diff options
| author | Vidhya Sudhan Loganathan <vidhyasudhan.loganathan@arm.com> | 2018-10-04 09:21:15 +0100 |
|---|---|---|
| committer | Anthony Barbier <anthony.barbier@arm.com> | 2018-11-02 16:55:19 +0000 |
| commit | d307f06591f674f1b1f53f96b31404e4da754b3b (patch) | |
| tree | 2218b65e1f84817131015271644cf6ecd2efd831 /tests | |
| parent | 188708170a51887868a7170c9ee963372bfb9ced (diff) | |
| download | ComputeLibrary-d307f06591f674f1b1f53f96b31404e4da754b3b.tar.gz | |
COMPMID-1559 : (Nightly) CLWinograd FP16 SIGABORT and mismatches
Current implementation of winograd fp16 is not accurate enough for large runs.
disabling its use and reopening ticket(COMPMID-1266) to fix it.
The sigbus error that was originally reported against COMPMID-1559 is being tracked as COMPMID-1606
Change-Id: I45129aa366d5710402bc54b623c5fbfb865b3cd5
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/151543
Tested-by: bsgcomp <bsgcomp@arm.com>
Reviewed-by: Isabella Gottardi <isabella.gottardi@arm.com>
Diffstat (limited to 'tests')
| -rw-r--r-- | tests/validation/CL/Winograd.cpp | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/tests/validation/CL/Winograd.cpp b/tests/validation/CL/Winograd.cpp index 3762e397ac..930f7aa8ce 100644 --- a/tests/validation/CL/Winograd.cpp +++ b/tests/validation/CL/Winograd.cpp @@ -834,7 +834,7 @@ FIXTURE_DATA_TEST_CASE(RunLarge, CLWinogradConvolutionLayerFastMathFixture, fram TEST_SUITE_END() // Conv1x5 TEST_SUITE_END() // FP32 - +#ifdef WINOGRAD_F16_SUPPORT //to be reintroduced after COMPMID-1266 is resolved TEST_SUITE(FP16) using CLWinogradConvolutionLayerFastMathFixture16 = WinogradConvolutionLayerFastMathValidationFixture<CLTensor, CLAccessor, CLWinogradConvolutionLayer, half>; @@ -977,7 +977,7 @@ FIXTURE_DATA_TEST_CASE(RunLarge, CLWinogradConvolutionLayerFastMathFixture16, fr TEST_SUITE_END() // Conv1x5 TEST_SUITE_END() // FP16 - +#endif /*#ifdef WINOGRAD_F16_SUPPORT*/ TEST_SUITE_END() // ConvolutionLayer TEST_SUITE_END() // Winograd TEST_SUITE_END() // CL |