Trevor L. McDonell

The low-level nature of LLVM is fine; that's all handled by `accelerate-llvm`. Note that an `accelerate-llvm-gcn` (or whatever we call it) backend is generating code _only_ for the kernel parts...

It might be worthwhile shooting an email to AMD / LLVM mailing list or opening a github issue on that repo asking for advice / clarification / pointer to the...

Possibly useful links: * http://openwall.info/wiki/john/development/AMD-IL * https://community.amd.com/thread/166955

If you have an older version of LLVM available, it might be worth trying that? I know the NVIDIA tools are also based off of LLVM, but typically lag by...

@typedrat thanks for the info!

There is some documentation on the AMD toolchain [here](https://books.google.ca/books?id=otXUBQAAQBAJ&pg=PA33&lpg=PA33&dq=clang+hsa+kernel&source=bl&ots=g7c99N0Ceb&sig=ACfU3U2DP2iBtGf2DSyOAgrm9zG3hmzFjQ&hl=en&sa=X&ved=2ahUKEwj7nvvY7Z_oAhVMop4KHVxxD2cQ6AEwBHoECAkQAQ#v=onepage&q=clang%20hsa%20kernel&f=false).

@typedrat wow thanks for the insight! Well, I just bought a Radeon VII, so let's see what we can do.

@gozzarda oh nice find, thanks!

I think the (old now) 1.2 release of accelerate-llvm-native isn't going to work with Cabal-3.x. The current GitHub version should avoid this problem though, can you try installing that? I...

(Also, sorry for the very late reply! I've been swamped and only just saw this)