From: Bruce Richardson <bruce.richardson@intel.com>
To: "Yang, Zhiyong" <zhiyong.yang@intel.com>
Cc: "Ananyev, Konstantin" <konstantin.ananyev@intel.com>,
Thomas Monjalon <thomas.monjalon@6wind.com>,
"dev@dpdk.org" <dev@dpdk.org>,
"yuanhan.liu@linux.intel.com" <yuanhan.liu@linux.intel.com>,
"De Lara Guarch, Pablo" <pablo.de.lara.guarch@intel.com>
Subject: Re: [dpdk-dev] [PATCH 1/4] eal/common: introduce rte_memset on IA platform
Date: Thu, 15 Dec 2016 10:12:43 +0000 [thread overview]
Message-ID: <20161215101242.GA125588@bricha3-MOBL3.ger.corp.intel.com> (raw)
In-Reply-To: <E182254E98A5DA4EB1E657AC7CB9BD2A3EB599D4@BGSMSX101.gar.corp.intel.com>
On Thu, Dec 15, 2016 at 06:51:08AM +0000, Yang, Zhiyong wrote:
> Hi, Thomas, Konstantin:
>
> > -----Original Message-----
> > From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Yang, Zhiyong
> > Sent: Sunday, December 11, 2016 8:33 PM
> > To: Ananyev, Konstantin <konstantin.ananyev@intel.com>; Thomas
> > Monjalon <thomas.monjalon@6wind.com>
> > Cc: dev@dpdk.org; yuanhan.liu@linux.intel.com; Richardson, Bruce
> > <bruce.richardson@intel.com>; De Lara Guarch, Pablo
> > <pablo.de.lara.guarch@intel.com>
> > Subject: Re: [dpdk-dev] [PATCH 1/4] eal/common: introduce rte_memset on
> > IA platform
> >
> > Hi, Konstantin, Bruce:
> >
> > > -----Original Message-----
> > > From: Ananyev, Konstantin
> > > Sent: Thursday, December 8, 2016 6:31 PM
> > > To: Yang, Zhiyong <zhiyong.yang@intel.com>; Thomas Monjalon
> > > <thomas.monjalon@6wind.com>
> > > Cc: dev@dpdk.org; yuanhan.liu@linux.intel.com; Richardson, Bruce
> > > <bruce.richardson@intel.com>; De Lara Guarch, Pablo
> > > <pablo.de.lara.guarch@intel.com>
> > > Subject: RE: [dpdk-dev] [PATCH 1/4] eal/common: introduce rte_memset
> > > on IA platform
> > >
> > >
> > >
> > > > -----Original Message-----
> > > > From: Yang, Zhiyong
> > > > Sent: Thursday, December 8, 2016 9:53 AM
> > > > To: Ananyev, Konstantin <konstantin.ananyev@intel.com>; Thomas
> > > > Monjalon <thomas.monjalon@6wind.com>
> > > > Cc: dev@dpdk.org; yuanhan.liu@linux.intel.com; Richardson, Bruce
> > > > <bruce.richardson@intel.com>; De Lara Guarch, Pablo
> > > > <pablo.de.lara.guarch@intel.com>
> > > > Subject: RE: [dpdk-dev] [PATCH 1/4] eal/common: introduce rte_memset
> > > > on IA platform
> > > >
> > > extern void *(*__rte_memset_vector)( (void *s, int c, size_t n);
> > >
> > > static inline void*
> > > rte_memset_huge(void *s, int c, size_t n) {
> > > return __rte_memset_vector(s, c, n); }
> > >
> > > static inline void *
> > > rte_memset(void *s, int c, size_t n)
> > > {
> > > If (n < XXX)
> > > return rte_memset_scalar(s, c, n);
> > > else
> > > return rte_memset_huge(s, c, n);
> > > }
> > >
> > > XXX could be either a define, or could also be a variable, so it can
> > > be setuped at startup, depending on the architecture.
> > >
> > > Would that work?
> > > Konstantin
> > >
> I have implemented the code for choosing the functions at run time.
> rte_memcpy is used more frequently, So I test it at run time.
>
> typedef void *(*rte_memcpy_vector_t)(void *dst, const void *src, size_t n);
> extern rte_memcpy_vector_t rte_memcpy_vector;
> static inline void *
> rte_memcpy(void *dst, const void *src, size_t n)
> {
> return rte_memcpy_vector(dst, src, n);
> }
> In order to reduce the overhead at run time,
> I assign the function address to var rte_memcpy_vector before main() starts to init the var.
>
> static void __attribute__((constructor))
> rte_memcpy_init(void)
> {
> if (rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX2))
> {
> rte_memcpy_vector = rte_memcpy_avx2;
> }
> else if (rte_cpu_get_flag_enabled(RTE_CPUFLAG_SSE4_1))
> {
> rte_memcpy_vector = rte_memcpy_sse;
> }
> else
> {
> rte_memcpy_vector = memcpy;
> }
>
> }
> I run the same virtio/vhost loopback tests without NIC.
