Update SVE tests for recent XPASSes

Recent target-independent patches mean that several SVE tests
now produce the code that we'd originally wanted them to produce.
Really nice to see :-)

This patch therefore updates the expected baseline, so that hopefully
we don't regress from this point in future.

2019-10-25  Richard Sandiford  <richard.sandiford@arm.com>

gcc/testsuite/
	* gcc.target/aarch64/sve/loop_add_5.c: Remove XFAILs for tests
	that now pass.
	* gcc.target/aarch64/sve/reduc_1.c: Likewise.
	* gcc.target/aarch64/sve/reduc_2.c: Likewise.
	* gcc.target/aarch64/sve/reduc_5.c: Likewise.
	* gcc.target/aarch64/sve/reduc_8.c: Likewise.
	* gcc.target/aarch64/sve/slp_13.c: Likewise.
	* gcc.target/aarch64/sve/slp_5.c: Likewise.  Update expected
	WHILELO counts.
	* gcc.target/aarch64/sve/slp_7.c: Likewise.

From-SVN: r277441

gcc/testsuite/ChangeLog

 2019-10-25  Richard Sandiford  <richard.sandiford@arm.com>
 
+	* gcc.target/aarch64/sve/loop_add_5.c: Remove XFAILs for tests
+	that now pass.
+	* gcc.target/aarch64/sve/reduc_1.c: Likewise.
+	* gcc.target/aarch64/sve/reduc_2.c: Likewise.
+	* gcc.target/aarch64/sve/reduc_5.c: Likewise.
+	* gcc.target/aarch64/sve/reduc_8.c: Likewise.
+	* gcc.target/aarch64/sve/slp_13.c: Likewise.
+	* gcc.target/aarch64/sve/slp_5.c: Likewise.  Update expected
+	WHILELO counts.
+	* gcc.target/aarch64/sve/slp_7.c: Likewise.
+
+2019-10-25  Richard Sandiford  <richard.sandiford@arm.com>
+
 	* gcc.dg/vect/pr65947-1.c: No longer expect doubled dump lines
 	for FOLD_EXTRACT_LAST reductions.
 	* gcc.dg/vect/pr65947-2.c: Likewise.

gcc/testsuite/gcc.target/aarch64/sve/loop_add_5.c

@@ -3,11 +3,11 @@
 
 #include "loop_add_4.c"
 
-/* { dg-final { scan-assembler-times {\tindex\tz[0-9]+\.b, w[0-9]+, #-16\n} 1 { xfail *-*-* } } } */
-/* { dg-final { scan-assembler-times {\tindex\tz[0-9]+\.b, w[0-9]+, #-15\n} 1 { xfail *-*-* }  } } */
+/* { dg-final { scan-assembler-times {\tindex\tz[0-9]+\.b, w[0-9]+, #-16\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tindex\tz[0-9]+\.b, w[0-9]+, #-15\n} 1 } } */
 /* { dg-final { scan-assembler-times {\tindex\tz[0-9]+\.b, w[0-9]+, #1\n} 1 } } */
-/* { dg-final { scan-assembler-times {\tindex\tz[0-9]+\.b, w[0-9]+, #15\n} 1 { xfail *-*-* } } } */
-/* { dg-final { scan-assembler-times {\tindex\tz[0-9]+\.b, w[0-9]+, w[0-9]+\n} 3 { xfail *-*-* }  } } */
+/* { dg-final { scan-assembler-times {\tindex\tz[0-9]+\.b, w[0-9]+, #15\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tindex\tz[0-9]+\.b, w[0-9]+, w[0-9]+\n} 3 } } */
 /* { dg-final { scan-assembler-times {\tld1b\tz[0-9]+\.b, p[0-7]+/z, \[x[0-9]+, x[0-9]+\]} 8 } } */
 /* { dg-final { scan-assembler-times {\tst1b\tz[0-9]+\.b, p[0-7]+, \[x[0-9]+, x[0-9]+\]} 8 } } */
 
@@ -16,11 +16,11 @@
 /* { dg-final { scan-assembler-times {\tadd\tz[0-9]+\.b, z[0-9]+\.b, #} 6 } } */
 /* { dg-final { scan-assembler-times {\tadd\tz[0-9]+\.b, z[0-9]+\.b, z[0-9]+\.b\n} 8 } } */
 
