procyberian/gcc
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

omp-expand.cc: Fix wrong code with non-rectangular loop nest [PR111017]

Browse source 
Before commit r12-5295-g47de0b56ee455e, all gimple_build_cond in
expand_omp_for_* were inserted with
  gsi_insert_before (gsi_p, cond_stmt, GSI_SAME_STMT);
except the one dealing with the multiplicative factor that was
  gsi_insert_after (gsi, cond_stmt, GSI_CONTINUE_LINKING);

That commit for PR103208 fixed the issue of some missing regimplify of
operands of GIMPLE_CONDs by moving the condition handling to the new function
expand_omp_build_cond. While that function has an 'bool after = false'
argument to switch between the two variants.

However, all callers ommited this argument. This commit reinstates the
prior behavior by passing 'true' for the factor != 0 condition, fixing
the included testcase.

	PR middle-end/111017
gcc/
	* omp-expand.cc (expand_omp_for_init_vars): Pass after=true
	to expand_omp_build_cond for 'factor != 0' condition, resulting
	in pre-r12-5295-g47de0b56ee455e code for the gimple insert.

libgomp/
	* testsuite/libgomp.c-c++-common/non-rect-loop-1.c: New test.
This commit is contained in:
Tobias Burnus 2023-08-19 07:49:06 +02:00
parent 3e31573638
commit 1dc65003b6
2 changed files with 74 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
gcc/omp-expand.cc
View file

@ -2562,7 +2562,8 @@ expand_omp_for_init_vars (struct omp_for_data *fd, gimple_stmt_iterator *gsi,
tree factor = fd->factor;
gcond *cond_stmt
= expand_omp_build_cond (gsi, NE_EXPR, factor,
build_zero_cst (TREE_TYPE (factor)));
build_zero_cst (TREE_TYPE (factor)),
true);
edge e = split_block (gsi_bb (*gsi), cond_stmt);
basic_block bb0 = e->src;
e->flags = EDGE_TRUE_VALUE;

72
libgomp/testsuite/libgomp.c-c++-common/non-rect-loop-1.c Normal file
View file

@ -0,0 +1,72 @@
/* PR middle-end/111017 */
#include <omp.h>
#define DIM 32
#define N (DIM*DIM)
int
main ()
{
int a[N], b[N], c[N];
int dim = DIM;
for (int i = 0; i < N; i++)
{
a[i] = 3*i;
b[i] = 7*i;
c[i] = 42;
}
#pragma omp parallel for collapse(2)
for (int i = 0; i < DIM; i++)
for (int j = (i*DIM); j < (i*DIM + DIM); j++)
c[j] = a[j] + b[j];
for (int i = 0; i < DIM; i++)
for (int j = (i*DIM); j < (i*DIM + DIM); j++)
if (c[j] != a[j] + b[j] || c[j] != 3*j +7*j)
__builtin_abort ();
for (int i = 0; i < N; i++)
c[i] = 42;
#pragma omp parallel for collapse(2)
for (int i = 0; i < dim; i++)
for (int j = (i*dim); j < (i*dim + dim); j++)
c[j] = a[j] + b[j];
for (int i = 0; i < DIM; i++)
for (int j = (i*DIM); j < (i*DIM + DIM); j++)
if (c[j] != a[j] + b[j] || c[j] != 3*j +7*j)
__builtin_abort ();
for (int i = 0; i < N; i++)
c[i] = 42;
for (int dev = 0; dev <= omp_get_num_devices(); dev++)
{
#pragma omp target teams loop device(dev) map(to:a,b) map(from:c)
for (int i = 0; i < DIM; i++)
for (int j = (i*DIM); j < (i*DIM + DIM); j++)
c[j] = a[j] + b[j];
for (int i = 0; i < DIM; i++)
for (int j = (i*DIM); j < (i*DIM + DIM); j++)
if (c[j] != a[j] + b[j] || c[j] != 3*j +7*j)
__builtin_abort ();
for (int i = 0; i < N; i++)
c[i] = 42;
#pragma omp target teams loop device(dev) map(to:a,b) map(from:c)
for (int i = 0; i < dim; i++)
for (int j = (i*dim); j < (i*dim + dim); j++)
c[j] = a[j] + b[j];
for (int i = 0; i < DIM; i++)
for (int j = (i*DIM); j < (i*DIM + DIM); j++)
if (c[j] != a[j] + b[j] || c[j] != 3*j +7*j)
__builtin_abort ();
for (int i = 0; i < N; i++)
c[i] = 42;
}
return 0;
}