The Chip Letter

The Chip Letter

Home
Notes
Chiplets
Start Here
Archive
Demystifying GPU Compute Architectures
Getting 'low level' with Nvidia and AMD GPUs
 • 
Babbage
9
Google's First Tensor Processing Unit : Architecture
Looking in more detail at Google's first Tensor Processing Unit
 • 
Babbage
5
Qualcomm RISCs, Arm Pulls: The Legal Battle for the Future of Client Computing
What happens when a gladiator takes on the “Warren Buffett of Japan”?
 • 
Babbage
2
Demystifying NPUs: Questions & Answers
Let's answer some 'what', 'why' and 'hows' for the Neural Processing Unit.
 • 
Babbage
4
Intel’s Immiseration
The long, seemingly inevitable decline of an icon
 • 
Babbage
6
A History of C Compilers - Part 1: Performance, Portability and Freedom
Let's talk compilers with part one of a whistle stop tour of their history
 • 
Babbage
4
Learning Assembly for Fun, Performance and Profit
Why take an interest in assembly language and which to learn?
 • 
Babbage
31
The Nvidia Way
Tae Kim's terrific new book on the story of Nvidia and Jensen Huang
 • 
Babbage
12
Moore on Moore
We look at the past, present and uncertain future of Moore's Law, with some help from Gordon Moore himself
 • 
Babbage
Demystifying GPU Compute Software
Comparing CUDA with its competitors
 • 
Babbage
4
Tiny Computers from Texas
The Early History of the Microcontroller - Part 1
 • 
Babbage
6
The Paradox of x86
When a moat becomes a prison with huge economic and geopolitical consequences.
 • 
Babbage
4
© 2025 The Chip Letter
Privacy ∙ Terms ∙ Collection notice
Start writingGet the app
Substack is the home for great culture