On Tue, Aug 16, 2022 at 05:28:40PM +0200, Tobias Burnus wrote:
> The testcase is just a copy of linear-1 with 'omp ... for' replaced by 'omp ... for simd',
> matching what the PR report referred to.
>
> The problem occurs for 'omp ... for simd linear( i : step)' when 'step' is a variable
> when a omp_fn... is generated - as in this case, the original variable is used (in the
> reduced example of the PR, the PARM_DECL of 'f') instead of the replacement.
>
> OK for mainline? Thoughts on backporting (and for which versions)?
>
> Tobias
> -----------------
> Siemens Electronic Design Automation GmbH; Anschrift: Arnulfstraße 201, 80634 München; Gesellschaft mit beschränkter Haftung; Geschäftsführer: Thomas Heurung, Frank Thürauf; Sitz der Gesellschaft: München; Registergericht München, HRB 106955
> OpenMP: Fix var replacement with 'simd' and linear-step vars [PR106548]
>
> gcc/ChangeLog:
>
> PR middle-end/106548
> * omp-low.cc (lower_rec_input_clauses): Use build_outer_var_ref
> for 'simd' linear-step values that are variable.
>
> libgomp/ChangeLog:
>
> PR middle-end/106548
> * testsuite/libgomp.c/linear-2.c: New test.
>
> diff --git a/gcc/omp-low.cc b/gcc/omp-low.cc
> index 3c4b8593c8b..d6d6ff372a1 100644
> --- a/gcc/omp-low.cc
> +++ b/gcc/omp-low.cc
> @@ -6188,6 +6188,10 @@ lower_rec_input_clauses (tree clauses, gimple_seq *ilist, gimple_seq *dlist,
> && gimple_omp_for_combined_into_p (ctx->stmt))
> {
> tree t = OMP_CLAUSE_LINEAR_STEP (c);
> + if (VAR_P (t)
> + || TREE_CODE (t) == PARM_DECL
> + || TREE_CODE (t) == RESULT_DECL)
> + t = build_outer_var_ref (t, ctx);
I think this should be just
if (DECL_P (t))
t = build_outer_var_ref (t, ctx);
Ok with that change.
With backports I'd wait a week or two (12.2 is frozen anyway), can be
applied to any open release branches you are willing to backport it to.
> --- /dev/null
> +++ b/libgomp/testsuite/libgomp.c/linear-2.c
> @@ -0,0 +1,251 @@
> +/* PR middle-end/106548. */
Usually simd related runtime tests in libgomp use something like
/* { dg-do run } */
/* { dg-additional-options "-msse2" { target sse2_runtime } } */
/* { dg-additional-options "-mavx" { target avx_runtime } } */
to test some actual vectorization if possible.
Jakub
OpenMP: Fix var replacement with 'simd' and linear-step vars [PR106548]
gcc/ChangeLog:
PR middle-end/106548
* omp-low.cc (lower_rec_input_clauses): Use build_outer_var_ref
for 'simd' linear-step values that are variable.
libgomp/ChangeLog:
PR middle-end/106548
* testsuite/libgomp.c/linear-2.c: New test.
@@ -6188,6 +6188,10 @@ lower_rec_input_clauses (tree clauses, gimple_seq *ilist, gimple_seq *dlist,
&& gimple_omp_for_combined_into_p (ctx->stmt))
{
tree t = OMP_CLAUSE_LINEAR_STEP (c);
+ if (VAR_P (t)
+ || TREE_CODE (t) == PARM_DECL
+ || TREE_CODE (t) == RESULT_DECL)
+ t = build_outer_var_ref (t, ctx);
tree stept = TREE_TYPE (t);
tree ct = omp_find_clause (clauses,
OMP_CLAUSE__LOOPTEMP_);
new file mode 100644
@@ -0,0 +1,251 @@
+/* PR middle-end/106548. */
+int a[256];
+
+__attribute__((noinline, noclone)) int
+f1 (int i)
+{
+ #pragma omp parallel for simd linear (i: 4)
+ for (int j = 16; j < 64; j++)
+ {
+ a[i] = j;
+ i += 4;
+ }
+ return i;
+}
+
+__attribute__((noinline, noclone)) short int
+f2 (short int i, char k)
+{
+ #pragma omp parallel for simd linear (i: k + 1)
+ for (long j = 16; j < 64; j++)
+ {
+ a[i] = j;
+ i += 4;
+ }
+ return i;
+}
+
+__attribute__((noinline, noclone)) long long int
+f3 (long long int i, long long int k)
+{
+ #pragma omp parallel for simd linear (i: k)
+ for (short j = 16; j < 64; j++)
+ {
+ a[i] = j;
+ i += 4;
+ }
+ return i;
+}
+
+__attribute__((noinline, noclone)) int
+f4 (int i)
+{
+ #pragma omp parallel for simd linear (i: 4) schedule(static, 3)
+ for (int j = 16; j < 64; j++)
+ {
+ a[i] = j;
+ i += 4;
+ }
+ return i;
+}
+
+__attribute__((noinline, noclone)) short int
+f5 (short int i, char k)
+{
+ #pragma omp parallel for simd linear (i: k + 1) schedule(static, 5)
