Compiler Explorer

Source code

#if !defined(__NVCC__)
struct textureReference {
  int desc;
};

enum cudaTextureReadMode {
  cudaReadModeElementType = 0,
  cudaReadModeNormalizedFloat = 1
};

template <typename T, int dim = 1, enum cudaTextureReadMode mode = cudaReadModeElementType>
struct __attribute__((device_builtin_texture_type)) texture : public textureReference {
};
#endif

// On the device side, texture references are represented as `i64` handles.
// DEVICE: @tex = addrspace(1) global i64 undef, align 4
// DEVICE: @norm = addrspace(1) global i64 undef, align 4
// On the host side, they remain in the original type.
// HOST: @tex = internal global %struct.texture
// HOST: @norm = internal global %struct.texture
// HOST: @0 = private unnamed_addr constant [4 x i8] c"tex\00"
// HOST: @1 = private unnamed_addr constant [5 x i8] c"norm\00"
using tex_t = texture<float, 1, cudaReadModeElementType>;
tex_t tex;

using tex_norm_t = texture<float, 1, cudaReadModeNormalizedFloat>;
tex_norm_t texn;

struct v4f {
  float x, y, z, w;
};

#if defined(__NVCC__)
#define tex2d_ld tex2D
#else
__attribute__((device)) float tex2d_ld(tex_t, float, float) asm("llvm.nvvm.tex.unified.2d.v4f32.f32");
__attribute__((device)) float tex2d_ld(tex_norm_t, int, int) asm("llvm.nvvm.tex.unified.2d.v4f32.s32");
#endif

// DEVICE-LABEL: float @_Z3fooff(float %x, float %y)
// DEVICE: call i64 @llvm.nvvm.texsurf.handle.internal.p1i64(i64 addrspace(1)* @tex)
// DEVICE: call %struct.v4f @llvm.nvvm.tex.unified.2d.v4f32.f32(i64 %{{.*}}, float %{{.*}}, float %{{.*}})
// DEVICE: call i64 @llvm.nvvm.texsurf.handle.internal.p1i64(i64 addrspace(1)* @norm)
// DEVICE: call %struct.v4f @llvm.nvvm.tex.unified.2d.v4f32.s32(i64 %{{.*}}, i32 %{{.*}}, i32 %{{.*}})
__attribute__((device)) float foo(float x, float y) {
  return tex2d_ld(tex, x, y) + tex2d_ld(texn, int(x), int(y));
}