L4 Cache--not quite that bad?

Article: AMD's Mobile Strategy
By: Paul A. Clayton (paaronclayton.delete@this.gmail.com), January 4, 2012 1:10 pm
Room: Moderated Discussions
David Kanter (dkanter@realworldtech.com) on 1/3/12 wrote:
---------------------------
[snip]
>The economics don't make sense. As I mentioned in another
>post, that means you need:
>
>1. An L4 cache controller

This problem could be addressed by mapping the L4 cache as
a region of memory and using the page table as tags. With
nested page tables this could probably even be made
transparent to the OS if desired. With a 256 MiB L4, 4 KiB
blocks might not be horrible. The software managing the
cache might run on one reserved thread of a modest-
performance MT core.

A perhaps more attractive option could be to include the
cache controller with the cache memory. To allow remote
memory to be cached in L4, something like a snoop filter
might be used to filter accesses to the L4.

It might also be possible to use a section of L3 cache for
L4 tags rather than L3 data. If the overhead of snoop
filter logic is acceptable, then the overhead of handling
tag matching et al. is likely to be acceptable.

>2. Pins to connect to the L4 cache, with sufficient
>bandwidth to handle snooping traffic in servers

If all versions used an auxiliary chip in a MCM, the
normal memory access path could pass through the
auxiliary chip. This could reduce die area on the
processor chip (less power to drive MCM-internal
communication) and even increase available bandwidth.

>The controller and pins use up substantial extra die area >and power. So are you going to have a separate CPU die for
>low-end desktops (no L4), high-end desktops (small L4) and
>servers (big L4)?

If low-end desktops use a different (Bobcat-like)
processor, then having the middle-and-above processors use
an interface to an auxiliary chip would not seem to be a
major problem.

>If so, now your validation is 3X worse because you have 3
>models. And each separate die will need masks (probably
>$1-2M/each).

Even with three different mask sets, this would not
increase validation costs three fold.

>If you use the same die, then you are wasting significant
>power and area on the high volume (low-end desktops), to
>improve things for relatively low volume parts (high-end
>desktop and server).

As noted above, the die area costs might be reduced even if
a single mask set was used for L4 and no-L4 versions. For
single-socket systems, a local-only L4 might not be
horrible.

>How many of these do you think AMD can sell, and how much
>do you think they can increase their prices by?

Unfortunately, I do not think AMD is positioned to lead in
the re-introduction of off-chip cache. The learning curve
for MCM fabrication might excessively penalize their
smaller production volume.

>Let's just recap the costs:
>
>1. More die area for L4 controller

Move it off-chip, reuse page tables, or use L3 data space.

>2. More die area for pins

Use L4 pins for accessing memory as well.

>3. More validation for different models

Minimize variation and limit risk by multipurposing (e.g.,
using L3 data space for tags might allow a broken or
unvalidated version to ship [like the Pentium4's
hyperthreading?]).

>4. External SRAM chips (how much would a 32MB SRAM cost?)

It is not clear that pure SRAM would be better than DRAM or
a DRAM/SRAM hybrid in terms of capacity and power
efficiency.

>5. More complex packaging, lower total yields

I think this factor kills such for AMD. I think the
latency and bandwidth walls are going to require a tightly
integrated off-chip cache with memory pass-through (for
better bandwidth and perhaps better power distribution--
the higher power interfaces to DIMMs could be farther
separated from the power-intensive processing elements).

>6. Need to design a new snoop filter to deal with larger
>cache sizes in servers

A new snoop filter design will be needed anyway, right?

If the L4 was purely local (which might not be bad for
some workloads on 4+ socket systems [e.g., virtualization
workloads?] and might be quite decent for most 2 socket
system workloads), no snoop filter extension would be
necessary.

It might also be practical to include additional coherence
and I/O interfaces on the L4 chips, facilitating a larger
socket count and/or more aggressive I/O.

>Those costs are pretty significant.
>
>I'm also very skeptical that the additional performance
>will be enough to raise ASPs higher than the extra costs.
>In other words, I suspect it would make AMD less >profitable.

While I agree with the idea that AMD would benefit from a
differentiating factor (Bobcat--a better low-end processor
than Atom--and Fusion--exploiting GPU expertise--seem to be
good steps toward such a strategy), I doubt AMD could
overcome the costs to develop cost-effective MCM
technology.

A more attractive alternative (which Intel seems to be
ignoring) would seem to be heterogeneous multicore. AMD
might also be able to exploit the fact that it now uses
generally available fabrication to sell hard core designs
or possibly other smaller design elements, though I tend to
doubt that much market exists for most of AMD's designs.


[snip]
>How much do you think each of those chips is going to
>cost? If they are relatively cutting edge silicon (to
>avoid excessive power consumption), you're talking about
>hundreds of dollars right there. Which far exceeds the
>higher prices you could command for desktops.

It might be nice if there were more cooperation in system
design and manufacture. E.g., being able to use something
like the L4 controller from IBM's zSeries in other systems
could be a net benefit to everyone (users win by better
price/performance, chip designers and manufacturers win
from higher volume)--and such would probably not hurt
zSeries sales (which are based more on reliability and
compatibility than performance or price/performance).

>It might be interesting for servers, but the validation
>and complexity is VASTLY more difficult there.

