Your matching engine passed every test. Your risk engine rejects every bad order. Your FPGA gateway hits its latency target on the bench.On day one, all four components ran together against live order flow, and the system breached its exposure limit by several multiples.No component was wrong. The seams between them were.This book is about those seams.
A risk check that adds 50 microseconds does not add 50 microseconds. It hands your queue position to whoever skipped the check.Most risk engines pass the quiet-market demo. Then a mutex meets a fast market, a cache line is shared by two instruments, or a covariance matrix gets rebuilt on every fill, and the check that looked cheap becomes the slowest thing in the order path. The numbers stay correct. They arrive late.This book builds the engine that doesn’t do that: lock-free position tracking, a pre-trade gate with no mutex, VaR maintained at O(k) per fill instead of recomputed, and stress tests that never touch the fill path’s cache lines. Then it proves the result with replay tests, property-based invariants, and reconciliation against an independent source.Every technique is paired with the failure it prevents, and every section ends with what it changed in the latency budget.For engineers who build the thing that has to be fast and has to be right.
Your feed handler parsed every test message correctly. Then a real exchange dropped two packets on an ordinary Tuesday, and the book kept building, internally consistent and wrong.Nothing crashed. Nothing threw. Four minutes of bad quotes went out before anyone noticed.This book is about that gap: the distance between a parser that works and a feed handler you can trust. You will build zero-copy FIX, ITCH, and OUCH parsers with no heap allocation on the hot path, detect sequence gaps without stalling live traffic, recover from outages without corrupting book state, and prove the result with byte-identical replay.If your system has never lost a sequence number in testing, you do not have a feed handler. You have a demo.Weston Ashgrove is a trading systems architect who has built and debugged the failures in these pages.
The engine never crashed. Every test passed. Then the opening auction cleared, order flow jumped fivefold, and for eight minutes it matched every order correctly against a book that was already 700 milliseconds out of date. Several hundred clients got fills that were individually plausible and collectively wrong. Nothing in the logs said why.This book is about that gap between "thread-safe" and "deterministic," and how to close it: lock-free CAS design, cache-line layout measured with perf c2c, zero-allocation hot paths, jitter hunted down to the interrupt level, and proof that the same event log replays byte-for-byte identical ten thousand times, including after a crash.
Go beyond writing kernel modules and learn how real Linux GPU drivers are built. Starting with GPU architecture and the graphics stack, this hands-on guide walks you through creating a complete DRM driver, from a minimal module to memory management, command submission, display support and error recovery.
Master the GPU from the Streaming Multiprocessor to Production-Grade High-Performance KernelsCUDA C++: High-Performance GPU Programming is an advanced technical guide to GPU programming, CUDA execution, memory architecture, kernel optimization, low-level hardware analysis, and high-throughput AI workloads.Designed for engineers who want to move beyond basic CUDA programming, this 53-chapter technical reference explores the NVIDIA GPU programming stack in depth, progressing from Streaming Multiprocessor architecture and SIMT execution to PTX/SASS analysis, Tensor Cores, asynchronous data movement, multi-GPU systems, NCCL, and production inference engines.The book takes a hardware-aware approach to performance engineering. Rather than treating CUDA as a black box, it examines how threads execute, how warps communicate, how memory transactions are formed, and how registers, caches, compiler decisions, and hardware scheduling influence performance. The emphasis is on understanding the mechanisms behind kernel behavior and using that knowledge to make informed optimization decisions.
An introduction to Common Lisp and many useful example programs. Use LLMs, as well as classic symbolic AI techniques.
#1 Best Seller in Management Science (Amazon International, France, Germany, Netherlands, Poland, Sweden – Feb 2026) and in other categories. Available worldwide on Amazon (Hardcover, Paperback, Kindle) and across all major digital platforms, including Leanpub, Apple Books, and Google Play. Learn how to drive your organizational performance with people and AI to 10X and beyond — in impact and relevance.
"If you intend to use machine learning to solve business problems at scale, I'm delighted you got your hands on this book." —Cassie Kozyrkov, Chief Decision Scientist at Google "Foundational work about the reality of building machine learning models in production." —Karolis Urbonas, Head of Machine Learning and Science at Amazon
Kotlin coroutines have revolutionized JVM development, especially on Android and the backend, as they let us easily implement efficient and reliable multithreading. Their cutting-edge design and features are ideally suited to modern use cases. In this book, we will explore how Kotlin coroutines work and how we can use them to improve our code.
Learn first-hand from the founder of GraphQL Java and co-author of Spring for GraphQL how to develop GraphQL services in Java. See the Table of Contents below for a full chapter listing.
This book helps you uncover the world of Arm-based microcontroller firmware development, equipping you to decode datasheets, expertly manipulate registers, and autonomously craft optimized code.
Excel in the CISA exam with this guide, covering IT governance, systems development, operations, and asset protection. The book includes practical examples and over 1000 targeted practice test questions to prepare you for the CISA exam.
With this new edition, get to grips with Linux kernel development on the long-term 6.1 (S)LTS kernel in a hands-on way with the help of brilliant code examples. Linux Kernel Programming 2E teaches you how to write high-quality kernel modules suitable for real-world products, following industry best practices and with security awareness. It covers essential kernel internals and kernel synchronization.
Architecture is still often considered as black art. If you develop large hardware/software systems maybe including mechanical or electrical components, this book is for you. Source Code is not enough to understand complex embedded systems. This is where arc42 as a pragmatic and practical template comes into the game. Read some real-life examples!