From b8d5e148f669d56ccfd294dc396daba607237cdb Mon Sep 17 00:00:00 2001 From: Richard Sandiford Date: Thu, 9 Aug 2018 16:03:25 +0000 Subject: [PATCH] Allow inner-loop reductions with variable-length vectors While working on PR 86871, I noticed we were being overly restrictive when handling variable-length vectors. For: for (i : ...) { res = ...; for (j : ...) res op= ...; a[i] = res; } we don't need a reduction operation (although we do for double reductions like: res = ...; for (i : ...) for (j : ...) res op= ...; a[i] = res; which must still be rejected). 2018-08-08 Richard Sandiford gcc/ * tree-vect-loop.c (vectorizable_reduction): Allow inner-loop reductions for variable-length vectors. gcc/testsuite/ * gcc.target/aarch64/sve/reduc_8.c: New test. From-SVN: r263451 --- gcc/ChangeLog | 5 +++++ gcc/testsuite/ChangeLog | 4 ++++ .../gcc.target/aarch64/sve/reduc_8.c | 20 +++++++++++++++++++ gcc/tree-vect-loop.c | 1 + 4 files changed, 30 insertions(+) create mode 100644 gcc/testsuite/gcc.target/aarch64/sve/reduc_8.c diff --git a/gcc/ChangeLog b/gcc/ChangeLog index dd088bb46a8..839dfc3c2c2 100644 --- a/gcc/ChangeLog +++ b/gcc/ChangeLog @@ -1,3 +1,8 @@ +2018-08-09 Richard Sandiford + + * tree-vect-loop.c (vectorizable_reduction): Allow inner-loop + reductions for variable-length vectors. + 2018-08-09 David Malcolm PR other/84889 diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog index 3da9f3baa36..8ea8530243d 100644 --- a/gcc/testsuite/ChangeLog +++ b/gcc/testsuite/ChangeLog @@ -1,3 +1,7 @@ +2018-08-09 Richard Sandiford + + * gcc.target/aarch64/sve/reduc_8.c: New test. + 2018-08-09 David Malcolm PR other/84889 diff --git a/gcc/testsuite/gcc.target/aarch64/sve/reduc_8.c b/gcc/testsuite/gcc.target/aarch64/sve/reduc_8.c new file mode 100644 index 00000000000..3913b8848c0 --- /dev/null +++ b/gcc/testsuite/gcc.target/aarch64/sve/reduc_8.c @@ -0,0 +1,20 @@ +/* { dg-do compile } */ +/* { dg-options "-O2 -ftree-vectorize" } */ + +int +reduc (int *restrict a, int *restrict b, int *restrict c) +{ + for (int i = 0; i < 100; ++i) + { + int res = 0; + for (int j = 0; j < 100; ++j) + if (b[i + j] != 0) + res = c[i + j]; + a[i] = res; + } +} + +/* { 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-times {\tsel\tz[0-9]+\.s, } 1 } } */ diff --git a/gcc/tree-vect-loop.c b/gcc/tree-vect-loop.c index 0669f62c960..c167aec326e 100644 --- a/gcc/tree-vect-loop.c +++ b/gcc/tree-vect-loop.c @@ -6714,6 +6714,7 @@ vectorizable_reduction (stmt_vec_info stmt_info, gimple_stmt_iterator *gsi, } if (reduction_type != EXTRACT_LAST_REDUCTION + && (!nested_cycle || double_reduc) && reduc_fn == IFN_LAST && !nunits_out.is_constant ()) { -- 2.30.2