From 1fafd3936474517ebf3f413c23f169902986d25e Mon Sep 17 00:00:00 2001 From: Carsten Bauer Date: Sun, 21 Jul 2024 13:00:37 +0200 Subject: [PATCH] typo --- website/user_gettingstarted.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/website/user_gettingstarted.md b/website/user_gettingstarted.md index d8be9c0..314b8b4 100644 --- a/website/user_gettingstarted.md +++ b/website/user_gettingstarted.md @@ -48,7 +48,7 @@ You want to choose a file system with the following properties ## Set `JULIA_CPU_TARGET` appropriately. -On many clusters, the sections above are all you need to get a solid Julia setup. However, if your on a **heterogeneous HPC cluster**, that is, if different nodes have different CPU (micro-)architectures, you should/need to do a few more preparations. Otherwise, you might encounter nasty error messages like "`Illegal instruction`". +On many clusters, the sections above are all you need to get a solid Julia setup. However, if you're on a **heterogeneous HPC cluster**, that is, if different nodes have different CPU (micro-)architectures, you should/need to do a few more preparations. Otherwise, you might encounter nasty error messages like "`Illegal instruction`". To make Julia produce efficient code that works on different CPUs, you need to set [`JULIA_CPU_TARGET`](https://docs.julialang.org/en/v1.10-dev/manual/environment-variables/#JULIA_CPU_TARGET). For example, if you want Julia to compile all functions (`clone_all`) for Intel Skylake (`skylake-avx512`), AMD Zen 2 (`znver2`), and a generic fallback (`generic`), for safety, you could put the following into your `.bashrc`: