3D engine that AI agents drive
Add measured tier tables to the README and home page (Part of #890)
Nguyen Xuan An59a842444338
diff --git a/README.md b/README.mdindex 875db22a..bfc46d8b 100644--- a/README.md+++ b/README.md@@ -30,7 +30,25 @@ The names are working names. Draft is a low-resolution Glaze frame with cheap liRealtime-high is planned: Glaze on WebGPU with GPU-driven geometry, cached global illumination and temporal upscaling ([issue 901](https://github.com/codepawl/67.js/issues/901) and [issue 902](https://github.com/codepawl/67.js/issues/902)).It does not exist yet. The `quality` setting that picks a tier is planned too ([issue 904](https://github.com/codepawl/67.js/issues/904)), and so is refine-at-rest ([issue 903](https://github.com/codepawl/67.js/issues/903)).-<!-- tiers-table -->+### Measured tiers++One scene (`lit-interior`, 960x540), medians with ranges over 3 interleaved runs. The error column is FLIP against a Cycles 4096-sample reference, lower is better. The other five reference scenes were not run. The source is [`bench/tiers`](https://github.com/codepawl/67.js/tree/main/bench/tiers) from [pull request 931](https://github.com/codepawl/67.js/pull/931), which builds on [pull request 921](https://github.com/codepawl/67.js/pull/921).++| Tier | What runs it today | 67js time | Blender equivalent and its time | FLIP error | Card memory (shared) |+| --- | --- | --- | --- | --- | --- |+| draft (working name) | Glaze, 0.5 render scale, 1 sample | 1.20 ms per frame (0.88 to 2.43) | EEVEE 5.3 at 1 sample: 99 ms per render call (76 to 157) | Glaze 0.188, EEVEE 0.562 | Glaze +62 MiB, EEVEE +2,218 MiB |+| realtime | Glaze, default settings | 1.11 ms per frame (1.05 to 1.24) | EEVEE 5.3 defaults: 1,127 ms per render call (716 to 1,891) | Glaze 0.197, EEVEE 0.562 | Glaze +119 MiB, EEVEE +2,503 MiB |+| realtime-high | Planned ([issue 901](https://github.com/codepawl/67.js/issues/901), [issue 902](https://github.com/codepawl/67.js/issues/902)) | not measurable yet | none | none | none |+| final | Cook native (Vulkan ray queries) | 6.05 ms per sample (4.7 to 6.4), 1.9 s at 256 samples | Cycles 5.3 OptiX: 36.2 ms per sample (28.7 to 220), 12.6 s at 256 samples | Cook 0.080, Cycles 0.039, both at 256 samples | Cook +622 MiB, Cycles +733 MiB |+| final | Cook webgpu (WGSL compute, software BVH) | 34.4 ms per sample (22.6 to 60.6) | same Cycles | same as native at the same samples | +456 MiB |+| final | Cook gpu (WebGL2) | 74.4 ms per sample (57.3 to 79.2), plus 4.8 to 7.9 s of shader compile | same Cycles | same as native at the same samples | +496 MiB |+| final | Cook cpu (JavaScript, 8 threads) | 786 ms per sample (561 to 1,022) | same Cycles | same as native at the same samples | not a card job |++The experimental real-time path tracer is not the realtime-high tier. On the WebGPU backend it draws a frame in 5.6 ms, reaches FLIP under 0.20 after 16 frames (0.15 s) and under 0.10 after 64 frames (0.41 s), and ends at 0.056 after 256 frames. The WebGL2 fallback takes 6.7 ms per frame and 6.1 s for the first frame, which includes shader compile. It runs at 2 bounces against an 8-bounce reference.++The draft tier is not faster than realtime here: at 960x540 a Glaze frame costs about as much as the browser's pixel read, and the ranges overlap. Cook native draws a sample faster than Cycles but needs more samples for the same error, so at equal error the two are about equal (see [pull request 921](https://github.com/codepawl/67.js/pull/921) for the one-scene comparison and its conditions).++Machine: RTX 3060 12 GB, Intel i7-14700KF, headless Chrome 157 on D3D11, Node 24, Blender 5.3, measured 2026-11-11. The card was shared with other jobs in every run, so the ranges are wide. Card memory is the card-wide change while the job ran, an upper bound. EEVEE time is a full background render call, with ray tracing off.