Repository navigation
Donkey Kong Bananza on an iPhone 17 Pro Max: what was measured and what was not, in the game note - #1204
Closed
oliverames wants to merge 1 commit into
Closed
Donkey Kong Bananza on an iPhone 17 Pro Max: what was measured and what was not, in the game note#1204oliverames wants to merge 1 commit into
oliverames wants to merge 1 commit into
Conversation
github-actions
Bot
added
docs
2 of 3 tasks
oliverames
force-pushed
the
dkb-iphone-measurements-note
branch
from
November 5, 2026 20:06
983f278 to
67a0b92
Compare
…at was not, in the game note The note said iOS was untested. The update now runs a saved gameplay spot on an iPhone 17 Pro Max (A19 Pro, iOS 27.2), so the note gets an iPhone measurements section instead: the scene size and upscaler (1676x943 into MetalFX's 2304x1296, the game's 2880x1620 window presented into a 2346x1320 drawable), the encoder timings of 33 sampled frames at thermal state 2, a 70-second route on a combined local build at thermal state 0 (six windows at p99 33.34 ms, 5131 MiB footprint, 3060 MiB headroom), and the handheld and docked reruns that did not hold 30 fps. Every number comes from a log in the session's evidence folder, and each feature that is not on main (drawable capture, the native-size window copy, the scaler size log) is named with its PR. The section ends with what is not established: sustained frame rate under heat, every-dispatch scene sizes, a handheld rate above 30 fps and any change to the fur's shimmer. The intro and the Open list drop "iOS untested" and point at the section.
oliverames
force-pushed
the
dkb-iphone-measurements-note
branch
from
November 6, 2026 21:05
2efea10 to
c2d30c4
Compare
Contributor
Author
|
Merged into #1369 to combine doc-only updates into a single PR. |
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.
What and why
The Donkey Kong Bananza note says iOS is untested. The game now runs a saved gameplay spot on a physical iPhone 17 Pro Max, and the measurements so far are scattered across session logs. This PR records them in the note as an "iPhone measurements" section, replaces the two "iOS untested" mentions with a pointer to it, and changes nothing else (docs only, no code, no profile).
@seedds: this is a note for Switch 2 games running on iPhone. Every number is from a local build that carried changes not on
main, and the section says so. Features that live only in an open PR are named with it (#1136 drawable capture and thepresent dimensionsline, #1140 native-size window copy, #1167 scaler size log, #1032 / #1203 border-colour shader split) and are never described as present. Claims that a log does not support are left out: no shimmer fix, no pacing fix, no sustained-30-fps claim. The section ends with a "Not established" paragraph.Overlap to know about: #1101 edits the same intro line and the "iOS untested" bullet (a player's 30-minute report on iOS 27.0.1), and #1032 / #1203 add DKB README lines. Whichever lands first, the other needs a small manual merge in the intro and the Open list; the measurements section itself is independent and its anchor is
#iphone-measurements.Checked
python3 dm/tools/tests/test_docs.py(11 tests OK, links and anchors);python3 dm/tools/docs_symptoms.pyandpython3 dm/tools/docs_patches.py(no diff),python3 dm/tools/docs_gallery.py(no diff). Nothing else applies to a docs-only change; no code, no CI-scoped tool touched.040074A01BF12000v458752.mainas it stands, so there is no exact-head iPhone run. The phone runs used mixed local builds (for examplec7ba23df0872+dirty, executable SHA-25637de3a284c1e27176d3d274fd7384ae9d99d6d6aef1659cbd7f24380866551fafor the215a6d278114run). Thermal states differed between runs, so no run is a controlled comparison of another. Hosted CI for this PR had not finished when it was opened.Evidence, all under
anygame/logs/dkb-sharpness-2026-11-03/(kept by the author, not in this repository):95ba69b5403e, MetalFX 1676x943 to 2304x1296, windows at 50 ms then 33.34 mscurrent-metalfx-log.txt(scaler line 1010),env-current-metalfx-readback.txt215a6d278114: six 300-frame windows p99 33.34 ms, 0 drops, thermal 0; 5131 MiB footprint, 3060 MiB headroom; 16 of 16 bases; audio 209 msborder-summary.json,border-final-log.txt,border-final-memstat.tsvmesh-summary.jsonborder-handheld-summary.jsonborder-restored-summary.jsonnative-prof-route-analysis.json,native-prof-final-log.txt(interval lines 14889 and 15536)[gpuprof]lines ofnative-prof-final-log.txtwindow-live-final-log.txtwindow-vertex-final-log.txt(line 160)recovered-user-handoff.md, WORKLOG entry on the installed MetalFX hostDocs
python3 dm/tools/docs_symptoms.pywas run (no change)