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. Tested on aarch64-linux-gnu (with and without SVE) and applied as r277441. Richard 2019-10-25 Richard Sandiford <richard.sandif...@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. Index: gcc/testsuite/gcc.target/aarch64/sve/loop_add_5.c =================================================================== --- gcc/testsuite/gcc.target/aarch64/sve/loop_add_5.c 2019-03-08 18:14:29.784994721 +0000 +++ gcc/testsuite/gcc.target/aarch64/sve/loop_add_5.c 2019-10-25 10:13:06.144292748 +0100 @@ -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 } } */ Index: gcc/testsuite/gcc.target/aarch64/sve/reduc_1.c =================================================================== --- gcc/testsuite/gcc.target/aarch64/sve/reduc_1.c 2019-03-08 18:14:29.776994751 +0000 +++ gcc/testsuite/gcc.target/aarch64/sve/reduc_1.c 2019-10-25 10:13:06.144292748 +0100 @@ -105,8 +105,8 @@ #define TEST_BITWISE(T) \ 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 } } */ Index: gcc/testsuite/gcc.target/aarch64/sve/reduc_2.c =================================================================== --- gcc/testsuite/gcc.target/aarch64/sve/reduc_2.c 2019-03-08 18:14:29.776994751 +0000 +++ gcc/testsuite/gcc.target/aarch64/sve/reduc_2.c 2019-10-25 10:13:06.144292748 +0100 @@ -116,8 +116,8 @@ #define TEST_BITWISE(T) \ 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 } } */ Index: gcc/testsuite/gcc.target/aarch64/sve/reduc_5.c =================================================================== --- gcc/testsuite/gcc.target/aarch64/sve/reduc_5.c 2019-03-08 18:14:29.792994691 +0000 +++ gcc/testsuite/gcc.target/aarch64/sve/reduc_5.c 2019-10-25 10:13:06.144292748 +0100 @@ -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 } } */ Index: gcc/testsuite/gcc.target/aarch64/sve/reduc_8.c =================================================================== --- gcc/testsuite/gcc.target/aarch64/sve/reduc_8.c 2019-03-08 18:14:29.772994767 +0000 +++ gcc/testsuite/gcc.target/aarch64/sve/reduc_8.c 2019-10-25 10:13:06.144292748 +0100 @@ -15,6 +15,5 @@ reduc (int *restrict a, int *restrict b, } /* { 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 } } */ Index: gcc/testsuite/gcc.target/aarch64/sve/slp_13.c =================================================================== --- gcc/testsuite/gcc.target/aarch64/sve/slp_13.c 2019-03-08 18:14:29.772994767 +0000 +++ gcc/testsuite/gcc.target/aarch64/sve/slp_13.c 2019-10-25 10:13:06.148292720 +0100 @@ -32,7 +32,6 @@ #define TEST_ALL(T) \ 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 } } */ Index: gcc/testsuite/gcc.target/aarch64/sve/slp_5.c =================================================================== --- gcc/testsuite/gcc.target/aarch64/sve/slp_5.c 2019-03-08 18:14:29.776994751 +0000 +++ gcc/testsuite/gcc.target/aarch64/sve/slp_5.c 2019-10-25 10:13:06.148292720 +0100 @@ -33,34 +33,24 @@ #define TEST_ALL(T) \ 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 } } */ Index: gcc/testsuite/gcc.target/aarch64/sve/slp_7.c =================================================================== --- gcc/testsuite/gcc.target/aarch64/sve/slp_7.c 2019-03-08 18:14:29.784994721 +0000 +++ gcc/testsuite/gcc.target/aarch64/sve/slp_7.c 2019-10-25 10:13:06.148292720 +0100 @@ -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 } } */