve/struct_vect_14.c
@@ -43,12 +43,12 @@
 #undef NAME
 #undef TYPE
 
-/* { dg-final { scan-assembler-times {\tld2b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7]/z, \[x[0-9]+, x[0-9]+\]\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tld2b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7]/z, \[x[0-9]+\]\n} 1 } } */
 /* { dg-final { scan-assembler-times {\tld3b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7]/z, \[x[0-9]+\]\n} 1 } } */
-/* { dg-final { scan-assembler-times {\tld4b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7]/z, \[x[0-9]+, x[0-9]+\]\n} 1 } } */
-/* { dg-final { scan-assembler-times {\tst2b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7], \[x[0-9]+, x[0-9]+\]\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tld4b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7]/z, \[x[0-9]+\]\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tst2b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7], \[x[0-9]+\]\n} 1 } } */
 /* { dg-final { scan-assembler-times {\tst3b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7], \[x[0-9]+\]\n} 1 } } */
-/* { dg-final { scan-assembler-times {\tst4b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7], \[x[0-9]+, x[0-9]+\]\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tst4b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7], \[x[0-9]+\]\n} 1 } } */
 
 /* { dg-final { scan-assembler-times {\tld2h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
 /* { dg-final { scan-assembler-times {\tld3h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/struct_vect_15.c b/gcc/testsuite/gcc.target/aarch64/sve/struct_vect_15.c
index bc00267..814dbb3 100644
--- a/gcc/testsuite/gcc.target/aarch64/sve/struct_vect_15.c
+++ b/gcc/testsuite/gcc.target/aarch64/sve/struct_vect_15.c
@@ -3,12 +3,12 @@
 
 #include "struct_vect_14.c"
 
-/* { dg-final { scan-assembler-times {\tld2b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7]/z, \[x[0-9]+, x[0-9]+\]\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tld2b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7]/z, \[x[0-9]+\]\n} 1 } } */
 /* { dg-final { scan-assembler-times {\tld3b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7]/z, \[x[0-9]+\]\n} 1 } } */
-/* { dg-final { scan-assembler-times {\tld4b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7]/z, \[x[0-9]+, x[0-9]+\]\n} 1 } } */
-/* { dg-final { scan-assembler-times {\tst2b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7], \[x[0-9]+, x[0-9]+\]\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tld4b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7]/z, \[x[0-9]+\]\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tst2b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7], \[x[0-9]+\]\n} 1 } } */
 /* { dg-final { scan-assembler-times {\tst3b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7], \[x[0-9]+\]\n} 1 } } */
-/* { dg-final { scan-assembler-times {\tst4b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7], \[x[0-9]+, x[0-9]+\]\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tst4b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7], \[x[0-9]+\]\n} 1 } } */
 
 /* { dg-final { scan-assembler-times {\tld2h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
 /* { dg-final { scan-assembler-times {\tld3h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/struct_vect_16.c b/gcc/testsuite/gcc.target/aarch64/sve/struct_vect_16.c
index 9e2a549..6ecf89b 100644
--- a/gcc/testsuite/gcc.target/aarch64/sve/struct_vect_16.c
+++ b/gcc/testsuite/gcc.target/aarch64/sve/struct_vect_16.c
@@ -3,12 +3,12 @@
 
 #include "struct_vect_14.c"
 
-/* { dg-final { scan-assembler-times {\tld2b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7]/z, \[x[0-9]+, x[0-9]+\]\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tld2b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7]/z, \[x[0-9]+\]\n} 1 } } */
 /* { dg-final { scan-assembler-times {\tld3b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7]/z, \[x[0-9]+\]\n} 1 } } */
-/* { dg-final { scan-assembler-times {\tld4b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7]/z, \[x[0-9]+, x[0-9]+\]\n} 1 } } */
-/* { dg-final { scan-assembler-times {\tst2b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7], \[x[0-9]+, x[0-9]+\]\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tld4b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7]/z, \[x[0-9]+\]\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tst2b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7], \[x[0-9]+\]\n} 1 } } */
 /* { dg-final { scan-assembler-times {\tst3b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7], \[x[0-9]+\]\n} 1 } } */
-/* { dg-final { scan-assembler-times {\tst4b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7], \[x[0-9]+, x[0-9]+\]\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tst4b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7], \[x[0-9]+\]\n} 1 } } */
 
