ayo
7c5d3c9157
Add native K/M/RR inference engines, HIP kernels, replay and validation harnesses, and Windows DLSS setup and runtime support. Include GPU profiling tools, build and packaging scripts, platform integration patches, and implementation documentation.
41 lines
2.7 KiB
Diff
41 lines
2.7 KiB
Diff
From: d4r
|
|
Subject: [PATCH] null texture objects read as zero
|
|
|
|
CUDA texture object 0 reads as zeros on NVIDIA GPUs, and DLSS samples absent optional inputs
|
|
(its exposure scales, with the flags Ghost of Tsushima uses) that way. A ZLUDA texture object is a
|
|
descriptor pointer, so handle 0 made the GPU read address 0 and fault. Handle 0 now points at an
|
|
all-zero descriptor, which AMD hardware treats as a null resource. Rebuild ptx/lib/*.bc after
|
|
applying (scripts/build_zluda_ptx_helpers.sh).
|
|
---
|
|
--- a/ptx/lib/zluda_ptx_impl.cpp 2026-09-27 16:47:02.815623944 -0400
|
|
+++ b/ptx/lib/zluda_ptx_impl.cpp 2026-09-27 16:47:02.815623944 -0400
|
|
@@ -1725,9 +1725,18 @@
|
|
c;
|
|
}
|
|
|
|
+ // d4r: CUDA texture object 0 reads as zeros on NVIDIA GPUs, and DLSS samples absent optional inputs
|
|
+ // (exposure scales) that way. A ZLUDA texture object is a descriptor pointer, so 0 is redirected to
|
|
+ // an all-zero descriptor, which AMD hardware treats as a null resource (reads return 0).
|
|
+ __device__ static unsigned int d4r_null_texture[32];
|
|
+ static uint64_t texture_or_null(uint64_t texobj) __device__
|
|
+ {
|
|
+ return texobj != 0 ? texobj : uint64_t(uintptr_t(d4r_null_texture));
|
|
+ }
|
|
+
|
|
static std::pair<GLOBAL_SPACE void *, GLOBAL_SPACE void *> get_image_and_sampler(uint64_t texobj) __device__
|
|
{
|
|
- unsigned int GLOBAL_SPACE *image = (unsigned int GLOBAL_SPACE *)texobj;
|
|
+ unsigned int GLOBAL_SPACE *image = (unsigned int GLOBAL_SPACE *)texture_or_null(texobj);
|
|
unsigned int GLOBAL_SPACE *sampler = image + HIP_SAMPLER_OBJECT_OFFSET_DWORD;
|
|
return {image, sampler};
|
|
}
|
|
@@ -1868,7 +1877,7 @@
|
|
#define tex_2d_gather4(COMPONENT) \
|
|
v4f32 FUNC(texobj_gather4##COMPONENT##_2d_v4_f32_f32)(uint64_t texobj, v2f32 coord) \
|
|
{ \
|
|
- auto image = reinterpret_cast<unsigned int CONSTANT_SPACE *>(static_cast<uintptr_t>(texobj)); \
|
|
+ auto image = reinterpret_cast<unsigned int CONSTANT_SPACE *>(static_cast<uintptr_t>(texture_or_null(texobj))); \
|
|
auto sampler = image + HIP_SAMPLER_OBJECT_OFFSET_DWORD; \
|
|
float2 coordinates{coord.x, coord.y}; \
|
|
auto result = __ockl_image_gather4##COMPONENT##_2D(image, sampler, get_native_vector(coordinates)); \
|