Hi,
When running testcases libgomp.fortran/examples-4/declare_target-{1,2}.f90 on
an RTX A2000 (sm_86) with driver 510.60.02 and with GOMP_NVPTX_JIT=-O0 I run
into:
...
FAIL: libgomp.fortran/examples-4/declare_target-1.f90 -O0 \
-DGOMP_NVPTX_JIT=-O0 execution test
FAIL: libgomp.fortran/examples-4/declare_target-2.f90 -O0 \
-DGOMP_NVPTX_JIT=-O0 execution test
...
Fix this by further limiting recursion depth in the test-cases for nvptx.
Furthermore, make the recursion depth limiting nvptx-specific.
Tested on x86_64 with nvptx accelerator.
Any comments?
Thanks,
- Tom
[libgomp, testsuite, nvptx] Limit recursion in declare_target-{1,2}.f90
libgomp/ChangeLog:
2022-04-01 Tom de Vries <tdevr...@suse.de>
* testsuite/libgomp.fortran/examples-4/declare_target-1.f90: Define
and use REC_DEPTH.
* testsuite/libgomp.fortran/examples-4/declare_target-2.f90: Same.
---
.../libgomp.fortran/examples-4/declare_target-1.f90 | 18 +++++++++++++-----
.../libgomp.fortran/examples-4/declare_target-2.f90 | 20 ++++++++++++++------
2 files changed, 27 insertions(+), 11 deletions(-)
diff --git a/libgomp/testsuite/libgomp.fortran/examples-4/declare_target-1.f90
b/libgomp/testsuite/libgomp.fortran/examples-4/declare_target-1.f90
index b761979ecde..03c5c53ed67 100644
--- a/libgomp/testsuite/libgomp.fortran/examples-4/declare_target-1.f90
+++ b/libgomp/testsuite/libgomp.fortran/examples-4/declare_target-1.f90
@@ -1,4 +1,16 @@
! { dg-do run }
+! { dg-additional-options "-cpp" }
+! Reduced from 25 to 23, otherwise execution runs out of thread stack on
+! Nvidia Titan V.
+! Reduced from 23 to 22, otherwise execution runs out of thread stack on
+! Nvidia T400 (2GB variant), when run with GOMP_NVPTX_JIT=-O0.
+! Reduced from 22 to 20, otherwise execution runs out of thread stack on
+! Nvidia RTX A2000 (6GB variant), when run with GOMP_NVPTX_JIT=-O0.
+! { dg-additional-options "-DREC_DEPTH=20" { target { offload_target_nvptx } }
} */
+
+#ifndef REC_DEPTH
+#define REC_DEPTH 25
+#endif
module e_53_1_mod
integer :: THRESHOLD = 20
@@ -27,9 +39,5 @@ end module
program e_53_1
use e_53_1_mod, only : fib, fib_wrapper
if (fib (15) /= fib_wrapper (15)) stop 1
- ! Reduced from 25 to 23, otherwise execution runs out of thread stack on
- ! Nvidia Titan V.
- ! Reduced from 23 to 22, otherwise execution runs out of thread stack on
- ! Nvidia T400 (2GB variant), when run with GOMP_NVPTX_JIT=-O0.
- if (fib (22) /= fib_wrapper (22)) stop 2
+ if (fib (REC_DEPTH) /= fib_wrapper (REC_DEPTH)) stop 2
end program
diff --git a/libgomp/testsuite/libgomp.fortran/examples-4/declare_target-2.f90
b/libgomp/testsuite/libgomp.fortran/examples-4/declare_target-2.f90
index f576c25ba39..0e8bea578a8 100644
--- a/libgomp/testsuite/libgomp.fortran/examples-4/declare_target-2.f90
+++ b/libgomp/testsuite/libgomp.fortran/examples-4/declare_target-2.f90
@@ -1,16 +1,24 @@
! { dg-do run }
+! { dg-additional-options "-cpp" }
+! Reduced from 25 to 23, otherwise execution runs out of thread stack on
+! Nvidia Titan V.
+! Reduced from 23 to 22, otherwise execution runs out of thread stack on
+! Nvidia T400 (2GB variant), when run with GOMP_NVPTX_JIT=-O0.
+! Reduced from 22 to 18, otherwise execution runs out of thread stack on
+! Nvidia RTX A2000 (6GB variant), when run with GOMP_NVPTX_JIT=-O0.
+! { dg-additional-options "-DREC_DEPTH=18" { target { offload_target_nvptx } }
} */
+
+#ifndef REC_DEPTH
+#define REC_DEPTH 25
+#endif
program e_53_2
!$omp declare target (fib)
integer :: x, fib
!$omp target map(from: x)
- ! Reduced from 25 to 23, otherwise execution runs out of thread stack on
- ! Nvidia Titan V.
- ! Reduced from 23 to 22, otherwise execution runs out of thread stack on
- ! Nvidia T400 (2GB variant), when run with GOMP_NVPTX_JIT=-O0.
- x = fib (22)
+ x = fib (REC_DEPTH)
!$omp end target
- if (x /= fib (22)) stop 1
+ if (x /= fib (REC_DEPTH)) stop 1
end program
integer recursive function fib (n) result (f)
