15 Dec
2016
15 Dec
'16
4:29 p.m.
On Thu, Dec 15, 2016 at 01:23:15PM -0200, Fabio Estevam wrote:
If CONFIG_USE_ARCH_MEMCPY is selected, let's use the assembly optimized memcpy implementation for the 'cp' command.
Currently only Blackfin uses memcpy for the 'cp' command, so extend this to the CONFIG_USE_ARCH_MEMCPY users.
Tested on a mx6qsabreauto board where a 5x gain in performance is seen when reading 10MB from the parallel NOR memory.
Signed-off-by: Fabio Estevam fabio.estevam@nxp.com
Sending as RFC as I don't know if any extra checks would be required here, so I appreciate any feedback.
We should re-work this to simply call memcpy() always, outside of the case of dealing with flash/dataflash as that would simplify this code, no?
--
Tom