-/* { dg-final { scan-assembler-times {\tindex\tz[0-9]+\.h, w[0-9]+, #-16\n} 1 { xfail *-*-* } } } */
-/* { dg-final { scan-assembler-times {\tindex\tz[0-9]+\.h, w[0-9]+, #-15\n} 1 { xfail *-*-* } } } */
+/* { dg-final { scan-assembler-times {\tindex\tz[0-9]+\.h, w[0-9]+, #-16\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tindex\tz[0-9]+\.h, w[0-9]+, #-15\n} 1 } } */
 /* { dg-final { scan-assembler-times {\tindex\tz[0-9]+\.h, w[0-9]+, #1\n} 1 } } */
 /* { dg-final { scan-assembler-times {\tindex\tz[0-9]+\.h, w[0-9]+, #15\n} 1 } } */
-/* { dg-final { scan-assembler-times {\tindex\tz[0-9]+\.h, w[0-9]+, w[0-9]+\n} 3 { xfail *-*-* } } } */
+/* { dg-final { scan-assembler-times {\tindex\tz[0-9]+\.h, w[0-9]+, w[0-9]+\n} 3 } } */
 /* { dg-final { scan-assembler-times {\tld1h\tz[0-9]+\.h, p[0-7]+/z, \[x[0-9]+, x[0-9]+, lsl 1\]} 8 } } */
 /* { dg-final { scan-assembler-times {\tst1h\tz[0-9]+\.h, p[0-7]+, \[x[0-9]+, x[0-9]+, lsl 1\]} 8 } } */
 

gcc/testsuite/gcc.target/aarch64/sve/reduc_1.c

@@ -105,8 +105,8 @@ reduc_##NAME##_##TYPE (TYPE *a, int n)		\
 
 TEST_BITWISE (DEF_REDUC_BITWISE)
 
-/* { dg-final { scan-assembler-times {\tadd\tz[0-9]+\.b, p[0-7]/m, z[0-9]+\.b, z[0-9]+\.b\n} 1 } } */
-/* { dg-final { scan-assembler-times {\tadd\tz[0-9]+\.h, p[0-7]/m, z[0-9]+\.h, z[0-9]+\.h\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tadd\tz[0-9]+\.b, p[0-7]/m, z[0-9]+\.b, z[0-9]+\.b\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tadd\tz[0-9]+\.h, p[0-7]/m, z[0-9]+\.h, z[0-9]+\.h\n} 2 } } */
 /* { dg-final { scan-assembler-times {\tadd\tz[0-9]+\.s, p[0-7]/m, z[0-9]+\.s, z[0-9]+\.s\n} 2 } } */
 /* { dg-final { scan-assembler-times {\tadd\tz[0-9]+\.d, p[0-7]/m, z[0-9]+\.d, z[0-9]+\.d\n} 2 } } */
 
@@ -157,8 +157,8 @@ TEST_BITWISE (DEF_REDUC_BITWISE)
 /* { dg-final { scan-assembler-times {\teor\tz[0-9]+\.s, p[0-7]/m, z[0-9]+\.s, z[0-9]+\.s\n} 2 } } */
 /* { dg-final { scan-assembler-times {\teor\tz[0-9]+\.d, p[0-7]/m, z[0-9]+\.d, z[0-9]+\.d\n} 2 } } */
 
-/* { dg-final { scan-assembler-times {\tuaddv\td[0-9]+, p[0-7], z[0-9]+\.b\n} 1 } } */
-/* { dg-final { scan-assembler-times {\tuaddv\td[0-9]+, p[0-7], z[0-9]+\.h\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tuaddv\td[0-9]+, p[0-7], z[0-9]+\.b\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tuaddv\td[0-9]+, p[0-7], z[0-9]+\.h\n} 2 } } */
 /* { dg-final { scan-assembler-times {\tuaddv\td[0-9]+, p[0-7], z[0-9]+\.s\n} 2 } } */
 /* { dg-final { scan-assembler-times {\tuaddv\td[0-9]+, p[0-7], z[0-9]+\.d\n} 2 } } */
 /* { dg-final { scan-assembler-times {\tfaddv\th[0-9]+, p[0-7], z[0-9]+\.h\n} 1 } } */

gcc/testsuite/gcc.target/aarch64/sve/reduc_2.c

@@ -116,8 +116,8 @@ reduc_##NAME##TYPE (TYPE (*restrict a)[NUM_ELEMS(TYPE)],	\
 
 TEST_BITWISE (DEF_REDUC_BITWISE)
 
