aha...@arm.com" , Idan
> Werpoler , "konstantin.anan...@intel.com"
> , "ola.liljed...@arm.com"
> , Olga Shern , Ori Kam
> , Shahaf Shuler , David
> Wilder , Yongseok Koh
> Date: 03/27/2019 04:50 PM
> Subject: Re: [dpdk-dev] [PATCH] eal/ppc: remove fix of memo
28/03/2019 18:51, Pradeep Satyanarayana:
> From: Pradeep Satyanarayana/Beaverton/IBM
> > From: Thomas Monjalon
> > > Pradeep, Chao,
> > >
> > > Do we have more news?
> > > We must merge this patch for DPDK 19.05-rc1.
> > >
> > > I understand you want to try improving performance
> > > by using lig
...@arm.com" ,
> "konstantin.anan...@intel.com" ,
> "ola.liljed...@arm.com" , Ori Kam
> , David Wilder , Yongseok Koh
> , Idan Werpoler , Olga Shern
>
> Date: 03/27/2019 02:19 AM
> Subject: Re: [dpdk-dev] [PATCH] eal/ppc: remove fix of memory
> barrier
Shahaf Shuler wrote on 03/23/2019 11:37:42 PM:
> From: Shahaf Shuler
> To: "prad...@us.ibm.com" , Thomas Monjalon
>
> Cc: "bruce.richard...@intel.com" , Chao
> Zhu , Dekel Peled ,
> "dev@dpdk.org" , David Christensen ,
> "honnappa.nagaraha...@arm.com" ,
> "konstantin.anan...@intel.com" ,
> "
Thomas Monjalon wrote on 03/22/2019 10:51:17 AM:
> From: Thomas Monjalon
> To: Pradeep Satyanarayana
> Cc: bruce.richard...@intel.com, Chao Zhu
> , Dekel Peled ,
> dev@dpdk.org, David Christensen ,
> honnappa.nagaraha...@arm.com, konstantin.anan...@intel.com,
> ola.liljed...@arm.com, Ori Kam
Thomas Monjalon wrote on 03/22/2019 01:49:03 AM:
> From: Thomas Monjalon
> To: Pradeep Satyanarayana , David Wilder
>
> Cc: Shahaf Shuler , Chao Zhu
> , Dekel Peled ,
> dev@dpdk.org, David Christensen , Ori Kam
> , Yongseok Koh ,
> konstantin.anan...@intel.com, ola.liljed...@arm.com,
> honnap
Shahaf Shuler wrote on 03/21/2019 01:49:39 AM:
> From: Shahaf Shuler
> To: "prad...@us.ibm.com" , Thomas Monjalon
>
> Cc: Chao Zhu , Dekel Peled
> , "dev@dpdk.org" , Ori Kam
> , "sta...@dpdk.org" , Yongseok
> Koh , David Christensen , David
> Wilder
> Date: 03/21/2019 01:54 AM
> Subject: RE:
Pradeep, Chao,
Do we have more news?
We must merge this patch for DPDK 19.05-rc1.
I understand you want to try improving performance
by using lightweight sync for SMP barrier,
and this change can be done later.
First priority is to fix the bug of the general barrier.
That's why I should push this
+Idan Werpoler.
From: Pradeep Satyanarayana
Sent: Sunday, March 24, 2019 7:38 PM
To: Shahaf Shuler
Cc: bruce.richard...@intel.com; Chao Zhu ; Dekel
Peled ; dev@dpdk.org; David Christensen ;
honnappa.nagaraha...@arm.com; konstantin.anan...@intel.com;
ola.liljed...@arm.com; Ori Kam ; Thomas Mon
Pradeep,
Pradeep Satyanarayana wrote on Saturday, March 23, 2019 12:58 AM
>Thomas Monjalon wrote on 03/22/2019 10:51:17 AM:
>> Date: 03/22/2019 10:51 AM
>> Subject: Re: [PATCH] eal/ppc: remove fix of memory barrier for IBM POWER
>>
>> 22/03/2019 16:30, Pradeep Satyanarayana:
>> > Thomas Monjalon
22/03/2019 16:30, Pradeep Satyanarayana:
> Thomas Monjalon wrote on 03/22/2019 01:49:03 AM:
> > 22/03/2019 02:40, Pradeep Satyanarayana:
> > > - rte_[rw]mb (general memory barrier) --> should be lwsync
> >
> > This is what may be discussed.
> > The assumption is that the general memory barrier sho
We need to agree on the definitions.
Please see below,
22/03/2019 02:40, Pradeep Satyanarayana:
> Shahaf Shuler wrote on 03/21/2019 01:49:39 AM:
> > Pradeep Satyanarayana wrote on Thu 3/21/2019 12:41
> AM:
> > >> > So far, when not running on power, we used the rte_wmb for that.
> > >> On x86 an
Thomas Monjalon wrote on 03/19/2019 01:45:01 PM:
> From: Thomas Monjalon
> To: Shahaf Shuler
> Cc: Dekel Peled , Chao Zhu
> , Yongseok Koh ,
> "dev@dpdk.org" , Ori Kam ,
> "sta...@dpdk.org" , prad...@us.ibm.com
> Date: 03/19/2019 01:45 PM
> Subject: Re: [PATCH] eal/ppc: remove fix of memory
Pradeep Satyanarayana wrote on Thu 3/21/2019 12:41 AM:
>Thomas Monjalon wrote on 03/19/2019 01:45:01 PM:
>
>> From: Thomas Monjalon
>> To: Shahaf Shuler
>> Cc: Dekel Peled , Chao Zhu
>> , Yongseok Koh ,
>> "dev@dpdk.org" , Ori Kam ,
>> "sta...@dpdk.org" , prad...@us.ibm.com
>> Date: 03/19/2019
19/03/2019 20:42, Shahaf Shuler:
> Tuesday, March 19, 2019 1:15 PM, Thomas Monjalon:
> > Subject: Re: [PATCH] eal/ppc: remove fix of memory barrier for IBM POWER
> >
> > Guys, please let's avoid top-post.
> >
> > You are both not replying to each other:
> >
> > 1/ Dekel mentioned the IBM doc but
Tuesday, March 19, 2019 1:15 PM, Thomas Monjalon:
> Subject: Re: [PATCH] eal/ppc: remove fix of memory barrier for IBM POWER
>
> Guys, please let's avoid top-post.
>
> You are both not replying to each other:
>
> 1/ Dekel mentioned the IBM doc but Chao did not argue about the lack of IO
> protec
Guys, please let's avoid top-post.
You are both not replying to each other:
1/ Dekel mentioned the IBM doc but Chao did not argue about
the lack of IO protection with lwsync.
We assume that rte_mb should protect any access including IO.
2/ Chao asked about the semantic of the barrier used in mlx
Hi,
For ppc, rte_io_mb() is defined as rte_mb(), which is defined as asm sync.
According to comments in arch/ppc_64/rte_atomic.h, rte_wmb() and rte_rmb() are
the same as rte_mb(), for store and load respectively.
My patch propose to define rte_wmb() and rte_rmb() as asm sync, like rte_mb(),
sinc
Dekel£¬
To control the memory order for device memory, I think you should use
rte_io_mb() instead of rte_mb(). This will generate correct result. rte_wmb()
is used for system memory.
> -Original Message-
> From: Dekel Peled
> Sent: Monday, March 18, 2019 8:58 PM
> To: chao...@linux.vne
19 matches
Mail list logo