> I can see the throughput drop when running choosing functions at run time
> compared to original code as following on the same platform(my machine is haswell)
> Packet size perf drop
> 64 -4%
> 256 -5.4%
> 1024 -5%
> 1500 -2.5%
> Another thing, I run the memcpy_perf_autotest, when N= <128,
> the rte_memcpy perf gains almost disappears
> When choosing functions at run time. For N=other numbers, the perf gains will become narrow.
>
How narrow. How significant is the improvement that we gain from having
to maintain our own copy of memcpy. If the libc version is nearly as
good we should just use that.
/Bruce
next prev parent reply other threads:[~2016-12-15 10:12 UTC|newest]
Thread overview: 44+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-12-05 8:26 [dpdk-dev] [PATCH 0/4] eal/common: introduce rte_memset and related test Zhiyong Yang
2016-12-02 10:00 ` Maxime Coquelin
2016-12-06 6:33 ` Yang, Zhiyong
2016-12-06 8:29 ` Maxime Coquelin
2016-12-07 9:28 ` Yang, Zhiyong
2016-12-07 9:37 ` Yuanhan Liu
2016-12-07 9:43 ` Yang, Zhiyong
2016-12-07 9:48 ` Yuanhan Liu
2016-12-05 8:26 ` [dpdk-dev] [PATCH 1/4] eal/common: introduce rte_memset on IA platform Zhiyong Yang
2016-12-02 10:25 ` Thomas Monjalon
2016-12-08 7:41 ` Yang, Zhiyong
2016-12-08 9:26 ` Ananyev, Konstantin
2016-12-08 9:53 ` Yang, Zhiyong
2016-12-08 10:27 ` Bruce Richardson
2016-12-08 10:30 ` Ananyev, Konstantin
2016-12-11 12:32 ` Yang, Zhiyong
2016-12-15 6:51 ` Yang, Zhiyong
2016-12-15 10:12 ` Bruce Richardson [this message]
2016-12-16 10:19 ` Yang, Zhiyong
2016-12-19 6:27 ` Yuanhan Liu
2016-12-20 2:41 ` Yao, Lei A
2016-12-15 10:53 ` Ananyev, Konstantin
2016-12-16 2:15 ` Yang, Zhiyong
2016-12-16 11:47 ` Ananyev, Konstantin
2016-12-20 9:31 ` Yang, Zhiyong
2016-12-08 15:09 ` Thomas Monjalon
2016-12-11 12:04 ` Yang, Zhiyong
2016-12-27 10:04 ` [dpdk-dev] [PATCH v2 0/4] eal/common: introduce rte_memset and related test Zhiyong Yang
2016-12-27 10:04 ` [dpdk-dev] [PATCH v2 1/4] eal/common: introduce rte_memset on IA platform Zhiyong Yang
2016-12-27 10:04 ` [dpdk-dev] [PATCH v2 2/4] app/test: add functional autotest for rte_memset Zhiyong Yang
2016-12-27 10:04 ` [dpdk-dev] [PATCH v2 3/4] app/test: add performance " Zhiyong Yang
2016-12-27 10:04 ` [dpdk-dev] [PATCH v2 4/4] lib/librte_vhost: improve vhost perf using rte_memset Zhiyong Yang
2017-01-09 9:48 ` [dpdk-dev] [PATCH v2 0/4] eal/common: introduce rte_memset and related test Yang, Zhiyong
2017-01-17 6:24 ` Yang, Zhiyong
2017-01-17 20:14 ` Thomas Monjalon
2017-01-18 0:15 ` Vincent JARDIN
2017-01-18 2:42 ` Yang, Zhiyong
2017-01-18 7:42 ` Thomas Monjalon
2017-01-19 1:36 ` Yang, Zhiyong
2016-12-05 8:26 ` [dpdk-dev] [PATCH 2/4] app/test: add functional autotest for rte_memset Zhiyong Yang
2016-12-05 8:26 ` [dpdk-dev] [PATCH 3/4] app/test: add performance " Zhiyong Yang
2016-12-05 8:26 ` [dpdk-dev] [PATCH 4/4] lib/librte_vhost: improve vhost perf using rte_memset Zhiyong Yang
2016-12-02 9:46 ` Thomas Monjalon
2016-12-06 8:04 ` Yang, Zhiyong
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20161215101242.GA125588@bricha3-MOBL3.ger.corp.intel.com \
--to=bruce.richardson@intel.com \
--cc=dev@dpdk.org \
--cc=konstantin.ananyev@intel.com \
--cc=pablo.de.lara.guarch@intel.com \
--cc=thomas.monjalon@6wind.com \
--cc=yuanhan.liu@linux.intel.com \
--cc=zhiyong.yang@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).