 /* { dg-final { scan-assembler-times {\tld2h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
 /* { dg-final { scan-assembler-times {\tld3h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/struct_vect_17.c b/gcc/testsuite/gcc.target/aarch64/sve/struct_vect_17.c
index e791e2e..571c6d0 100644
--- a/gcc/testsuite/gcc.target/aarch64/sve/struct_vect_17.c
+++ b/gcc/testsuite/gcc.target/aarch64/sve/struct_vect_17.c
@@ -3,12 +3,12 @@
 
 #include "struct_vect_14.c"
 
-/* { dg-final { scan-assembler-times {\tld2b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7]/z, \[x[0-9]+, x[0-9]+\]\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tld2b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7]/z, \[x[0-9]+\]\n} 1 } } */
 /* { dg-final { scan-assembler-times {\tld3b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7]/z, \[x[0-9]+\]\n} 1 } } */
-/* { dg-final { scan-assembler-times {\tld4b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7]/z, \[x[0-9]+, x[0-9]+\]\n} 1 } } */
-/* { dg-final { scan-assembler-times {\tst2b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7], \[x[0-9]+, x[0-9]+\]\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tld4b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7]/z, \[x[0-9]+\]\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tst2b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7], \[x[0-9]+\]\n} 1 } } */
 /* { dg-final { scan-assembler-times {\tst3b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7], \[x[0-9]+\]\n} 1 } } */
-/* { dg-final { scan-assembler-times {\tst4b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7], \[x[0-9]+, x[0-9]+\]\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tst4b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7], \[x[0-9]+\]\n} 1 } } */
 
 /* { dg-final { scan-assembler-times {\tld2h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
 /* { dg-final { scan-assembler-times {\tld3h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
diff --git a/gcc/tree-vect-loop.c b/gcc/tree-vect-loop.c
index 3af4cf7..3021be3 100644
--- a/gcc/tree-vect-loop.c
+++ b/gcc/tree-vect-loop.c
@@ -991,6 +991,51 @@ vect_min_prec_for_max_niters (loop_vec_info loop_vinfo, unsigned int factor)
   return wi::min_precision (max_ni * factor, UNSIGNED);
 }
 
+/* True if the loop needs peeling or partial vectors when vectorized.  */
+
+static bool
+vect_need_peeling_or_partial_vectors_p (loop_vec_info loop_vinfo)
+{
+  unsigned HOST_WIDE_INT const_vf;
+  HOST_WIDE_INT max_niter
+    = likely_max_stmt_executions_int (LOOP_VINFO_LOOP (loop_vinfo));
+
+  unsigned th = LOOP_VINFO_COST_MODEL_THRESHOLD (loop_vinfo);
+  if (!th && LOOP_VINFO_ORIG_LOOP_INFO (loop_vinfo))
+    th = LOOP_VINFO_COST_MODEL_THRESHOLD (LOOP_VINFO_ORIG_LOOP_INFO
+					  (loop_vinfo));
+
+  if (LOOP_VINFO_NITERS_KNOWN_P (loop_vinfo)
+      && LOOP_VINFO_PEELING_FOR_ALIGNMENT (loop_vinfo) >= 0)
+    {
+      /* Work out the (constant) number of iterations that need to be
+	 peeled for reasons other than niters.  */
+      unsigned int peel_niter = LOOP_VINFO_PEELING_FOR_ALIGNMENT (loop_vinfo);
+      if (LOOP_VINFO_PEELING_FOR_GAPS (loop_vinfo))
+	peel_niter += 1;
+      if (!multiple_p (LOOP_VINFO_INT_NITERS (loop_vinfo) - peel_niter,
+		       LOOP_VINFO_VECT_FACTOR (loop_vinfo)))
+	return true;
+    }
+  else if (LOOP_VINFO_PEELING_FOR_ALIGNMENT (loop_vinfo)
+      /* ??? When peeling for gaps but not alignment, we could
+	 try to check whether the (variable) niters is known to be
+	 VF * N + 1.  That's something of a niche case though.  */
+      || LOOP_VINFO_PEELING_FOR_GAPS (loop_vinfo)
+      || !LOOP_VINFO_VECT_FACTOR (loop_vinfo).is_constant (&const_vf)
+      || ((tree_ctz (LOOP_VINFO_NITERS (loop_vinfo))
+	   < (unsigned) exact_log2 (const_vf))
+	  /* In case of versioning, check if the maximum number of
+	     iterations is greater than th.  If they are identical,
+	     the epilogue is unnecessary.  */
+	  && (!LOOP_REQUIRES_VERSIONING (loop_vinfo)
+	      || ((unsigned HOST_WIDE_INT) max_niter
+		  > (th / const_vf) * const_vf))))
+    return true;
+
+  return false;
+}
+
 /* Each statement in LOOP_VINFO can be masked where necessary.  Check
    whether we can actually generate the masks required.  Return true if so,
    storing the type of the scalar IV in LOOP_VINFO_RGROUP_COMPARE_TYPE.  */
@@ -1967,44 +2012,10 @@ determine_peel_for_niter (loop_vec_info loop_vinfo)
 {
   LOOP_VINFO_PEELING_FOR_NITER (loop_vinfo) = false;
 
