 |
|
 |
|
Next: Sun has to switch to Itanium?
|
| Author |
Message |
External

Since: Feb 05, 2004 Posts: 84
|
(Msg. 1) Posted: Sun Apr 18, 2004 1:48 pm
Post subject: Intel's FB-DIMM, any kind of RAM will work for your controller? Archived from groups: comp>sys>ibm>pc>hardware>chips, others (more info?)
|
|
|
Intel is introducing a type of DRAM called FB-DIMMs (fully buffered).
Apparently the idea is to be able to put any kind of DRAM technology (e.g.
DDR1 vs. DDR2) behind a buffer without having to worry about redesigning
your memory controller. Of course this intermediate step will add some
latency to the performance of the DRAM.
It is assumed that this is Intel's way of finally acknowledging that it has
to start integrating DRAM controllers onboard its CPUs, like AMD does
already. Of course adding latency to the interfaces is exactly the opposite
of what is the main advantage of integrating the DRAM controllers in the
first place.
http://arstechnica.com/news/posts/1082164553.html
Yousuf Khan
--
Humans: contact me at ykhan at rogers dot com
Spambots: just reply to this email address  >> Stay informed about: Intel's FB-DIMM, any kind of RAM will work for your contro.. |
|
| Back to top |
|
 |  |
External

Since: Jan 31, 2004 Posts: 23
|
(Msg. 2) Posted: Sun Apr 18, 2004 5:28 pm
Post subject: Re: Intel's FB-DIMM, any kind of RAM will work for your controller? [Login to view extended thread Info.] Archived from groups: per prev. post (more info?)
|
|
|
A buffer is meant to reduce overall latency, not to increase it AFAIK.
On Sun, 18 Apr 2004 10:48:44 GMT, "Yousuf Khan" <news.tally.bbbl67 DeleteThis @spamgourmet.com> wrote:
>Intel is introducing a type of DRAM called FB-DIMMs (fully buffered).
>Apparently the idea is to be able to put any kind of DRAM technology (e.g.
>DDR1 vs. DDR2) behind a buffer without having to worry about redesigning
>your memory controller. Of course this intermediate step will add some
>latency to the performance of the DRAM.
>
>It is assumed that this is Intel's way of finally acknowledging that it has
>to start integrating DRAM controllers onboard its CPUs, like AMD does
>already. Of course adding latency to the interfaces is exactly the opposite
>of what is the main advantage of integrating the DRAM controllers in the
>first place.
>
>http://arstechnica.com/news/posts/1082164553.html
>
> Yousuf Khan<!-- ~MESSAGE_AFTER~ --> >> Stay informed about: Intel's FB-DIMM, any kind of RAM will work for your contro.. |
|
| Back to top |
|
 |  |
External

Since: Feb 05, 2004 Posts: 84
|
(Msg. 3) Posted: Sun Apr 18, 2004 8:37 pm
Post subject: Re: Intel's FB-DIMM, any kind of RAM will work for your controller? [Login to view extended thread Info.] Archived from groups: per prev. post (more info?)
|
|
|
|
|
| Back to top |
|
 |  |
External

Since: Jan 31, 2004 Posts: 23
|
(Msg. 4) Posted: Mon Apr 19, 2004 12:43 am
Post subject: Re: Intel's FB-DIMM, any kind of RAM will work for your controller? [Login to view extended thread Info.] Archived from groups: per prev. post (more info?)
|
|
|
On Sun, 18 Apr 2004 17:37:36 GMT, "Yousuf Khan" <news.tally.bbbl67.TakeThisOut@spamgourmet.com> wrote:
><geno_cyber.TakeThisOut@tin.it> wrote in message
>news:u34580ltlccpd5p5e47mjv9j2c4lk4b4d9@4ax.com...
>> A buffer is meant to reduce overall latency, not to increase it AFAIK.
>
>Not necessarily, a buffer is also meant to increase overall bandwidth, which
>may be done at the expense of latency.
>
Cache on CPU is not meant to increase bandwidth but to decrease overall latency to retrieve data
from slower RAM. More cache-like buffers in the path thru the memory controller can only improve
latency, unless there's some serious design flaws.
I never seen a CPU that gets slower in accessing data when it can cache and has a good hit/miss
ratio.<!-- ~MESSAGE_AFTER~ --> >> Stay informed about: Intel's FB-DIMM, any kind of RAM will work for your contro.. |
|
| Back to top |
|
 |  |
External

