Trading at light speed: designing low latency systems in C++ - David Gross - Meeting C++ 2022

David Gross shares insights on designing low-latency trading systems from scratch, focusing on CPU architecture, concurrency, and performance-driven design.

Trading at light speed: designing low latency systems in C++ - David Gross - Meeting C++ 2022 Slides: slides.meetingcpp.com Survey: survey.meetingcpp.com Making a trading system "fast" cannot be an afterthought. While low latency programming is sometimes seen under the umbrella of "code optimization", the truth is that most of the work needed to achieve such latency is done upfront, at the design phase. How to translate our knowledge about the CPU and hardware into C++? How to use multiple CPU cores, handle concurrency issues and cost, and stay fast? In this talk, David Gross, Auto-Trading Tech Lead at global trading firm Optiver will share industry insights on how to design from scratch a low latency trading system. 0:00 Introduction 0:11 AUTOMATED TRADING A HIGH STAKES GAME 1:40 AUTOMATED TRADING: THE NEED FOR SPEED 4:34 DESIGN FOR PERFORMANCE 5:48 STRATEGY & TACTICS 7:42 HOW FAST IS FAST? 15:24 AN UNDERWHELMING PROFILING RESULT 16:34 DATA MODEL FOR PERFORMANCE 19:06 DATA MODEL: INSTRUMENT STORE 22:23 STABLE VECTOR 24:46 WSS ESTIMATION 27:55 CONCURRENT DATA IN TRADING SYSTEMS 29:21 HOW MUCH DATA? 35:06 SEQLOCK PROPERTIES 37:33 CONCURRENT DATA: EVENTS 38:37 SPMC QUEUE V2 47:00 IS YOUR SYSTEM TUNED CORRECTLY? 48:28 C-STATE, P-STATE 50:36 SHARED LLC OPTIMIZATION 53:53 METRICS 57:59 CONCLUSION