From: Arnd Bergmann <arnd-r2nGTMty4D4@public.gmane.org>
To: Frode Isaksen <fisaksen-rdvid1DuHRBWk0Htik3J/w@public.gmane.org>
Cc: nsekhar-l0cyMroinI0@public.gmane.org,
Kevin Hilman <khilman-rdvid1DuHRBWk0Htik3J/w@public.gmane.org>,
ptitiano-rdvid1DuHRBWk0Htik3J/w@public.gmane.org,
Linux ARM
<linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r@public.gmane.org>,
Mark Brown <broonie-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>,
linux-spi-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
Subject: Re: [PATCH v2 5/6] spi: davinci: do not use DMA if transfer length is less than 16
Date: Fri, 17 Feb 2017 17:55:01 +0100 [thread overview]
Message-ID: <CAK8P3a2_FL2rBcHdmK040LMRMZCV-70pOBFVUh=VpO+q45nQ0Q@mail.gmail.com> (raw)
In-Reply-To: <3358b5f1-c7b6-0955-0c36-6f135a585762-rdvid1DuHRBWk0Htik3J/w@public.gmane.org>
On Fri, Feb 17, 2017 at 5:43 PM, Frode Isaksen <fisaksen-rdvid1DuHRBWk0Htik3J/w@public.gmane.org> wrote:
> On 17/02/2017 17:37, Arnd Bergmann wrote:
>> On Fri, Feb 17, 2017 at 11:38 AM, Frode Isaksen <fisaksen-rdvid1DuHRBWk0Htik3J/w@public.gmane.org> wrote:
>> 16 seems low as the cutoff. Have you found this experimentally and
>> tested that for e.g. 32
>> bytes there is actually an advantage in using DMA?
> Yes, I have tested for different sizes. Actually 32 bytes is better @30MHz, but if the bit rate goes down, DMA wins over PIO. Do you prefer 32 bytes ?
No, I don't care about the specific value, just making sure that you had
actually tested this, as I had expected PIO to be faster here.
Arnd
--
To unsubscribe from this list: send the line "unsubscribe linux-spi" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
WARNING: multiple messages have this Message-ID (diff)
From: arnd@arndb.de (Arnd Bergmann)
To: linux-arm-kernel@lists.infradead.org
Subject: [PATCH v2 5/6] spi: davinci: do not use DMA if transfer length is less than 16
Date: Fri, 17 Feb 2017 17:55:01 +0100 [thread overview]
Message-ID: <CAK8P3a2_FL2rBcHdmK040LMRMZCV-70pOBFVUh=VpO+q45nQ0Q@mail.gmail.com> (raw)
In-Reply-To: <3358b5f1-c7b6-0955-0c36-6f135a585762@baylibre.com>
On Fri, Feb 17, 2017 at 5:43 PM, Frode Isaksen <fisaksen@baylibre.com> wrote:
> On 17/02/2017 17:37, Arnd Bergmann wrote:
>> On Fri, Feb 17, 2017 at 11:38 AM, Frode Isaksen <fisaksen@baylibre.com> wrote:
>> 16 seems low as the cutoff. Have you found this experimentally and
>> tested that for e.g. 32
>> bytes there is actually an advantage in using DMA?
> Yes, I have tested for different sizes. Actually 32 bytes is better @30MHz, but if the bit rate goes down, DMA wins over PIO. Do you prefer 32 bytes ?
No, I don't care about the specific value, just making sure that you had
actually tested this, as I had expected PIO to be faster here.
Arnd
next prev parent reply other threads:[~2017-02-17 16:55 UTC|newest]
Thread overview: 50+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-02-17 10:38 [PATCH v2 0/6] Enable DMA for daVinci SPI controller Frode Isaksen
2017-02-17 10:38 ` Frode Isaksen
[not found] ` <1487327904-28311-1-git-send-email-fisaksen-rdvid1DuHRBWk0Htik3J/w@public.gmane.org>
2017-02-17 10:38 ` [PATCH v2 1/6] spi: davinci: Use SPI framework to handle DMA mapping Frode Isaksen
2017-02-17 10:38 ` Frode Isaksen
[not found] ` <1487327904-28311-2-git-send-email-fisaksen-rdvid1DuHRBWk0Htik3J/w@public.gmane.org>
2017-02-19 16:29 ` Mark Brown
2017-02-19 16:29 ` Mark Brown
2017-02-17 10:38 ` [PATCH v2 2/6] spi: davinci: enable DMA when channels are defined in DT Frode Isaksen
2017-02-17 10:38 ` Frode Isaksen
[not found] ` <1487327904-28311-3-git-send-email-fisaksen-rdvid1DuHRBWk0Htik3J/w@public.gmane.org>
2017-02-19 16:30 ` Mark Brown
2017-02-19 16:30 ` Mark Brown