Since: May 05, 2004 Posts: 92
|
(Msg. 5) Posted: Mon Apr 19, 2004 12:43 am
Post subject: Re: Intel's FB-DIMM, any kind of RAM will work for your controller? [Login to view extended thread Info.] Archived from groups: per prev. post (more info?)
|
|
|
<geno_cyber RemoveThis @tin.it> wrote in message
news:lft5801qjivarf2mhfoiko04riq02srkp5@4ax.com...
> On Sun, 18 Apr 2004 17:37:36 GMT, "Yousuf Khan"
> <news.tally.bbbl67 RemoveThis @spamgourmet.com> wrote:
>
>><geno_cyber RemoveThis @tin.it> wrote in message
>>news:u34580ltlccpd5p5e47mjv9j2c4lk4b4d9@4ax.com...
>>> A buffer is meant to reduce overall latency, not to increase it AFAIK.
>>
>>Not necessarily, a buffer is also meant to increase overall bandwidth,
>>which
>>may be done at the expense of latency.
> Cache on CPU is not meant to increase bandwidth but to decrease overall
> latency to retrieve data
> from slower RAM.
Yes, but not by making the RAM any faster, but by avoiding RAM accesses.
We add cache to the CPU because we admit our RAM is slow.
> More cache-like buffers in the path thru the memory controller can only
> improve
> latency, unless there's some serious design flaws.
That makes no sense. Everything between the CPU and the memory will
increase latency. Even caches increase worst case latency because some time
is spent searching the cache before we start the memory access. I think
you're confused.
> I never seen a CPU that gets slower in accessing data when it can cache
> and has a good hit/miss
> ratio.
Except that we're talking about memory latency due to buffers. And by
memory latency we mean the most time it will take between when we ask the
CPU to read a byte of memory and when we get that byte.
DS<!-- ~MESSAGE_AFTER~ --> >> Stay informed about: Intel's FB-DIMM, any kind of RAM will work for your contro.. |
|
| Back to top |
|
 |  |
External

Since: Nov 18, 2003 Posts: 523
|
(Msg. 6) Posted: Mon Apr 19, 2004 1:32 am
Post subject: Re: Intel's FB-DIMM, any kind of RAM will work for your controller? [Login to view extended thread Info.] Archived from groups: per prev. post (more info?)
|
|
|
On Sun, 18 Apr 2004 21:43:19 GMT, geno_cyber.DeleteThis@tin.it wrote:
>On Sun, 18 Apr 2004 17:37:36 GMT, "Yousuf Khan" <news.tally.bbbl67.DeleteThis@spamgourmet.com> wrote:
>
>><geno_cyber.DeleteThis@tin.it> wrote in message
>>news:u34580ltlccpd5p5e47mjv9j2c4lk4b4d9@4ax.com...
>>> A buffer is meant to reduce overall latency, not to increase it AFAIK.
>>
>>Not necessarily, a buffer is also meant to increase overall bandwidth, which
>>may be done at the expense of latency.
>>
>
>Cache on CPU is not meant to increase bandwidth but to decrease overall latency to retrieve data
>from slower RAM. More cache-like buffers in the path thru the memory controller can only improve
>latency, unless there's some serious design flaws.
>I never seen a CPU that gets slower in accessing data when it can cache and has a good hit/miss
>ratio.
You're using "buffer" interchangeably with "cache" - a mistake our Yousuf
would never, ever make. Caches and their effects aren't pertinent to a
discussion of the buffering technique found on Fully Buffered DIMMs and their
effects on latency and bandwidth...
/daytripper (hth  <!-- ~MESSAGE_AFTER~ --> >> Stay informed about: Intel's FB-DIMM, any kind of RAM will work for your contro.. |
|
| Back to top |
|
 |  |
External

