On Thu, Jan 27, 2011 at 2:03 AM, David Gilbert david.gilbert@linaro.org wrote:

On 26 January 2011 12:12, Dave Martin dave.martin@linaro.org wrote:

...

Hi Vijay,

On Sat, Jan 22, 2011 at 9:59 AM, Vijay Kilari vijay.kilari@gmail.com wrote:

...

Hello Dave,

Thanks for this info.

I have few more queries after looking at the results of memset on A9 & A8. I agree that externel bus speed matters in comparision across platforms.

1. Why memset is performance is good on A8 than A9?. any justification?

I've CC'd the linaro-toolchain list who have been working on this topic and may be able to provide you with more information.

Unfortunately we don't know why Neon was a bad idea for memset etc on A9, it's just the tests show it being worse and the advice we get says to avoid it - we've just not got an explanation.

To add some hearsay to the mix, I understand that the NEON unit on the A8 has a 128 bit connection straight into the L2 cache while the core has a 64 bit connection into the L1. This means that a NEON memcpy() (and probably memset()) on the A8 does twice as well for large or cold writes.

-- Michael