[ was: Re: [PR65637][PATCH][2/3] Fix inner loop phi in
expand_omp_for_static_chunk ]
On 15/04/15 15:17, Tom de Vries wrote:
On 15-04-15 15:10, Tom de Vries wrote:
Hi,
This patch series fixes PR65637.
<SNIP>
This patch fixes an libgomp.c/autopar-1.c execution failure.
For autopar-1.c, the original loop has a loop phi:
...
# s.5_20 = PHI <s.5_12(4), 0.0(20)>
...
After expand_omp_for_static_chunk, there's an inner and an outer loop.
The outer
loop phi is:
...
# s.5_11 = PHI <0.0(15), s.5_12(21)>
...
and the inner loop phi is:
...
# s.5_20 = PHI <s.5_12(4), 0.0(20)>
...
The inner loop phi should not have 0.0 as argument, but the result of
the outer
loop phi, like this:
...
# s.5_20 = PHI <s.5_12(4), s.5_11(20)>
...
This patch fixes the inner loop phi, and allows the autopar-1.c
execution test
to pass.
This updated patch includes a test-case. It also handles simple latches.
OK for trunk?
Thanks,
- Tom
Fix inner loop phi in expand_omp_for_static_chunk
2015-08-31 Tom de Vries <t...@codesourcery.com>
PR tree-optimization/65637
* omp-low.c (find_phi_with_arg_on_edge): New function.
(expand_omp_for_static_chunk): Fix inner loop phi.
* testsuite/libgomp.c/autopar-1-chunk-size.c: New test.
---
gcc/ChangeLog | 6 +++
gcc/omp-low.c | 30 ++++++++++++++-
libgomp/testsuite/libgomp.c/autopar-1-chunk-size.c | 44 ++++++++++++++++++++++
3 files changed, 79 insertions(+), 1 deletion(-)
create mode 100644 libgomp/testsuite/libgomp.c/autopar-1-chunk-size.c
diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 5a273ba..a14564c 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,6 +1,12 @@
2015-05-18 Tom de Vries <t...@codesourcery.com>
PR tree-optimization/65637
+ * omp-low.c (find_phi_with_arg_on_edge): New function.
+ (expand_omp_for_static_chunk): Fix inner loop phi.
+
+2015-05-18 Tom de Vries <t...@codesourcery.com>
+
+ PR tree-optimization/65637
* omp-low.c (expand_omp_for_static_chunk): Fix gcc_assert for the case
that head is NULL.
diff --git a/gcc/omp-low.c b/gcc/omp-low.c
index 4e732ae..e2be7c7 100644
--- a/gcc/omp-low.c
+++ b/gcc/omp-low.c
@@ -6885,6 +6885,22 @@ expand_omp_for_static_nochunk (struct omp_region *region,
}
}
+static gphi *
+find_phi_with_arg_on_edge (tree arg, edge e)
+{
+ basic_block bb = e->dest;
+
+ for (gphi_iterator gpi = gsi_start_phis (bb);
+ !gsi_end_p (gpi);
+ gsi_next (&gpi))
+ {
+ gphi *phi = gpi.phi ();
+ if (PHI_ARG_DEF_FROM_EDGE (phi, e) == arg)
+ return phi;
+ }
+
+ return NULL;
+}
/* A subroutine of expand_omp_for. Generate code for a parallel
loop with static schedule and a specified chunk size. Given
@@ -7324,7 +7340,19 @@ expand_omp_for_static_chunk (struct omp_region *region,
t = vextra;
add_phi_arg (nphi, t, ene, locus);
locus = redirect_edge_var_map_location (vm);
- add_phi_arg (nphi, redirect_edge_var_map_def (vm), re, locus);
+ tree back_arg = redirect_edge_var_map_def (vm);
+ add_phi_arg (nphi, back_arg, re, locus);
+ edge ce = find_edge (cont_bb, body_bb);
+ if (ce == NULL)
+ {
+ ce = BRANCH_EDGE (cont_bb);
+ gcc_assert (single_succ (ce->dest) == body_bb);
+ ce = single_succ_edge (ce->dest);
+ }
+ gphi *inner_loop_phi = find_phi_with_arg_on_edge (back_arg, ce);
+ gcc_assert (inner_loop_phi != NULL);
+ add_phi_arg (inner_loop_phi, gimple_phi_result (nphi),
+ find_edge (seq_start_bb, body_bb), locus);
}
gcc_assert (gsi_end_p (psi) && (head == NULL || i == head->length ()));
redirect_edge_var_map_clear (re);
diff --git a/libgomp/testsuite/libgomp.c/autopar-1-chunk-size.c b/libgomp/testsuite/libgomp.c/autopar-1-chunk-size.c
new file mode 100644
index 0000000..5a36474
--- /dev/null
+++ b/libgomp/testsuite/libgomp.c/autopar-1-chunk-size.c
@@ -0,0 +1,44 @@
+/* { dg-do run } */
+/* { dg-additional-options "-ftree-parallelize-loops=4 -ffast-math --param parloops-chunk-size=100" } */
+
+extern void abort (void);
+
+double d[1024], e[1024];
+int f[1024], g[1024];
+
+double __attribute__((noinline))
+foo (void)
+{
+ double s = 0.0;
+ int i;
+ for (i = 0; i < 1024; i++)
+ s += d[i] - e[i];
+ return s;
+}
+
+int __attribute__((noinline))
+bar (void)
+{
+ int s = 0, i;
+ for (i = 0; i < 1024; i++)
+ s += f[i] - g[i];
+ return s;
+}
+
+int
+main (void)
+{
+ int i;
+ for (i = 0; i < 1024; i++)
+ {
+ d[i] = i * 2;
+ e[i] = i;
+ f[i] = i * 2;
+ g[i] = i;
+ }
+ if (foo () != 1023 * 1024 / 2)
+ abort ();
+ if (bar () != 1023 * 1024 / 2)
+ abort ();
+ return 0;
+}
--
1.9.1
