technologybriefs
10:52in productionCh. 1 · Born operational/ 10:52 · ceiling 15 min
Hardware · Tech history

PDP-11

It didn’t invent computing — it made abstraction feel physical.

The PDP-11 is a foundational 16-bit minicomputer series launched by DEC in January 1970. It established memory-mapped I/O and orthogonality as practical engineering standards — not theoretical ideals. Its limitations — no memory protection, fixed interrupt priority, Unibus bottlenecks — are as instructive as its successes. It matters today because its abstractions live on, not because its hardware does.

HardwareTech historyComputingHardwareInventionComputing across the network →
Chapters & takeaways4
  1. 1:12
    Born operational

    A 16-bit minicomputer launched in January 1970 — not a prototype, but a mass-manufactured product from day one.

  2. 2:46
    One bus, one map, one logic

    Orthogonal instructions and memory-mapped I/O replaced ad-hoc hardware interfaces with a unified, programmable address space.

  3. 4:34
    Interrupts you can count on

    Four interrupt priorities and a built-in serial debugger gave developers immediate, low-level control without external tools.

  4. 6:16
    Silicon for the shop floor

    The LSI-11 cut the CPU to four chips — proving minicomputers could be assembled cheaply, not just designed elegantly.

Worth your time?

Yes. Study the whole thing.

4.5/ 5
What works
  • memory-mapped I/O
  • orthogonal instruction set
  • four-level hardware interrupts
  • built-in serial debugger
What does not
  • memory protection
  • virtual memory
  • privilege modes
  • scalable I/O
Study it if
  • systems architects
  • retrocomputing practitioners
  • compiler developers
Skip it if
  • cloud infrastructure engineers
  • security researchers
  • AI hardware designers
The written brief2 min read

What it is and the problem it solves

The PDP-11 is a 16-bit minicomputer series introduced by DEC in January 1970. It solves the problem of providing programmable computing power at lower cost and size than mainframes — for labs, industrial controllers, and early time-sharing sites.

How it works

The PDP-11 uses a mostly orthogonal instruction set, enabling consistent addressing across operations. Early models rely on the Unibus — a single system bus connecting CPU, memory, and I/O devices mapped directly into memory space. Hardware interrupts operate at four fixed priority levels. The CPU microcode includes a built-in debugger with a direct serial interface to a terminal. Later LSI-based models (starting February 1975) integrate the entire CPU onto four MOSFET chips.

What works

Memory-mapped I/O via the Unibus works reliably for small-scale systems. The orthogonal instruction set simplifies programming and compiler development. Hardware interrupts at four priority levels enable predictable real-time response. The built-in debugger allows immediate terminal-based inspection and control. Manufacture by semiskilled labor succeeds — the design prioritises assembly-line simplicity over density or speed.

What does not

It does not scale beyond single-user or small multi-user workloads. It lacks memory protection, virtual memory, or privilege modes — making robust multitasking or secure isolation impossible. The Unibus becomes a bottleneck as I/O demand grows. No model supports more than four hardware interrupt priorities, limiting real-time responsiveness.

What it changes

It changes how engineers think about instruction sets and I/O. Memory-mapped I/O replaces dedicated I/O instructions, unifying access semantics. Orthogonality reduces special cases in assembler and compiler design. The LSI-11 proves minicomputers can be built from integrated MOSFET chips — accelerating cost reduction and volume manufacturing.

Is it worth your time

Yes — if you work on systems architecture, retrocomputing, or embedded firmware design. Its memory-mapped I/O and orthogonal model directly shaped Unix, C, and modern OS abstractions. But it offers no performance, scalability, or security features relevant to contemporary infrastructure.

Same field · Hardware4 of 238
9:15
Mobile robotA mobile robot is a locomotive, automatic machine—not fixed, not necessarily intelligent. It works by combining controller, sensors, actuators and power. It succeeds where movement and environment match. It fails when autonomy is assumed but not engineered. It changes infrastructure from static to relocatable. It is worth your time if you need machines that move—not just compute.
10:33
Brain–computer interfaceBCIs decode brain signals to operate devices. They work in controlled settings for specific users—cursor control since 1977, robots since 1988, intracortical prostheses since 1998, and artificial hands since 2005. But they remain low-bandwidth, unstable, and clinically niche. No general-purpose interface exists.
9:20
ChipletChiplets are modular ICs—functional fragments designed for assembly on an interposer. They enable heterogeneous integration, pre-test validation, and IP reuse. But they shift complexity from fabrication to integration, and require standards compliance to deliver on their promise.
8:58
Computer numerical controlCNC replaced punched-tape numerical control with computer-driven instruction sets. It shifted manufacturing from fixed logic to editable code—making parts repeatable, but not autonomous. Its success came from falling computing costs, not new physics or AI.
Up next in Technology

PDP-8

1965 · 10:24

The PDP-8 didn’t invent the minicomputer—it weaponised price.

Play nextBack to Hardware
10:24