docs: architecture backlog — correct fleet hardware mapping #4

2026-05-23T13:48:31Z

marfrit commented

2026-05-23 13:48:31 +00:00

Fixes factual errors in the per-SoC host table from PR #3.

What was wrong

Original draft put hertz and tesla under RK3588 and omitted boltzmann + noether entirely. Verified via /proc/device-tree/compatible:

Host	Original draft	Reality
hertz	RK3588	Pi 5 (BCM2712)
tesla	RK3588	Pi 5 (BCM2712) (LXD container on hertz)
boltzmann	omitted	RK3588 (the only actual RK3588 in the fleet)
noether	omitted	Pi 4 (BCM2711) — the user's interactive workstation

Corrected mapping

BCM2712 Pi 5  — higgs, hertz, broglie, tesla (LXD on hertz)
BCM2711 Pi 4  — noether (workstation), dcw3, dcw2
RK3588        — boltzmann (32 GB, kernel-dev / MCP hub, 8 W always-on)
Allwinner H6  — (not in fleet)

Reasoning consequences

Pi 5 row is four hosts but one SoC. Adding a fifth Pi 5 doesn't pressure-test the architecture; substrate decisions are identical across the row.
Pi 4 forcing function is closer than the draft implied. noether is a daily-driver workstation; once HW decode on it becomes a real ask and rpivid is still unstable upstream, the substrate-composed path with V3D4 + NEON becomes the right backend and the caps-file mechanism is needed.
RK3588 forcing function via boltzmann + AV1. rkvdec doesn't cover AV1, so Mali Valhall compute substrate becomes the only HW acceleration option there. Triggers a cycle-5-equivalent measurement campaign on Mali.

What's unchanged

The architecture sketch (caps directory, plugin layout, two-backend conclusion) is unchanged — those parts were correct in the original; only the host-to-SoC mapping underneath them was wrong.

Diff: 1 file, +17 / -12 lines.

Refs PR #3 (the merged original).

Fixes factual errors in the per-SoC host table from PR #3. ## What was wrong Original draft put hertz and tesla under RK3588 and omitted boltzmann + noether entirely. Verified via `/proc/device-tree/compatible`: | Host | Original draft | Reality | |---|---|---| | hertz | RK3588 | **Pi 5 (BCM2712)** | | tesla | RK3588 | **Pi 5 (BCM2712)** (LXD container on hertz) | | boltzmann | omitted | **RK3588** (the only actual RK3588 in the fleet) | | noether | omitted | **Pi 4 (BCM2711)** — the user's interactive workstation | ## Corrected mapping ``` BCM2712 Pi 5 — higgs, hertz, broglie, tesla (LXD on hertz) BCM2711 Pi 4 — noether (workstation), dcw3, dcw2 RK3588 — boltzmann (32 GB, kernel-dev / MCP hub, 8 W always-on) Allwinner H6 — (not in fleet) ``` ## Reasoning consequences - **Pi 5 row is four hosts but one SoC.** Adding a fifth Pi 5 doesn't pressure-test the architecture; substrate decisions are identical across the row. - **Pi 4 forcing function is closer than the draft implied.** noether is a daily-driver workstation; once HW decode on it becomes a real ask and rpivid is still unstable upstream, the substrate-composed path with V3D4 + NEON becomes the right backend and the caps-file mechanism is needed. - **RK3588 forcing function via boltzmann + AV1.** rkvdec doesn't cover AV1, so Mali Valhall compute substrate becomes the only HW acceleration option there. Triggers a cycle-5-equivalent measurement campaign on Mali. ## What's unchanged The architecture sketch (caps directory, plugin layout, two-backend conclusion) is unchanged — those parts were correct in the original; only the host-to-SoC mapping underneath them was wrong. Diff: 1 file, +17 / -12 lines. Refs PR #3 (the merged original).

marfrit added 1 commit 2026-05-23 13:48:35 +00:00

docs: architecture backlog — correct fleet hardware mapping 68dccd2911

Original draft (PR #3) speculated wrongly on host-to-SoC mapping:

  - hertz and tesla were listed under RK3588.  Verified via
    /proc/device-tree/compatible: both are raspberrypi,5-model-b /
    brcm,bcm2712 (tesla is an LXD container hosted on hertz, so
    necessarily shares the host SoC).
  - boltzmann (the only actual RK3588 in the fleet, 32 GB, kernel-
    dev / MCP hub, 8 W always-on) was omitted entirely.
  - noether (Pi 4 / BCM2711, the user's interactive workstation,
    where Firefox and mpv actually run) was omitted entirely.

Corrects the per-SoC coverage table:

    BCM2712 Pi 5  — higgs, hertz, broglie, tesla (LXD on hertz)
    BCM2711 Pi 4  — noether (workstation), dcw3, dcw2
    RK3588        — boltzmann
    Allwinner H6  — (not in fleet)

Reasoning consequences:

  - Pi 5 row is now four hosts but one SoC.  Adding a fifth Pi 5
    doesn't pressure-test the architecture; substrate decisions
    are identical across the row.
  - The realistic forcing function for the Pi 4 path is "HW decode
    on noether matters and rpivid is still unstable upstream" —
    noether is a daily-driver Pi 4 workstation, so this is closer
    than the original draft implied.
  - The realistic forcing function for an RK3588 caps file is
    "AV1 playback on boltzmann matters" — rkvdec doesn't cover
    AV1, so Mali Valhall compute substrate becomes the only HW
    acceleration option there.

"Re-read this when" list at the top + "Why deferred" section
+ decision log all updated.  No change to the architecture sketch
(caps directory, plugin layout, two-backend conclusion) — those
were correct in the original; only the host-to-SoC mapping
underneath them was wrong.

Refs PR #3 (the merged original).

marfrit merged commit 3ecfc8b0ef into main

2026-05-23 15:12:30 +00:00

marfrit deleted branch noether/architecture-backlog-fleet-fix

2026-05-23 15:12:30 +00:00

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: marfrit/daedalus-fourier#4