From 44ecc784da69ca58b674639be509ce68962c5612 Mon Sep 17 00:00:00 2001
From: Andrej <andrej.karpathy@gmail.com>
Date: Sun, 23 Jul 2023 20:09:25 -0700
Subject: [PATCH] performance guide tweak

---
 README.md | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/README.md b/README.md
index fe7068b..ec4e2cc 100644
--- a/README.md
+++ b/README.md
@@ -120,6 +120,8 @@ Putting a few of these together, the fastest throughput I saw so far on my MacBo
 gcc -O3 -funsafe-math-optimizations -Ofast -ffast-math -o run run.c -lm
 ```
 
+Also, I saw someone report higher throughput replacing `gcc` with `clang`.
+
 ## unsorted todos
 
 - why SentencePiece can't iteratively decode properly?