From bbdf59fdbc2ce41ccfac807b15cf3fac7b465a56 Mon Sep 17 00:00:00 2001 From: Jakub Jelinek Date: Sat, 13 Mar 2021 08:56:15 +0100 Subject: [PATCH] match.pd: Don't optimize vector X + (X << C) -> X * (1 + (1 << C)) if there is no mult support [PR99544] E.g. on aarch64, the target has V2DImode addition and shift by scalar optabs, but doesn't have V2DImode multiply. The following testcase ICEs because this simplification is done after last lowering, but generally, even if it is done before that, turning it into a multiplication will not be an improvement because that means scalarization, while the former can be done in vectors. It would be nice if we added expansion support for vector multiplication by uniform constants using shifts and additions like we have for scalar multiplication, but that is something that can be done in stage1. 2021-03-13 Jakub Jelinek PR tree-optimization/99544 * match.pd (X + (X << C) -> X * (1 + (1 << C))): Don't simplify if for vector types multiplication can't be done in type's mode. * gcc.dg/gomp/pr99544.c: New test. --- gcc/match.pd | 10 ++++++++-- gcc/testsuite/gcc.dg/gomp/pr99544.c | 13 +++++++++++++ 2 files changed, 21 insertions(+), 2 deletions(-) create mode 100644 gcc/testsuite/gcc.dg/gomp/pr99544.c diff --git a/gcc/match.pd b/gcc/match.pd index a34c283e28c9..036f92fa959e 100644 --- a/gcc/match.pd +++ b/gcc/match.pd @@ -2788,7 +2788,10 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT) (plus:c @0 (lshift:s @0 INTEGER_CST@1)) (if (ANY_INTEGRAL_TYPE_P (TREE_TYPE (@0)) && tree_fits_uhwi_p (@1) - && tree_to_uhwi (@1) < element_precision (type)) + && tree_to_uhwi (@1) < element_precision (type) + && (INTEGRAL_TYPE_P (TREE_TYPE (@0)) + || optab_handler (smul_optab, + TYPE_MODE (type)) != CODE_FOR_nothing)) (with { tree t = type; if (!TYPE_OVERFLOW_WRAPS (t)) t = unsigned_type_for (t); wide_int w = wi::set_bit_in_zero (tree_to_uhwi (@1), @@ -2804,7 +2807,10 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT) && tree_fits_uhwi_p (@1) && tree_to_uhwi (@1) < element_precision (type) && tree_fits_uhwi_p (@2) - && tree_to_uhwi (@2) < element_precision (type)) + && tree_to_uhwi (@2) < element_precision (type) + && (INTEGRAL_TYPE_P (TREE_TYPE (@0)) + || optab_handler (smul_optab, + TYPE_MODE (type)) != CODE_FOR_nothing)) (with { tree t = type; if (!TYPE_OVERFLOW_WRAPS (t)) t = unsigned_type_for (t); unsigned int prec = element_precision (type); diff --git a/gcc/testsuite/gcc.dg/gomp/pr99544.c b/gcc/testsuite/gcc.dg/gomp/pr99544.c new file mode 100644 index 000000000000..4ea07cf2b4d5 --- /dev/null +++ b/gcc/testsuite/gcc.dg/gomp/pr99544.c @@ -0,0 +1,13 @@ +/* PR tree-optimization/99544 */ +/* { dg-do compile } */ +/* { dg-options "-Os -fopenmp" } */ + +long +foo (long a, long b, long c) +{ + long d, e; + #pragma omp teams distribute parallel for simd firstprivate (a, b, c) lastprivate(e) + for (d = a; d < b; d++) + e = c + d * 5; + return e; +} -- 2.47.3