- engine/compile_rr2.py, runtime_rr2.inc, engine/rr/rr2_m.comp, exposure_f.comp, gen_rr2_enc0.py, rr2_pack.py, rr2_ref.py: the rr2_* model (nvngx_dlssd.dll 310.9's third network) as d4r's own shaders - exposure, enc0 gather/block split, enc1-5 and dec4-0 through one matrix shader, translated output passes; weights packed from the DLL, argument blocks from the capture - ptx2rr: match the driver's fused roundings - opaque-zero OR around cvt.rn.f16.f32 against v_fma_mix, half-away-from-zero formatted stores, UNORM 10:10:10:2 as RGBA32F of q/1023, OCML tanhF with the AMDGPU exp lowering, binary16 fma and fetch roundings; --probe for register bisection against ZLUDA - dec0_m/swin_m/enc0_*: RR_MIX build option (D4R_RR_MIX=1), one v_fma_mix rounding per 32-deep step, ~5% faster, not bit-exact; default build stays exact - runtime_rr.inc: RModel/REngine dispatch to the D4RR0002 model; replay_rr: RGBA32F and A2B10G10R1010 texel sizes, roughnessPacked bit, larger debug staging - shim: engine\rr-f model slot, 310.9 version probe so preset F is only claimed when the CUDA path has it; d4r.ini / d4r_config.py Model = F; run_rr_engine_compare.sh D4R_RR_DLL - kernels/rr/swin_native.h + rr_swin_native_test.cpp: HIP port of encoder 1 for the FP8-product and rounding cost measurements - engine/rr/README: preset F's block, options, capture-by-capture results, timings and the open camera-matrix difference
105 lines
5.9 KiB
Python
105 lines
5.9 KiB
Python
#!/usr/bin/env python3
|
|
"""Replay one captured denoiser launch through ZLUDA on Linux (tools/replay_rr_launch.cpp) and compare it with the
|
|
capture, like test_layer.py does for a stage shader.
|
|
|
|
usage: zluda_replay.py CAPTURE KERNEL FRAME WORK [--ptx MODULE] [--zluda DIR]
|
|
|
|
KERNEL and FRAME select the launch as in test_layer.py. MODULE defaults to the corpus module holding the kernel
|
|
(~/.cache/d4r-rr-corpus); pass an edited copy to add debug stores. ZLUDA's own settings (D4R_ZLUDA_WMMA,
|
|
D4R_ZLUDA_WMMA_FP8, D4R_ZLUDA_WMMA_FP8_NATIVE, ...) are taken from the environment. Outputs land in WORK
|
|
(surfOFFSET.bin, arena.out.bin) so the two replays can be compared with each other too.
|
|
"""
|
|
import argparse
|
|
import os
|
|
import subprocess
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
|
|
from rr_capture import Capture # noqa: E402
|
|
from test_layer import compare_arena, compare_image # noqa: E402
|
|
|
|
ROOT = Path(__file__).resolve().parents[2]
|
|
|
|
|
|
def main():
|
|
ap = argparse.ArgumentParser()
|
|
ap.add_argument('capture')
|
|
ap.add_argument('kernel')
|
|
ap.add_argument('frame', type=int)
|
|
ap.add_argument('work')
|
|
ap.add_argument('--ptx')
|
|
ap.add_argument('--zluda', default=os.path.expanduser('~/.cache/d4r-zluda-rr'))
|
|
ap.add_argument('--rocm', default='/opt/rocm/lib')
|
|
ap.add_argument('--tex', action='append', default=[], metavar='OFFSET=FILE:W:H',
|
|
help='an RGBA32F texture for a handle the capture has no dump of (preset F pooled histories)')
|
|
ap.add_argument('--pad', type=int, default=0, help='bytes of zeros appended to the arena (debug stores)')
|
|
o = ap.parse_args()
|
|
cap = Capture(o.capture)
|
|
exact = [l for l in cap.launches if l.kernel == o.kernel]
|
|
launch = (exact or [l for l in cap.launches if o.kernel in l.kernel and 'diamond' not in l.kernel or
|
|
('diamond' in o.kernel and o.kernel in l.kernel)])[o.frame - 1]
|
|
work = Path(o.work)
|
|
work.mkdir(parents=True, exist_ok=True)
|
|
corpus = '~/.cache/d4r-rr-corpus-f' if launch.kernel.startswith('rr2_') else '~/.cache/d4r-rr-corpus'
|
|
