[committed,openmp] Fix SIMT reduction using TRUTH_{AND,OR}IF_EXPR
Commit Message
Hi,
Consider test-case pr104952-1.c, included in this commit, containing:
...
#pragma omp target map(tofrom:result) map(to:arr)
#pragma omp simd reduction(||: result)
...
When run on x86_64 with nvptx accelerator, the test-case either aborts or
hangs.
The reduction clause is translated by the SIMT code (active for nvptx) as a
butterfly reduction loop with this butterfly shuffle / update pair:
...
D.2163 = D.2163 || .GOMP_SIMT_XCHG_BFLY (D.2163, D.2164)
...
in the loop body.
The problem is that the butterfly shuffle is possibly not executed, while it
needs to be executed unconditionally.
Fix this by translating instead as:
...
D.tmp_bfly = .GOMP_SIMT_XCHG_BFLY (D.2163, D.2164)
D.2163 = D.2163 || D.tmp_bfly
...
Tested on x86_64-linux with nvptx accelerator.
Committed to trunk.
Thanks,
- Tom
[openmp] Fix SIMT reduction using TRUTH_{AND,OR}IF_EXPR
gcc/ChangeLog:
2022-03-17 Tom de Vries <tdevries@suse.de>
PR target/104952
* omp-low.cc (lower_rec_input_clauses): Make sure GOMP_SIMT_XCHG_BFLY
is executed unconditionally.
libgomp/ChangeLog:
2022-03-17 Tom de Vries <tdevries@suse.de>
PR target/104952
* testsuite/libgomp.c/pr104952-1.c: New test.
* testsuite/libgomp.c/pr104952-2.c: New test.
---
gcc/omp-low.cc | 5 ++++-
libgomp/testsuite/libgomp.c/pr104952-1.c | 24 ++++++++++++++++++++++++
libgomp/testsuite/libgomp.c/pr104952-2.c | 22 ++++++++++++++++++++++
3 files changed, 50 insertions(+), 1 deletion(-)
@@ -6743,7 +6743,10 @@ lower_rec_input_clauses (tree clauses, gimple_seq *ilist, gimple_seq *dlist,
x = build_call_expr_internal_loc
(UNKNOWN_LOCATION, IFN_GOMP_SIMT_XCHG_BFLY,
TREE_TYPE (ivar), 2, ivar, simt_lane);
- x = build2 (code, TREE_TYPE (ivar), ivar, x);
+ /* Make sure x is evaluated unconditionally. */
+ tree bfly_var = create_tmp_var (TREE_TYPE (ivar));
+ gimplify_assign (bfly_var, x, &llist[2]);
+ x = build2 (code, TREE_TYPE (ivar), ivar, bfly_var);
gimplify_assign (ivar, x, &llist[2]);
}
tree ivar2 = ivar;
new file mode 100644
@@ -0,0 +1,24 @@
+#define N 32
+
+static char arr[N];
+
+int
+main (void)
+{
+ unsigned int result = 0;
+
+ for (unsigned int i = 0; i < N; ++i)
+ arr[i] = 0;
+
+ arr[5] = 42;
+
+#pragma omp target map(tofrom:result) map(to:arr)
+#pragma omp simd reduction(||: result)
+ for (unsigned int i = 0; i < N; ++i)
+ result = result || arr[i];
+
+ if (result != 1)
+ __builtin_abort ();
+
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,22 @@
+#define N 32
+
+static char arr[N];
+
+int
+main (void)
+{
+ unsigned int result = 2;
+
+ for (unsigned int i = 0; i < N; ++i)
+ arr[i] = i + 1;
+
+#pragma omp target map(tofrom:result) map(to:arr)
+#pragma omp simd reduction(&&: result)
+ for (unsigned int i = 0; i < N; ++i)
+ result = result && arr[i];
+
+ if (result != 1)
+ __builtin_abort ();
+
+ return 0;
+}