Cpu

Lab 1: CPU Internals This is a hands-on report for the lab in /home/sanketh/cpu-lab on your Linux x86 laptop. It ties each experiment back to the ideas in content/posts/performance-engineering/2026-10-04-cpu-microarchitecture.markdown. Important note about this laptop: the CPU is an Intel Core i5-8250U (15 W mobile part, base 1.6 GHz, max 3.4 GHz). Under sustained load it thermally throttles, so absolute nanoseconds vary between runs. The conclusions come from ratios and TMA buckets, not from chasing the exact ns. ...

Performance Engineering: CPU Microarchitecture for the Practitioner This note explains what a modern CPU actually does while your program runs, and how to read that behavior through hardware performance counters. The goal is not to memorize every unit in a specific core design, but to build a mental model that makes perf output meaningful. If the previous note asked “where does the time go,” this note answers “what is the CPU doing with the cycles it consumes.” ...

Performance Engineering: A Practical Starting Map This is the first note in a performance-engineering sequence. It is not a summary of an SRE handbook, a cloud-observability guide, or a treatise on dashboard design. The goal is practical skill at the level of a single machine: understand why a program is slow, decide what to change, and verify that the change worked. The contexts that matter here are things like a chess engine, the microbenchmark problems on HFT University, a hot loop in the Linux kernel, or any single-node program where you own the source and the hardware. The operating system is the boundary we press against; the hardware is the ground truth. ...

Pipelining — First Principles What is pipelining? Pipelining is the technique of overlapping the execution of multiple instructions. An instruction consists of multiple pieces of work. Instead of completing one instruction entirely before starting the next, we divide the work into stages and let different instructions occupy different stages simultaneously. For a simple example: IF ID EX MEM WB Instruction 1 → → → → → Instruction 2 → → → → Instruction 3 → → → Instruction 4 → → At any moment, several instructions are being worked on, but each is at a different stage. ...

When learning assembly, it’s easy to get lost in the “why” of CPU design, but this blog will stay focused on the x86 instruction set itself. The goal here isn’t to study computer architecture or dive into microarchitectural details — instead, we’ll build a working reference for how to write and understand x86 assembly code. Everything that follows is about the x86 family of processors, starting from the registers that form the foundation of all instructions. ...

When your x86 computer first starts up, it’s in a surprisingly primitive state: No operating system - Obviously, since we haven’t loaded one yet No memory management - No virtual memory, no protection between processes No file system - Can’t open files, no directories, no abstraction layer No network stack - No TCP/IP, no internet connectivity No device drivers - No USB drivers, no graphics drivers, nothing What Services Are Available at Boot Time? Despite the barren landscape, the BIOS (Basic Input/Output System) gives us a few essential tools: ...

Introduction: The Communication Challenges At its core, a CPU is designed for one primary task: processing data and executing instructions at incredible speed. But this processing power becomes meaningful only when it can interact with the rich ecosystem of peripheral devices that extend its capabilities. Why CPUs Need to Talk to Many Different Devices? Your CPU must read input from your mouse or keyboard, process that input to understand your intent, communicate with memory to load the browser application, send rendering commands to your graphics card, request data from your network interface to load the webpage, and potentially write temporary files to your storage device. Each of these interactions involves a different type of peripheral device, each with its own communication requirements, data formats, and timing constraints. ...

The 8086 Processor A Brief History The Intel 8086, released in 1978, marked a pivotal moment in computing history as Intel’s first 16-bit microprocessor. Designed by a team led by Stephen Morse, the 8086 was Intel’s answer to the growing demand for more powerful processors that could handle larger programs and address more memory than the existing 8-bit chips of the era. The processor introduced the x86 architecture that would become the foundation for decades of computing evolution. With its 16-bit registers and 20-bit address bus 1, the 8086 could access up to 1 megabyte of memory—a massive improvement over the 64KB limitation of 8-bit processors. However, it retained backward compatibility concepts that would prove both beneficial and constraining for future generations. ...

The Fetch-decode-execute cycle or instruction cycle is how CPU executes programs. During this cycle, the CPU retrieves an instruction from memory (fetch), interprets what action is required (decode), and then carries out the necessary operations to complete the instruction (execute). This cycle is crucial for the CPU to perform any computational tasks, and it repeats continuously while the computer is powered on. What is Machine Code? Machine code is the lowest-level programming language that consists of binary instructions directly executed by a CPU. Any program is compiled to a binary executable is transformed into machine code. Machine code consists of set of instructions which varies for each CPU architecture and is decided by the CPU manufacturer, eg: ARM, MIPS, x86, etc. Machine code consists of a set of instructions defined by the Instruction Set Architecture (ISA) of each CPU. The ISA, determined by the CPU manufacturer, varies across different architectures such as ARM, MIPS, and x86. This architecture-specific design means that machine code written for one type of CPU cannot be directly executed on another without translation or emulation. ...

CPU Manufacturers publish several metrics related to CPU like clock speed, number of cores, cache sizes, ISA, performance per Watt, number of transistors and more. Measuring CPU performance is complex, and it cannot be summarized by a single metric. In this post, I’ll explore each of these metrics and discuss some standard benchmarking software and their limitations. What is Clock Speed, How does it Affects CPU Performance? All Synchronous digital electronic circuits require an externally generated time reference. This is usually a square wave signal provided to the circuit called as clock. A clock cycle is the fundamental unit of time measurement for a CPU. A clock cycle is a single electrical pulse in a CPU, during which the CPU can execute a fundamental operation such as accessing memory, writing data, or fetching a new set of instructions. A clock cycle is measured as the amount of time between two pulses of an oscillator. The clock speed of a CPU is measured in Hertz (Hz), which signifies the number of clock cycles it can complete in one second. Common units are Megahertz (MHz) and Gigahertz (GHz). ...