From: Fiona Glaser <fiona@x264.com>
Date: Wed, 22 Feb 2012 21:33:36 +0000 (-0800)
Subject: x86inc: switch to amdnops
X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=5b2c62aec269be7d0b1ff62df09660369f4e20e0;p=libx264

x86inc: switch to amdnops
Recent AMD CPUs' instruction decoders choke horribly on extremely long nops (i.e. with 4 prefixes).
Won't affect much, since we don't use ALIGN much.
---

diff --git a/common/x86/x86inc.asm b/common/x86/x86inc.asm
index def62fa2..648bb815 100644
--- a/common/x86/x86inc.asm
+++ b/common/x86/x86inc.asm
@@ -92,7 +92,7 @@
 %endif
 
 ; Always use long nops (reduces 0x90 spam in disassembly on x86_32)
-CPU intelnop
+CPU amdnop
 
 ; Macros to eliminate most code duplication between x86_32 and x86_64:
 ; Currently this works only for leaf functions which load all their arguments