diff options
| -rw-r--r-- | gcc/testsuite/gcc.dg/vect/vect-early-break_138-pr121020.c | 54 | ||||
| -rw-r--r-- | gcc/tree-vect-loop-manip.cc | 2 | ||||
| -rw-r--r-- | gcc/tree-vectorizer.h | 4 |
3 files changed, 59 insertions, 1 deletions
diff --git a/gcc/testsuite/gcc.dg/vect/vect-early-break_138-pr121020.c b/gcc/testsuite/gcc.dg/vect/vect-early-break_138-pr121020.c new file mode 100644 index 0000000..8cb62bf --- /dev/null +++ b/gcc/testsuite/gcc.dg/vect/vect-early-break_138-pr121020.c @@ -0,0 +1,54 @@ +/* PR tree-optimization/121020 */ +/* { dg-options "-O3 --vect-cost-model=unlimited" } */ +/* { dg-additional-options "-march=znver2" { target x86_64-*-* i?86-*-* } } */ +/* { dg-require-effective-target mmap } */ +/* { dg-require-effective-target vect_early_break } */ + +#include <stdint.h> +#include <stdio.h> +#include <sys/mman.h> +#include <unistd.h> +#include "tree-vect.h" + +__attribute__((noipa)) +bool equal (uint64_t *restrict p, uint64_t *restrict q, int length) +{ + for (int i = 0; i < length; i++) { + if (*(p + i) != *(q + i)) + return false; + } + return true; +} + +int main () +{ + check_vect (); + + long pgsz = sysconf (_SC_PAGESIZE); + if (pgsz == -1) { + fprintf (stderr, "sysconf failed\n"); + return 0; + } + + /* Allocate a whole page of memory. */ + void *mem = mmap (NULL, pgsz, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + if (mem == MAP_FAILED) { + fprintf (stderr, "mmap failed\n"); + return 0; + } + uint64_t *p1 = (uint64_t *) mem; + uint64_t *p2 = (uint64_t *) mem + 32; + + /* The first 16 elements pointed to by p1 and p2 are the same. */ + for (int i = 0; i < 32; i++) { + *(p1 + i) = 0; + *(p2 + i) = (i < 16 ? 0 : -1); + } + + /* All calls to equal should return true. */ + for (int len = 0; len < 16; len++) { + if (!equal (p1 + 1, p2 + 1, len)) + __builtin_abort(); + } +} diff --git a/gcc/tree-vect-loop-manip.cc b/gcc/tree-vect-loop-manip.cc index 2d01a4b..7fcbc1a 100644 --- a/gcc/tree-vect-loop-manip.cc +++ b/gcc/tree-vect-loop-manip.cc @@ -3295,7 +3295,7 @@ vect_do_peeling (loop_vec_info loop_vinfo, tree niters, tree nitersm1, bool skip_vector = (LOOP_VINFO_NITERS_KNOWN_P (loop_vinfo) ? maybe_lt (LOOP_VINFO_INT_NITERS (loop_vinfo), bound_prolog + bound_epilog) - : (!LOOP_REQUIRES_VERSIONING_FOR_ALIGNMENT (loop_vinfo) + : (!LOOP_VINFO_USE_VERSIONING_WITHOUT_PEELING (loop_vinfo) || vect_epilogues)); /* Epilog loop must be executed if the number of iterations for epilog diff --git a/gcc/tree-vectorizer.h b/gcc/tree-vectorizer.h index 203e5ad..e1900279 100644 --- a/gcc/tree-vectorizer.h +++ b/gcc/tree-vectorizer.h @@ -1197,6 +1197,10 @@ public: || LOOP_REQUIRES_VERSIONING_FOR_NITERS (L) \ || LOOP_REQUIRES_VERSIONING_FOR_SIMD_IF_COND (L)) +#define LOOP_VINFO_USE_VERSIONING_WITHOUT_PEELING(L) \ + ((L)->may_misalign_stmts.length () > 0 \ + && !LOOP_VINFO_ALLOW_MUTUAL_ALIGNMENT (L)) + #define LOOP_VINFO_NITERS_KNOWN_P(L) \ (tree_fits_shwi_p ((L)->num_iters) && tree_to_shwi ((L)->num_iters) > 0) |