Learn SIDRACHIP, in the workshop.

From physics to silicon, from neurons to transformers — 9 modules, ~75 chapters, zero external dependencies.

77 published · 77 planned

Choose your path

L1 · Curious (High School)

You're curious but you're not comfortable beyond middle-school math. We start right there — electrons, synapses, Ohm's law.

L2 · Undergraduate

Undergrad years 1–3. Comfortable with calculus, circuits, probability. From here we can build memristor models, MVM equations, thermal math.

L3 · Advanced / Expert

You know quantum mechanics, signal processing, transformer architectures. We go to the level where Sidrachip's architectural choices can be justified.

Curriculum

🧭

Module 0 — Welcome

Because you're here, we're going to tell you a story that will carry you for 18 months.

0.1 · What is SIDRACHIP? 0.2 · How to Read This Book 0.3 · Where Am I? — Self-Assessment
⚛️

Module 1 — Physics Foundation

Before we can understand a memristor, let's remember what an electron is.

1.1 · The Atom and the Electron 1.2 · Bands and Semiconductors 1.3 · The P-N Diode 1.4 · MOSFET — The Atom of 28 nm CMOS 1.5 · Resistance and Ohm's Law 1.6 · Capacitance and the RC Time Constant 1.7 · Quantum Tunneling 1.8 · Electrochemistry and Ion Motion 1.9 · Thermodynamics and Joule Heating 1.10 · Physics Module Review
🧪

Module 2 — Chemistry and Materials Science

Every atom in your chip is a deliberate choice.

2.1 · The Chip Side of the Periodic Table 2.2 · HfO₂ — Why Hafnium Oxide? 2.3 · NbOx — The Chemistry of OTS 2.4 · Thin-Film Deposition: ALD, PVD, CVD 2.5 · Lithography Chemistry 2.6 · Plasma Etching (ICP-RIE) 2.7 · CMP and the SOG Alternative 2.8 · Metallization: Tungsten vs Copper 2.9 · Contamination and the Doom of a Single Speck 2.10 · Chemistry Module Review
🧠

Module 3 — From Biology to Algorithm

Because the brain's power budget is 20 W, ours is 1.5 kW.

3.1 · Neuron Biology 3.2 · The Synapse 3.3 · Hebbian Learning 3.4 · Brain Energy Efficiency 3.5 · From Artificial Neuron to Transformer 3.6 · Backpropagation 3.7 · Memristor ↔ Synapse Mapping 3.8 · Spike-Timing-Dependent Plasticity
📐

Module 4 — The Math Arsenal

Linear algebra is our gym.

4.1 · Vector, Matrix, MVM 4.2 · Ohm + Kirchhoff = Analog MVM 4.3 · Derivative and Gradient 4.4 · Probability and Noise 4.5 · Fourier Transform 4.6 · Quantization and Quantization Error 4.7 · Information Theory: Entropy and Channel 4.8 · Linear Algebra Laboratory
🔌

Module 5 — Chip Hardware

The existing 13 chapters, updated to YILDIRIM v3.0 spec.

5.1 · The Neuromorphic Computing Paradigm 5.2 · Deep Dive: The Memristor 5.3 · The Crossbar Array 5.4 · YILDIRIM Chip Architecture 5.5 · DAC — SAR + ISPP 5.6 · TDC — Time-Domain Readout 5.7 · TIA — Transimpedance Sensing 5.8 · MUX, Decoder, and Analog ECC 5.9 · Compute Engine and DMA 5.10 · Noise Models 5.11 · Power and Thermal Management 5.12 · Metal Lines and IR Drop 5.13 · Signal Chain and Packaging 5.14 · Y1 / Y10 / Y100 Comparison 5.15 · Thermal and Packaging Deep Dive
💻

Module 6 — Software Stack

Hardware is only half of it.

6.1 · OS and PCIe Driver Basics 6.2 · Linux Kernel and aether-driver 6.3 · RISC-V Firmware 6.4 · The ISPP Algorithm, Step by Step 6.5 · SDK Layers 6.6 · Writing a PyTorch Backend 6.7 · Compiler: Model → Analog Mapping 6.8 · Digital Twin / Simulator 6.9 · Test, Calibration, Verification 6.10 · End-to-End Production Stack Lab
🏭

Module 7 — Fabrication and Ecosystem

What happens to a wafer at UNAM?

7.1 · Cleanrooms and ISO Classes 7.2 · Three Months of a Wafer 7.3 · TSMC 28nm MPW Process 7.4 · UNAM 4-Layer BEOL (Y1) 7.5 · METU CMP Collaboration (Y10) 7.6 · Test and Characterization 7.7 · Packaging — FC-BGA 7.8 · Fab Line Simulation
🌐

Module 8 — Context and the Future

Why does this matter, and where are we going?

8.1 · The AI Chip Competition 8.2 · Turkey's Semiconductor Strategy 8.3 · Ethics: Accelerate Responsibly 8.4 · Y100 Photonics Vision 8.5 · Your Place