ayo
34e6b0fe71
Add an experimental FSR Ray Regeneration backend for D3D12 RR requests: - Convert depth, motion, normals and albedos into AMD denoiser inputs. - Split and recompose diffuse/specular signals, then run Super Sampling. - Add stability/detail controls, demodulation guards and halo limiting. - Handle AMD provider discovery under NVIDIA GPU spoofing. - Add runtime probes, synthetic reference scenes and per-dispatch profiling. Add exact gfx11 DLSS-RR inference using f16 cooperative matrices: - Reproduce FP8 conversions, accumulation and camera reprojection arithmetic. - Widen model weights and avoid requiring VK_EXT_shader_float8. - Extend model building, replay tools and descriptor metadata. Expand motion preprocessing and experimental AW2 native-motion support: - Add tiled LDS dilation, padded allocation handling and thin-only sky fill. - Order dilation with input waits and NGX on the selected stream. - Add jitter-aligned native composition, hybrid routing and wire history repair. - Add prepared masks, sparse repair and independent motion/repair controls. Add optional fused R11G11B10 input/output conversion, sampled stage timings and profile summarization. Extend configuration, packaging, documentation, FidelityFX headers and CPU/GPU regression coverage.
76 lines
3.4 KiB
Python
76 lines
3.4 KiB
Python
"""Dilation must not enter GPU input waits while lazy resources can synchronize."""
|
|
from pathlib import Path
|
|
import subprocess
|
|
import tempfile
|
|
import unittest
|
|
|
|
ROOT = Path(__file__).resolve().parents[1]
|
|
|
|
|
|
class MotionSubmissionTests(unittest.TestCase):
|
|
def test_gpu_wait_requires_a_warm_compatible_lds_slot(self):
|
|
source = (ROOT / 'tools/d4r_nvngx_shim.cpp').read_text()
|
|
begin = source.index('static bool motion_dilation_parameters(')
|
|
end = source.index('static CudaObject prepare_dilated_motion(', begin)
|
|
program = r'''
|
|
#include "d4r_motion_dilation.h"
|
|
#include <cassert>
|
|
#include <cmath>
|
|
#include <cstddef>
|
|
using CudaObject = uint64_t;
|
|
static unsigned radius = 1;
|
|
static unsigned env_uint(const char*, unsigned) { return radius; }
|
|
struct HostPlane { unsigned width=20, height=20; size_t rowBytes=128; size_t size() const { return rowBytes*height; } };
|
|
struct InputSlot {
|
|
HostPlane host[3];
|
|
struct { uint64_t device=1; } vram[3];
|
|
uint64_t dilatedMotion=3, dilatedTexture=4;
|
|
size_t dilatedBytes=2560, dilatedPitch=128;
|
|
unsigned dilatedWidth=20, dilatedHeight=20;
|
|
bool dilationEnqueued=false;
|
|
};
|
|
struct Feature { unsigned flags=2, outWidth=40, outHeight=40; bool linearInputs=true; };
|
|
struct FrameParams {
|
|
unsigned renderWidth=17, renderHeight=19;
|
|
float jitterX=.25f, jitterY=-.25f;
|
|
bool vram=true;
|
|
unsigned colorBaseX=0, colorBaseY=0, depthBaseX=0, depthBaseY=0,
|
|
mvBaseX=0, mvBaseY=0, outputBaseX=0, outputBaseY=0;
|
|
};
|
|
struct { struct { void* dilateMotion=(void*)1; void* dilateMotionPadded=(void*)1; } cu; } g;
|
|
''' + source[begin:end] + r'''
|
|
int main() {
|
|
Feature f; InputSlot slot; FrameParams p;
|
|
assert(!motion_dilation_gpu_wait_ready(f,slot,p));
|
|
slot.dilationEnqueued=true;
|
|
assert(motion_dilation_gpu_wait_ready(f,slot,p));
|
|
radius=2; assert(motion_dilation_gpu_wait_ready(f,slot,p));
|
|
auto changed=slot; changed.host[2].rowBytes+=4;
|
|
assert(!motion_dilation_gpu_wait_ready(f,changed,p));
|
|
changed=slot; ++changed.host[2].width;
|
|
assert(!motion_dilation_gpu_wait_ready(f,changed,p));
|
|
changed=slot; ++changed.host[2].height;
|
|
assert(!motion_dilation_gpu_wait_ready(f,changed,p));
|
|
changed=slot; changed.dilatedTexture=0;
|
|
assert(!motion_dilation_gpu_wait_ready(f,changed,p));
|
|
changed=slot; changed.dilatedBytes=0;
|
|
assert(!motion_dilation_gpu_wait_ready(f,changed,p));
|
|
g.cu.dilateMotionPadded=nullptr;
|
|
assert(!motion_dilation_gpu_wait_ready(f,slot,p));
|
|
g.cu.dilateMotionPadded=(void*)1;
|
|
p.depthBaseX=1; assert(!motion_dilation_gpu_wait_ready(f,slot,p));
|
|
p.depthBaseX=0; f.flags=6; assert(!motion_dilation_gpu_wait_ready(f,slot,p));
|
|
f.flags=0; f.outWidth=20; f.outHeight=20;
|
|
assert(!motion_dilation_gpu_wait_ready(f,slot,p)); // mapped display-res fallback
|
|
f.flags=2; p.renderWidth=21;
|
|
assert(!motion_dilation_gpu_wait_ready(f,slot,p)); // invalid allocation
|
|
radius=0; assert(motion_dilation_gpu_wait_ready(f,slot,p)); // dilation off
|
|
}
|
|
'''
|
|
with tempfile.TemporaryDirectory() as temporary:
|
|
runner = Path(temporary)/'submission'
|
|
subprocess.run(['c++', '-std=c++17', '-Wall', '-Wextra', '-Werror', '-I', str(ROOT/'tools'),
|
|
'-x', 'c++', '-', '-o', str(runner)], input=program, text=True,
|
|
check=True, capture_output=True)
|
|
subprocess.run([str(runner)], check=True, timeout=5)
|