<html>
<head>
<base href="https://bugs.freedesktop.org/">
</head>
<body>
<p>
<div>
<b><a class="bz_bug_link
bz_status_NEW "
title="NEW - OpenCL enqueueReadBuffer returns trash"
href="https://bugs.freedesktop.org/show_bug.cgi?id=101952#c2">Comment # 2</a>
on <a class="bz_bug_link
bz_status_NEW "
title="NEW - OpenCL enqueueReadBuffer returns trash"
href="https://bugs.freedesktop.org/show_bug.cgi?id=101952">bug 101952</a>
from <span class="vcard"><a class="email" href="mailto:janpieter.sollie@dommel.be" title="Janpieter Sollie <janpieter.sollie@dommel.be>"> <span class="fn">Janpieter Sollie</span></a>
</span></b>
<pre>Hi Mr. Vesely,
hereby a minimal extract:
__kernel void startTest(__constant char* arg, __constant uchar* arg2, size_t
arg3, __constant char* phrase, size_t _len, __global int* output) {
char result;
if(output[3] == 255) return;
result = external_function_call(phrase, arg2, arg3, _len, arg);
if(result == 2) {
output[3] = 255;
output[0] = get_global_id(0);
output[1] = get_global_id(1);
output[2] = get_global_id(2);
}
else if(result == -1) output[3] = 127;
return;
}
the reason why I doubt the correctness of readbuffer is there is no 255 int at
place 3, while something was read from somewhere, so I guess it's looking at
the wrong place ...
and yes, the global id (0.0.0) will give a result of 2, at least it does with
amdpro and pocl</pre>
</div>
</p>
<hr>
<span>You are receiving this mail because:</span>
<ul>
<li>You are the assignee for the bug.</li>
<li>You are the QA Contact for the bug.</li>
</ul>
</body>
</html>