+ for (long j = 16; j < 64; j++)
+ {
+ a[i] = j;
+ i += 4;
+ }
+ return i;
+}
+
+__attribute__((noinline, noclone)) long long int
+f6 (long long int i, long long int k)
+{
+ #pragma omp parallel for simd linear (i: k) schedule(static, 7)
+ for (short j = 16; j < 64; j++)
+ {
+ a[i] = j;
+ i += 4;
+ }
+ return i;
+}
+
+__attribute__((noinline, noclone)) int
+f7 (int i)
+{
+ #pragma omp parallel for simd linear (i: 4) schedule(dynamic, 3)
+ for (int j = 16; j < 64; j++)
+ {
+ a[i] = j;
+ i += 4;
+ }
+ return i;
+}
+
+__attribute__((noinline, noclone)) short int
+f8 (short int i, char k)
+{
+ #pragma omp parallel for simd linear (i: k + 1) schedule(dynamic, 5)
+ for (long j = 16; j < 64; j++)
+ {
+ a[i] = j;
+ i += 4;
+ }
+ return i;
+}
+
+__attribute__((noinline, noclone)) long long int
+f9 (long long int i, long long int k)
+{
+ #pragma omp parallel for simd linear (i: k) schedule(dynamic, 7)
+ for (short j = 16; j < 64; j++)
+ {
+ a[i] = j;
+ i += 4;
+ }
+ return i;
+}
+
+__attribute__((noinline, noclone)) int
+f10 (int i, long step)
+{
+ #pragma omp parallel for simd linear (i: 4)
+ for (int j = 16; j < 112; j += step)
+ {
+ a[i] = j / 2 + 8;
+ i += 4;
+ }
+ return i;
+}
+
+__attribute__((noinline, noclone)) short int
+f11 (short int i, char k, char step)
+{
+ #pragma omp parallel for simd linear (i: k + 1)
+ for (long j = 16; j < 112; j += step)
+ {
+ a[i] = j / 2 + 8;
+ i += 4;
+ }
+ return i;
+}
+
+__attribute__((noinline, noclone)) long long int
+f12 (long long int i, long long int k, int step)
+{
+ #pragma omp parallel for simd linear (i: k)
+ for (short j = 16; j < 112; j += step)
+ {
+ a[i] = j / 2 + 8;
+ i += 4;
+ }
+ return i;
+}
+
+__attribute__((noinline, noclone)) int
+f13 (int i, long long int step)
+{
+ #pragma omp parallel for simd linear (i: 4) schedule(static, 3)
+ for (int j = 16; j < 112; j += step)
+ {
+ a[i] = j / 2 + 8;
+ i += 4;
+ }
+ return i;
+}
+
+__attribute__((noinline, noclone)) short int
+f14 (short int i, char k, int step)
+{
+ #pragma omp parallel for simd linear (i: k + 1) schedule(static, 5)
+ for (long j = 16; j < 112; j += step)
+ {
+ a[i] = j / 2 + 8;
+ i += 4;
+ }
+ return i;
+}
+
+__attribute__((noinline, noclone)) long long int
+f15 (long long int i, long long int k, long int step)
+{
+ #pragma omp parallel for simd linear (i: k) schedule(static, 7)
+ for (short j = 16; j < 112; j += step)
+ {
+ a[i] = j / 2 + 8;
+ i += 4;
+ }
+ return i;
+}
+
+__attribute__((noinline, noclone)) int
+f16 (int i, long long int step)
+{
+ #pragma omp parallel for simd linear (i: 4) schedule(dynamic, 3)
+ for (int j = 16; j < 112; j += step)
+ {
+ a[i] = j / 2 + 8;
+ i += 4;
+ }
+ return i;
+}
+
+__attribute__((noinline, noclone)) short int
+f17 (short int i, char k, int step)
+{
+ #pragma omp parallel for simd linear (i: k + 1) schedule(dynamic, 5)
+ for (long j = 16; j < 112; j += step)
+ {
+ a[i] = j / 2 + 8;
+ i += 4;
+ }
+ return i;
+}
+
+__attribute__((noinline, noclone)) long long int
+f18 (long long int i, long long int k, long int step)
+{
+ #pragma omp parallel for simd linear (i: k) schedule(dynamic, 7)
+ for (short j = 16; j < 112; j += step)
+ {
+ a[i] = j / 2 + 8;
+ i += 4;
+ }
+ return i;
+}
+
+int
+main ()
+{
+#define TEST(x) \
+ if (x != 8 + 48 * 4) \
+ __builtin_abort (); \
+ for (int i = 0; i < 256; i++) \
+ if (a[i] != (((i & 3) == 0 && i >= 8 \
+ && i < 8 + 48 * 4) \
+ ? ((i - 8) / 4) + 16 : 0)) \
+ __builtin_abort (); \
+ __builtin_memset (a, 0, sizeof (a))
+ TEST (f1 (8));
+ TEST (f2 (8, 3));
+ TEST (f3 (8LL, 4LL));
+ TEST (f4 (8));
+ TEST (f5 (8, 3));
+ TEST (f6 (8LL, 4LL));
+ TEST (f7 (8));
+ TEST (f8 (8, 3));
+ TEST (f9 (8LL, 4LL));
+ TEST (f10 (8, 2));
+ TEST (f11 (8, 3, 2));
+ TEST (f12 (8LL, 4LL, 2));
+ TEST (f13 (8, 2));
+ TEST (f14 (8, 3, 2));
+ TEST (f15 (8LL, 4LL, 2));
+ TEST (f16 (8, 2));
+ TEST (f17 (8, 3, 2));
+ TEST (f18 (8LL, 4LL, 2));
+ return 0;
+}