Skip to content

Commit c0f199a

Browse files
committed
test: ml_perf: skip test when ml offload is not available
Skip test instead of failing it when ML offload is not available. Automake uses special value 77 to consider test as SKIPPED. Signed-off-by: Matias Elo <[email protected]> Reviewed-by: Jere Leppänen <[email protected]> Reviewed-by: Tuomas Taipale <[email protected]>
1 parent 8d388f2 commit c0f199a

File tree

1 file changed

+3
-1
lines changed

1 file changed

+3
-1
lines changed

test/performance/odp_ml_perf.c

Lines changed: 3 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -21,6 +21,8 @@
2121
/* Max number of inputs and outputs */
2222
#define MAX_IO 8
2323

24+
#define TEST_SKIP 77
25+
2426
enum {
2527
MODE_INFERENCE = 0,
2628
MODE_INFERENCE_QUANT,
@@ -841,7 +843,7 @@ int main(int argc, char *argv[])
841843

842844
if (glb->capa.max_models < 1) {
843845
ODPH_ERR("ML not supported (maximum number of models is zero)\n");
844-
ret = -1;
846+
ret = TEST_SKIP;
845847
goto odp_term;
846848
}
847849

0 commit comments

Comments
 (0)