docs(perf): preserve runtime benchmark evidence
Record the sanitized six-minute CPU/GPU/memory audit, compact machine-readable metrics, checkpoint plateaus, attribution, reproduction method, and raw-artifact retention policy. Link the evidence from the consolidated architecture plan and roadmap without committing binary traces or session metadata. Co-authored-by: Codex <codex@openai.com>
This commit is contained in:
parent
944ee55584
commit
e627d9a403
5 changed files with 776 additions and 0 deletions
|
|
@ -1573,6 +1573,8 @@ port in any phase — no separate listing here.
|
|||
> memory audit reproduced a larger portal allocation/GC storm (approximately
|
||||
> 204 MiB in one frame, 276 ms maximum frame, 38 Gen-2 collections) while
|
||||
> confirming stable entity/effect/GPU plateaus and low steady GPU utilization.
|
||||
> The complete sanitized benchmark report is
|
||||
> [`2026-07-24-runtime-performance-audit.md`](../research/2026-07-24-runtime-performance-audit.md).
|
||||
> The user requested a detailed modern architecture plan. The resulting
|
||||
> [`2026-07-24-modern-runtime-architecture.md`](2026-07-24-modern-runtime-architecture.md)
|
||||
> unifies the unfinished MP pak/render-world work with future Track LH, preserves
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue