<div dir="ltr"><div dir="ltr" style="font-size:14px">1. Yes, you both are right. My platform is Jetson TX1, AArch64. <div><br></div><div>2. And I obtain all the necessary files for TX1 by JetPack from the host(X86) and so `nvcc` can work rightly.</div><div><br></div><div>3. Althrough I can compile LLVM3.9 on TX1, I can not compile the CUDA program using `clang` tools. The error is "sys/cedfs.h no such file".</div></div><div class="gmail-yj6qo gmail-ajU" style="font-size:14px"></div></div><div class="gmail_extra"><br><div class="gmail_quote">2016-10-28 4:07 GMT+08:00 Justin Lebar <span dir="ltr"><<a href="mailto:jlebar@google.com" target="_blank">jlebar@google.com</a>></span>:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><span class="">> NVidia TX1 is the AArch64 Jetson board with proper GPU (we use those).<br>
<br>
</span>Sure, I believe that others use this configuration. I was saying,<br>
"we", being, myself and those whom I work closely with, do not. Sorry<br>
if that wasn't precise.<br>
<br>
It is still not clear to me if the original poster is compiling for<br>
ARM or not. But it sounds like you're going to help them get this<br>
working, which is great, because I have no experience with this setup.<br>
<span class=""><br>
> It should be just a matter of finding them and using with -isystem.<br>
<br>
</span>As I originally suggested. :)<br>
<span class="HOEnZb"><font color="#888888"><br>
-Justin<br>
</font></span><div class="HOEnZb"><div class="h5"><br>
On Thu, Oct 27, 2016 at 1:04 PM, Renato Golin <<a href="mailto:renato.golin@linaro.org">renato.golin@linaro.org</a>> wrote:<br>
> On 27 October 2016 at 19:02, Justin Lebar via llvm-dev<br>
> <<a href="mailto:llvm-dev@lists.llvm.org">llvm-dev@lists.llvm.org</a>> wrote:<br>
>> Hi, it looks like you're compiling CUDA for an ARM host? This is not<br>
>> a configuration we have tested, nor is it something we have the<br>
>> capability of testing at the moment.<br>
><br>
> Hi Justin,<br>
><br>
> NVidia TX1 is the AArch64 Jetson board with proper GPU (we use those).<br>
><br>
><br>
>> You may be able to make it work by providing the appropriate -isystem<br>
>> flags to clang so that it can find your headers, but who knows, it may<br>
>> be more complicated than that.<br>
><br>
> We don't use them for their GPU, so I don't know, but those kits are<br>
> meant to be CUDA development boxes.<br>
><br>
> The board setup process has an installer (JetPack) which gets all the<br>
> drivers, headers and libraires for CUDA development. It should be just<br>
> a matter of finding them and using with -isystem.<br>
><br>
> cheers,<br>
> --renato<br>
</div></div></blockquote></div><br></div>