DPDK patches and discussions
 help / color / mirror / Atom feed
From: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
To: Fady Bader <fady@mellanox.com>
Cc: Narcisa Ana Maria Vasile <navasile@linux.microsoft.com>,
	"dev@dpdk.org" <dev@dpdk.org>,
	Thomas Monjalon <thomas@monjalon.net>,
	Tasnim Bashar <tbashar@mellanox.com>,
	Tal Shnaiderman <talshn@mellanox.com>,
	Yohad Tor <yohadt@mellanox.com>,
	"harini.ramakrishnan@microsoft.com"
	<harini.ramakrishnan@microsoft.com>,
	"ocardona@microsoft.com" <ocardona@microsoft.com>,
	"anand.rawat@intel.com" <anand.rawat@intel.com>,
	"ranjit.menon@intel.com" <ranjit.menon@intel.com>,
	"olivier.matz@6wind.com" <olivier.matz@6wind.com>
Subject: Re: [dpdk-dev] [PATCH v2 3/3] eal/windows: librte_net build on Windows
Date: Mon, 20 Jul 2020 19:26:40 +0300	[thread overview]
Message-ID: <20200720192640.2cd0c58e@sovereign> (raw)
In-Reply-To: <VI1PR05MB58721DC152E7E557B6377D4DBF7B0@VI1PR05MB5872.eurprd05.prod.outlook.com>

On Mon, 20 Jul 2020 12:54:08 +0000, Fady Bader wrote:
[snip]
> > Getting the same error with a setup similar to Dmitry's. My setup: SDK 10.0.18362,  
> 
> I'm sending v4 patch that should resolve this.
> 
> > clang 9.0.0. What version of clang are you using on your system?
> > You can try installing LLVM 9.0.0 from
> > https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Freleases.ll
> > vm.org%2Fdownload.html&amp;data=02%7C01%7Cfady%40mellanox.com%7C0b
> > 29fed755494b55361d08d82a9ff2b4%7Ca652971c7d2e4d9ba6a4d149256f461b%7C0
> > %7C0%7C637306213753996879&amp;sdata=5lPQtvt8EO7q8OAYN60J8rIdYdNJHjsS
> > Pp%2B6P9PL3N0%3D&amp;reserved=0  
> 
> Thanks for the link, even with clang and SDK version same as yours and Dmitry's I'm still
> passing compilation and not getting the error described. 
> That's because the _m_prefetchw function that is defined in Clang's prfchwintrin.h is an
> intrinsic function corresponding to the instruction PREFETCHW that is part of the 
> instruction set extension 3DNOW, my processor doesn't support this instruction set 
> extension, so my compiler isn't reaching the part where it defines _m_prefetchw. 
> I think your processor does support the 3DNOW instruction set extension and that why 
> you are reaching this part and I'm not.

You can try building DPDK for a machine with RDSEED like so:

	meson -Dmachine=broadwell -Dexamples=helloworld build

FWIW, replacing <x86intrin.h> with <immintrin.h> in rte_random.c resolves the
issue on my setup and also looks valid as per [1]. I checked LLVM 10.0.0, and
both native and cross MinGW-w64 (GCC 9.2.0).

[1]:
https://software.intel.com/sites/landingpage/IntrinsicsGuide/#text=_rdseed32_step&expand=4541

  reply	other threads:[~2020-07-20 16:26 UTC|newest]

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <'20200610112326.18576-1-fady@mellanox.com'>
2020-06-10 12:00 ` [dpdk-dev] [PATCH v2 0/3] compile librte_net for windows Fady Bader
2020-06-10 12:00   ` [dpdk-dev] [PATCH v2 1/3] net: fix s_addr redefinition in Windows Fady Bader
2020-06-10 12:00   ` [dpdk-dev] [PATCH v2 2/3] net: add htons to minGW for Windows Fady Bader
2020-06-10 12:33     ` Jerin Jacob
2020-06-10 12:00   ` [dpdk-dev] [PATCH v2 3/3] eal/windows: librte_net build on Windows Fady Bader
2020-06-16  9:04     ` Thomas Monjalon
2020-07-06  8:44       ` Fady Bader
2020-06-20 19:22     ` Dmitry Kozlyuk
2020-06-28  9:48       ` Fady Bader
2020-07-17 22:22         ` Narcisa Ana Maria Vasile
2020-07-20 12:54           ` Fady Bader
2020-07-20 16:26             ` Dmitry Kozlyuk [this message]
2020-07-22 10:20               ` Fady Bader
2020-07-22 10:30                 ` Bruce Richardson
2020-07-27  8:54                   ` Fady Bader
2020-07-27  8:53                 ` Fady Bader
2020-07-08  8:25   ` [dpdk-dev] [PATCH v3 0/3] compile librte_net for windows Fady Bader
2020-07-08  8:25     ` [dpdk-dev] [PATCH v3 1/3] net: fix s_addr redefinition in Windows Fady Bader
2020-07-13 14:38       ` Olivier Matz
2020-07-15  6:26         ` Fady Bader
2020-07-08  8:25     ` [dpdk-dev] [PATCH v3 2/3] net: replace htons with rte_cpu_to_be_16 Fady Bader
2020-07-09 13:39       ` Morten Brørup
2020-07-13 14:38       ` Olivier Matz
2020-07-15  6:04         ` Fady Bader
2020-07-08  8:25     ` [dpdk-dev] [PATCH v3 3/3] eal/windows: librte_net build on Windows Fady Bader
2020-07-08  9:10       ` Thomas Monjalon
2020-07-08 10:19         ` Fady Bader
2020-07-23  7:08   ` [dpdk-dev] [PATCH v4 0/3] compile librte_net for windows Fady Bader
2020-07-23  7:08     ` [dpdk-dev] [PATCH v4 1/3] net: fix s_addr redefinition in Windows Fady Bader
2020-07-23  7:08     ` [dpdk-dev] [PATCH v4 2/3] net: replace htons with RTE_BE16 Fady Bader
2020-07-23  7:08     ` [dpdk-dev] [PATCH v4 3/3] eal/windows: librte_net build on Windows Fady Bader
2020-09-08  8:14       ` Ophir Munk
2020-07-24  1:11     ` [dpdk-dev] [PATCH v4 0/3] compile librte_net for windows Ranjit Menon
2020-09-10 19:55       ` Thomas Monjalon
2020-07-24 15:52     ` Kadam, Pallavi

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=20200720192640.2cd0c58e@sovereign \
    --to=dmitry.kozliuk@gmail.com \
    --cc=anand.rawat@intel.com \
    --cc=dev@dpdk.org \
    --cc=fady@mellanox.com \
    --cc=harini.ramakrishnan@microsoft.com \
    --cc=navasile@linux.microsoft.com \
    --cc=ocardona@microsoft.com \
    --cc=olivier.matz@6wind.com \
    --cc=ranjit.menon@intel.com \
    --cc=talshn@mellanox.com \
    --cc=tbashar@mellanox.com \
    --cc=thomas@monjalon.net \
    --cc=yohadt@mellanox.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).