## Showcasediff --git a/changes/890-renderer-copy.md b/changes/890-renderer-copy.mdindex cc4c71f4..04a5295f 100644--- a/changes/890-renderer-copy.md+++ b/changes/890-renderer-copy.md@@ -1 +1,2 @@- The README, home page, `llms.txt`, package keywords and plugin text name every renderer backend (Glaze on WebGL2, Cook on CPU, WebGL2, WebGPU and Vulkan) and give measured numbers (#890)+- The README and home page show a measured tier table (lit-interior, 960x540) from `bench/tiers`, with the realtime-high tier marked as planned (#890)diff --git a/index.html b/index.htmlindex 87c9fef5..8ae77bff 100644--- a/index.html+++ b/index.html@@ -174,6 +174,21 @@ renderer.render({ eye: [58, 31, 84], target: [-8, 3, -18] });</code></pre></div></section>+ <section id="tiers" class="tiers" aria-labelledby="tiers-title">+ <h2 id="tiers-title">Quality tiers, measured</h2>+ <p>One scene at 960x540 on an RTX 3060 shared with other jobs. Medians of 3 runs. FLIP is the error against a Cycles 4096-sample reference, lower is better. Tier names are working names, and the <code>quality</code> setting that picks one is planned. Source: <a href="https://github.com/codepawl/67.js/pull/931">bench/tiers</a>, built on <a href="https://github.com/codepawl/67.js/pull/921">the Cook against Cycles run</a>.</p>+ <ul class="tier-list">+ <li class="tier-row tier-head" aria-hidden="true"><span>Tier</span><span>Runs on</span><span>67js</span><span>Blender</span><span>FLIP error</span></li>+ <li class="tier-row"><span data-label="Tier">draft</span><span data-label="Runs on">Glaze, 0.5 scale, 1 sample</span><span data-label="67js">1.20 ms per frame</span><span data-label="Blender">EEVEE 1 sample: 99 ms</span><span data-label="FLIP error">0.188 (EEVEE 0.562)</span></li>+ <li class="tier-row"><span data-label="Tier">realtime</span><span data-label="Runs on">Glaze, defaults</span><span data-label="67js">1.11 ms per frame</span><span data-label="Blender">EEVEE defaults: 1,127 ms</span><span data-label="FLIP error">0.197 (EEVEE 0.562)</span></li>+ <li class="tier-row"><span data-label="Tier">realtime-high</span><span data-label="Runs on">Planned, issues 901 and 902</span><span data-label="67js">not measurable yet</span><span data-label="Blender">none</span><span data-label="FLIP error">none</span></li>+ <li class="tier-row"><span data-label="Tier">final</span><span data-label="Runs on">Cook native, Vulkan</span><span data-label="67js">6.05 ms per sample</span><span data-label="Blender">Cycles OptiX: 36.2 ms per sample</span><span data-label="FLIP error">0.080 (Cycles 0.039)</span></li>+ <li class="tier-row"><span data-label="Tier">final</span><span data-label="Runs on">Cook webgpu</span><span data-label="67js">34.4 ms per sample</span><span data-label="Blender">same Cycles</span><span data-label="FLIP error">same as native</span></li>+ <li class="tier-row"><span data-label="Tier">final</span><span data-label="Runs on">Cook gpu, WebGL2</span><span data-label="67js">74.4 ms per sample</span><span data-label="Blender">same Cycles</span><span data-label="FLIP error">same as native</span></li>+ <li class="tier-row"><span data-label="Tier">final</span><span data-label="Runs on">Cook cpu, 8 threads</span><span data-label="67js">786 ms per sample</span><span data-label="Blender">same Cycles</span><span data-label="FLIP error">same as native</span></li>+ </ul>+ </section>+<section id="documentation" class="documentation-links" aria-labelledby="documentation-title"><h2 id="documentation-title">Documentation</h2><div class="doc-links">diff --git a/src/site.css b/src/site.cssindex eb761b2b..7ff48341 100644--- a/src/site.css+++ b/src/site.css@@ -376,3 +376,18 @@ body.site > main > section { scroll-margin-top: 96px; }.site .size-bar-fill.is-other {background: #ffffff36;}++/* Measured tiers */+.site .tiers { display: grid; gap: 14px; }+.site .tiers p { color: var(--muted); max-width: 70ch; }+.site .tiers p a { text-decoration: underline; }+.site .tier-list { display: grid; gap: 6px; margin: 0; padding: 0; list-style: none; }+.site .tier-row { display: grid; grid-template-columns: 1fr 1.6fr 1.3fr 1.8fr 1.4fr; gap: 12px; padding: 12px 16px; border-radius: var(--panel-radius); background: var(--bg); font-size: 13.5px; }+.site .tier-row > span { min-width: 0; overflow-wrap: anywhere; }+.site .tier-row > span:first-child { color: var(--text); font-weight: 600; }+.site .tier-head { background: none; padding-top: 0; padding-bottom: 0; color: var(--muted); font-size: 12.5px; }+@media (max-width: 760px) {+ .site .tier-head { display: none; }+ .site .tier-row { grid-template-columns: 1fr; gap: 4px; }+ .site .tier-row > span[data-label]:not(:first-child)::before { content: attr(data-label) ": "; color: var(--muted); }+}