+2019-05-23 Richard Biener <rguenther@suse.de>
+
+ PR tree-optimization/88440
+ * opts.c (default_options_table): Enable -ftree-loop-distribute-patterns
+ at -O[2s]+.
+ * tree-loop-distribution.c (generate_memset_builtin): Fold the
+ generated call.
+ (generate_memcpy_builtin): Likewise.
+ (distribute_loop): Pass in whether to only distribute patterns.
+ (prepare_perfect_loop_nest): Also allow size optimization.
+ (pass_loop_distribution::execute): When optimizing a loop
+ nest for size allow pattern replacement.
+
2019-05-23 Jakub Jelinek <jakub@redhat.com>
PR target/90568
{ OPT_LEVELS_3_PLUS, OPT_fpredictive_commoning, NULL, 1 },
{ OPT_LEVELS_3_PLUS, OPT_fsplit_loops, NULL, 1 },
{ OPT_LEVELS_3_PLUS, OPT_fsplit_paths, NULL, 1 },
- { OPT_LEVELS_3_PLUS, OPT_ftree_loop_distribute_patterns, NULL, 1 },
+ { OPT_LEVELS_2_PLUS, OPT_ftree_loop_distribute_patterns, NULL, 1 },
{ OPT_LEVELS_3_PLUS, OPT_ftree_loop_distribution, NULL, 1 },
{ OPT_LEVELS_3_PLUS, OPT_ftree_loop_vectorize, NULL, 1 },
{ OPT_LEVELS_3_PLUS, OPT_ftree_partial_pre, NULL, 1 },
+2019-05-23 Richard Biener <rguenther@suse.de>
+
+ PR tree-optimization/88440
+ * gcc.dg/tree-ssa/ldist-37.c: New testcase.
+ * gcc.dg/tree-ssa/ldist-38.c: Likewise.
+ * gcc.dg/vect/vect.exp: Add -fno-tree-loop-distribute-patterns.
+ * gcc.dg/tree-ssa/ldist-37.c: Adjust.
+ * gcc.dg/tree-ssa/ldist-38.c: Likewise.
+ * g++.dg/tree-ssa/pr78847.C: Likewise.
+ * gcc.dg/autopar/pr39500-1.c: Likewise.
+ * gcc.dg/autopar/reduc-1char.c: Likewise.
+ * gcc.dg/autopar/reduc-7.c: Likewise.
+ * gcc.dg/tree-ssa/ivopts-lt-2.c: Likewise.
+ * gcc.dg/tree-ssa/ivopts-lt.c: Likewise.
+ * gcc.dg/tree-ssa/predcom-dse-1.c: Likewise.
+ * gcc.dg/tree-ssa/predcom-dse-2.c: Likewise.
+ * gcc.dg/tree-ssa/predcom-dse-3.c: Likewise.
+ * gcc.dg/tree-ssa/predcom-dse-4.c: Likewise.
+ * gcc.dg/tree-ssa/prefetch-7.c: Likewise.
+ * gcc.dg/tree-ssa/prefetch-8.c: Likewise.
+ * gcc.dg/tree-ssa/prefetch-9.c: Likewise.
+ * gcc.dg/tree-ssa/scev-11.c: Likewise.
+ * gcc.dg/vect/costmodel/i386/costmodel-vect-31.c: Likewise.
+ * gcc.dg/vect/costmodel/i386/costmodel-vect-33.c: Likewise.
+ * gcc.dg/vect/costmodel/x86_64/costmodel-vect-31.c: Likewise.
+ * gcc.dg/vect/costmodel/x86_64/costmodel-vect-33.c: Likewise.
+ * gcc.target/i386/pr30970.c: Likewise.
+ * gcc.target/i386/vect-double-1.c: Likewise.
+ * gcc.target/i386/vect-double-2.c: Likewise.
+ * gcc.dg/tree-ssa/gen-vect-2.c: Likewise.
+ * gcc.dg/tree-ssa/gen-vect-26.c: Likewise.
+ * gcc.dg/tree-ssa/gen-vect-28.c: Likewise.
+ * gcc.dg/tree-ssa/gen-vect-32.c: Likewise.
+ * gfortran.dg/vect/vect-5.f90: Likewise.
+ * gfortran.dg/vect/vect-8.f90: Likewise.
+
2019-05-23 Martin Liska <mliska@suse.cz>
PR sanitizer/90570
/* { dg-do compile } */
/* { dg-require-effective-target c++14 } */
-/* { dg-options "-O3 -fdump-tree-ldist" } */
+/* { dg-options "-O3 -fdump-tree-ldist-optimized" } */
#include <stddef.h>
#include <cstring>
buf_[ptr++] = c;
}
-/* { dg-final { scan-tree-dump "memcpy\[^\n\r\]*, 9\\);" "ldist" } } */
+/* { dg-final { scan-tree-dump "split to 0 loops and 1 library calls" "ldist" } } */
/* pr39500: autopar fails to parallel */
/* origin: nemokingdom@gmail.com(LiFeng) */
/* { dg-do compile } */
-/* { dg-options "-O2 -ftree-parallelize-loops=4 -fdump-tree-parloops2-details" } */
+/* { dg-options "-O2 -fno-tree-loop-distribute-patterns -ftree-parallelize-loops=4 -fdump-tree-parloops2-details" } */
void abort (void);
/* { dg-final { scan-tree-dump-times "Detected reduction" 3 "parloops2" } } */
-/* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 4 "parloops2" } } */
+/* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 3 "parloops2" } } */
/* { dg-final { scan-tree-dump-times "Detected reduction" 2 "parloops2" } } */
-/* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 3 "parloops2" } } */
+/* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 2 "parloops2" } } */
/* { dg-do run { target vect_cmdline_needed } } */
-/* { dg-options "-O2 -ftree-vectorize -fdump-tree-vect-details -fvect-cost-model=dynamic" } */
-/* { dg-options "-O2 -ftree-vectorize -fdump-tree-vect-details -fvect-cost-model=dynamic -mno-sse" { target { i?86-*-* x86_64-*-* } } } */
+/* { dg-options "-O2 -fno-tree-loop-distribute-patterns -ftree-vectorize -fdump-tree-vect-details -fvect-cost-model=dynamic" } */
+/* { dg-additional-options "-mno-sse" { target { i?86-*-* x86_64-*-* } } } */
#include <stdlib.h>
/* { dg-do run { target vect_cmdline_needed } } */
-/* { dg-options "-O2 -ftree-vectorize -fdump-tree-vect-details -fvect-cost-model=dynamic" } */
-/* { dg-options "-O2 -ftree-vectorize -fdump-tree-vect-details -fvect-cost-model=dynamic -mno-sse" { target { i?86-*-* x86_64-*-* } } } */
+/* { dg-options "-O2 -fno-tree-loop-distribute-patterns -ftree-vectorize -fdump-tree-vect-details -fvect-cost-model=dynamic" } */
+/* { dg-additional-options "-mno-sse" { target { i?86-*-* x86_64-*-* } } } */
#include <stdlib.h>
/* { dg-do run { target vect_cmdline_needed } } */
-/* { dg-options "-O2 -ftree-vectorize -fdump-tree-vect-details -fvect-cost-model=dynamic" } */
-/* { dg-options "-O2 -ftree-vectorize -fdump-tree-vect-details -fvect-cost-model=dynamic -mno-sse" { target { i?86-*-* x86_64-*-* } } } */
+/* { dg-options "-O2 -fno-tree-loop-distribute-patterns -ftree-vectorize -fdump-tree-vect-details -fvect-cost-model=dynamic" } */
+/* { dg-additional-options "-mno-sse" { target { i?86-*-* x86_64-*-* } } } */
#include <stdlib.h>
/* { dg-do run { target vect_cmdline_needed } } */
-/* { dg-options "-O2 -ftree-vectorize -fdump-tree-vect-details -fno-vect-cost-model" } */
+/* { dg-options "-O2 -fno-tree-loop-distribute-patterns -ftree-vectorize -fdump-tree-vect-details -fno-vect-cost-model" } */
/* { dg-additional-options "-mno-sse" { target { i?86-*-* x86_64-*-* } } } */
#include <stdlib.h>
/* { dg-do compile } */
-/* { dg-options "-O2 -fdump-tree-ivopts" } */
+/* { dg-options "-O2 -fno-tree-loop-distribute-patterns -fdump-tree-ivopts" } */
/* { dg-skip-if "PR68644" { hppa*-*-* powerpc*-*-* } } */
void
/* { dg-do compile } */
-/* { dg-options "-O2 -fdump-tree-ivopts" } */
