[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <7B59AB4E-F084-43FA-B21B-292319D30501@zytor.com>
Date: Wed, 20 Aug 2025 08:04:52 -0700
From: "H. Peter Anvin" <hpa@...or.com>
To: Masami Hiramatsu <mhiramat@...nel.org>
CC: "Alan J . Wylie" <alan@...ie.me.uk>, Josh Poimboeuf <jpoimboe@...nel.org>,
Thomas Gleixner <tglx@...utronix.de>, Ingo Molnar <mingo@...hat.com>,
Borislav Petkov <bp@...en8.de>,
Dave Hansen <dave.hansen@...ux.intel.com>,
linux-kernel@...r.kernel.org, regressions@...ts.linux.dev,
stable@...r.kernel.org, Linus Torvalds <torvalds@...ux-foundation.org>,
x86@...nel.org
Subject: Re: [PATCH] x86: XOP prefix instructions decoder support
On August 19, 2025 6:00:04 PM PDT, Masami Hiramatsu <mhiramat@...nel.org> wrote:
>On Sat, 16 Aug 2025 18:36:17 -0700
>"H. Peter Anvin" <hpa@...or.com> wrote:
>
>> The easiest way to think of XOP is as a VEX3 supporting a different set of map numbers (VEX3 supports maps 0-31, XOP maps are 8-31 but separate); however, the encoding format is the same.
>
>Hmm, OK. We need to enable VEX3 support too. What about the opcode?
>Most of the opcode are the same, or different instructions?
>
>Thank you,
>
>
Different, that's the whole point ...
Powered by blists - more mailing lists