<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
</head>
<body>
hmm, perhaps this is not the list to ask such a question. Does any
one have insight to where a new user can get information about the
plan for supporting more recent cuda versions? is there work in
progress? is it documented somewhere?<br>
<br>
Thanks<br>
Burlen<br>
<br>
<div class="moz-cite-prefix">On 1/19/21 8:50 PM, Burlen Loring
wrote:<br>
</div>
<blockquote type="cite"
cite="mid:5a13e46b-779a-ae51-5a92-1abdf52ec06e@lbl.gov">
<meta http-equiv="content-type" content="text/html; charset=UTF-8">
I'm trying to get up and running with llvm/clang + cuda. llvm
11.0.1 successfully installed.<br>
<br>
When I try to compile the simple example shown in llvm examples I
get<br>
<blockquote><font face="monospace">clang-11: warning: Unknown CUDA
version. cuda.h: CUDA_VERSION=11020. Assuming the latest
supported version 10.1 [-Wunknown-cuda-version]<br>
axpy.cu:23:7: error: use of undeclared identifier
cudaConfigureCall<br>
axpy<<<1, kDataLen>>>(a, device_x,
device_y);<br>
</font></blockquote>
I have cuda 11.2 installed however clang apparently needs cuda
10.1 and I'm running fedora 33 which is too new for cuda 10.1.
cuda 10.1 is supported on fedora 29 but I don't wish to downgrade
the os.<br>
<br>
Is there any plan for llvm/clang to use newer cuda? on what time
frame?<br>
<br>
Thanks<br>
Burlen<br>
<br>
<br>
<br>
<br>
</blockquote>
<br>
</body>
</html>