[PATCH] D76365: [cuda][hip] Add CUDA builtin surface/texture reference support.

[Michael Liao via Phabricator via cfe-commits]

hliao added a comment.

In D76365#1932517 <https://reviews.llvm.org/D76365#1932517>, @tra wrote:

> In D76365#1932439 <https://reviews.llvm.org/D76365#1932439>, @hliao wrote:
>
> >
>
>
>
>
> > That's a magic. I could not figure out how it works. From its use, e.g. `tex2D` on `texture<T, cudaTextureType2D, cudaReadModeElementType>`,
> > 
> >   __nv_tex_surf_handler("__tex2D_v2", (typename __nv_tex_rmet_cast<T>::type) &temp, t, x, y);
> > 
> > 
> > `__tex2D_v2` is a string literal. However, it's more likely a underly function name for the real implementation. Hardly imagine that that string literal is checked directly instead used for constructing the real function name. If that's the case, we also need to find that where that underlying functions are defined as the device bitcode library has no such definition.
>
> Most likely it's a compiler built-in with no implementation we could reuse and we'll need to implement our own. It should be fairly straightforward to figure out what it does by compiling all variants used by CUDA headers and observing generated PTX. The first 'meta' argument may be tricky, but we should be able to retrieve the constant string value in the front-end and map it to appropriate intrinsic or generate necessary glue.


I could add that support gradually in my spare time. The goal of this patch not only addresses the texture/surface reference support for CUDA but also for HIP to keep the maximum compatibility. Once this is landed, we will follow the similar approach in HIP.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D76365/new/

https://reviews.llvm.org/D76365