Repository navigation
Model L frame check on real weights: --model for the converter's model.wgcm; record - #133
Merged
Merged
Conversation
…ghts), largest difference and magnitudes per stage l_frame_check.py --prepare --model <model.wgcm> [--map <map>] runs the HIP frame check with the converter's Model L file in place of the synthetic model: the runtime checks it against the map (default: the shipped preset-L map) and the reference gets the values the file holds. Synthetic frames as before; the model file stays in the build folder. The summary now gives per stage the largest difference, the non-finite values on each side and the largest finite magnitude on each side. Refs #89 Signed-off-by: phantoslayer21 <156617979+phantoslayer21@users.noreply.github.com>
…frame Signed-off-by: phantoslayer21 <156617979+phantoslayer21@users.noreply.github.com>
…frame Signed-off-by: phantoslayer21 <156617979+phantoslayer21@users.noreply.github.com>
phantoslayer21
marked this pull request as ready for review
November 14, 2026 03:27
This was referenced Nov 14, 2026
Merged
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Model L's HIP frame (#111) on real weights:
clean/l/runner/l_frame_check.py --prepare --model <model.wgcm>runsthe frame check with the converter's Model L file in place of the synthetic model. The runtime loads it through
l::load_wgcm_modeland checks it against the map (default: the shippeddata/preset-L.v1.map.json); the CPUreference gets the values the file holds. Frames stay synthetic. The model file stays in the build folder and is
never part of the repository; only its digest is recorded.
The summary now also gives, per stage, the largest difference, the non-finite values on each side and the largest
finite magnitude on each side (saturation would show as one side stopping where the other goes on).
What changes
clean/l/runner/l_frame_check.py:--model/--map(with--prepareonly; refused otherwise), asource.jsonbeside the model (synthetic seed, or the file's and map's SHA-256), carried into the JSON;got_absmax/ref_absmax/ref_nonfinitein the FP8 and FP16 metrics;max_diff,nonfinite,ref_nonfiniteand the magnitudes in the per-stage summary. The pass rules are unchanged.Record
The model:
WrongGPU.exe model convert --preset=L --model=<the game's upscaler DLL> --noscan, the launcher built frommain dbdfaff. As the launcher reports it: file version 310.9.1.0, DLL SHA-256
3975567b8943c53acce397f2b72380092f84f162d00b0d2c7d08a1025c563983; map SHA-25658e6d0e7…e857(preset-L v1.1);"all 15 stage digests match";
model.wgcmSHA-256d3c040191ec7ab0164efc03ee76413277e7fb54e6e6d2b168f2c0202aa1ad806.The run: this branch (main dbdfaff + this commit), Model M's code objects from
clean.runner.build --no-runtime --no-model-k, then--prepare(synthetic) and--prepare --model(real) in two build folders;--runin a lockedGPU slot (
gpu_slot.py --cap-s 170, 2.0 s each, no wait),--compareon the CPU. Re-run on the merged head 262482c (main 26eb21e with #131, #132, #134 + this commit), same GPU-slot procedure (2.0 s): every per-stage summary identical to the first run, same single failure. Same 11 frames as #111 (96 x 64x 5, 80 x 48 x 3, 77 x 45 x 3; resets on frames 0, 2, 5, 8, 9; both parities). Post kernel
post_recon2_r_band.Result: real-weight Model L fails its post rule on 1 of 11 frames (frame 6, 80 x 48, not a reset). Every other
stage passes on all 11 frames; frame state, exposure (11 / 11 identical) and default-kernels-vs-six-launch (11 / 11
byte-identical) pass. The synthetic Model L and the Model M control pass everything, as in #111.
Values differing / values compared (largest difference: FP8 steps under the per-stage rule, FP16 ulps, or codes):
Real-weight findings, plainly:
80 x 48 render) is 12 / 79 / 78 FP16 ulps off in its three channels, and the reduced history there is 6 and 3 codes
off. The rule allows 1 code, so the frame fails. History and display themselves pass the FP16 acceptance on that
frame (5.1e-5 of values over 1 ulp; rule 1e-4). Post runs on the runtime's own A, B, C, so the difference is inside
the post kernel against
clean/reference/post.pyat that pixel, not in the decoder.model stays within +-7.57. The synthetic check never exercised this range. C reaches 64.0 exactly in both the
runtime and the reference (C differs in only 31 values). Largest C difference 313 FP16 ulps (frame 8, 6 values);
within the 99.5 % rule.
dec1 (37); all within the per-stage rule (worst enc0 frame: 0.11 % of values more than one step off; rule 2 %).
on both sides in every stage (no clipping on one side); the bottleneck reaches 256 (b4) against 18 synthetic.
Nothing was tuned; the rules are #111's.
Tested
current main).
py_compileof the script; the existing synthetic path unchanged apart from the extra summary fields.Not tested
Refs #89