[Beignet] possilbe bug when run opencv_test_imgproc

Zhigang Gong zhigang.gong at linux.intel.com
Thu Oct 23 05:23:29 PDT 2014


Ok. So this is likely a BYT T platform only issue, it may trigger
a GPU hang at OCL_ImageProc/Filter2D.Mat/256. You can use dmesg to
check whether there was a hang.
 
On Thu, Oct 23, 2014 at 06:04:47AM -0700, yan.wang at linux.intel.com wrote:
> In my baytail T platform, it is still exist.
> 
> > Before leaving office, I have built the latest beignet. I will try it
> > again tomorrow.
> > Thanks.
> >
> > Yan Wang
> >
> >> Can't reproduce it here. Did you use the latest git master?
> >>
> >> The latest git version is
> >> commit 33a043e903f9d61445d3fb7972becf83c2842276
> >> Author: Junyan He <junyan.he at linux.intel.com>
> >> Date:   Thu Oct 23 13:09:00 2014 +0800
> >>
> >>     Add the disasm support for Gen8
> >>
> >>     Signed-off-by: Junyan He <junyan.he at linux.intel.com>
> >>     Reviewed-by: Zhigang Gong <zhigang.gong at linux.intel.com>
> >>     Reviewed-by: "Yang, Rong R" <rong.r.yang at intel.com>
> >>
> >>
> >> Just a reminder, when report a bug/issue, please update to the latest
> >> git
> >> master version and test it again and if it could reproduce please write
> >> done the git hash in the report.
> >>
> >> Thanks,
> >> Zhigang Gong.
> >>
> >> On Thu, Oct 23, 2014 at 03:24:01AM -0700, yan.wang at linux.intel.com
> >> wrote:
> >>> Hi, All,
> >>>    I found one possible bug for review.
> >>>    if run the following:
> >>> ./opencv_test_imgproc --gtest_filter=OCL_ImageProc/Filter2D.Mat*.
> >>>    OCL_ImageProc/Filter2D.Mat/256 failed and continue. But the whole
> >>> test
> >>> flow will crash in OCL_ImageProc/Filter2D.Mat/257:
> >>> [  FAILED  ] OCL_ImageProc/Filter2D.Mat/240, where GetParam() = (CV_8U,
> >>> Channels(2), 7, 1, BORDER_CONSTANT, false, false) (6433 ms)
> >>> [ RUN      ] OCL_ImageProc/Filter2D.Mat/241
> >>> [       OK ] OCL_ImageProc/Filter2D.Mat/241 (358 ms)
> >>> [ RUN      ] OCL_ImageProc/Filter2D.Mat/242
> >>> [       OK ] OCL_ImageProc/Filter2D.Mat/242 (311 ms)
> >>> [ RUN      ] OCL_ImageProc/Filter2D.Mat/243
> >>> [       OK ] OCL_ImageProc/Filter2D.Mat/243 (6 ms)
> >>> [ RUN      ] OCL_ImageProc/Filter2D.Mat/244
> >>> [       OK ] OCL_ImageProc/Filter2D.Mat/244 (203 ms)
> >>> [ RUN      ] OCL_ImageProc/Filter2D.Mat/245
> >>> [       OK ] OCL_ImageProc/Filter2D.Mat/245 (207 ms)
> >>> [ RUN      ] OCL_ImageProc/Filter2D.Mat/246
> >>> [       OK ] OCL_ImageProc/Filter2D.Mat/246 (203 ms)
> >>> [ RUN      ] OCL_ImageProc/Filter2D.Mat/247
> >>> [       OK ] OCL_ImageProc/Filter2D.Mat/247 (7 ms)
> >>> [ RUN      ] OCL_ImageProc/Filter2D.Mat/248
> >>> [       OK ] OCL_ImageProc/Filter2D.Mat/248 (210 ms)
> >>> [ RUN      ] OCL_ImageProc/Filter2D.Mat/249
> >>> [       OK ] OCL_ImageProc/Filter2D.Mat/249 (207 ms)
> >>> [ RUN      ] OCL_ImageProc/Filter2D.Mat/250
> >>> [       OK ] OCL_ImageProc/Filter2D.Mat/250 (208 ms)
> >>> [ RUN      ] OCL_ImageProc/Filter2D.Mat/251
> >>> [       OK ] OCL_ImageProc/Filter2D.Mat/251 (7 ms)
> >>> [ RUN      ] OCL_ImageProc/Filter2D.Mat/252
> >>> [       OK ] OCL_ImageProc/Filter2D.Mat/252 (214 ms)
> >>> [ RUN      ] OCL_ImageProc/Filter2D.Mat/253
> >>> [       OK ] OCL_ImageProc/Filter2D.Mat/253 (207 ms)
> >>> [ RUN      ] OCL_ImageProc/Filter2D.Mat/254
> >>> [       OK ] OCL_ImageProc/Filter2D.Mat/254 (212 ms)
> >>> [ RUN      ] OCL_ImageProc/Filter2D.Mat/255
> >>> [       OK ] OCL_ImageProc/Filter2D.Mat/255 (7 ms)
> >>> [ RUN      ] OCL_ImageProc/Filter2D.Mat/256
> >>> /home/yanwang/opencv/modules/imgproc/test/ocl/test_filter2d.cpp:106:
> >>> Failure
> >>> Expected: (TestUtils::checkNorm2(dst, udst)) <= (threshold), actual:
> >>> 255
> >>> vs 1
> >>> Size: [92 x 61]
> >>>
> >>> /home/yanwang/opencv/modules/imgproc/test/ocl/test_filter2d.cpp:107:
> >>> Failure
> >>> Expected: (TestUtils::checkNorm2(dst_roi, udst_roi)) <= (threshold),
> >>> actual: 255 vs 1
> >>> Size: [92 x 61]
> >>>
> >>> [  FAILED  ] OCL_ImageProc/Filter2D.Mat/256, where GetParam() = (CV_8U,
> >>> Channels(2), 7, 4, BORDER_CONSTANT, false, false) (7413 ms)
> >>> [ RUN      ] OCL_ImageProc/Filter2D.Mat/257
> >>> opencv_test_imgproc: /home/yanwang/beignet/src/intel/intel_gpgpu.c:703:
> >>> intel_gpgpu_check_binded_buf_address: Assertion
> >>> `gpgpu->binded_buf[i]->offset != 0' failed.
> >>> Segmentation fault (core dumped)
> >>>
> >>>   But if I run OCL_ImageProc/Filter2D.Mat/257 only, it passed. I think
> >>> 256
> >>> case may influence it.
> >>>   Thanks.
> >>>
> >>> Yan Wang
> >>> _______________________________________________
> >>> Beignet mailing list
> >>> Beignet at lists.freedesktop.org
> >>> http://lists.freedesktop.org/mailman/listinfo/beignet
> >> _______________________________________________
> >> Beignet mailing list
> >> Beignet at lists.freedesktop.org
> >> http://lists.freedesktop.org/mailman/listinfo/beignet
> >>
> >
> > _______________________________________________
> > Beignet mailing list
> > Beignet at lists.freedesktop.org
> > http://lists.freedesktop.org/mailman/listinfo/beignet
> >
> 
> _______________________________________________
> Beignet mailing list
> Beignet at lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/beignet


More information about the Beignet mailing list