On Wed, Jan 11, 2017 at 01:49:55PM -0200, Fabio Estevam wrote:
Hi Tom,
On Mon, Dec 19, 2016 at 8:09 PM, Tom Rini trini@konsulko.com wrote:
On Thu, Dec 15, 2016 at 04:00:13PM -0200, Fabio Estevam wrote:
Simplify the 'cp' command implementation by using the memcpy() function, which brings the additional benefit of performance gain for those who have CONFIG_USE_ARCH_MEMCPY selected.
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
Changes since v1:
- Always use memcpy()
I feel like this is correct. I also feel like it's too close to release to do this, so I'll be applying this shortly after release, thanks!
Is it a good time to apply this one now?
Yes, yes it would, thanks for the reminder. I'm kicking off a round of testing in travis-ci now along with another pre-req of finally, really, making arch/arm/lib/mem{set,cpy}.S be used by default in most cases.