[dpdk-dev] [PATCH 0/4] DPDK memcpy optimization
Luke Gorrie
luke at snabb.co
Thu Jan 22 19:27:12 CET 2015
On 22 January 2015 at 14:29, Jay Rolette <rolette at infiniteio.com> wrote:
> Microseconds matter. Scaling up to 100GbE, nanoseconds matter.
>
True. Is there a cut-off point though? Does one nanosecond matter?
AVX512 will fit a 64-byte packet in one register and move that to or from
memory with one instruction. L1/L2 cache bandwidth per server is growing on
a double-exponential curve (both bandwidth per core and cores per CPU). I
wonder if moving data around in cache will soon be too cheap for us to
justify worrying about.
I suppose that 1500 byte wide registers are still a ways off though ;-)
Cheers!
-Luke (begging your indulgence for wandering off on a tangent)
More information about the dev
mailing list