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

Michael Liao via Phabricator via cfe-commits cfe-commits at lists.llvm.org
Sat Apr 11 09:35:50 PDT 2020


hliao added a comment.

In D76365#1975784 <https://reviews.llvm.org/D76365#1975784>, @tra wrote:

> It appears I can crash clang with some texture code: https://godbolt.org/z/5vdEwC


`llvm.nvvm.tex.unified.2d.v4f32.f32` has a vector output, the alias

  __attribute__((device)) float tex2d_ld(tex_t, float, float) asm("llvm.nvvm.tex.unified.2d.v4f32.f32");

needs replacing with

  __attribute__((device)) v4f tex2d_ld(tex_t, float, float) asm("llvm.nvvm.tex.unified.2d.v4f32.f32");

see this revised sample code https://godbolt.org/z/B7rtxR


Repository:
  rG LLVM Github Monorepo

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

https://reviews.llvm.org/D76365





More information about the cfe-commits mailing list