Since: Oct 16, 2003 Posts: 125
|
(Msg. 7) Posted: Mon Apr 19, 2004 1:28 pm
Post subject: Re: Intel's FB-DIMM, any kind of RAM will work for your controller? [Login to view extended thread Info.] Archived from groups: per prev. post (more info?)
|
|
|
"Yousuf Khan" <news.tally.bbbl67.RemoveThis@spamgourmet.com> wrote in message
news:A1zgc.114205$2oI1.47233@twister01.bloor.is.net.cable.rogers.com..
..
> <geno_cyber.RemoveThis@tin.it> wrote in message
> news:u34580ltlccpd5p5e47mjv9j2c4lk4b4d9@4ax.com...
> > A buffer is meant to reduce overall latency, not to increase it
AFAIK.
>
> Not necessarily, a buffer is also meant to increase overall
bandwidth, which
> may be done at the expense of latency.
This particular buffer reduces the DRAM interface pinout by a factor
of 3 for CPU chips having the memory interface on-chip (such as
Opteron, the late and unlamented Timna, and future Intel CPUs). This
reduces the cost of the CPU chip while increasing the cost of the DIMM
(because of the added buffer chip).
And yes, the presence of the buffer does increase the latency.
There are other tradeoffs, the main one being the ability to add lots
more DRAM into a server. Not important for desktops. YMMV.<!-- ~MESSAGE_AFTER~ --> >> Stay informed about: Intel's FB-DIMM, any kind of RAM will work for your contro.. |
|
| Back to top |
|
 |  |
External

Since: Jan 31, 2004 Posts: 23
|
(Msg. 8) Posted: Mon Apr 19, 2004 4:05 pm
Post subject: Re: Intel's FB-DIMM, any kind of RAM will work for your controller? [Login to view extended thread Info.] Archived from groups: per prev. post (more info?)
|
|
|
On Sun, 18 Apr 2004 17:37:36 GMT, "Yousuf Khan" <news.tally.bbbl67.TakeThisOut@spamgourmet.com> wrote:
><geno_cyber.TakeThisOut@tin.it> wrote in message
>news:u34580ltlccpd5p5e47mjv9j2c4lk4b4d9@4ax.com...
>> A buffer is meant to reduce overall latency, not to increase it AFAIK.
>
>Not necessarily, a buffer is also meant to increase overall bandwidth, which
>may be done at the expense of latency.
>
> Yousuf Khan
>
<a style='text-decoration: underline;' href="http://www.analog.com/UploadedFiles/Application_Notes/144361534EE157.pdf" target="_blank">http://www.analog.com/UploadedFiles/Application_Notes/144361534EE157.pdf</a>
As you can see this Analog Devices DSP uses a mixed technique of buffering/caching to improve
latency in the best case scenario. Obviously if the caching doesn't work and the data it's not
locally available then the latency has to be higher because you've to get data from slower memory
but when the data is locally available the latency can be reduced down to zero approx in some cases.<!-- ~MESSAGE_AFTER~ --> >> Stay informed about: Intel's FB-DIMM, any kind of RAM will work for your contro.. |
|
| Back to top |
|
 |  |
External

Since: Feb 05, 2004 Posts: 84
|
(Msg. 9) Posted: Mon Apr 19, 2004 8:58 pm
Post subject: Re: Intel's FB-DIMM, any kind of RAM will work for your controller? [Login to view extended thread Info.] Archived from groups: per prev. post (more info?)
|
|
|
<geno_cyber.RemoveThis@tin.it> wrote in message
news:udj7801kk4mg1ba4sdsh2fcuga90knoc8f@4ax.com...
> On Sun, 18 Apr 2004 17:37:36 GMT, "Yousuf Khan"
<news.tally.bbbl67.RemoveThis@spamgourmet.com> wrote:
> As you can see this Analog Devices DSP uses a mixed technique of
buffering/caching to improve
> latency in the best case scenario. Obviously if the caching doesn't work
and the data it's not
> locally available then the latency has to be higher because you've to get
data from slower memory
> but when the data is locally available the latency can be reduced down to
zero approx in some cases.
In this case the buffer is used to eliminate DRAM interface differences when
going from one technology to a new one.
Yousuf Khan<!-- ~MESSAGE_AFTER~ --> >> Stay informed about: Intel's FB-DIMM, any kind of RAM will work for your contro.. |
|
| Back to top |
|
 |  |
External

