[Mesa-dev] llvm TGSI backend (WIP) questions

[Tom Stellard]

On Fri, Nov 13, 2015 at 02:46:52PM +0100, Hans de Goede wrote:
> Hi All,
> 
> So as discussed I've started working on a TGSI backend for
> llvm to use as a way to get compute going on nouveau (and other gpu-s).
> 
> I'm still learning all the ins and outs of llvm so I do not have
> much to show yet.
> 
> I've rebased Francisco's (curro's) latest version on top of llvm
> trunk, and added a commit on top to actual get it build with the
> latest trunk. So currently I'm at the point where I've just
> taken Francisco's code, and made it compile, no more and no less.
> 
> I have a git repo with this work available here:
> 
> http://cgit.freedesktop.org/~jwrdegoede/llvm/
> 
> So the next step would be to test this and see if it actually
> does anything, questions:
> 
> 1) Does anyone have a simple test case / command where I can
> invoke just llvm and get TGSI asm output to check ?
> 

The easiest way to do this is with the llc tool which ships with llvm.
It compiles LLVM IR to target code, which in this case is tgsi.
I would recommend taking one of the simple examples from
test/CodeGen/AMDGPU (you may need to get these from llvm trunk, not sure
what llvm version you are using).

To use llc:

llc -march=tgsi input.ll -o -


This will output TGSI.


If you want to use clang to compile OpenCL C kernels to clang you will
need to teach clang about the TGSI target by implementing the a
sub-class of TargetInfo in lib/Basic/Targets.cpp.  Look at the 
AMDGPU target for examples, but I recommend starting with llc.

> 2) Assuming I get the above to (somewhat) work, is there a
> way to make llvm show the output of the various intermediate
> passes in a human readable form ?
> 

You can pass -print-before-all or -print-after-all to dump the
intermediate forms.

> Regards,
> 
> Hans
> _______________________________________________
> mesa-dev mailing list
> mesa-dev at lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/mesa-dev