-/* { dg-final { scan-assembler-times {\tuaddv\td[0-9]+, p[0-7], z[0-9]+\.b\n} 1 } } */
-/* { dg-final { scan-assembler-times {\tuaddv\td[0-9]+, p[0-7], z[0-9]+\.h\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tuaddv\td[0-9]+, p[0-7], z[0-9]+\.b\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tuaddv\td[0-9]+, p[0-7], z[0-9]+\.h\n} 2 } } */
 /* { dg-final { scan-assembler-times {\tuaddv\td[0-9]+, p[0-7], z[0-9]+\.s\n} 2 } } */
 /* { dg-final { scan-assembler-times {\tuaddv\td[0-9]+, p[0-7], z[0-9]+\.d\n} 2 } } */
 /* { dg-final { scan-assembler-times {\tfaddv\th[0-9]+, p[0-7], z[0-9]+\.h\n} 1 } } */

gcc/testsuite/gcc.target/aarch64/sve/reduc_5.c

@@ -23,16 +23,12 @@ REDUC (uint64_t)
 REDUC (float)
 REDUC (double)
 
-/* XFAILed until we support sub-int reductions for signed types.  */
-/* { dg-final { scan-assembler-times {\tsub\tz[0-9]+\.b, p[0-7]/m} 2 { xfail *-*-* } } } */
-/* { dg-final { scan-assembler-times {\tsub\tz[0-9]+\.h, p[0-7]/m} 2 { xfail *-*-* } } } */
-/* { dg-final { scan-assembler-times {\tsub\tz[0-9]+\.b, p[0-7]/m} 1 } } */
-/* { dg-final { scan-assembler-times {\tsub\tz[0-9]+\.h, p[0-7]/m} 1 } } */
+/* { dg-final { scan-assembler-times {\tsub\tz[0-9]+\.b, p[0-7]/m} 2 } } */
+/* { dg-final { scan-assembler-times {\tsub\tz[0-9]+\.h, p[0-7]/m} 2 } } */
 /* { dg-final { scan-assembler-times {\tsub\tz[0-9]+\.s, p[0-7]/m} 2 } } */
 /* { dg-final { scan-assembler-times {\tsub\tz[0-9]+\.d, p[0-7]/m} 2 } } */
 /* { dg-final { scan-assembler-times {\tfsub\tz[0-9]+\.s, p[0-7]/m} 1 } } */
 /* { dg-final { scan-assembler-times {\tfsub\tz[0-9]+\.d, p[0-7]/m} 1 } } */
 
-/* XFAILed until we support sub-int reductions for signed types.  */
-/* { dg-final { scan-assembler-times {\tsub\t} 8 { xfail *-*-* } } } */
+/* { dg-final { scan-assembler-times {\tsub\t} 8 } } */
 /* { dg-final { scan-assembler-times {\tfsub\t} 2 } } */

gcc/testsuite/gcc.target/aarch64/sve/reduc_8.c

@@ -15,6 +15,5 @@ reduc (int *restrict a, int *restrict b, int *restrict c)
 }
 
 /* { dg-final { scan-assembler-times {\tcmpne\tp[0-9]+\.s, } 1 } } */
-/* We ought to use the CMPNE result for the SEL too.  */
-/* { dg-final { scan-assembler-not {\tcmpeq\tp[0-9]+\.s, } { xfail *-*-* } } } */
+/* { dg-final { scan-assembler-not {\tcmpeq\tp[0-9]+\.s, } } } */
 /* { dg-final { scan-assembler-times {\tsel\tz[0-9]+\.s, } 1 } } */

gcc/testsuite/gcc.target/aarch64/sve/slp_13.c

@@ -32,7 +32,6 @@ vec_slp_##TYPE (TYPE *restrict a, int n)			\
 
 TEST_ALL (VEC_PERM)
 
-/* ??? We don't treat the int8_t and int16_t loops as reductions.  */
 /* ??? We don't treat the uint loops as SLP.  */
 /* The loop should be fully-masked.  */
 /* { dg-final { scan-assembler-times {\tld1b\t} 2 { xfail *-*-* } } } */
@@ -41,15 +40,15 @@ TEST_ALL (VEC_PERM)
 /* { dg-final { scan-assembler-times {\tld1w\t} 2 } } */
 /* { dg-final { scan-assembler-times {\tld1d\t} 3 { xfail *-*-* } } } */
 /* { dg-final { scan-assembler-times {\tld1d\t} 2 } } */
-/* { dg-final { scan-assembler-not {\tldr} { xfail *-*-* } } } */
+/* { dg-final { scan-assembler-not {\tldr} } } */
 
