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.
43 lines
2.1 KiB
Python
43 lines
2.1 KiB
Python
"""Conversion labels must belong to the older Vulkan query slot, not this frame."""
|
|
from pathlib import Path
|
|
import subprocess
|
|
import tempfile
|
|
import unittest
|
|
|
|
ROOT=Path(__file__).resolve().parents[1]
|
|
|
|
|
|
class VramProfileTimingTests(unittest.TestCase):
|
|
def test_older_slot_mode_labels(self):
|
|
source=(ROOT/'tools/d4r_nvngx_shim.cpp').read_text()
|
|
start=source.index('static void read_profile_timestamps(Feature& feature, uint32_t frame, FrameTiming& timing)\n{')
|
|
end=source.index('\n}\n',start)+3
|
|
program=r'''
|
|
#include <cassert>
|
|
#include <cstdint>
|
|
constexpr unsigned kOutputSlots=4;
|
|
struct FrameTiming {double vkInput=-1,vkDlssWait=-1,vkOutput=-1,vkTotal=-1;int vkOutputFused=-1,vkInputFused=-1;};
|
|
struct Feature {uint64_t values[16]={};volatile uint64_t* timestampValues=values;double timestampTicksPerMs=10;
|
|
uint8_t timestampOutputFused[4]={},timestampInputFused[4]={};bool recordOutputFused=true,recordInputFused=true;};
|
|
''' + source[start:end] + r'''
|
|
int main() {
|
|
Feature f;FrameTiming old;
|
|
f.values[0]=10;f.values[1]=20;f.values[2]=50;f.values[3]=60;
|
|
f.timestampOutputFused[0]=0;f.timestampInputFused[0]=1;
|
|
read_profile_timestamps(f,300,old); // frame 296 used transfer output, despite current mode switching on
|
|
assert(old.vkOutputFused==0 && old.vkInputFused==1 && old.vkTotal==5);
|
|
assert(!f.recordOutputFused && !f.recordInputFused && f.values[0]==0);
|
|
f.values[0]=70;f.values[1]=80;f.values[2]=110;f.values[3]=120;
|
|
f.timestampOutputFused[0]=1;f.timestampInputFused[0]=0;FrameTiming next;
|
|
read_profile_timestamps(f,304,next);
|
|
assert(next.vkOutputFused==1 && next.vkInputFused==0);
|
|
FrameTiming unavailable;read_profile_timestamps(f,308,unavailable);
|
|
assert(unavailable.vkOutputFused==-1 && unavailable.vkInputFused==-1 && unavailable.vkTotal==-1);
|
|
}
|
|
'''
|
|
with tempfile.TemporaryDirectory() as temp:
|
|
runner=Path(temp)/'timing'
|
|
subprocess.run(['c++','-std=c++17','-Wall','-Wextra','-Werror','-x','c++','-',
|
|
'-o',str(runner)],input=program,text=True,check=True,capture_output=True)
|
|
subprocess.run([str(runner)],check=True,timeout=5)
|