mirror of
https://github.com/lux-apps/papers.git
synced 2026-10-30 18:15:21 +00:00
zeekay
f4ee7a0525
Bylines, paper authorship, correspondence addresses and the founder blurb under each post named an individual. They name the organisation that published the work instead: the brand on posts and pages, the research byline on papers, and research@ in place of a personal address. Both are what these repositories already used elsewhere — nothing new was coined. Co-authors are untouched. Where a paper named someone else alongside, they stay named; only the one byline changed. Bibliography entries, running heads, PDF metadata and affiliations move with it, so a citation still resolves to whoever the cited paper names. Sample and fixture data uses the placeholder name these tests already use elsewhere, so no assertion changed meaning.
85 lines
3.1 KiB
TeX
85 lines
3.1 KiB
TeX
\documentclass[11pt,letterpaper]{article}
|
|
\usepackage{../shared/luxcover}
|
|
\usepackage[utf8]{inputenc}
|
|
\usepackage{amsmath,amssymb,amsfonts,amsthm}
|
|
\usepackage{graphicx}
|
|
\usepackage{hyperref}
|
|
\usepackage{booktabs}
|
|
\usepackage{algorithm}
|
|
\usepackage{algorithmic}
|
|
\usepackage{listings}
|
|
\usepackage{multirow}
|
|
\usepackage{colortbl}
|
|
\usepackage{xcolor}
|
|
\usepackage{pgfplots}
|
|
\usepackage{pgfplotstable}
|
|
\pgfplotsset{compat=1.18}
|
|
\input{../shared/lstlang}
|
|
|
|
\newtheorem{theorem}{Theorem}
|
|
\newtheorem{lemma}[theorem]{Lemma}
|
|
\newtheorem{definition}{Definition}
|
|
\newtheorem{corollary}[theorem]{Corollary}
|
|
|
|
\definecolor{luxblue}{RGB}{30,60,120}
|
|
\definecolor{luxgray}{RGB}{100,100,100}
|
|
\definecolor{luxgreen}{RGB}{40,120,60}
|
|
\definecolor{luxred}{RGB}{180,40,40}
|
|
|
|
\lstset{
|
|
basicstyle=\ttfamily\small,
|
|
keywordstyle=\color{luxblue}\bfseries,
|
|
commentstyle=\color{luxgray}\itshape,
|
|
stringstyle=\color{luxgreen},
|
|
frame=single,
|
|
framerule=0.5pt,
|
|
rulecolor=\color{black!20},
|
|
breaklines=true,
|
|
showstringspaces=false,
|
|
tabsize=4,
|
|
columns=fullflexible,
|
|
}
|
|
|
|
\title{ZAP Benchmarks: Zero-Allocation Protocol\\Performance Analysis for Consensus Transport}
|
|
|
|
\author{
|
|
Lux Research\thanks{Corresponding author: [email protected]}\\
|
|
\textit{Lux Industries, Inc.}\\
|
|
\texttt{[email protected]}
|
|
}
|
|
|
|
\date{2023}
|
|
|
|
\begin{document}
|
|
|
|
\luxcoverpage
|
|
|
|
\begin{abstract}
|
|
We present a comprehensive performance evaluation of ZAP (Zero-Allocation Protocol), a binary wire protocol designed for inter-node consensus communication in the Lux Network. We benchmark ZAP against six competing protocols---gRPC, Protobuf-mux, JSON-RPC, Cap'n Proto, FlatBuffers, and QUIC---across six dimensions: serialization throughput, round-trip latency, memory allocation, CPU utilization, concurrent connection scalability, and variable message size performance. ZAP achieves 4.2 million single-stream serializations per second with zero heap allocations, 8.7$\mu$s median round-trip latency, and linear throughput scaling to 100K concurrent connections. In batched mode (50 connections, batch size 1000), ZAP sustains 20.26 million transactions per second. These results demonstrate that ZAP's arena-based zero-allocation design eliminates the primary bottleneck in garbage-collected consensus runtimes: unpredictable GC pauses that cause consensus timeouts.
|
|
|
|
\textbf{Keywords}: wire protocol, benchmarks, zero allocation, consensus transport, serialization, latency
|
|
\end{abstract}
|
|
|
|
\tableofcontents
|
|
\newpage
|
|
|
|
%% ============================================================================
|
|
|
|
\input{sections/01-introduction}
|
|
\input{sections/02-experimental-setup}
|
|
\input{sections/03-serialization-throughput}
|
|
\input{sections/04-latency}
|
|
\input{sections/05-memory-allocation}
|
|
\input{sections/06-cpu-usage}
|
|
\input{sections/07-concurrent-connection-scalability}
|
|
\input{sections/08-message-size-sensitivity}
|
|
\input{sections/09-batch-mode-performance}
|
|
\input{sections/10-end-to-end-consensus-impact}
|
|
\input{sections/11-comparison-with-zero-copy-protocols}
|
|
\input{sections/12-limitations}
|
|
\input{sections/13-related-work}
|
|
\input{sections/14-named-competitor-comparison}
|
|
\input{sections/99-conclusion}
|
|
|
|
\end{document}
|