diff options
| author | Andre Vieira <andre.simoesdiasvieira@arm.com> | 2023-10-19 18:28:12 +0100 |
|---|---|---|
| committer | Andre Vieira <andre.simoesdiasvieira@arm.com> | 2023-10-19 18:30:25 +0100 |
| commit | 8b704ed0b8f35ec1a57e70bd8e6913ba0e9d1f24 (patch) | |
| tree | 2f55086b9e5933ea220d524fdb2f0c406f74d131 | |
| parent | c9ce846763c3d220c754ac0a327e275ac00a83e1 (diff) | |
| download | gcc-8b704ed0b8f35ec1a57e70bd8e6913ba0e9d1f24.zip gcc-8b704ed0b8f35ec1a57e70bd8e6913ba0e9d1f24.tar.gz gcc-8b704ed0b8f35ec1a57e70bd8e6913ba0e9d1f24.tar.bz2 | |
vect: don't allow fully masked loops with non-masked simd clones [PR 110485]
When analyzing a loop and choosing a simdclone to use it is possible to choose
a simdclone that cannot be used 'inbranch' for a loop that can use partial
vectors. This may lead to the vectorizer deciding to use partial vectors which
are not supported for notinbranch simd clones. This patch fixes that by
disabling the use of partial vectors once a notinbranch simd clone has been
selected.
gcc/ChangeLog:
PR tree-optimization/110485
* tree-vect-stmts.cc (vectorizable_simd_clone_call): Disable partial
vectors usage if a notinbranch simdclone has been selected.
gcc/testsuite/ChangeLog:
* gcc.dg/gomp/pr110485.c: New test.
| -rw-r--r-- | gcc/testsuite/gcc.dg/gomp/pr110485.c | 19 | ||||
| -rw-r--r-- | gcc/tree-vect-stmts.cc | 11 |
2 files changed, 30 insertions, 0 deletions
diff --git a/gcc/testsuite/gcc.dg/gomp/pr110485.c b/gcc/testsuite/gcc.dg/gomp/pr110485.c new file mode 100644 index 0000000..ba6817a --- /dev/null +++ b/gcc/testsuite/gcc.dg/gomp/pr110485.c @@ -0,0 +1,19 @@ +/* PR 110485 */ +/* { dg-do compile } */ +/* { dg-additional-options "-Ofast -fdump-tree-vect-details" } */ +/* { dg-additional-options "-march=znver4 --param=vect-partial-vector-usage=1" { target x86_64-*-* } } */ +#pragma omp declare simd notinbranch uniform(p) +extern double __attribute__ ((const)) bar (double a, double p); + +double a[1024]; +double b[1024]; + +void foo (int n) +{ + #pragma omp simd + for (int i = 0; i < n; ++i) + a[i] = bar (b[i], 71.2); +} + +/* { dg-final { scan-tree-dump-not "MASK_LOAD" "vect" } } */ +/* { dg-final { scan-tree-dump "can't use a fully-masked loop because a non-masked simd clone was selected." "vect" { target x86_64-*-* } } } */ diff --git a/gcc/tree-vect-stmts.cc b/gcc/tree-vect-stmts.cc index 8abb5f1..e96ff2c 100644 --- a/gcc/tree-vect-stmts.cc +++ b/gcc/tree-vect-stmts.cc @@ -4377,6 +4377,17 @@ vectorizable_simd_clone_call (vec_info *vinfo, stmt_vec_info stmt_info, ? boolean_true_node : boolean_false_node; simd_clone_info.safe_push (sll); } + + if (!bestn->simdclone->inbranch && loop_vinfo) + { + if (dump_enabled_p () + && LOOP_VINFO_CAN_USE_PARTIAL_VECTORS_P (loop_vinfo)) + dump_printf_loc (MSG_NOTE, vect_location, + "can't use a fully-masked loop because a" + " non-masked simd clone was selected.\n"); + LOOP_VINFO_CAN_USE_PARTIAL_VECTORS_P (loop_vinfo) = false; + } + STMT_VINFO_TYPE (stmt_info) = call_simd_clone_vec_info_type; DUMP_VECT_SCOPE ("vectorizable_simd_clone_call"); /* vect_model_simple_cost (vinfo, stmt_info, ncopies, |