Linux MIPS Architecture development
 help / color / mirror / Atom feed
From: Ralf Baechle <ralf@linux-mips.org>
To: Matt Redfearn <matt.redfearn@imgtec.com>
Cc: Aleksandar Markovic <aleksandar.markovic@rt-rk.com>,
	linux-mips@linux-mips.org, James.Hogan@imgtec.com,
	Paul.Burton@imgtec.com, Raghu.Gandham@imgtec.com,
	Leonid.Yegoshin@imgtec.com, Douglas.Leung@imgtec.com,
	Petar.Jovanovic@imgtec.com, Miodrag.Dinic@imgtec.com,
	Goran.Ferenc@imgtec.com
Subject: Re: [PATCH 3/8] MIPS: R6: Fix PREF instruction usage by memcpy for MIPS R6
Date: Wed, 28 Jun 2017 02:58:53 +0200	[thread overview]
Message-ID: <20170628005853.GC6738@linux-mips.org> (raw)
In-Reply-To: <a5842e4b-a75b-2dde-d835-6a488790dbda@imgtec.com>

On Tue, Jun 20, 2017 at 09:04:16AM +0100, Matt Redfearn wrote:

> Hi Aleksandar,
> 
> Wouldn't the more correct thing be to modify the memcpy loop such that
> prefetches do not fetch the larger offset? Just turning off prefetch
> altogether in memcpy for r6 seems like a heavy hammer to me...

It's the same heavy hammer we've been using for ages to deal with this
problem for other configurations as well.  So while you're right I don't
want to force Aleksandar to come up with The One Perfect Fix.  Though
that would be lovely :)

  Ralf

  parent reply	other threads:[~2017-06-28  0:59 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-06-19 15:50 [PATCH 0/8] MIPS: Miscellaneous fixes related to Android Mips emulator Aleksandar Markovic
2017-06-19 15:50 ` [PATCH 1/8] MIPS: cmdline: Add support for 'memmap' parameter Aleksandar Markovic
2017-06-19 15:50 ` [PATCH 2/8] MIPS: build: Fix "-modd-spreg" switch usage when compiling for mips32r6 Aleksandar Markovic
2017-06-19 15:50 ` [PATCH 3/8] MIPS: R6: Fix PREF instruction usage by memcpy for MIPS R6 Aleksandar Markovic
2017-06-20  8:04   ` Matt Redfearn
2017-06-20  8:04     ` Matt Redfearn
2017-06-28  0:58     ` Ralf Baechle [this message]
2017-06-28  1:35       ` Maciej W. Rozycki
2017-06-28  1:35         ` Maciej W. Rozycki
     [not found]         ` <9915e476-70fe-4281-a1e4-85ca2e8683b3@imgtec.com>
2017-06-28  2:36           ` Maciej W. Rozycki
2017-06-28  8:34             ` Ralf Baechle
2017-06-28 11:23               ` Maciej W. Rozycki
2017-06-19 15:50 ` [PATCH 4/8] MIPS: unaligned: Add DSP lwx & lhx missaligned access support Aleksandar Markovic
2017-06-19 15:50 ` [PATCH 5/8] MIPS: math-emu: Handle zero accumulator case in MADDF and MSUBF separately Aleksandar Markovic
2017-06-19 15:50 ` [PATCH 6/8] input: goldfish: Fix multitouch event handling Aleksandar Markovic
2017-06-19 15:50 ` [PATCH 7/8] tty: goldfish: Use streaming DMA for r/w operations on Ranchu platforms Aleksandar Markovic
2017-06-19 15:50 ` [PATCH 8/8] tty: goldfish: Implement support for kernel 'earlycon' parameter Aleksandar Markovic

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20170628005853.GC6738@linux-mips.org \
    --to=ralf@linux-mips.org \
    --cc=Douglas.Leung@imgtec.com \
    --cc=Goran.Ferenc@imgtec.com \
    --cc=James.Hogan@imgtec.com \
    --cc=Leonid.Yegoshin@imgtec.com \
    --cc=Miodrag.Dinic@imgtec.com \
    --cc=Paul.Burton@imgtec.com \
    --cc=Petar.Jovanovic@imgtec.com \
    --cc=Raghu.Gandham@imgtec.com \
    --cc=aleksandar.markovic@rt-rk.com \
    --cc=linux-mips@linux-mips.org \
    --cc=matt.redfearn@imgtec.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox