予想
シングルスコアが高い順にコンパイラ時間が短くなるだろう
比較表
| OS | 機種 | CPU | GHz | single | multi | TIME |
|---|---|---|---|---|---|---|
| Linux (Windows10 WSL2) | 自作PC | Ryzen5 3600 | 3.60 | 1172 (1193) | 6362 (8433) | 2.64s |
| Mac | MacBook Air early 2015 | Core i5 5250U | 1.60 | 655 (599) | 1396 (1571) | 5.00s |
| iPad (a-shell) | iPad Pro 11 (3rd) | Apple M1 | 3.19 | 1686 | 7166 | 2.01s |
| iPhone (a-shell) | iPhone SE2 | Apple A13 Bionic | 2.66 | 1319 | 2846 | 2.71s |
| Mac | MacBook Pro late 2020 | Apple M1 | 3.2 | 1752 | 7711 | 1.1s |
| Windows 11 | Lenovo ideapad Slim5 | Core i7-13620H | - | - | - | 1.99s |
| Mac | MacBook Air 2020 | Apple M1 | - | - | - | 1.08s |
| - | Overleaf | - | - | - | - | 1.48s |
- スコアは Geekbench 5
- 括弧内のスコアは Cinebench R23 (10 minutes)
テストファイル
\RequirePackage{l3benchmark}
\ExplSyntaxOn
\AtEndDocument { \benchmark_toc: }
\benchmark_tic:
\ExplSyntaxOff
\documentclass[12pt]{beamer}
\usepackage{mathpazo}
\newcount\K
\def\myfor#1{
\K=0 \loop\ifnum\K<#1
{ \begin{frame}{title}Hello, world!\end{frame} }
\advance\K by1\repeat
}
\begin{document}
\myfor{50}
\end{document}
- 50ページのbeamer
- .log ファイルのドキュメントの最後でコンパイラ時間が表示される
参考
[I]t is only one thing that really makes a difference: Single-Threaded CPU power!
[T]he result roughly is: compilation times scale nearly linear with the CPU clock. It's the fasted Core i7 that makes the run; memory and disk plays only a minor role (given that you provide modest quality and size of both).
To sum up: For a "LaTeX machine" it is the processor and in particularly it's single-core throughput one should look for. However, the latter is not always easy to figure out, as basically all processors nowadays are multi-core and benchmarked and advertised with their multi-core throughput. A good starting point is the PassMark CPU Benchmarks site, which provides a frequently updated report on "Single Thread Performance" for all current IA32e/AMD64 CPUs.