-/* { dg-final { scan-assembler-times {\twhilelo\tp[0-7]\.b} 4 { xfail *-*-* } } } */
-/* { dg-final { scan-assembler-times {\twhilelo\tp[0-7]\.h} 6 { xfail *-*-* } } } */
+/* { dg-final { scan-assembler-times {\twhilelo\tp[0-7]\.b} 4 } } */
+/* { dg-final { scan-assembler-times {\twhilelo\tp[0-7]\.h} 6 } } */
 /* { dg-final { scan-assembler-times {\twhilelo\tp[0-7]\.s} 6 } } */
 /* { dg-final { scan-assembler-times {\twhilelo\tp[0-7]\.d} 6 } } */
 
-/* { dg-final { scan-assembler-times {\tuaddv\td[0-9]+, p[0-7], z[0-9]+\.b\n} 2 { xfail *-*-* } } } */
-/* { dg-final { scan-assembler-times {\tuaddv\td[0-9]+, p[0-7], z[0-9]+\.h\n} 2 { xfail *-*-* } } } */
+/* { dg-final { scan-assembler-times {\tuaddv\td[0-9]+, p[0-7], z[0-9]+\.b\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tuaddv\td[0-9]+, p[0-7], z[0-9]+\.h\n} 2 } } */
 /* { dg-final { scan-assembler-times {\tuaddv\td[0-9]+, p[0-7], z[0-9]+\.s\n} 2 } } */
 /* { dg-final { scan-assembler-times {\tuaddv\td[0-9]+, p[0-7], z[0-9]+\.d\n} 2 } } */
 /* { dg-final { scan-assembler-times {\tfadda\th[0-9]+, p[0-7], h[0-9]+, z[0-9]+\.h\n} 1 } } */

gcc/testsuite/gcc.target/aarch64/sve/slp_5.c

@@ -33,34 +33,24 @@ vec_slp_##TYPE (TYPE *restrict a, TYPE *restrict b, int n)	\
 
 TEST_ALL (VEC_PERM)
 
-/* ??? We don't think it's worth using SLP for the 64-bit loops and fall
-   back to the less efficient non-SLP implementation instead.  */
-/* ??? At present we don't treat the int8_t and int16_t loops as
-   reductions.  */
-/* { dg-final { scan-assembler-times {\tld1b\t} 2 { xfail *-*-* } } } */
-/* { dg-final { scan-assembler-times {\tld1h\t} 3 { xfail *-*-* } } } */
-/* { dg-final { scan-assembler-times {\tld1b\t} 1 } } */
-/* { dg-final { scan-assembler-times {\tld1h\t} 2 } } */
+/* { dg-final { scan-assembler-times {\tld1b\t} 2 } } */
+/* { dg-final { scan-assembler-times {\tld1h\t} 3 } } */
 /* { dg-final { scan-assembler-times {\tld1w\t} 3 } } */
 /* { dg-final { scan-assembler-times {\tld1d\t} 3 } } */
 /* { dg-final { scan-assembler-not {\tld2b\t} } } */
 /* { dg-final { scan-assembler-not {\tld2h\t} } } */
 /* { dg-final { scan-assembler-not {\tld2w\t} } } */
 /* { dg-final { scan-assembler-not {\tld2d\t} } } */
-/* { dg-final { scan-assembler-times {\tuaddv\td[0-9]+, p[0-7], z[0-9]+\.b} 4 { xfail *-*-* } } } */
-/* { dg-final { scan-assembler-times {\tuaddv\td[0-9]+, p[0-7], z[0-9]+\.h} 4 { xfail *-*-* } } } */
-/* { dg-final { scan-assembler-times {\tuaddv\td[0-9]+, p[0-7], z[0-9]+\.b} 2 } } */
-/* { dg-final { scan-assembler-times {\tuaddv\td[0-9]+, p[0-7], z[0-9]+\.h} 2 } } */
+/* { dg-final { scan-assembler-times {\tuaddv\td[0-9]+, p[0-7], z[0-9]+\.b} 4 } } */
+/* { dg-final { scan-assembler-times {\tuaddv\td[0-9]+, p[0-7], z[0-9]+\.h} 4 } } */
 /* { dg-final { scan-assembler-times {\tuaddv\td[0-9]+, p[0-7], z[0-9]+\.s} 4 } } */
 /* { dg-final { scan-assembler-times {\tuaddv\td[0-9]+, p[0-7], z[0-9]+\.d} 4 } } */
 /* { dg-final { scan-assembler-times {\tfaddv\th[0-9]+, p[0-7], z[0-9]+\.h} 2 } } */
 /* { dg-final { scan-assembler-times {\tfaddv\ts[0-9]+, p[0-7], z[0-9]+\.s} 2 } } */
 /* { dg-final { scan-assembler-times {\tfaddv\td[0-9]+, p[0-7], z[0-9]+\.d} 2 } } */
 
