 | | | CPUs and XSI/mental ray... | CPUs and XSI/mental ray... 2005-06-21 - By Josh One
Back
yea, thanks! i have a dual xeon 2ghz with 256 cache installed and have
been sitting on a pair of 2ghz 512 cache... i guess i should put those
puppies to use :). i will run some before/after test and see the direct
effect.
Lee Hallett wrote:
> Cheers Brad - what's the availabillity of dual core like at the
> moment? I thought they weren't readily available for a while?
>
> Cheers for the tips on cache (and it's relative importance) and the
> memory controller issues on dual procs.
>
>
>
> Lee|3d animation and design..
>
> Pixel pusher & 'telly colouring in' bloke
>
> There are only 10 sorts of people in the World - those that understand
> binary, and those that don't.
>
>
> * BBC Wales | C4 graphics area | Broadcasting House|
> Llandaff, Cardiff. CF5 2QY.* *
> * (* +44 (0)29 203 23370
> e-* lee.hallett@(protected)
>
>
> -- --Original Message-- --
> *From:* owner-xsi@(protected) [mailto:owner-xsi@(protected)] *On
> Behalf Of *Brad Friedman
> *Sent:* 21 June 2005 14:19
> *To:* XSI@(protected)
> *Subject:* Re: CPUs and XSI/mental ray...
>
> The larger the cache, the better. Especially for rendering. A larger
> cache means more rendering binary code can live closer to the CPU
> along with more data. Since rendering is such a repetitive process,
> cache is very important. It keeps one from taking too many memory
> access performance hits.
>
> I have seen nothing but stunning benchmark results for AMD Dual Core
> chips.
>
> As far as motherboards go, when it comes to AMD opteron dual proc
> systems, there are two main types:
>
> 1) The type in which a single memory controller is shared between the
> CPUs (in which case one CPU has slower memory access due to using a
> hypertransport pipe to get access to main memory)
>
> 2) The type in which each CPU has its own dedicated memory
> controller. This is faster.
>
> The introduction of dual core opterons will make for a frightening
> machine for certain, with four cores spread over two CPUs. Though,
> with the uncertainty of mental ray licensing on dual cores... I don't
> know how that works out with regards to $$. Anyone know if mental
> images ever got around to telling us how licensing will be affected by
> dual core chips?
>
> -brad
>
> Lee Hallett wrote:
>
>> Very basic question: given the currently available hardware, what's
>> the best processor for a kick-ass XSI/mental ray workstation? Any
>> noteable considerations (Cache/motherboards etc)
>>
>> *sorry, I know this should go to the hardware list, but the reponse
>> is always minimal!*
>>
>>
>> Lee|3d animation and design..
>>
>> Pixel pusher & 'telly colouring in' bloke
>>
>> There are only 10 sorts of people in the World - those that
>> understand binary, and those that don't.
>>
>>
>> * BBC Wales | C4 graphics area | Broadcasting House|
>> Llandaff, Cardiff. CF5 2QY.* *
>> * (* +44 (0)29 203 23370
>> e-* lee.hallett@(protected)
>>
>>
>>
>>
>> http://www.bbc.co.uk/
>>
>> This e-mail (and any attachments) is confidential and may contain
>> personal views which are not the views of the BBC unless specifically
>> stated.
>> If you have received it in error, please delete it from your system.
>> Do not use, copy or disclose the information in any way nor act in
>> reliance on it and notify the sender immediately. Please note that the
>> BBC monitors e-mails sent or received.
>> Further communication will signify your consent to this.
>
>
>
> http://www.bbc.co.uk/
>
> This e-mail (and any attachments) is confidential and may contain
> personal views which are not the views of the BBC unless specifically
> stated.
> If you have received it in error, please delete it from your system.
> Do not use, copy or disclose the information in any way nor act in
> reliance on it and notify the sender immediately. Please note that the
> BBC monitors e-mails sent or received.
> Further communication will signify your consent to this.
---
Unsubscribe? Mail Majordomo@(protected) with the following text in body:
unsubscribe xsi
|
|
|