Per Forlin
be18a25189
usb: musb: ux500: optimize DMA callback routine
Skip the use of work queue and call musb_dma_completion() directly from
DMA callback context.
Here follows measurements on a Snowball board with ondemand governor active.
Performance using work queue:
(105 MB) copied, 6.23758 s, 16.8 MB/s
(105 MB) copied, 5.7151 s, 18.3 MB/s
(105 MB) copied, 5.83583 s, 18.0 MB/s
(105 MB) copied, 5.93611 s, 17.7 MB/s
Performance without work queue
(105 MB) copied, 5.62173 s, 18.7 MB/s
(105 MB) copied, 5.61811 s, 18.7 MB/s
(105 MB) copied, 5.57817 s, 18.8 MB/s
(105 MB) copied, 5.58549 s, 18.8 MB/s
Signed-off-by: Per Forlin <per.forlin@linaro.org>
Acked-by: Mian Yousaf Kaukab <mian.yousaf.kaukab@stericsson.com>
Signed-off-by: Felipe Balbi <balbi@ti.com>
2011-12-12 11:51:39 +02:00
..
2011-11-14 11:51:32 -08:00
2011-08-12 11:52:51 +03:00
2011-07-01 14:31:10 -07:00
2011-08-12 11:52:47 +03:00
2009-07-12 12:22:34 -07:00
2011-11-14 11:51:32 -08:00
2011-08-08 14:27:55 +01:00
2009-03-24 16:20:36 -07:00
2011-11-14 11:51:18 -08:00
2011-07-01 14:31:10 -07:00
2011-11-29 23:19:03 +09:00
2011-08-12 11:52:50 +03:00
2011-05-13 14:34:04 +03:00
2011-09-26 10:08:31 -04:00
2011-02-01 10:41:30 +02:00
2011-09-09 15:58:02 -07:00
2011-11-29 23:19:04 +09:00
2011-02-17 21:11:46 +02:00
2011-08-23 09:47:40 -07:00
2011-07-01 14:31:10 -07:00
2010-12-10 10:21:09 +02:00
2011-08-12 11:52:50 +03:00
2011-07-01 14:31:10 -07:00
2011-09-18 01:39:36 -07:00
2011-02-16 11:32:38 -08:00
2011-07-01 14:31:10 -07:00
2010-03-02 14:54:38 -08:00
2011-08-12 11:52:50 +03:00
2011-08-12 11:52:50 +03:00
2009-04-23 14:15:27 -07:00
2011-12-12 11:51:39 +02:00
2011-04-13 11:50:57 +03:00