<html> <head> <base href="https://bugs.freedesktop.org/" /> </head> <body> <div> <a class="bz_bug_link bz_status_NEW " title="NEW - [HSW] compute shader shared var + atomic op = fail" href="https://bugs.freedesktop.org/show_bug.cgi?id=94081#c1">Comment # 1</a> on <a class="bz_bug_link bz_status_NEW " title="NEW - [HSW] compute shader shared var + atomic op = fail" href="https://bugs.freedesktop.org/show_bug.cgi?id=94081">bug 94081</a> from <a class="email" href="mailto:imirkin@alum.mit.edu" title="Ilia Mirkin <imirkin@alum.mit.edu>"> Ilia Mirkin</a> <pre>One additional observation: the (wrong) count of group 0 (after which it stops comparing) is different every time - tends to cycle between a few different values. My suspicion is that there's something execmask-related going on. Right now we always use 0xffff as the execmask arg for all the untyped surface reads/writes/atomics, as supplied by fs_builder::sample_mask_reg(), but e.g. the HSW prm has very difficult to understand explanation of how the exec mask should be computed (page 832, Execution Masks). I wonder if data is being picked up from threads that are logically "off". The shader in question does a 4x4x4 grid of 3x2x1 blocks.</pre> </div> <hr> You are receiving this mail because: <ul> <li>You are the QA Contact for the bug.</li> </ul> </body> </html>