>>-Original Message-
>>From: Jesse Barnes [mailto:jbar...@virtuousgeek.org]
>>Sent: 2011年6月24日 1:20
>>To: Zou, Nanhai
>>Cc: Keith Packard; intel-gfx@lists.freedesktop.org; Anholt, Eric
>>Subject: Re: [Intel-gfx] gem clflush optimization for media enc
On Wed, 22 Jun 2011 12:29:21 +0800
"Zou, Nanhai" wrote:
> map_gtt in current gem is super slow.
> I've tried map_gtt but it seems that the speed is unacceptable.
>
> >>> Since it is CPU read only surface, clflush in not needed at all.
> >>
> >>You'd still have to invalidate cache l
On Wed, 22 Jun 2011 09:20:35 -0700, Keith Packard wrote:
> On Wed, 22 Jun 2011 08:29:24 +0200, Daniel Vetter wrote:
>
> > The important thing is that you may never use the cpu mappings with
> > these functions (for objects of similar size). Because libdrm reuses
> > bos without checking their do
On Wed, 22 Jun 2011 08:29:24 +0200, Daniel Vetter wrote:
> The important thing is that you may never use the cpu mappings with
> these functions (for objects of similar size). Because libdrm reuses
> bos without checking their domain, you'll get tons of unnecessary
> clflush even on objects that
On Wed, 22 Jun 2011 12:29:21 +0800, "Zou, Nanhai" wrote:
> As I understand,
> with movnti + sfence, data should be surly reach memory. Cache should be
> coherent at this case.
I wouldn't mind seeing additional experiments in this area, but when
Eric and I tried this a couple of years ago, w
2011/6/22 Zou, Nanhai :
> map_gtt in current gem is super slow.
> I've tried map_gtt but it seems that the speed is unacceptable.
map_gtt should be pretty fast for large things on the upload side. For
the gpu->cpu download, have you tried pread? btw, the counterpart
(pwrite) also beat
s.freedesktop.org
>>Cc: Anholt, Eric
>>Subject: Re: [Intel-gfx] gem clflush optimization for media encoding
>>
>>
>>
>>>>-Original Message-
>>>>From: Keith Packard [mailto:kei...@keithp.com]
>>>>Sent: 2011年6月22日 12:14
>
>>-Original Message-
>>From: Keith Packard [mailto:kei...@keithp.com]
>>Sent: 2011年6月22日 12:14
>>To: Zou, Nanhai; intel-gfx@lists.freedesktop.org
>>Cc: Anholt, Eric
>>Subject: Re: [Intel-gfx] gem clflush optimization for media encoding
>>
On Wed, 22 Jun 2011 11:13:09 +0800, "Zou, Nanhai" wrote:
> If I upload input buffer with movnti or movntdq (bypass cache) +
> sfence(clear write combine buffer) in the end, clflush should
> not be needed.
Alas, neither of these will flush existing cached data, so you must
still