+/* { dg-options "-O2 -fno-tree-loop-distribute-patterns -fdump-tree-ivopts" } */
/* { dg-require-effective-target stdint_types } */
#include "stdint.h"
/* { dg-do run } */
-/* { dg-options "-O2 -fno-inline -fpredictive-commoning -fdump-tree-pcom-details" } */
+/* { dg-options "-O2 -fno-inline -fno-tree-loop-distribute-patterns -fpredictive-commoning -fdump-tree-pcom-details" } */
int arr[105] = {2, 3, 5, 7, 11};
int result0[10] = {2, 3, 5, 7, 11};
/* { dg-do run } */
-/* { dg-options "-O2 -fno-inline -fpredictive-commoning -fdump-tree-pcom-details" } */
+/* { dg-options "-O2 -fno-inline -fno-tree-loop-distribute-patterns -fpredictive-commoning -fdump-tree-pcom-details" } */
int arr[105] = {2, 3, 5, 7, 11};
int result0[10] = {2, 3, 5, 7, 11};
/* { dg-do run } */
-/* { dg-options "-O2 -fno-inline -fpredictive-commoning -fdump-tree-pcom-details" } */
+/* { dg-options "-O2 -fno-inline -fno-tree-loop-distribute-patterns -fpredictive-commoning -fdump-tree-pcom-details" } */
int arr1[105] = {2, 3, 5, 7, 11, 13, 0};
int arr2[105] = {2, 3, 5, 7, 11, 13, 0};
/* { dg-do run } */
-/* { dg-options "-O2 -fno-inline -fpredictive-commoning -fdump-tree-pcom-details" } */
+/* { dg-options "-O2 -fno-inline -fno-tree-loop-distribute-patterns -fpredictive-commoning -fdump-tree-pcom-details" } */
int arr[105] = {2, 3, 5, 7, 11};
int result0[10] = {2, 3, 5, 7, 11};
/* { dg-do compile { target { i?86-*-* x86_64-*-* } } } */
-/* { dg-options "-O2 -fprefetch-loop-arrays -march=amdfam10 --param simultaneous-prefetches=100 -fdump-tree-aprefetch-details -fdump-tree-optimized" } */
+/* { dg-options "-O2 -fno-tree-loop-distribute-patterns -fprefetch-loop-arrays -march=amdfam10 --param simultaneous-prefetches=100 -fdump-tree-aprefetch-details -fdump-tree-optimized" } */
#define K 1000000
int a[K];
/* { dg-do compile { target { i?86-*-* x86_64-*-* } } } */
-/* { dg-options "-O2 -fprefetch-loop-arrays -march=amdfam10 --param simultaneous-prefetches=100 -fdump-tree-aprefetch-details -fdump-tree-optimized" } */
+/* { dg-options "-O2 -fno-tree-loop-distribute-patterns -fprefetch-loop-arrays -march=amdfam10 --param simultaneous-prefetches=100 -fdump-tree-aprefetch-details -fdump-tree-optimized" } */
#define K 1000000
int a[K];
/* { dg-do compile { target { i?86-*-* x86_64-*-* } } } */
-/* { dg-options "-O2 -fprefetch-loop-arrays -march=amdfam10 --param simultaneous-prefetches=100 -fdump-tree-aprefetch-details -fdump-tree-optimized" } */
+/* { dg-options "-O2 -fno-tree-loop-distribute-patterns -fprefetch-loop-arrays -march=amdfam10 --param simultaneous-prefetches=100 -fdump-tree-aprefetch-details -fdump-tree-optimized" } */
#define K 1000000
int a[K], b[K];
{
unsigned char uc = (unsigned char)i;
a[i] = i;
- b[uc] = 0;
+ b[uc] = 1;
}
bar (a);
/* { dg-require-effective-target vect_int } */
+/* { dg-additional-options "-fno-tree-loop-distribute-patterns" } */
#include <stdarg.h>
#include "../../tree-vect.h"
/* { dg-do compile } */
/* { dg-require-effective-target vect_int } */
+/* { dg-additional-options "-fno-tree-loop-distribute-patterns" } */
#include <stdarg.h>
#include "../../tree-vect.h"
/* { dg-require-effective-target vect_int } */
+/* { dg-additional-options "-fno-tree-loop-distribute-patterns" } */
#include <stdarg.h>
#include "../../tree-vect.h"
/* { dg-do compile } */
/* { dg-require-effective-target vect_int } */
+/* { dg-additional-options "-fno-tree-loop-distribute-patterns" } */
#include <stdarg.h>
#include "../../tree-vect.h"