2017-02-17 10:38 ` [PATCH v2 3/6] spi: davinci: use rx buffer as dummy tx buffer Frode Isaksen
2017-02-17 10:38 ` Frode Isaksen
[not found] ` <1487327904-28311-4-git-send-email-fisaksen-rdvid1DuHRBWk0Htik3J/w@public.gmane.org>
2017-03-15 19:37 ` Applied "spi: davinci: use rx buffer as dummy tx buffer" to the spi tree Mark Brown
2017-03-15 19:37 ` Mark Brown
2017-02-17 10:38 ` [PATCH v2 4/6] spi: davinci: flush caches when performing DMA Frode Isaksen
2017-02-17 10:38 ` Frode Isaksen
[not found] ` <1487327904-28311-5-git-send-email-fisaksen-rdvid1DuHRBWk0Htik3J/w@public.gmane.org>
2017-02-17 10:57 ` Vignesh R
2017-02-17 10:57 ` Vignesh R
[not found] ` <5fab0c33-6e1d-c63a-8758-6672236045a7-l0cyMroinI0@public.gmane.org>
2017-02-17 11:22 ` Russell King - ARM Linux
2017-02-17 11:22 ` Russell King - ARM Linux
[not found] ` <20170217112247.GE21222-l+eeeJia6m9URfEZ8mYm6t73F7V6hmMc@public.gmane.org>
2017-02-17 11:36 ` Frode Isaksen
2017-02-17 11:36 ` Frode Isaksen
[not found] ` <eaf93c6c-52a7-826b-9c53-2b13c0b280ca-rdvid1DuHRBWk0Htik3J/w@public.gmane.org>
2017-02-17 12:07 ` Russell King - ARM Linux
2017-02-17 12:07 ` Russell King - ARM Linux
2017-02-17 17:45 ` Frode Isaksen
2017-02-17 17:45 ` Frode Isaksen
[not found] ` <20170217120749.GF21222-l+eeeJia6m9URfEZ8mYm6t73F7V6hmMc@public.gmane.org>
2017-02-20 6:55 ` Vignesh R
2017-02-20 6:55 ` Vignesh R
[not found] ` <0f3607fd-4542-be92-da2e-b2da6f8ac26f-l0cyMroinI0@public.gmane.org>
2017-02-20 9:26 ` Frode Isaksen
2017-02-20 9:26 ` Frode Isaksen
[not found] ` <f0fcc000-6c07-647a-ada2-04b61f0e2e3b-rdvid1DuHRBWk0Htik3J/w@public.gmane.org>
2017-02-20 9:47 ` Vignesh R
2017-02-20 9:47 ` Vignesh R
[not found] ` <57721a60-52bb-c9d1-d5a7-ae450e7adcc0-l0cyMroinI0@public.gmane.org>
2017-02-20 10:34 ` Frode Isaksen
2017-02-20 10:34 ` Frode Isaksen
[not found] ` <2a1954a3-edbd-7ac4-6fde-9b6d046a6560-rdvid1DuHRBWk0Htik3J/w@public.gmane.org>
2017-02-20 11:27 ` Vignesh R
2017-02-20 11:27 ` Vignesh R
[not found] ` <954333da-4d15-ce77-4021-268530365edc-l0cyMroinI0@public.gmane.org>
2017-02-20 15:49 ` Frode Isaksen
2017-02-20 15:49 ` Frode Isaksen
[not found] ` <69d41f8a-371b-abd9-7e78-f8701652877f-rdvid1DuHRBWk0Htik3J/w@public.gmane.org>
2017-02-21 5:08 ` Vignesh R
2017-02-21 5:08 ` Vignesh R
2017-02-17 10:38 ` [PATCH v2 5/6] spi: davinci: do not use DMA if transfer length is less than 16 Frode Isaksen
2017-02-17 10:38 ` Frode Isaksen
[not found] ` <1487327904-28311-6-git-send-email-fisaksen-rdvid1DuHRBWk0Htik3J/w@public.gmane.org>
2017-02-17 16:37 ` Arnd Bergmann
2017-02-17 16:37 ` Arnd Bergmann
[not found] ` <CAK8P3a24HkxrU-6a727RY5JqwQgyf9SpprPXvurSqf1Q_W_AMQ-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2017-02-17 16:43 ` Frode Isaksen
2017-02-17 16:43 ` Frode Isaksen
[not found] ` <3358b5f1-c7b6-0955-0c36-6f135a585762-rdvid1DuHRBWk0Htik3J/w@public.gmane.org>
2017-02-17 16:55 ` Arnd Bergmann [this message]
2017-02-17 16:55 ` Arnd Bergmann
2017-02-17 10:38 ` [PATCH v2 6/6] spi: loopback-test: add option to use vmalloc'ed buffers Frode Isaksen
2017-02-17 10:38 ` Frode Isaksen
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='CAK8P3a2_FL2rBcHdmK040LMRMZCV-70pOBFVUh=VpO+q45nQ0Q@mail.gmail.com' \
--to=arnd-r2ngtmty4d4@public.gmane.org \
--cc=broonie-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org \
--cc=fisaksen-rdvid1DuHRBWk0Htik3J/w@public.gmane.org \
--cc=khilman-rdvid1DuHRBWk0Htik3J/w@public.gmane.org \
--cc=linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r@public.gmane.org \
--cc=linux-spi-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=nsekhar-l0cyMroinI0@public.gmane.org \
--cc=ptitiano-rdvid1DuHRBWk0Htik3J/w@public.gmane.org \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.