From: Jerry Van Baren <gerald.vanbaren@ge.com>
To: u-boot@lists.denx.de
Subject: [U-Boot] [PATCH 1/3 v2] 83xx: Default to using DMA to initialize SDRAM
Date: Thu, 09 Jul 2009 13:00:23 -0400 [thread overview]
Message-ID: <4A562227.2020803@ge.com> (raw)
In-Reply-To: <20090709155823.GA29383@ovro.caltech.edu>
Ira W. Snyder wrote:
> On Wed, Jul 08, 2009 at 05:58:50PM -0700, Ira W. Snyder wrote:
>> On Wed, Jul 08, 2009 at 07:32:26PM -0500, Peter Tyser wrote:
>>> On Thu, 2009-07-09 at 08:24 +0800, Liu Dave-R63238 wrote:
[snip]
>> Both the DMA and CPU methods are definitely on the same order of
>> magnitude. The time taken by the CFI flash driver is MUCH longer than
>> the SDRAM initialization. I wonder, should the icache be enabled for
>> that as well?
>>
>> I'll do some more testing when I get back to the office tomorrow.
>>
>
> Ok, I've added back the get_tbms() code, and created a routine to
> initialize ECC with the CPU. I've inlined my patch below, just for
> reference.
>
> DMA 945ms
> CPU 581ms
>
> As an interesting comparison, I also benchmarked the method of using the
> DDR controller to initialize ECC.
>
> DDRC 129ms
>
> So there you have it. Dave Liu is correct, the CPU method is faster,
> though definitely on the same order of magnitude with the
> icache_enable()/icache_disable() patch.
Thanks for the measurements and the update.
> I may stick with the DDRC method on my board, the difference is just
> amazing. The flash init still takes up most of the boot process,
> however.
>
> Peter, feel free to fold the patch below into your own work.
> Ira
[snip]
FWIIW, and it doesn't materially change your results, but it would have
been better to duplicate the get_tbms() call and put it directly around
the *_meminit() calls rather than having the print statements inside the
timed part. Since U-Boot printing is a blocking call (generally), you
are adding the UART Tx time to your measurement.
#if 0
debug("\nInitializing ECC (using DMA)!\n");
s = get_tbms();
dma_meminit(CONFIG_MEM_INIT_VALUE, dram_size);
#else
debug("\nInitializing ECC (using CPU)!\n");
s = get_tbms();
cpu_meminit(CONFIG_MEM_INIT_VALUE, dram_size);
#endif
e = get_tbms();
> + s = get_tbms();
> +#if 0
> + debug("\nInitializing ECC (using DMA)!\n");
> dma_meminit(CONFIG_MEM_INIT_VALUE, dram_size);
> +#else
> + debug("\nInitializing ECC (using CPU)!\n");
> + cpu_meminit(CONFIG_MEM_INIT_VALUE, dram_size);
> +#endif
> + e = get_tbms();
>
> debug("\nREADY!\n");
> + debug("ddr init duration: %ld ms\n", e - s);
>
> /* Clear All ECC Errors */
> if ((ddr->err_detect & ECC_ERROR_DETECT_MME) == ECC_ERROR_DETECT_MME)
Thanks,
gvb
next prev parent reply other threads:[~2009-07-09 17:00 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-07-09 0:11 [U-Boot] [PATCH 0/3 v2] DMA ECC update Peter Tyser
2009-07-09 0:11 ` [U-Boot] [PATCH 1/3 v2] 83xx: Default to using DMA to initialize SDRAM Peter Tyser
2009-07-09 0:24 ` [U-Boot] [PATCH 1/3 v2] 83xx: Default to using DMA to initializeSDRAM Liu Dave-R63238
2009-07-09 0:32 ` Peter Tyser
2009-07-09 0:43 ` Liu Dave-R63238
2009-07-09 12:39 ` Jerry Van Baren
2009-07-09 12:51 ` Jerry Van Baren
2009-07-09 0:58 ` Ira W. Snyder
2009-07-09 15:58 ` [U-Boot] [PATCH 1/3 v2] 83xx: Default to using DMA to initialize SDRAM Ira W. Snyder
2009-07-09 17:00 ` Jerry Van Baren [this message]
2009-07-14 9:22 ` Wolfgang Denk
2009-07-14 14:41 ` Kumar Gala
2009-07-14 14:42 ` Peter Tyser
2009-07-14 15:21 ` Wolfgang Denk
2009-07-14 17:32 ` Kim Phillips
2009-07-14 18:37 ` Peter Tyser
2009-07-09 0:11 ` [U-Boot] [PATCH 2/3 v2] 83xx: Add CONFIG_MEM_INIT_VALUE for boards with ECC Peter Tyser
2009-07-09 0:11 ` [U-Boot] [PATCH 3/3 v2] fsl_dma: Fix SDRAM initial value Peter Tyser
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=4A562227.2020803@ge.com \
--to=gerald.vanbaren@ge.com \
--cc=u-boot@lists.denx.de \
/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