; Zhang, Helin ;
> ophi...@mellanox.com
> Subject: Re: [dpdk-dev] [PATCH v8 1/3] eal/x86: run-time dispatch over
> memcpy
>
> 02/11/2017 11:22, Wang, Zhihong:
> > > I don't know what is creating this drop exactly.
> > > When doing different tests on different envir
02/11/2017 11:58, Li, Xiaoyun:
> From: Thomas Monjalon [mailto:tho...@monjalon.net]
> > 02/11/2017 11:22, Wang, Zhihong:
> > > > I don't know what is creating this drop exactly.
> > > > When doing different tests on different environments, we do not see
> > > > this drop.
> > > > If nobody else can
@mellanox.com
> Subject: Re: [dpdk-dev] [PATCH v8 1/3] eal/x86: run-time dispatch over
> memcpy
>
> 02/11/2017 11:22, Wang, Zhihong:
> > > I don't know what is creating this drop exactly.
> > > When doing different tests on different environments, we do not see
> &
02/11/2017 11:22, Wang, Zhihong:
> > I don't know what is creating this drop exactly.
> > When doing different tests on different environments, we do not see this
> > drop.
> > If nobody else can see such issue, I guess we can ignore it.
>
> Hi Thomas, Xiaoyun,
>
> With this patch (commit 84cc318
> I don't know what is creating this drop exactly.
> When doing different tests on different environments, we do not see this
> drop.
> If nobody else can see such issue, I guess we can ignore it.
Hi Thomas, Xiaoyun,
With this patch (commit 84cc318424d49372dd2a5fbf3cf84426bf95acce) I see
more tha
25/10/2017 09:25, Thomas Monjalon:
> 25/10/2017 08:55, Li, Xiaoyun:
> > From: Li, Xiaoyun
> > > From: Richardson, Bruce
> > > > On Thu, Oct 19, 2017 at 11:00:33AM +0200, Thomas Monjalon wrote:
> > > > > 19/10/2017 10:50, Li, Xiaoyun:
> > > > > > From: Thomas Monjalon
> > > > > > > 19/10/2017 09:51,
t: Re: [dpdk-dev] [PATCH v8 1/3] eal/x86: run-time dispatch over
> memcpy
>
> 25/10/2017 10:54, Li, Xiaoyun:
> > > > > > > I think we should focus on micro-benchmark and find a
> > > > > > > reasonnable threshold for a reasonnable drop tradeof
2017 7:55 AM
> > > To: Li, Xiaoyun ; Richardson, Bruce
> > > ; Thomas Monjalon
> > > Cc: Ananyev, Konstantin ; dev@dpdk.org;
> > > Lu, Wenzhuo ; Zhang, Helin
> > > ; ophi...@mellanox.com
> > > Subject: RE: [dpdk-dev] [PATCH v8 1/3] eal/x86: run-t
25/10/2017 10:54, Li, Xiaoyun:
> > > > > > I think we should focus on micro-benchmark and find a
> > > > > > reasonnable threshold for a reasonnable drop tradeoff.
> > > > > >
> > > > > Sadly, it may not be that simple. What shows best performance for
> > > > > micro- benchmarks may not show the sa
g;
> > Lu, Wenzhuo ; Zhang, Helin
> > ; ophi...@mellanox.com
> > Subject: RE: [dpdk-dev] [PATCH v8 1/3] eal/x86: run-time dispatch over
> > memcpy
> >
> > Hi
> >
> > > -Original Message-
> > > From: dev [mailto:dev-boun...@dpdk.or
gt; >
> > Cc: Ananyev, Konstantin ; dev@dpdk.org;
> > Lu, Wenzhuo ; Zhang, Helin
> > ; ophi...@mellanox.com
> > Subject: Re: [dpdk-dev] [PATCH v8 1/3] eal/x86: run-time dispatch over
> > memcpy
> >
> >
> >
> > > -Original Message---
25/10/2017 08:55, Li, Xiaoyun:
> From: Li, Xiaoyun
> > From: Richardson, Bruce
> > > On Thu, Oct 19, 2017 at 11:00:33AM +0200, Thomas Monjalon wrote:
> > > > 19/10/2017 10:50, Li, Xiaoyun:
> > > > > From: Thomas Monjalon
> > > > > > 19/10/2017 09:51, Li, Xiaoyun:
> > > > > > > From: Thomas Monjalon
nanyev, Konstantin
> > ; dev@dpdk.org; Lu, Wenzhuo
> > ; Zhang, Helin ;
> > ophi...@mellanox.com
> > Subject: Re: [dpdk-dev] [PATCH v8 1/3] eal/x86: run-time dispatch over
> > memcpy
> >
> > On Thu, Oct 19, 2017 at 11:00:33AM +0200, Thomas Monjalon wrote:
&g
net]
> > > > Sent: Thursday, October 19, 2017 16:34
> > > > To: Li, Xiaoyun
