From: "Li, Xiaoyun" <xiaoyun.li@intel.com>
To: "Wang, Liang-min" <liang-min.wang@intel.com>,
"Richardson, Bruce" <bruce.richardson@intel.com>,
"Ananyev, Konstantin" <konstantin.ananyev@intel.com>
Cc: "Zhang, Qi Z" <qi.z.zhang@intel.com>,
"Lu, Wenzhuo" <wenzhuo.lu@intel.com>,
"Zhang, Helin" <helin.zhang@intel.com>,
"pierre@emutex.com" <pierre@emutex.com>,
"dev@dpdk.org" <dev@dpdk.org>
Subject: [dpdk-dev] [PATCH v2 1/3] eal/x86: run-time dispatch over memcpy
Date: Wed, 20 Sep 2017 06:57:33 +0000 [thread overview]
Message-ID: <B9E724F4CB7543449049E7AE7669D82F460A0F@SHSMSX101.ccr.corp.intel.com> (raw)
In-Reply-To: <B9E724F4CB7543449049E7AE7669D82F443E45@SHSMSX101.ccr.corp.intel.com>
Hi all
After further investigating, we have found some benefits with the patchset.
So the plan is to add a config parameter CONFIG_RTE_ENABLE_RUNTIME_DISPATCH.
By default, the value is "n" and would use current memcpy codes.
Only if users config it to "y", it would use the run-time dispatch codes(without inline).
Best Regards,
Xiaoyun Li
> -----Original Message-----
> From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Li, Xiaoyun
> Sent: Tuesday, September 12, 2017 10:27
> To: Wang, Liang-min <liang-min.wang@intel.com>; Richardson, Bruce
> <bruce.richardson@intel.com>; Ananyev, Konstantin
> <konstantin.ananyev@intel.com>
> Cc: Zhang, Qi Z <qi.z.zhang@intel.com>; Lu, Wenzhuo
> <wenzhuo.lu@intel.com>; Zhang, Helin <helin.zhang@intel.com>;
> pierre@emutex.com; dev@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH v2 1/3] eal/x86: run-time dispatch over
> memcpy
>
> Hi ALL
>
> After investigating, most DPDK codes are already run-time dispatching. Only
> rte_memcpy chooses the ISA at build-time.
>
> To modify memcpy, there are two ways. The first one is function pointers
> and another is function multi-versioning in GCC.
>
> But memcpy has been greatly optimized and gets benefit from total inline. If
> changing it to run-time dispatching via function pointers, the perf will drop a
> lot especially when copy size is small.
>
> And function multi-versioning in GCC only works for C++. Even if it is said that
> GCC6 can support C, but in fact it does not support C in my trial.
>
>
>
> The attachment is the perf results of memcpy with and without my patch and
> original DPDK codes but without inline.
>
> It's just for comparison, so right now, I only tested on Broadwell, using AVX2.
>
> The results are from running test/test/test_memcpy_perf.c.
>
> (C = compile-time constant)
>
> /* Do aligned tests where size is a variable */
>
> /* Do aligned tests where size is a compile-time constant */
>
> /* Do unaligned tests where size is a variable */
>
> /* Do unaligned tests where size is a compile-time constant */
>
>
>
> 4-7 means dpdk costs time 4 and glibc costs time 7
>
> For size smaller than 128 bytes. This patch's perf is bad and even worse than
> glibc.
>
> When size grows, the perf is better than glibc but worse than original dpdk.
>
> And when grows above about 1024 bytes, it performs similarly to original
> dpdk.
>
> Furthermore, if delete inline in original dpdk, the perf are similar to the perf
> with patch.
>
> Different situations(4 types, such as cache to cache) perform differently but
> the trend is the same (size grows, perf grows).
>
>
>
> So if needs dynamic, needs sacrifices some perf and needs to compile for the
> minimum target (e.g. compile for target avx, run on avx, avx2, avx512f).
>
>
>
> Thus, I think this feature shouldn't be delivered in this release.
>
>
>
> Best Regards,
>
> Xiaoyun Li
next prev parent reply other threads:[~2017-09-20 6:57 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-08-25 2:06 [dpdk-dev] [PATCH 0/3] dynamic linking support Xiaoyun Li
2017-08-25 2:06 ` [dpdk-dev] [PATCH 1/3] eal/x86: run-time dispatch over memcpy Xiaoyun Li
2017-08-30 14:56 ` Ananyev, Konstantin
2017-08-30 17:51 ` Bruce Richardson
2017-08-31 1:21 ` Lu, Wenzhuo
2017-08-30 18:00 ` Stephen Hemminger
2017-08-31 1:23 ` Lu, Wenzhuo
2017-08-31 5:05 ` Stephen Hemminger
2017-08-31 5:24 ` Li, Xiaoyun
2017-08-25 2:06 ` [dpdk-dev] [PATCH 2/3] app/test: run-time dispatch over memcpy perf test Xiaoyun Li
2017-08-25 2:06 ` [dpdk-dev] [PATCH 3/3] efd: run-time dispatch over x86 EFD functions Xiaoyun Li
2017-09-01 8:56 ` [dpdk-dev] [PATCH v2 0/3] dynamic linking support Xiaoyun Li
2017-09-01 8:57 ` [dpdk-dev] [PATCH v2 1/3] eal/x86: run-time dispatch over memcpy Xiaoyun Li
2017-09-01 9:16 ` Ananyev, Konstantin
2017-09-01 9:28 ` Li, Xiaoyun
2017-09-01 10:38 ` Ananyev, Konstantin
2017-09-04 1:41 ` Li, Xiaoyun
[not found] ` <B9E724F4CB7543449049E7AE7669D82F44216E@SHSMSX101.ccr.corp.intel.com>
[not found] ` <B9E724F4CB7543449049E7AE7669D82F442FE6@SHSMSX101.ccr.corp.intel.com>
2017-09-12 2:27 ` Li, Xiaoyun
2017-09-20 6:57 ` Li, Xiaoyun [this message]
2017-09-01 15:34 ` Stephen Hemminger
2017-09-01 8:57 ` [dpdk-dev] [PATCH v2 2/3] app/test: run-time dispatch over memcpy perf test Xiaoyun Li
2017-09-01 8:57 ` [dpdk-dev] [PATCH v2 3/3] efd: run-time dispatch over x86 EFD functions Xiaoyun Li
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=B9E724F4CB7543449049E7AE7669D82F460A0F@SHSMSX101.ccr.corp.intel.com \
--to=xiaoyun.li@intel.com \
--cc=bruce.richardson@intel.com \
--cc=dev@dpdk.org \
--cc=helin.zhang@intel.com \
--cc=konstantin.ananyev@intel.com \
--cc=liang-min.wang@intel.com \
--cc=pierre@emutex.com \
--cc=qi.z.zhang@intel.com \
--cc=wenzhuo.lu@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).