Since: May 08, 2004 Posts: 64
|
(Msg. 10) Posted: Thu Apr 22, 2004 12:45 am
Post subject: Re: Intel's FB-DIMM, any kind of RAM will work for your controller? [Login to view extended thread Info.] Archived from groups: per prev. post (more info?)
|
|
|
In article <A1zgc.114205$2oI1.47233
@twister01.bloor.is.net.cable.rogers.com>, news.tally.bbbl67
@spamgourmet.com says...
> <geno_cyber RemoveThis @tin.it> wrote in message
> news:u34580ltlccpd5p5e47mjv9j2c4lk4b4d9@4ax.com...
> > A buffer is meant to reduce overall latency, not to increase it AFAIK.
>
> Not necessarily, a buffer is also meant to increase overall bandwidth, which
> may be done at the expense of latency.
Jeez Yousuf, a "buffer" may be used simply to increase drive
(current, if you will). An INVERTER can be a buffer "buffer"
(though most buffers are non-inverting to avoid confusion. Then
again there are unbuffered inverters (74xxU...
The point is that there are *many* uses of the term "buffer" and
most have nothing to do with any kind of a "cache". A "cache"
implies an addressed (usually with a directory) storage element.
A "buffer" implies no such thing.
--
Keith<!-- ~MESSAGE_AFTER~ --> >> Stay informed about: Intel's FB-DIMM, any kind of RAM will work for your contro.. |
|
| Back to top |
|
 |  |
External

Since: May 08, 2004 Posts: 64
|
(Msg. 11) Posted: Thu Apr 22, 2004 12:57 am
Post subject: Re: Intel's FB-DIMM, any kind of RAM will work for your controller? [Login to view extended thread Info.] Archived from groups: per prev. post (more info?)
|
|
|
In article <c5vbe0$fjk$1@nntp.webmaster.com>,
davids RemoveThis @webmaster.com says...
>
> <geno_cyber RemoveThis @tin.it> wrote in message
> news:lft5801qjivarf2mhfoiko04riq02srkp5@4ax.com...
> > On Sun, 18 Apr 2004 17:37:36 GMT, "Yousuf Khan"
> > <news.tally.bbbl67 RemoveThis @spamgourmet.com> wrote:
> >
> >><geno_cyber RemoveThis @tin.it> wrote in message
> >>news:u34580ltlccpd5p5e47mjv9j2c4lk4b4d9@4ax.com...
> >>> A buffer is meant to reduce overall latency, not to increase it AFAIK.
> >>
> >>Not necessarily, a buffer is also meant to increase overall bandwidth,
> >>which
> >>may be done at the expense of latency.
>
> > Cache on CPU is not meant to increase bandwidth but to decrease overall
> > latency to retrieve data
> > from slower RAM.
>
> Yes, but not by making the RAM any faster, but by avoiding RAM accesses.
> We add cache to the CPU because we admit our RAM is slow.
We "admit"?? Hell it's a known issue that RAM is *SLOW*. Caches
are there to improve apparent latency, sure.
>
> > More cache-like buffers in the path thru the memory controller can only
> > improve
> > latency, unless there's some serious design flaws.
>
> That makes no sense. Everything between the CPU and the memory will
> increase latency. Even caches increase worst case latency because some time
> is spent searching the cache before we start the memory access. I think
> you're confused.
No necessarily. Addresses can be broadcast to the entire memory
hierarchy simultaneously. The first to answer wins. If it's
cached, it's fast. If not, there is no penalty in asking the
cach if it's there and being answered in the negative.
> > I never seen a CPU that gets slower in accessing data when it can cache
> > and has a good hit/miss
> > ratio.
> Except that we're talking about memory latency due to buffers. And by
> memory latency we mean the most time it will take between when we ask the
> CPU to read a byte of memory and when we get that byte.
Buffers <> caches. IIRC, the issue here was about buffers.
--
Keith<!-- ~MESSAGE_AFTER~ --> >> Stay informed about: Intel's FB-DIMM, any kind of RAM will work for your contro.. |
|
| Back to top |
|
 |  |
External

