> Hi Zhihong Wang
>
> I test avx512 rte_memcpy found the performanc for ovs dpdk is lower than
> avx2 rte_memcpy.
Hi Haifeng,
AVX512 memcpy is marked as experimental and disabled by default, its
benefit varies from case to case. So enable it only when the case
(SW + HW setup with expected data p
在 2016/1/18 11:05, Zhihong Wang 写道:
> This patch set optimizes DPDK memcpy for AVX512 platforms, to make full
> utilization of hardware resources and deliver high performance.
>
> In current DPDK, memcpy holds a large proportion of execution time in
> libs like Vhost, especially for large packets,
2 matches
Mail list logo
