| Message ID | 1454684049-27195-2-git-send-email-thomas.monjalon@6wind.com (mailing list archive) |
|---|---|
| State | Rejected, archived |
| Headers |
Return-Path: <dev-bounces@dpdk.org> X-Original-To: patchwork@dpdk.org Delivered-To: patchwork@dpdk.org Received: from [92.243.14.124] (localhost [IPv6:::1]) by dpdk.org (Postfix) with ESMTP id BE230C310; Fri, 5 Feb 2016 15:55:32 +0100 (CET) Received: from mail-wm0-f46.google.com (mail-wm0-f46.google.com [74.125.82.46]) by dpdk.org (Postfix) with ESMTP id 61580BDAE for <dev@dpdk.org>; Fri, 5 Feb 2016 15:55:31 +0100 (CET) Received: by mail-wm0-f46.google.com with SMTP id g62so51456807wme.0 for <dev@dpdk.org>; Fri, 05 Feb 2016 06:55:31 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=6wind-com.20150623.gappssmtp.com; s=20150623; h=from:to:cc:subject:date:message-id:in-reply-to:references; bh=24x9DQDeWLXn+5u2ACLi4CrgBYJQJ2d+6inqrisf0IU=; b=AF2ksHp9m3tNgdChPTYFgOIN19QWHZR84G9RuRv2gXT/Dj2UmA1ZbwRxpK0zsbUikK tOL74VvyBYAGS/6S/AcSolwIMAweKnljFwc+2LMeUYw6HdDVwHFxsz7MWoVXZ3VLNKOX rGV0TDrNWp5y73vr+1aV1Flal5wauYbeWlhtdbZv7G5ZameUNEp0AMzDEY72y2zGvxoQ 7gkuoIuIs2QQ3xaa+zlA/w+qDd4tErEJPUFEkNu/GI5Jk17Sxduwk9nQ4JTlgkG+kk1A SsyeI0kstpvI/6tZaCodjxbOXNIwYODl+XvX2WPJQyuwb1eePS7U5Y3ZlF3OeELJU5C5 OhoQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20130820; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references; bh=24x9DQDeWLXn+5u2ACLi4CrgBYJQJ2d+6inqrisf0IU=; b=kKLmetaBOgRSrS+WozsugjC2vDwWGHP5pDTzCbQXYENY0zgNvDr+HYfp5X1j2NpwF1 zhzXYVjNwemsONJ7/Hf2z/D3svzvaOb378ZzEctS8/n4Cc7VPrrqN90gfDm3HefGTSM5 rECEW8eoIznbHMiYm48XdgRWFTTdFoYgAMqT6Fg1/mkxr1VIjtu++adlfj++gYcPgDJl OvbhL6w9x04UAw3+PXkGRHgWSAliIjG5aX+yqCb77NAkSBAdoq4ms/90OQv/9nnw5Uy2 bC13u/ZdoDGtuVq6yQVQq5UMS2ymbWMIB9ILRJbf9cl+ydLye0IaEteyzcjkC2z23Fd5 LkZg== X-Gm-Message-State: AG10YOTBYU1yWVjENokxKtRj7iF+QtHqSxtLDIEC/0+tqdrYr5K4vcIJW98DwbGz/5whp4oG X-Received: by 10.28.33.84 with SMTP id h81mr10610757wmh.36.1454684131263; Fri, 05 Feb 2016 06:55:31 -0800 (PST) Received: from localhost.localdomain (136-92-190-109.dsl.ovh.fr. [109.190.92.136]) by smtp.gmail.com with ESMTPSA id pu8sm16257933wjc.17.2016.02.05.06.55.30 (version=TLSv1/SSLv3 cipher=OTHER); Fri, 05 Feb 2016 06:55:30 -0800 (PST) From: Thomas Monjalon <thomas.monjalon@6wind.com> To: bruce.richardson@intel.com, remy.horton@intel.com Date: Fri, 5 Feb 2016 15:54:07 +0100 Message-Id: <1454684049-27195-2-git-send-email-thomas.monjalon@6wind.com> X-Mailer: git-send-email 2.7.0 In-Reply-To: <1454684049-27195-1-git-send-email-thomas.monjalon@6wind.com> References: <1454684049-27195-1-git-send-email-thomas.monjalon@6wind.com> Cc: dev@dpdk.org Subject: [dpdk-dev] [PATCH 1/3] examples/distributor: fix build for non-x86 arch X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: patches and discussions about DPDK <dev.dpdk.org> List-Unsubscribe: <http://dpdk.org/ml/options/dev>, <mailto:dev-request@dpdk.org?subject=unsubscribe> List-Archive: <http://dpdk.org/ml/archives/dev/> List-Post: <mailto:dev@dpdk.org> List-Help: <mailto:dev-request@dpdk.org?subject=help> List-Subscribe: <http://dpdk.org/ml/listinfo/dev>, <mailto:dev-request@dpdk.org?subject=subscribe> Errors-To: dev-bounces@dpdk.org Sender: "dev" <dev-bounces@dpdk.org> |
