This came up because the USM implementation with
-foffload-memory={unified,pinned}
as posted at https://gcc.gnu.org/pipermail/gcc-patches/2022-July/597976.html
does not handle USM with static variables.
This shows up for the OG12 alias devel/omp/gcc-12 branch as FAIL for
requires-4.c.
The attached patch prepares for skipping requires-4.c for the gcn/nvptx device
and adds an adjacent requires-4a.c testcase, using heap memory, that can still
run on gcn/nvptx.
Additionally, I commented on no longer used #defined, following the
precedence GOMP_DEVICE_HOST_NONSHM.
Thus, this tests adds another testcase and one effective-target check,
out-comments a unused #define - and that's it.
(Otherwise, it is just a prep patch.)
OK for mainline?
Tobias
PS: Currently, neither the preexisting offload_device_nvptx nor the new
offload_device_gcn target selector is used, neither in old code nor by this
patch.
-
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
libgomp: Add offload_device_gcn check, add requires-4a.c test
Duplicate libgomp.c-c++-common/requires-4.c (as ...-4a.c) but
with using a heap-allocated instead of static memory for a variable.
This change and the added offload_device_gcn check prepare for
pseudo-USM, where the device hardware cannot access all host
memory but only managed and pinned memory; for those, requires-4.c
will fail and the new check permits to add
target { ! { offload_device_nvptx || offload_device_gcn } }
to requires-4.c; however, it has not been added yet as pseuo-USM
support is not yet on mainline. (Review is pending for the USM
patches.)
include/ChangeLog:
* gomp-constants.h (GOMP_DEVICE_HSA): Comment (unused).
libgomp/ChangeLog:
* testsuite/lib/libgomp.exp (check_effective_target_offload_device_gcn):
New.
* testsuite/libgomp.c-c++-common/on_device_arch.h (device_arch_gcn,
on_device_arch_gcn): New.
* testsuite/libgomp.c-c++-common/requires-4a.c: New test; copied from
requires-4.c but using heap-allocated memory.
include/gomp-constants.h | 2 +-
libgomp/testsuite/lib/libgomp.exp | 12 +++
.../libgomp.c-c++-common/on_device_arch.h | 13
.../testsuite/libgomp.c-c++-common/requires-4a.c | 39 ++
4 files changed, 65 insertions(+), 1 deletion(-)
diff --git a/include/gomp-constants.h b/include/gomp-constants.h
index 84316f953d0..fac7316b858 100644
--- a/include/gomp-constants.h
+++ b/include/gomp-constants.h
@@ -229,9 +229,9 @@ enum gomp_map_kind
/* #define GOMP_DEVICE_HOST_NONSHM 3 removed. */
#define GOMP_DEVICE_NOT_HOST 4
#define GOMP_DEVICE_NVIDIA_PTX 5
#define GOMP_DEVICE_INTEL_MIC 6
-#define GOMP_DEVICE_HSA 7
+/* #define GOMP_DEVICE_HSA 7 removed. */
#define GOMP_DEVICE_GCN 8
/* We have a compatibility issue. OpenMP 5.2 introduced
omp_initial_device with value of -1 which clashes with our
diff --git a/libgomp/testsuite/lib/libgomp.exp b/libgomp/testsuite/lib/libgomp.exp
index 107a3c2ac9d..4b8c64de8a5 100644
--- a/libgomp/testsuite/lib/libgomp.exp
+++ b/libgomp/testsuite/lib/libgomp.exp
@@ -414,8 +414,20 @@ proc check_effective_target_offload_device_nvptx { } {
}
} ]
}
+# Return 1 if using a GCN offload device.
+proc check_effective_target_offload_device_gcn { } {
+return [check_runtime_nocache offload_device_gcn {
+ #include
+ #include "testsuite/libgomp.c-c++-common/on_device_arch.h"
+ int main ()
+ {
+ return !on_device_arch_gcn ();
+ }
+} ]
+}
+
# Return 1 if at least one Nvidia GPU is accessible.
proc check_effective_target_openacc_nvidia_accel_present { } {
return [check_runtime openacc_nvidia_accel_present {
diff --git a/libgomp/testsuite/libgomp.c-c++-common/on_device_arch.h b/libgomp/testsuite/libgomp.c-c++-common/on_device_arch.h
index f92743b04d7..6f66dbd784c 100644
--- a/libgomp/testsuite/libgomp.c-c++-common/on_device_arch.h
+++ b/libgomp/testsuite/libgomp.c-c++-common/on_device_arch.h
@@ -6,15 +6,22 @@ device_arch_nvptx (void)
{
return GOMP_DEVICE_NVIDIA_PTX;
}
+/* static */ int
+device_arch_gcn (void)
+{
+ return GOMP_DEVICE_GCN;
+}
+
/* static */ int
device_arch_intel_mic (void)
{
return GOMP_DEVICE_INTEL_MIC;
}
#pragma omp declare variant (device_arch_nvptx) match(construct={target},device={arch(nvptx)})
+#pragma omp declare variant (device_arch_gcn) match(construct={target},device={arch(gcn)})
#pragma omp declare variant (device_arch_intel_mic) match(construct={target},device={arch(intel_mic)})
/* static */ int
device_arch (void)
{
@@ -36,8 +43,14 @@ on_device_arch_nvptx ()
{
return on_device_arch (GOMP_DEVICE_NVIDIA_PTX);
}
+int
+on_device_arch_gcn ()
+{
+ return on_device_arch (GOMP_DEVICE_GCN);
+}
+
int
on_device_arch_intel_mic ()
{
return on_device_