Since: May 08, 2004 Posts: 64
|
(Msg. 12) Posted: Thu Apr 22, 2004 1:02 am
Post subject: Re: Intel's FB-DIMM, any kind of RAM will work for your controller? [Login to view extended thread Info.] Archived from groups: per prev. post (more info?)
|
|
|
In article <rRNgc.195$eZ5.136@newsread1.news.pas.earthlink.net>,
fmsfnf DeleteThis @jfoops.net says...
> "Yousuf Khan" <news.tally.bbbl67 DeleteThis @spamgourmet.com> wrote in message
> news:A1zgc.114205$2oI1.47233@twister01.bloor.is.net.cable.rogers.com..
> .
> > <geno_cyber DeleteThis @tin.it> wrote in message
> > news:u34580ltlccpd5p5e47mjv9j2c4lk4b4d9@4ax.com...
> > > A buffer is meant to reduce overall latency, not to increase it
> AFAIK.
> >
> > Not necessarily, a buffer is also meant to increase overall
> bandwidth, which
> > may be done at the expense of latency.
>
> This particular buffer reduces the DRAM interface pinout by a factor
> of 3 for CPU chips having the memory interface on-chip (such as
> Opteron, the late and unlamented Timna, and future Intel CPUs). This
> reduces the cost of the CPU chip while increasing the cost of the DIMM
> (because of the added buffer chip).
>
> And yes, the presence of the buffer does increase the latency.
It may reduce it too!  On-chip delay goes up with the square
of the length of the wire. Adding a *buffer* in the wire drops
this to 2x half the length squared (plus buffer delay). "Buffer"
has many meanings. Me thinks CG doesn't "get it".
>
> There are other tradeoffs, the main one being the ability to add lots
> more DRAM into a server. Not important for desktops. YMMV.
In this specific instance, perhaps not. Memory is good though.
More is better, and an upgrade path is also goodness. ...at
least for the folks in this group.
--
Keith<!-- ~MESSAGE_AFTER~ --> >> Stay informed about: Intel's FB-DIMM, any kind of RAM will work for your contro.. |
|
| Back to top |
|
 |  |
| Related Topics: | DDR DIMMs don't work together. Help! - Help! My RAM additions are doing weird things! Short version: I plugged in two 512MB PC2700 333MHz DIMMS, and Memtest-86 fails (enthusiastically) tests 5 and 7. Either one works fine on its own. Long version: This is a GA-7VRX/GA7VRXP motherboard....
In Search of Quiet PC, Will This Work Well? - Just trying to build a little cheap PC that won't do much more than playback Divx backups on a TV (I have most the parts, really just need a video card, and some cooling stuff). It's only going to be an Athlon 900, 320MB RAM, 40Gig single platter HD..
Hyperthreading does it work in the real world. - Hi, I wonder if this issue was ever resolved. I have seen benchmarks where hyperthreading was faster but some where it was slower. Is there much support for hyperthreading on p4 systems? Any interesting url's. I did the google search and hyperthreading....
AMD or Intel - Thinking to get a new PC. What should I get ? AMD or Intel ? AMD is cheaper than Intel. I am worried about the heat generated by AMD. Is it still very hot ?
Intel & 65nm - http://www.rapidcityjournal.com/articles/2003/11/24/ap/HiTech/d7v18m300.txt Intel demonstrating future technology at 65nm, using a sample SRAM circuit. No word about whether they'll be using SOI or high-k at that level yet. Yousuf Khan |
|
You can post new topics in this forum You can reply to topics in this forum You cannot edit your posts in this forum You cannot delete your posts in this forum You cannot vote in polls in this forum
|
|
|
|
 |
|
|