<html><head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8"></head><body dir="auto"><div>Those failures are in OpenPA, which is a separate component you can test by itself for convenience.</div><div><br></div><div><a href="http://git.mpich.org/openpa.git/">http://git.mpich.org/openpa.git/</a> is the official project source. You should try different implementations. The GCC intrinsics should be portable but if they don't work, that's a bug either in the compiler or OpenPA.</div><div><br></div><div>The most portable OpenPA port uses Pthread locks. That's quite slow but should not fail. You may need to force that if the ARM assembly port and the GCC __sync intrinsics ones break. </div><div><br></div><div>I wrote a C11 port with</div><div><a href="https://github.com/jeffhammond/OpenPA?files=1">https://github.com/jeffhammond/OpenPA</a> that has not been tested anywhere besides x86 but could be better if your compiler does a good job with C11.</div><div><br></div><div>It's trivial to make a __atomic or __c11 intrinsics port for GCC or Clang if that is necessary. Those should be more efficient on ARM than __sync intrinsics, if used properly.</div><div><br></div><div>My only programmable ARM system is an Adapteva Parallella board that hasn't been powered on in 3 years, so I'm not in a good position to test anything, but I'll hack on OpenPA if necessary.</div><div><br></div><div>Jeff <br><br><div>Sent from my iPhone</div></div><div><br>On Aug 13, 2017, at 4:23 AM, Alastair McKinstry <<a href="mailto:mckinstry@debian.org">mckinstry@debian.org</a>> wrote:<br><br></div><blockquote type="cite"><div><span>Hi,</span><br><span></span><br><span>I've built 3.3a2 on Debian on all supported architectures. Failures were</span><br><span>seen on the armhf architecture (Arm with hardware float support, </span><br><span>32-bit v7 architecture).</span><br><span></span><br><span>Testing integer swap with 4 threads *FAILED*</span><br><span> at test_primitives.c:3399 in test_threaded_swap_int()...</span><br><span> Value 0 was encountered 0 times. Expected: 1</span><br><span>Testing pointer swap with 4 threads *FAILED*</span><br><span> at test_primitives.c:3554 in test_threaded_swap_ptr()...</span><br><span> Value 3 was encountered 2 times. Expected: 1</span><br><span></span><br><span>Details: <a href="https://buildd.debian.org/status/fetch.php?pkg=mpich&arch=armhf&ver=3.3%7Ea2-2&stamp=1502381558&raw=0">https://buildd.debian.org/status/fetch.php?pkg=mpich&arch=armhf&ver=3.3%7Ea2-2&stamp=1502381558&raw=0</a></span><br><span></span><br><span>Is anyone working on this? If necessary I can do testing on armhf systems</span><br><span></span><br><span>Best regards</span><br><span>Alastair</span><br><span></span><br><span>-- </span><br><span>Alastair McKinstry, <<a href="mailto:alastair@sceal.ie">alastair@sceal.ie</a>>, <<a href="mailto:mckinstry@debian.org">mckinstry@debian.org</a>>, <a href="https://diaspora.sceal.ie/u/amckinstry">https://diaspora.sceal.ie/u/amckinstry</a></span><br><span>Misentropy: doubting that the Universe is becoming more disordered. H</span><br><span></span><br><span></span><br></div></blockquote><blockquote type="cite"><div><span>_______________________________________________</span><br><span>discuss mailing list <a href="mailto:discuss@mpich.org">discuss@mpich.org</a></span><br><span>To manage subscription options or unsubscribe:</span><br><span><a href="https://lists.mpich.org/mailman/listinfo/discuss">https://lists.mpich.org/mailman/listinfo/discuss</a></span></div></blockquote></body></html>