Date: Mon, 26 Sep 2016 10:51:29 +0300 From: Konstantin Belousov <kostikbel@gmail.com> To: Colin Percival <cperciva@tarsnap.com> Cc: Bruce Evans <brde@optusnet.com.au>, src-committers@FreeBSD.org, svn-src-all@FreeBSD.org, svn-src-head@FreeBSD.org Subject: Re: svn commit: r306319 - head/sys/i386/i386 Message-ID: <20160926075129.GD38409@kib.kiev.ua> In-Reply-To: <0100015765538d1e-07598541-d22e-4eac-8382-b9bad08db716-000000@email.amazonses.com> References: <201609251839.u8PIdO7t050380@repo.freebsd.org> <0100015762ed107c-206ced2e-2389-462f-afe0-cec7d6c34fb8-000000@email.amazonses.com> <20160926164406.T806@besplex.bde.org> <0100015765538d1e-07598541-d22e-4eac-8382-b9bad08db716-000000@email.amazonses.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On Mon, Sep 26, 2016 at 07:09:17AM +0000, Colin Percival wrote: > Traditionally x86 CPUs would generate an invalid-opcode fault if redundant > instruction prefixes resulted in an instruction exceeding 15 bytes. This > behaviour might have changed in the past two decades, but I doubt it. It did not, 15 bytes is the current limit. In fact, the longest AVX VEX-encoded instructions are 11 bytes without prefixes, AFAIR.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20160926075129.GD38409>