-/* Should be 4 and 6 respectively, if we used reductions for int8_t and
-   int16_t.  */
-/* { dg-final { scan-assembler-times {\twhilelo\tp[0-7]\.b} 2 } } */
-/* { dg-final { scan-assembler-times {\twhilelo\tp[0-7]\.h} 4 } } */
+/* { dg-final { scan-assembler-times {\twhilelo\tp[0-7]\.b} 4 } } */
+/* { dg-final { scan-assembler-times {\twhilelo\tp[0-7]\.h} 6 } } */
 /* { dg-final { scan-assembler-times {\twhilelo\tp[0-7]\.s} 6 } } */
 /* { dg-final { scan-assembler-times {\twhilelo\tp[0-7]\.d} 6 } } */
 

gcc/testsuite/gcc.target/aarch64/sve/slp_7.c

@@ -43,32 +43,24 @@ TEST_ALL (VEC_PERM)
    results might be greater than the number of elements in the vector.
    Otherwise we have two loads per loop, one for the initial vector
    and one for the loop body.  */
-/* ??? At present we don't treat the int8_t and int16_t loops as
-   reductions.  */
-/* { dg-final { scan-assembler-times {\tld1b\t} 2 { xfail *-*-* } } } */
-/* { dg-final { scan-assembler-times {\tld1h\t} 3 { xfail *-*-* } } } */
-/* { dg-final { scan-assembler-times {\tld1b\t} 1 } } */
-/* { dg-final { scan-assembler-times {\tld1h\t} 2 } } */
+/* { dg-final { scan-assembler-times {\tld1b\t} 2 } } */
+/* { dg-final { scan-assembler-times {\tld1h\t} 3 } } */
 /* { dg-final { scan-assembler-times {\tld1w\t} 3 } } */
 /* { dg-final { scan-assembler-times {\tld4d\t} 3 } } */
 /* { dg-final { scan-assembler-not {\tld4b\t} } } */
 /* { dg-final { scan-assembler-not {\tld4h\t} } } */
 /* { dg-final { scan-assembler-not {\tld4w\t} } } */
 /* { dg-final { scan-assembler-not {\tld1d\t} } } */
-/* { dg-final { scan-assembler-times {\tuaddv\td[0-9]+, p[0-7], z[0-9]+\.b} 8 { xfail *-*-* } } } */
-/* { dg-final { scan-assembler-times {\tuaddv\td[0-9]+, p[0-7], z[0-9]+\.h} 8 { xfail *-*-* } } } */
-/* { dg-final { scan-assembler-times {\tuaddv\td[0-9]+, p[0-7], z[0-9]+\.b} 4 } } */
-/* { dg-final { scan-assembler-times {\tuaddv\td[0-9]+, p[0-7], z[0-9]+\.h} 4 } } */
+/* { dg-final { scan-assembler-times {\tuaddv\td[0-9]+, p[0-7], z[0-9]+\.b} 8 } } */
+/* { dg-final { scan-assembler-times {\tuaddv\td[0-9]+, p[0-7], z[0-9]+\.h} 8 } } */
 /* { dg-final { scan-assembler-times {\tuaddv\td[0-9]+, p[0-7], z[0-9]+\.s} 8 } } */
 /* { dg-final { scan-assembler-times {\tuaddv\td[0-9]+, p[0-7], z[0-9]+\.d} 8 } } */
 /* { dg-final { scan-assembler-times {\tfaddv\th[0-9]+, p[0-7], z[0-9]+\.h} 4 } } */
 /* { dg-final { scan-assembler-times {\tfaddv\ts[0-9]+, p[0-7], z[0-9]+\.s} 4 } } */
 /* { dg-final { scan-assembler-times {\tfaddv\td[0-9]+, p[0-7], z[0-9]+\.d} 4 } } */
 
-/* Should be 4 and 6 respectively, if we used reductions for int8_t and
-   int16_t.  */
-/* { dg-final { scan-assembler-times {\twhilelo\tp[0-7]\.b} 2 } } */
-/* { dg-final { scan-assembler-times {\twhilelo\tp[0-7]\.h} 4 } } */
+/* { dg-final { scan-assembler-times {\twhilelo\tp[0-7]\.b} 4 } } */
+/* { dg-final { scan-assembler-times {\twhilelo\tp[0-7]\.h} 6 } } */
 /* { dg-final { scan-assembler-times {\twhilelo\tp[0-7]\.s} 6 } } */
 /* { dg-final { scan-assembler-times {\twhilelo\tp[0-7]\.d} 6 } } */