module = o.ptx or next(str(p) for p in sorted(Path(corpus).expanduser().glob('*.ptx'))
|
|
if f'.entry {launch.kernel}(' in p.read_text(errors='replace'))
|
|
(work / 'args.bin').write_bytes(launch.args)
|
|
arena = launch.arena_alloc
|
|
lines = [f'args {work}/args.bin', 'grid ' + ' '.join(map(str, launch.grid)),
|
|
'block ' + ' '.join(map(str, launch.block))]
|
|
if o.pad:
|
|
(work / 'arena-pad.bin').write_bytes(launch.pre(arena) + bytes(o.pad))
|
|
for p in launch.pointers:
|
|
out = f' {work}/arena.out.bin' if p.alloc == arena else ''
|
|
source = f'{work}/arena-pad.bin' if o.pad and p.alloc == arena else f'{launch.directory}/alloc-{p.alloc}.bin'
|
|
lines.append(f'buf {p.offset} {source} {p.delta}{out}')
|
|
# textures the launch names but the bridge could not read back (preset F's 10:10:10:2 pooled histories, which
|
|
# ZLUDA backs with RGBA32F): zeros, which is what they hold on a first frame
|
|
have = {i.offset for i in launch.images}
|
|
for line in (launch.directory / 'manifest.txt').read_text().split('\n'):
|
|
f = line.split()
|
|
given = {int(t.split('=')[0]): t.split('=')[1].split(':') for t in o.tex}
|
|
if len(f) == 2 and f[0] == 'texture' and int(f[1]) in given:
|
|
path, w_, h_ = given[int(f[1])]
|
|
lines.append(f'tex {f[1]} {path} {w_} {h_} 4 32 linear')
|
|
elif len(f) == 2 and f[0] == 'texture' and int(f[1]) not in have:
|
|
(work / 'zero16.bin').write_bytes(bytes(16 * 16 * 16))
|
|
lines.append(f'tex {f[1]} {work}/zero16.bin 16 16 4 32 linear')
|
|
if len(f) == 2 and f[0] == 'surface' and int(f[1]) not in have: # half the largest surface: the pooled history
|
|
big = max((i for i in launch.images if i.kind == 'surface'), key=lambda i: i.width, default=None)
|
|
if big is not None:
|
|
lines.append(f'surf {f[1]} {big.width // 2} {big.height // 2} 4 32 {work}/surf{f[1]}.bin')
|
|
for image in launch.images:
|
|
if image.kind == 'texture':
|
|
# SNORM_INT8X4 (200): a SIGNED_INT8 array read as normalized floats gives the same values
|
|
fmt = 8 if image.format == 200 else 1 if image.format == 194 else image.format
|
|
lines.append(f'tex {image.offset} {image.path} {image.width} {image.height} {image.channels} '
|
|
f'{fmt} {"linear" if image.linear else "nearest"}')
|
|
else:
|
|
# ZLUDA has no SNORM_INT8X4 arrays (format 200); surface stores write the same bytes to a SIGNED_INT8 one
|
|
fmt = 8 if image.format == 200 else 1 if image.format == 194 else image.format # 194: UNORM_INT8X4
|
|
lines.append(f'surf {image.offset} {image.width} {image.height} {image.channels} {fmt} '
|
|
f'{work}/surf{image.offset}.bin')
|
|
(work / 'manifest').write_text('\n'.join(lines) + '\n')
|
|
env = dict(os.environ, LD_LIBRARY_PATH=f'{o.zluda}:{o.rocm}:' + os.environ.get('LD_LIBRARY_PATH', ''))
|
|
print(f'{launch.kernel} (launch {launch.sequence}) through ZLUDA {o.zluda}')
|
|
r = subprocess.run([str(ROOT / 'build/replay_rr_launch'), module, launch.kernel, str(work / 'manifest')],
|
|
env=env, capture_output=True, text=True)
|
|
sys.stdout.write(r.stdout)
|
|
if r.returncode:
|
|
sys.stderr.write(r.stderr[-4000:])
|
|
sys.exit('replay failed')
|
|
same = True
|
|
for image in launch.images:
|
|
if image.kind == 'surface':
|
|
same &= compare_image(f'surface {image.offset}', image, (work / f'surf{image.offset}.bin').read_bytes(),
|
|
image.path.read_bytes())
|
|
if arena is not None and not o.pad:
|
|
same &= compare_arena((work / 'arena.out.bin').read_bytes(), launch.pre(arena), launch.post_buffer(cap, arena))
|
|
print('IDENTICAL' if same else 'DIFFERENT')
|
|
|
|
|
|
if __name__ == '__main__':
|
|
main()
|