> > > > Cc: Ananyev, Konstantin ;
> > > > Richardson, Bruce ; dev@dpdk.org; Lu,
> > > > Wenzhuo ; Zhang, Helin
> > > > ; ophi...@mellanox.com
> > > &
o: Li, Xiaoyun
> > > Cc: Ananyev, Konstantin ; Richardson,
> > > Bruce ; dev@dpdk.org; Lu, Wenzhuo
> > > ; Zhang, Helin ;
> > > ophi...@mellanox.com
> > > Subject: Re: [dpdk-dev] [PATCH v8 1/3] eal/x86: run-time dispatch over
> > > memcpy
&g
, Wenzhuo
> > ; Zhang, Helin ;
> > ophi...@mellanox.com
> > Subject: Re: [dpdk-dev] [PATCH v8 1/3] eal/x86: run-time dispatch over
> > memcpy
> >
> > 19/10/2017 09:51, Li, Xiaoyun:
> > > From: Thomas Monjalon [mailto:tho...@monjalon.net]
> > >
gt; > Bruce ; dev@dpdk.org; Lu, Wenzhuo
> > ; Zhang, Helin ;
> > ophi...@mellanox.com
> > Subject: Re: [dpdk-dev] [PATCH v8 1/3] eal/x86: run-time dispatch over
> > memcpy
> >
> > 19/10/2017 09:51, Li, Xiaoyun:
> > > From: Thomas Monjalon [mailto:tho...@monjalon.ne
t: Re: [dpdk-dev] [PATCH v8 1/3] eal/x86: run-time dispatch over
> memcpy
>
> 19/10/2017 09:51, Li, Xiaoyun:
> > From: Thomas Monjalon [mailto:tho...@monjalon.net]
> > > 19/10/2017 04:45, Li, Xiaoyun:
> > > > Hi
> > > > > > >
> > >
19/10/2017 09:51, Li, Xiaoyun:
> From: Thomas Monjalon [mailto:tho...@monjalon.net]
> > 19/10/2017 04:45, Li, Xiaoyun:
> > > Hi
> > > > > >
> > > > > > The significant change of this patch is to call a function
> > > > > > pointer for packet size > 128 (RTE_X86_MEMCPY_THRESH).
> > > > > The perf dr
t: Re: [dpdk-dev] [PATCH v8 1/3] eal/x86: run-time dispatch over
> memcpy
>
> 19/10/2017 04:45, Li, Xiaoyun:
> > Hi
> > > > >
> > > > > The significant change of this patch is to call a function
> > > > > pointer for packet size > 1
19/10/2017 04:45, Li, Xiaoyun:
> Hi
> > > >
> > > > The significant change of this patch is to call a function pointer
> > > > for packet size > 128 (RTE_X86_MEMCPY_THRESH).
> > > The perf drop is due to function call replacing inline.
> > >
> > > > Please could you provide some benchmark numbers?
Hi
> > >
> > > The significant change of this patch is to call a function pointer
> > > for packet size > 128 (RTE_X86_MEMCPY_THRESH).
> > The perf drop is due to function call replacing inline.
> >
> > > Please could you provide some benchmark numbers?
> > I ran memcpy_perf_test which would show t
v, Konstantin
> > ; Richardson, Bruce
> >
> > Cc: dev@dpdk.org; Lu, Wenzhuo ; Zhang, Helin
> > ; ophi...@mellanox.com
> > Subject: Re: [dpdk-dev] [PATCH v8 1/3] eal/x86: run-time dispatch over
> > memcpy
> >
> > Hi,
> >
> > 13/10/2017 11
ject: Re: [dpdk-dev] [PATCH v8 1/3] eal/x86: run-time dispatch over
> memcpy
>
> Hi,
>
> 13/10/2017 11:01, Xiaoyun Li:
> > This patch dynamically selects functions of memcpy at run-time based
> > on CPU flags that current machine supports. This patch uses function
&g
Hi,
13/10/2017 11:01, Xiaoyun Li:
> This patch dynamically selects functions of memcpy at run-time based
> on CPU flags that current machine supports. This patch uses function
> pointers which are bind to the relative functions at constrctor time.
> In addition, AVX512 instructions set would be co
> -Original Message-
> From: Thomas Monjalon [mailto:tho...@monjalon.net]
> Sent: Friday, October 13, 2017 10:29 AM
> To: Li, Xiaoyun ; Ananyev, Konstantin
>
> Cc: dev@dpdk.org; Richardson, Bruce ; Lu, Wenzhuo
> ; Zhang, Helin
>
> Subject: Re: [dpdk-dev]
13/10/2017 11:01, Xiaoyun Li:
> lib/librte_eal/common/arch/x86/rte_memcpy.c| 59 ++
> lib/librte_eal/common/arch/x86/rte_memcpy_avx2.c | 44 +
> .../common/arch/x86/rte_memcpy_avx512f.c | 44 +
> lib/librte_eal/common/arch/x86/rte_memcpy_sse.c| 40 +
> .../common/includ
27 matches
Mail list logo
