Re: Efficient x86 and x86_64 NOP microbenchmarks

!MAILaRCHIVE_VOTE_RePLACE
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]
To: Andi Kleen <andi@...>
Cc: Steven Rostedt <srostedt@...>, Thomas Gleixner <tglx@...>, Mathieu Desnoyers <mathieu.desnoyers@...>, Steven Rostedt <rostedt@...>, Jeremy Fitzhardinge <jeremy@...>, LKML <linux-kernel@...>, Ingo Molnar <mingo@...>, Peter Zijlstra <peterz@...>, Andrew Morton <akpm@...>, David Miller <davem@...>, Roland McGrath <roland@...>, Ulrich Drepper <drepper@...>, Rusty Russell <rusty@...>, Gregory Haskins <ghaskins@...>, Arnaldo Carvalho de Melo <acme@...>, Luis Claudio R. Goncalves <lclaudio@...>, Clark Williams <williams@...>
Date: Wednesday, August 13, 2008 - 4:21 pm

On Wed, 13 Aug 2008, Andi Kleen wrote:

Andi, you seem to have missed the whole point. This is a _correctness_ 
issue as long as the nop is not a single instruction. And the workaround 
for that is uglier than just making a single-instruction nop.

So the question now is to find a good nop that _is_ a single atomic 
instruction. Your blathering about frame pointers is missing the whole 
point!

			Linus
--
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]

Messages in current thread:
Re: Efficient x86 and x86_64 NOP microbenchmarks, Steven Rostedt, (Wed Aug 13, 4:00 pm)
Re: Efficient x86 and x86_64 NOP microbenchmarks, Andi Kleen, (Wed Aug 13, 4:15 pm)
Re: Efficient x86 and x86_64 NOP microbenchmarks, Steven Rostedt, (Wed Aug 13, 4:21 pm)
Re: Efficient x86 and x86_64 NOP microbenchmarks, Linus Torvalds, (Wed Aug 13, 4:21 pm)
Re: Efficient x86 and x86_64 NOP microbenchmarks, Jeremy Fitzhardinge, (Wed Aug 13, 4:06 pm)
Re: Efficient x86 and x86_64 NOP microbenchmarks, Steven Rostedt, (Wed Aug 13, 4:34 pm)