ayo
247fe1092d
Implement native NGX feature-13 RR through a LUID-matched D3D12/Vulkan shared-memory and timeline-fence bridge. Add owned parameter snapshots, GPU resource lifetime handling, inherited/enhanced barriers, optional guides, sampled input formats and depth-plane support with stencil preservation. Separate RR initialization from the SR CUDA runtime and expose explicit backend/model selection through player configuration. Add synthetic bridge, snapshot and NGX lifecycle harnesses covering camera/history/reset, parameter mutation, delayed submission, early release, capability gating and unsupported-input rejection. Add exact gfx11 D/E model generation, verified caches, versioned local deployment with configuration backups, and isolated portable model tools with pinned Python, NumPy and glslang dependencies. Extend Windows K benchmarking and private native-cache selection. Fix LLVM 22 emitter/helper compatibility and preserve exact-output validation for local output-kernel optimization. Add native FSR RR provider diagnostics, local development package refresh tooling, installer/checker updates, FidelityFX headers and Windows parity documentation. Keep NVIDIA binaries, derived models and private optimized kernels out of distributable packages. Native RR evidence remains synthetic; game validation, FSR RR dispatch, installer integration and Linux performance parity remain incomplete.
54 lines
2.2 KiB
Python
54 lines
2.2 KiB
Python
import math
|
|
from pathlib import Path
|
|
import random
|
|
import re
|
|
import struct
|
|
import sys
|
|
import unittest
|
|
|
|
sys.path.insert(0, str(Path(__file__).resolve().parents[2] / 'tools/windows'))
|
|
from llvm22_ir import compatible_ir, float_hex
|
|
|
|
|
|
class CompatibilityTests(unittest.TestCase):
|
|
def test_float_widening_preserves_finite_values(self):
|
|
rng = random.Random(22)
|
|
patterns = [rng.getrandbits(32) for _ in range(20000)]
|
|
patterns += [(sign << 31) | (exponent << 23) | mantissa
|
|
for sign in (0, 1) for exponent in range(255)
|
|
for mantissa in (0, 1, 0x3fffff, 0x400000, 0x7fffff)]
|
|
for bits in patterns:
|
|
value = struct.unpack('>f', bits.to_bytes(4, 'big'))[0]
|
|
if not math.isfinite(value):
|
|
continue
|
|
rendered = float_hex(re.match(r'(.*)', f'{bits:08X}'))
|
|
self.assertEqual(bytes.fromhex(rendered[2:]), struct.pack('>d', value))
|
|
|
|
def test_nan_payload_and_signaling_bit_preserved(self):
|
|
for source, expected in [('7F800001', '0x7FF0000020000000'),
|
|
('FFC00001', '0xFFF8000020000000')]:
|
|
self.assertEqual(float_hex(re.match(r'(.*)', source)), expected)
|
|
|
|
def test_decimal_half_and_float(self):
|
|
result = compatible_ir('%a = fcmp ult float %x, 8.507060e+37\n'
|
|
'%b = fmul half %h, 1.953130e-03\n')
|
|
self.assertIn('0x47D0000020000000', result)
|
|
self.assertIn('0xH1800', result)
|
|
|
|
def test_double_and_strings_not_rounded_to_float(self):
|
|
text = '%a = fmul double %x, 1.23456789012345e+00\n!0 = !{!"float 1.234567e+00"}\n'
|
|
self.assertEqual(compatible_ir(text), text)
|
|
|
|
def test_denormal_mode_and_conservative_promises(self):
|
|
result = compatible_ir('attributes #0 = { denormal_fpenv(dynamic) '
|
|
'nocreateundeforpoison memory(read, target_mem: none) }\n'
|
|
'%x = uitofp contract nneg i32 %v to double\n')
|
|
self.assertIn('"denormal-fp-math"="dynamic,dynamic"', result)
|
|
self.assertNotIn('nocreateundeforpoison', result)
|
|
self.assertNotIn('target_mem', result)
|
|
self.assertIn('uitofp nneg i32', result)
|
|
|
|
|
|
if __name__ == '__main__':
|
|
unittest.main()
|