diff options
-rw-r--r-- | gcc/testsuite/gcc.dg/vect/vect-reduc-cond-sub.c | 29 | ||||
-rw-r--r-- | gcc/testsuite/gcc.target/i386/vect-pr113078.c | 16 | ||||
-rw-r--r-- | gcc/tree-vect-loop.cc | 7 |
3 files changed, 52 insertions, 0 deletions
diff --git a/gcc/testsuite/gcc.dg/vect/vect-reduc-cond-sub.c b/gcc/testsuite/gcc.dg/vect/vect-reduc-cond-sub.c new file mode 100644 index 0000000..0213a0a --- /dev/null +++ b/gcc/testsuite/gcc.dg/vect/vect-reduc-cond-sub.c @@ -0,0 +1,29 @@ +/* { dg-require-effective-target vect_int } */ + +#include "tree-vect.h" + +int __attribute__((noipa)) +foo (int n, int* p, int* pi) +{ + int sum = 0; + for (int i = 0; i != n; i++) + { + if (pi[i] > 0) + sum -= p[i]; + } + return sum; +} + +int p[16] __attribute__((aligned(__BIGGEST_ALIGNMENT__))) + = { 7, 3, 1, 4, 9, 10, 14, 7, -10, -55, 20, 9, 1, 2, 0, -17 }; +int pi[16] __attribute__((aligned(__BIGGEST_ALIGNMENT__))) + = { 0, 1, 1, 1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 1, 1 }; +int +main() +{ + check_vect (); + + if (foo (16, p, pi) != 57) + abort (); + return 0; +} diff --git a/gcc/testsuite/gcc.target/i386/vect-pr113078.c b/gcc/testsuite/gcc.target/i386/vect-pr113078.c new file mode 100644 index 0000000..e766605 --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/vect-pr113078.c @@ -0,0 +1,16 @@ +/* { dg-do compile } */ +/* { dg-options "-O3 -mavx512vl" } */ + +int +foo (int n, int* p, int* pi) +{ + int sum = 0; + for (int i = 0; i != n; i++) + { + if (pi[i] > 0) + sum -= p[i]; + } + return sum; +} + +/* { dg-final { scan-assembler-times "vpsub\[^\r\n\]*%k" 2 } } */ diff --git a/gcc/tree-vect-loop.cc b/gcc/tree-vect-loop.cc index c5b2799..1bdad0f 100644 --- a/gcc/tree-vect-loop.cc +++ b/gcc/tree-vect-loop.cc @@ -4116,6 +4116,13 @@ pop: if (op.ops[1] == op.ops[opi]) neg = ! neg; } + else if (op.code == IFN_COND_SUB) + { + op.code = IFN_COND_ADD; + /* Track whether we negate the reduction value each iteration. */ + if (op.ops[2] == op.ops[opi]) + neg = ! neg; + } if (CONVERT_EXPR_CODE_P (op.code) && tree_nop_conversion_p (op.type, TREE_TYPE (op.ops[0]))) ; |