llvm dev - Oct 2016 - problem on compiling cuda program with clang++

On 27 October 2016 at 19:02, Justin Lebar via llvm-dev
<llvm-dev at lists.llvm.org> wrote:
> Hi, it looks like you're compiling CUDA for an ARM host?  This is not
> a configuration we have tested, nor is it something we have the
> capability of testing at the moment.
Hi Justin,

NVidia TX1 is the AArch64 Jetson board with proper GPU (we use those).

> You may be able to make it work by providing the appropriate -isystem
> flags to clang so that it can find your headers, but who knows, it may
> be more complicated than that.
We don't use them for their GPU, so I don't know, but those kits are
meant to be CUDA development boxes.

The board setup process has an installer (JetPack) which gets all the
drivers, headers and libraires for CUDA development. It should be just
a matter of finding them and using with -isystem.

cheers,
--renato

> NVidia TX1 is the AArch64 Jetson board with proper GPU (we use those).
Sure, I believe that others use this configuration.  I was saying,
"we", being, myself and those whom I work closely with, do not.  Sorry
if that wasn't precise.

It is still not clear to me if the original poster is compiling for
ARM or not.  But it sounds like you're going to help them get this
working, which is great, because I have no experience with this setup.
> It should be just a matter of finding them and using with -isystem.
As I originally suggested.  :)

-Justin

On Thu, Oct 27, 2016 at 1:04 PM, Renato Golin <renato.golin at linaro.org>
wrote:
> On 27 October 2016 at 19:02, Justin Lebar via llvm-dev
> <llvm-dev at lists.llvm.org> wrote:
>> Hi, it looks like you're compiling CUDA for an ARM host?  This is
not
>> a configuration we have tested, nor is it something we have the
>> capability of testing at the moment.
>
> Hi Justin,
>
> NVidia TX1 is the AArch64 Jetson board with proper GPU (we use those).
>
>
>> You may be able to make it work by providing the appropriate -isystem
>> flags to clang so that it can find your headers, but who knows, it may
>> be more complicated than that.
>
> We don't use them for their GPU, so I don't know, but those kits
are
> meant to be CUDA development boxes.
>
> The board setup process has an installer (JetPack) which gets all the
> drivers, headers and libraires for CUDA development. It should be just
> a matter of finding them and using with -isystem.
>
> cheers,
> --renato

1. Yes, you both are right. My platform is Jetson TX1, AArch64.

2. And I obtain all the necessary files for TX1 by JetPack from the
host(X86) and so `nvcc` can work rightly.

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".

2016-10-28 4:07 GMT+08:00 Justin Lebar <jlebar at google.com>:
> > NVidia TX1 is the AArch64 Jetson board with proper GPU (we use those).
>
> Sure, I believe that others use this configuration.  I was saying,
> "we", being, myself and those whom I work closely with, do not. 
Sorry
> if that wasn't precise.
>
> It is still not clear to me if the original poster is compiling for
> ARM or not.  But it sounds like you're going to help them get this
> working, which is great, because I have no experience with this setup.
>
> > It should be just a matter of finding them and using with -isystem.
>
> As I originally suggested.  :)
>
> -Justin
>
> On Thu, Oct 27, 2016 at 1:04 PM, Renato Golin <renato.golin at
linaro.org>
> wrote:
> > On 27 October 2016 at 19:02, Justin Lebar via llvm-dev
> > <llvm-dev at lists.llvm.org> wrote:
> >> Hi, it looks like you're compiling CUDA for an ARM host?  This
is not
> >> a configuration we have tested, nor is it something we have the
> >> capability of testing at the moment.
> >
> > Hi Justin,
> >
> > NVidia TX1 is the AArch64 Jetson board with proper GPU (we use those).
> >
> >
> >> You may be able to make it work by providing the appropriate
-isystem
> >> flags to clang so that it can find your headers, but who knows, it
may
> >> be more complicated than that.
> >
> > We don't use them for their GPU, so I don't know, but those
kits are
> > meant to be CUDA development boxes.
> >
> > The board setup process has an installer (JetPack) which gets all the
> > drivers, headers and libraires for CUDA development. It should be just
> > a matter of finding them and using with -isystem.
> >
> > cheers,
> > --renato
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://lists.llvm.org/pipermail/llvm-dev/attachments/20161028/b55e0729/attachment.html>

On 27 October 2016 at 21:07, Justin Lebar <jlebar at google.com>
wrote:
> Sure, I believe that others use this configuration.  I was saying,
> "we", being, myself and those whom I work closely with, do not. 
Sorry
> if that wasn't precise.
It was clear. :)

> It is still not clear to me if the original poster is compiling for
> ARM or not.  But it sounds like you're going to help them get this
> working, which is great, because I have no experience with this setup.
I think so. On ARM to ARM.

--renato