Record live ray comparison without claiming a performance improvement
This commit is contained in:
@@ -0,0 +1,71 @@
|
||||
{
|
||||
"schema": 1,
|
||||
"minecraft": "26.3",
|
||||
"entity_culling": "1.11.2",
|
||||
"original_mod_sha256": "7351b417fc83460def5947636444413874ee812e949342f091ef03674e0c0e58",
|
||||
"platform": "Linux x86_64",
|
||||
"graphics": "llvmpipe software OpenGL",
|
||||
"settings": {
|
||||
"heap_bytes": 3221225472,
|
||||
"gc": "G1",
|
||||
"compact_headers": true,
|
||||
"render_distance": 12,
|
||||
"simulation_distance": 12,
|
||||
"lod_radius_chunks": 128,
|
||||
"lod_quality": "MEDIUM/MEDIUM/BLOCK",
|
||||
"terrain_workers": 2,
|
||||
"runtime_ratio": 0.5,
|
||||
"world_difficulty": "PEACEFUL",
|
||||
"empty_culling_whitelist": false
|
||||
},
|
||||
"results": [
|
||||
{
|
||||
"profile": "m2-balanced",
|
||||
"ray_enabled": false,
|
||||
"elapsed_seconds": 120.02619604,
|
||||
"frame_samples": 599,
|
||||
"tick_samples": 2400,
|
||||
"excluded_frames": 0,
|
||||
"dropped_samples": 0,
|
||||
"visual_settings_changed": [],
|
||||
"culling_allocation_counter": {
|
||||
"thread_id": 49,
|
||||
"thread": "CullThread",
|
||||
"counter_observations": 2,
|
||||
"observed_seconds": 64.509265987,
|
||||
"observed_allocated_bytes": 1817768,
|
||||
"observed_bytes_per_second": 28178.40153949851
|
||||
}
|
||||
},
|
||||
{
|
||||
"profile": "culling-rays",
|
||||
"ray_enabled": true,
|
||||
"elapsed_seconds": 120.099980458,
|
||||
"frame_samples": 584,
|
||||
"tick_samples": 2401,
|
||||
"excluded_frames": 0,
|
||||
"dropped_samples": 0,
|
||||
"visual_settings_changed": [],
|
||||
"culling_allocation_counter": {
|
||||
"thread_id": 49,
|
||||
"thread": "CullThread",
|
||||
"counter_observations": 2,
|
||||
"observed_seconds": 64.321034235,
|
||||
"observed_allocated_bytes": 1798336,
|
||||
"observed_bytes_per_second": 27958.754416629756
|
||||
}
|
||||
}
|
||||
],
|
||||
"notes": [
|
||||
"Fixed-order single pair using separate copies of the same private saved world and stationary view, with approximately three-minute warm-up before clean frame recordings.",
|
||||
"One earlier candidate frame capture contained pause exclusions and was discarded; its separate preceding allocation recording had already completed.",
|
||||
"Allocation counters have their own roughly 64-second observation spans; recordings started approximately 36-42 seconds after joining. Profiling overhead and JIT/cache effects are not eliminated.",
|
||||
"Both worlds saved and exited with no crash report or remaining game process. The outer foreground control launcher returned 143; it did not expose the game exit status.",
|
||||
"No useful allocation reduction or whole-game speedup is established. Not a Mac, retained-memory or GPU performance benchmark."
|
||||
],
|
||||
"provenance": {
|
||||
"source_commit": "349724b3b612351daa1616daa79beca8897839ab",
|
||||
"runtime_mod_matches_linux_ci": true,
|
||||
"workflow_run": "https://github.com/ludovic111/minecraft-optimization-lab/actions/runs/37168818519"
|
||||
}
|
||||
}
|
||||
@@ -47,6 +47,21 @@ include source and workflow provenance. This is not a whole-game FPS/RAM or Mac
|
||||
GPU benchmark; repeated real hardware comparisons and live allocation profiles
|
||||
are required.
|
||||
|
||||
A fixed-order live Linux software-rendering pair observed about 28.18 KB/s
|
||||
allocated by `CullThread` with the hook off and 27.96 KB/s with it on, over
|
||||
roughly 64-second counter spans. This does not establish a useful reduction.
|
||||
Allocation samples were dominated by whitelist iteration; the recorded stacks
|
||||
did not include either ray constructor. The separate `culling-empty` experiment
|
||||
addresses that observed path. The clean 120-second frame captures produced
|
||||
599 control and 584 candidate frames, with zero exclusions and matching CSV
|
||||
counts; captured graphics and worker settings matched except the ray flag.
|
||||
Both worlds saved and exited without crash reports or remaining game processes.
|
||||
The outer control launcher returned 143 without exposing the game exit status;
|
||||
that return is not counted as a verified normal game exit. Selected
|
||||
[live observations](../benchmarks/culling-rays-2026-10-04/live-observations.json)
|
||||
retain the recording limits. These are per-thread diagnostic observations, not
|
||||
retained memory, a statistical comparison, or a Mac result.
|
||||
|
||||
The factory hook follows the upstream [Mixin constructor redirect contract](https://github.com/SpongePowered/Mixin/blob/master/src/main/java/org/spongepowered/asm/mixin/injection/Redirect.java).
|
||||
Compilation uses a checksum-verified publisher JAR; the release mod contains only
|
||||
original Horizon classes. Profiles without Entity Culling must still load.
|
||||
|
||||
Reference in New Issue
Block a user