}
# These flags are used for all targets.
-lappend DEFAULT_VECTCFLAGS "-ftree-vectorize" "-fno-vect-cost-model" "-fno-common"
+lappend DEFAULT_VECTCFLAGS "-ftree-vectorize" "-fno-tree-loop-distribute-patterns" "-fno-vect-cost-model" "-fno-common"
# Initialize `dg'.
dg-init
/* { dg-do compile }
-/* { dg-options "-msse2 -O2 -ftree-vectorize -mtune=generic" } */
+/* { dg-options "-msse2 -O2 -fno-tree-loop-distribute-patterns -ftree-vectorize -mtune=generic" } */
#define N 256
int b[N];
/* { dg-do compile } */
/* { dg-skip-if "" { *-*-* } { "-march=*" } { "-march=core2" } } */
-/* { dg-options "-O2 -ftree-vectorize -mfpmath=sse -march=core2 -fdump-tree-vect-stats" } */
+/* { dg-options "-O2 -ftree-vectorize -fno-tree-loop-distribute-patterns -mfpmath=sse -march=core2 -fdump-tree-vect-stats" } */
/* { dg-add-options bind_pic_locally } */
extern void abort (void);
/* { dg-do compile } */
-/* { dg-options "-O2 -ftree-vectorize -mfpmath=sse -msse2 -mtune=atom -fdump-tree-vect-stats" } */
+/* { dg-options "-O2 -ftree-vectorize -fno-tree-loop-distribute-patterns -mfpmath=sse -msse2 -mtune=atom -fdump-tree-vect-stats" } */
extern void abort (void);
! { dg-require-effective-target vect_int }
-! { dg-additional-options "--param vect-max-peeling-for-alignment=0" }
+! { dg-additional-options "-fno-tree-loop-distribute-patterns --param vect-max-peeling-for-alignment=0" }
Subroutine foo (N, M)
Integer N
! { dg-do compile }
! { dg-require-effective-target vect_double }
-! { dg-additional-options "-finline-matmul-limit=0" }
+! { dg-additional-options "-fno-tree-loop-distribute-patterns -finline-matmul-limit=0" }
module lfk_prec
integer, parameter :: dp=kind(1.d0)
#include "params.h"
#include "tree-vectorizer.h"
#include "tree-eh.h"
+#include "gimple-fold.h"
#define MAX_DATAREFS_NUM \
fn = build_fold_addr_expr (builtin_decl_implicit (BUILT_IN_MEMSET));
fn_call = gimple_build_call (fn, 3, mem, val, nb_bytes);
gsi_insert_after (&gsi, fn_call, GSI_CONTINUE_LINKING);
+ fold_stmt (&gsi);
if (dump_file && (dump_flags & TDF_DETAILS))
{
fn = build_fold_addr_expr (builtin_decl_implicit (kind));
fn_call = gimple_build_call (fn, 3, dest, src, nb_bytes);
gsi_insert_after (&gsi, fn_call, GSI_CONTINUE_LINKING);
+ fold_stmt (&gsi);
if (dump_file && (dump_flags & TDF_DETAILS))
{
static int
distribute_loop (struct loop *loop, vec<gimple *> stmts,
- control_dependences *cd, int *nb_calls, bool *destroy_p)
+ control_dependences *cd, int *nb_calls, bool *destroy_p,
+ bool only_patterns_p)
{
ddrs_table = new hash_table<ddr_hasher> (389);
struct graph *rdg;
/* If we are only distributing patterns but did not detect any,
simply bail out. */
- if (!flag_tree_loop_distribution
+ if (only_patterns_p
&& !any_builtin)
{
nbp = 0;
a loop into pieces, separated by builtin calls. That is, we
only want no or a single loop body remaining. */
struct partition *into;
- if (!flag_tree_loop_distribution)
+ if (only_patterns_p)
{
for (i = 0; partitions.iterate (i, &into); ++i)
if (!partition_builtin_p (into))
&& loop_outer (outer)
&& outer->inner == loop && loop->next == NULL
&& single_exit (outer)
- && optimize_loop_for_speed_p (outer)
&& !chrec_contains_symbols_defined_in_loop (niters, outer->num)
&& (niters = number_of_latch_executions (outer)) != NULL_TREE
&& niters != chrec_dont_know)
walking to innermost loops. */
FOR_EACH_LOOP (loop, LI_ONLY_INNERMOST)
{
- /* Don't distribute multiple exit edges loop, or cold loop. */
+ /* Don't distribute multiple exit edges loop, or cold loop when
+ not doing pattern detection. */
if (!single_exit (loop)
- || !optimize_loop_for_speed_p (loop))
+ || (!flag_tree_loop_distribute_patterns
+ && !optimize_loop_for_speed_p (loop)))
continue;
/* Don't distribute loop if niters is unknown. */
bool destroy_p;
int nb_generated_loops, nb_generated_calls;
- nb_generated_loops = distribute_loop (loop, work_list, cd,
- &nb_generated_calls,
- &destroy_p);
+ nb_generated_loops
+ = distribute_loop (loop, work_list, cd, &nb_generated_calls,
+ &destroy_p, (!optimize_loop_for_speed_p (loop)
+ || !flag_tree_loop_distribution));
if (destroy_p)
loops_to_be_destroyed.safe_push (loop);