Commit Message
Thomas Monjalon
Feb. 5, 2016, 2:54 p.m. UTC
_mm_prefetch is defined only in x86 compilers.
rte_prefetch functions are defined in EAL for each arch,
and must be preferred over compiler intrinsics.
Fixes: 07db4a975094 ("examples/distributor: new sample app")
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
---
examples/distributor/main.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
Comments
Hi Thomas, > -----Original Message----- > From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Thomas Monjalon > Sent: Friday, February 5, 2016 2:54 PM > To: Richardson, Bruce; Horton, Remy > Cc: dev@dpdk.org > Subject: [dpdk-dev] [PATCH 1/3] examples/distributor: fix build for non-x86 arch > > _mm_prefetch is defined only in x86 compilers. > rte_prefetch functions are defined in EAL for each arch, and must be preferred > over compiler intrinsics. > > Fixes: 07db4a975094 ("examples/distributor: new sample app") > > Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com> > --- > examples/distributor/main.c | 8 ++++---- > 1 file changed, 4 insertions(+), 4 deletions(-) > > diff --git a/examples/distributor/main.c b/examples/distributor/main.c index > 4e74f8f..87344ac 100644 > --- a/examples/distributor/main.c > +++ b/examples/distributor/main.c > @@ -335,13 +335,13 @@ lcore_tx(struct rte_ring *in_r) > > /* for traffic we receive, queue it up for transmit */ > uint16_t i; > - _mm_prefetch((void *)bufs[0], 0); > - _mm_prefetch((void *)bufs[1], 0); > - _mm_prefetch((void *)bufs[2], 0); > + rte_prefetch0((void *)bufs[0]); > + rte_prefetch0((void *)bufs[1]); > + rte_prefetch0((void *)bufs[2]); Some time back Jerin Jacob has sent patch for replacing the _mm_prefetch with rte_prefetch_non_temporal. This is FYI. Thanks, Reshma > for (i = 0; i < nb_rx; i++) { > struct output_buffer *outbuf; > uint8_t outp; > - _mm_prefetch((void *)bufs[i + 3], 0); > + rte_prefetch0((void *)bufs[i + 3]); > /* > * workers should update in_port to hold the > * output port value > -- > 2.7.0
> -----Original Message----- > From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Pattan, Reshma > Sent: Friday, February 05, 2016 3:08 PM > To: Thomas Monjalon > Cc: dev@dpdk.org > Subject: Re: [dpdk-dev] [PATCH 1/3] examples/distributor: fix build for non-x86 arch > > Hi Thomas, > > > -----Original Message----- > > From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Thomas Monjalon > > Sent: Friday, February 5, 2016 2:54 PM > > To: Richardson, Bruce; Horton, Remy > > Cc: dev@dpdk.org > > Subject: [dpdk-dev] [PATCH 1/3] examples/distributor: fix build for non-x86 arch > > > > _mm_prefetch is defined only in x86 compilers. > > rte_prefetch functions are defined in EAL for each arch, and must be preferred > > over compiler intrinsics. > > > > Fixes: 07db4a975094 ("examples/distributor: new sample app") > > > > Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com> > > --- > > examples/distributor/main.c | 8 ++++---- > > 1 file changed, 4 insertions(+), 4 deletions(-) > > > > diff --git a/examples/distributor/main.c b/examples/distributor/main.c index > > 4e74f8f..87344ac 100644 > > --- a/examples/distributor/main.c > > +++ b/examples/distributor/main.c > > @@ -335,13 +335,13 @@ lcore_tx(struct rte_ring *in_r) > > > > /* for traffic we receive, queue it up for transmit */ > > uint16_t i; > > - _mm_prefetch((void *)bufs[0], 0); > > - _mm_prefetch((void *)bufs[1], 0); > > - _mm_prefetch((void *)bufs[2], 0); > > + rte_prefetch0((void *)bufs[0]); > > + rte_prefetch0((void *)bufs[1]); > > + rte_prefetch0((void *)bufs[2]); > > Some time back Jerin Jacob has sent patch for replacing the _mm_prefetch with rte_prefetch_non_temporal. This is FYI. Yep: http://dpdk.org/dev/patchwork/patch/9369/ http://dpdk.org/dev/patchwork/patch/9370/ And on IA _mm_prefetch(p, 0) != rte_prefetch0(p). I think, as in Jacob implementation, it should be PREFETCHNTA. Konstantin > > Thanks, > Reshma > > > for (i = 0; i < nb_rx; i++) { > > struct output_buffer *outbuf; > > uint8_t outp; > > - _mm_prefetch((void *)bufs[i + 3], 0); > > + rte_prefetch0((void *)bufs[i + 3]); > > /* > > * workers should update in_port to hold the > > * output port value > > -- > > 2.7.0
2016-02-05 15:15, Ananyev, Konstantin: > From: Pattan, Reshma > > From: Thomas Monjalon > > > _mm_prefetch is defined only in x86 compilers. > > > rte_prefetch functions are defined in EAL for each arch, and must be preferred > > > over compiler intrinsics. [...] > > > - _mm_prefetch((void *)bufs[0], 0); > > > - _mm_prefetch((void *)bufs[1], 0); > > > - _mm_prefetch((void *)bufs[2], 0); > > > + rte_prefetch0((void *)bufs[0]); > > > + rte_prefetch0((void *)bufs[1]); > > > + rte_prefetch0((void *)bufs[2]); > > > > Some time back Jerin Jacob has sent patch for replacing the _mm_prefetch with rte_prefetch_non_temporal. This is FYI. > > Yep: > http://dpdk.org/dev/patchwork/patch/9369/ > http://dpdk.org/dev/patchwork/patch/9370/ > > And on IA _mm_prefetch(p, 0) != rte_prefetch0(p). > I think, as in Jacob implementation, it should be PREFETCHNTA. Oh yes, you're right. Thanks patch rejected
diff --git a/examples/distributor/main.c b/examples/distributor/main.c index 4e74f8f..87344ac 100644 --- a/examples/distributor/main.c +++ b/examples/distributor/main.c @@ -335,13 +335,13 @@ lcore_tx(struct rte_ring *in_r) /* for traffic we receive, queue it up for transmit */ uint16_t i; - _mm_prefetch((void *)bufs[0], 0); - _mm_prefetch((void *)bufs[1], 0); - _mm_prefetch((void *)bufs[2], 0); + rte_prefetch0((void *)bufs[0]); + rte_prefetch0((void *)bufs[1]); + rte_prefetch0((void *)bufs[2]); for (i = 0; i < nb_rx; i++) { struct output_buffer *outbuf; uint8_t outp; - _mm_prefetch((void *)bufs[i + 3], 0); + rte_prefetch0((void *)bufs[i + 3]); /* * workers should update in_port to hold the * output port value