2016-05-24 21:23, Zhihong Wang:
> This patch fixes rte_memcpy performance in Haswell and Broadwell for
> vhost when copy size larger than 256 bytes.
>
> It is observed that for large copies like 1024/1518 ones, rte_memcpy
> suffers high ratio of store buffer full issue which causes pipeline
> to
> -Original Message-
> From: Xu, Qian Q
> Sent: Thursday, May 26, 2016 1:19 PM
> To: Wang, Zhihong ; dev at dpdk.org
> Cc: Wang, Zhihong
> Subject: RE: [dpdk-dev] [PATCH] eal: fix rte_memcpy perf in hsw/bdw
>
> Tested-by: Qia
rformance increase on BDW-EP CPU server.
Thanks
Qian
-Original Message-
From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Zhihong Wang
Sent: Wednesday, May 25, 2016 9:23 AM
To: dev at dpdk.org
Cc: Wang, Zhihong
Subject: [dpdk-dev] [PATCH] eal: fix rte_memcpy perf in hsw/bdw
This pa
This patch fixes rte_memcpy performance in Haswell and Broadwell for
vhost when copy size larger than 256 bytes.
It is observed that for large copies like 1024/1518 ones, rte_memcpy
suffers high ratio of store buffer full issue which causes pipeline
to stall in scenarios like vhost enqueue. This
4 matches
Mail list logo