[dpdk-dev] [PATCH v4 07/12] librte_ether: extend flow director struct

2016-03-20 Thread Wu, Jingjing
Hi, Thomas > -Original Message- > From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com] > Sent: Friday, March 18, 2016 7:44 PM > To: Wu, Jingjing > Cc: dev at dpdk.org; Richardson, Bruce > Subject: Re: [dpdk-dev] [PATCH v4 07/12] librte_ether: extend flow director > struct > > H

[dpdk-dev] [PATCH v4 07/12] librte_ether: extend flow director struct

2016-03-20 Thread Wu, Jingjing
> -Original Message- > From: Wu, Jingjing > Sent: Sunday, March 20, 2016 4:57 PM > To: 'Thomas Monjalon' > Cc: dev at dpdk.org; Richardson, Bruce > Subject: RE: [dpdk-dev] [PATCH v4 07/12] librte_ether: extend flow director > struct > > Hi, Thomas > > > > -Original Message-

[dpdk-dev] [PATCH v3 4/4] eal/arm: introduce CONFIG_RTE_ARCH_ARM_NEON_MEMCPY

2016-03-20 Thread Jan Viktorin
On Sat, 19 Mar 2016 21:14:57 +0100 Thomas Monjalon wrote: > 2016-03-19 20:58, Jan Viktorin: > > The flag is used to enable memcpy optimizations in EAL. As it is not always > > the performance benefit, the flag allows to disable it. > > Ideally the default should be to choose the best optimizat

[dpdk-dev] [PATCH v3 4/4] eal/arm: introduce CONFIG_RTE_ARCH_ARM_NEON_MEMCPY

2016-03-20 Thread Jan Viktorin
On Sun, 20 Mar 2016 10:41:10 +0100 Jan Viktorin wrote: > On Sat, 19 Mar 2016 21:14:57 +0100 > Thomas Monjalon wrote: > > > 2016-03-19 20:58, Jan Viktorin: > > > The flag is used to enable memcpy optimizations in EAL. As it is not > > > always > > > the performance benefit, the flag allows to

[dpdk-dev] [PATCH v3 4/4] eal/arm: introduce CONFIG_RTE_ARCH_ARM_NEON_MEMCPY

2016-03-20 Thread Thomas Monjalon
2016-03-20 10:41, Jan Viktorin: > On Sat, 19 Mar 2016 21:14:57 +0100 > Thomas Monjalon wrote: > > > 2016-03-19 20:58, Jan Viktorin: > > > The flag is used to enable memcpy optimizations in EAL. As it is not > > > always > > > the performance benefit, the flag allows to disable it. > > > > Ide

[dpdk-dev] [PATCH v3 4/4] eal/arm: introduce CONFIG_RTE_ARCH_ARM_NEON_MEMCPY

2016-03-20 Thread Thomas Monjalon
2016-03-20 10:46, Jan Viktorin: > On Sun, 20 Mar 2016 10:41:10 +0100 > Jan Viktorin wrote: > > > On Sat, 19 Mar 2016 21:14:57 +0100 > > Thomas Monjalon wrote: > > > > > 2016-03-19 20:58, Jan Viktorin: > > > > The flag is used to enable memcpy optimizations in EAL. As it is not > > > > always

[dpdk-dev] [PATCH v4 07/12] librte_ether: extend flow director struct

2016-03-20 Thread Thomas Monjalon
2016-03-20 09:02, Wu, Jingjing: > From: Wu, Jingjing > > From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com] > > > 2016-03-10 11:25, Jingjing Wu: > > > > This patch changed rte_eth_fdir_flow from union to struct to > > > > support more packets formats, for example, Vxlan and GRE tunnel > >

[dpdk-dev] DPDK and HW offloads

2016-03-20 Thread Zhang, Helin
> -Original Message- > From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com] > Sent: Saturday, March 19, 2016 2:01 AM > To: Stephen Hemminger > Cc: Zhang, Helin ; dev at dpdk.org > Subject: Re: DPDK and HW offloads > > 2016-03-18 10:16, Stephen Hemminger: > > As I look at how the

[dpdk-dev] [PATCH v3 2/4] arm: detect NEON cpu feature by checking __ARM_NEON

2016-03-20 Thread Jerin Jacob
On Sat, Mar 19, 2016 at 08:58:03PM +0100, Jan Viktorin wrote: > The __ARM_NEON declares that the arm_neon.h is available which is not true for > the __ARM_NEON_FP. The __ARM_NEON_FP is not provided by aarch64 gcc. It depends on specific aarch64 compiler builds. Some aarch64 gcc versions do provide

[dpdk-dev] [PATCH v3 4/4] eal/arm: introduce CONFIG_RTE_ARCH_ARM_NEON_MEMCPY

2016-03-20 Thread Jerin Jacob
On Sun, Mar 20, 2016 at 11:29:48AM +0100, Thomas Monjalon wrote: > 2016-03-20 10:41, Jan Viktorin: > > On Sat, 19 Mar 2016 21:14:57 +0100 > > Thomas Monjalon wrote: > > > > > 2016-03-19 20:58, Jan Viktorin: > > > > The flag is used to enable memcpy optimizations in EAL. As it is not > > > > alwa

[dpdk-dev] DPDK and HW offloads

2016-03-20 Thread Thomas Monjalon
2016-03-20 14:17, Zhang, Helin: > From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com] > > 2016-03-18 10:16, Stephen Hemminger: > > > Right now, all those offload features are pretty much unusable in a > > > real product without lots and lots of extra codes and huge bug > > > surface. It bot