-  unsigned HOST_WIDE_INT const_vf;
-  HOST_WIDE_INT max_niter
-    = likely_max_stmt_executions_int (LOOP_VINFO_LOOP (loop_vinfo));
-
-  unsigned th = LOOP_VINFO_COST_MODEL_THRESHOLD (loop_vinfo);
-  if (!th && LOOP_VINFO_ORIG_LOOP_INFO (loop_vinfo))
-    th = LOOP_VINFO_COST_MODEL_THRESHOLD (LOOP_VINFO_ORIG_LOOP_INFO
-					  (loop_vinfo));
-
   if (LOOP_VINFO_USING_PARTIAL_VECTORS_P (loop_vinfo))
     /* The main loop handles all iterations.  */
     LOOP_VINFO_PEELING_FOR_NITER (loop_vinfo) = false;
-  else if (LOOP_VINFO_NITERS_KNOWN_P (loop_vinfo)
-	   && LOOP_VINFO_PEELING_FOR_ALIGNMENT (loop_vinfo) >= 0)
-    {
-      /* Work out the (constant) number of iterations that need to be
-	 peeled for reasons other than niters.  */
-      unsigned int peel_niter = LOOP_VINFO_PEELING_FOR_ALIGNMENT (loop_vinfo);
-      if (LOOP_VINFO_PEELING_FOR_GAPS (loop_vinfo))
-	peel_niter += 1;
-      if (!multiple_p (LOOP_VINFO_INT_NITERS (loop_vinfo) - peel_niter,
-		       LOOP_VINFO_VECT_FACTOR (loop_vinfo)))
-	LOOP_VINFO_PEELING_FOR_NITER (loop_vinfo) = true;
-    }
-  else if (LOOP_VINFO_PEELING_FOR_ALIGNMENT (loop_vinfo)
-	   /* ??? When peeling for gaps but not alignment, we could
-	      try to check whether the (variable) niters is known to be
-	      VF * N + 1.  That's something of a niche case though.  */
-	   || LOOP_VINFO_PEELING_FOR_GAPS (loop_vinfo)
-	   || !LOOP_VINFO_VECT_FACTOR (loop_vinfo).is_constant (&const_vf)
-	   || ((tree_ctz (LOOP_VINFO_NITERS (loop_vinfo))
-		< (unsigned) exact_log2 (const_vf))
-	       /* In case of versioning, check if the maximum number of
-		  iterations is greater than th.  If they are identical,
-		  the epilogue is unnecessary.  */
-	       && (!LOOP_REQUIRES_VERSIONING (loop_vinfo)
-		   || ((unsigned HOST_WIDE_INT) max_niter
-		       > (th / const_vf) * const_vf))))
+  else if (vect_need_peeling_or_partial_vectors_p (loop_vinfo))
     LOOP_VINFO_PEELING_FOR_NITER (loop_vinfo) = true;
 }
 
@@ -2265,7 +2276,9 @@ start_over:
      this vectorization factor.  */
   if (LOOP_VINFO_CAN_USE_PARTIAL_VECTORS_P (loop_vinfo))
     {
-      if (param_vect_partial_vector_usage == 0)
+      /* Don't use partial vectors if we don't need to peel the loop.  */
+      if (param_vect_partial_vector_usage == 0
+	  || !vect_need_peeling_or_partial_vectors_p (loop_vinfo))
 	LOOP_VINFO_USING_PARTIAL_VECTORS_P (loop_vinfo) = false;
       else if (vect_verify_full_masking (loop_vinfo)
 	       || vect_verify_loop_lens (loop_vinfo))