Again, it might be possible to use multipurposing to allow
delayed validation (and some validation in silicon might be
easier and/or faster).
< Previous Post in ThreadNext Post in Thread >
TopicPosted ByDate
AMD's Mobile StrategyMark Pillsbury2011/12/14 06:58 PM
  ARM vs. x86 is irrelevant from an energy efficiency POV Daniel Bizo2011/12/15 05:30 AM
    ARM vs. x86 is irrelevant from an energy efficiency POV Foo_2011/12/15 06:08 AM
    ARM vs. x86 is irrelevant from an energy efficiency POV an2011/12/15 06:25 AM
      ARM vs. x86 is irrelevant from an energy efficiency POV Azazel2011/12/15 09:50 PM
        ARM vs. x86 is irrelevant from an energy efficiency POV Mike C2011/12/22 02:14 PM
          ARM vs. x86 is irrelevant from an energy efficiency POV Michael S2011/12/23 07:06 AM
        ARM vs. x86 is irrelevant from an energy efficiency POV Mike C2011/12/23 08:07 PM
    ARM vs. x86 is irrelevant from an energy efficiency POV Wilco2011/12/15 07:46 AM
      ARM vs. x86 is irrelevant from an energy efficiency POV Linus Torvalds2011/12/15 10:32 AM
        ARM vs. x86 is irrelevant from an energy efficiency POV a person2011/12/15 10:59 AM
        ARM vs. x86 is irrelevant from an energy efficiency POV Michael S2011/12/15 11:18 AM
          ARM vs. x86 is irrelevant from an energy efficiency POV anon2011/12/16 07:22 PM
            ARM vs. x86 is irrelevant from an energy efficiency POV Wilco2011/12/17 06:56 AM
              Thumb vs ARM instruction countsnone2011/12/17 11:15 AM
                Thumb vs ARM instruction countsWilco2011/12/22 07:50 AM
                  Thumb vs ARM instruction countsExophase2011/12/22 08:56 AM
        ARM vs. x86 is irrelevant from an energy efficiency POV Exophase2011/12/15 11:44 AM
          ARM vs. x86 is irrelevant from an energy efficiency POV Linus Torvalds2011/12/15 03:24 PM
            ARM vs. x86 is irrelevant from an energy efficiency POV Exophase2011/12/15 04:15 PM
              ARM vs. x86 is irrelevant from an energy efficiency POV Linus Torvalds2011/12/15 04:51 PM
                ARM vs. x86 is irrelevant from an energy efficiency POV anon2011/12/15 05:32 PM
                  ARM vs. x86 is irrelevant from an energy efficiency POV David Kanter2011/12/15 06:57 PM
                    ARM vs. x86 is irrelevant from an energy efficiency POV anon2011/12/15 08:58 PM
                      ARM vs. x86 is irrelevant from an energy efficiency POV Wilco2011/12/16 12:27 AM
                    Is scalar x86 decode that easy?Paul A. Clayton2011/12/15 09:20 PM
                      Is scalar x86 decode that easy?Linus Torvalds2011/12/16 12:09 PM
                        Is scalar x86 decode that easy?EduardoS2011/12/17 10:03 AM
                        Is scalar x86 decode that easy?Ricardo B2011/12/17 02:21 PM
                          Is scalar x86 decode that easy?Megol2011/12/18 05:23 AM
                            Is scalar x86 decode that easy?rwessel2011/12/18 10:04 AM
                              Is scalar x86 decode that easy?Megol2011/12/18 10:38 AM
                              Is scalar x86 decode that easy?Linus Torvalds2011/12/18 12:15 PM
                                Is scalar x86 decode that easy?Ricardo B2011/12/18 01:57 PM
                                  Is scalar x86 decode that easy?Linus Torvalds2011/12/18 02:49 PM
                    ARM vs. x86 is irrelevant from an energy efficiency POV Wilco2011/12/16 12:00 AM
                    ARM vs. x86 is irrelevant from an energy efficiency POV anon2011/12/17 12:13 PM
                      Conditional comparesMichael S2011/12/17 01:05 PM
                        Conditional comparesEduardoS2011/12/17 01:32 PM
                ARM vs. x86 is irrelevant from an energy efficiency POV Exophase2011/12/15 05:56 PM
                  ARM free to innovate?Paul A. Clayton2011/12/15 09:14 PM
                  ARM vs. x86 is irrelevant from an energy efficiency POV Linus Torvalds2011/12/16 10:01 AM
                    ARM vs. x86 is irrelevant from an energy efficiency POV Exophase2011/12/16 02:33 PM
                      ARM vs. x86 is irrelevant from an energy efficiency POV Linus Torvalds2011/12/16 06:30 PM
                        ARM vs. x86 is irrelevant from an energy efficiency POV rwessel2011/12/17 12:51 AM
                          ARM vs. x86 is irrelevant from an energy efficiency POV Octoploid2011/12/17 07:46 AM
                          ARM vs. x86 is irrelevant from an energy efficiency POV Linus Torvalds2011/12/17 10:56 AM
                        ARM vs. x86 is irrelevant from an energy efficiency POV Wilco2011/12/17 07:45 AM
                          ARM vs. x86 is irrelevant from an energy efficiency POV Linus Torvalds2011/12/17 11:31 AM
                            ARM vs. x86 is irrelevant from an energy efficiency POV anon2011/12/21 09:12 AM
                          ARM vs. x86 is irrelevant from an energy efficiency POV David Kanter2011/12/17 02:16 PM
                            ARM vs. x86 is irrelevant from an energy efficiency POV Linus Torvalds2011/12/17 03:30 PM
                            ARM vs. x86 is irrelevant from an energy efficiency POV none2011/12/17 05:00 PM
                              ARM vs. x86 is irrelevant from an energy efficiency POV Wilco2011/12/17 05:29 PM
                            ARM vs. x86 is irrelevant from an energy efficiency POV Wilco2011/12/17 05:45 PM
                        ARM vs. x86 is irrelevant from an energy efficiency POV Exophase2011/12/20 10:24 AM
                          ARM vs. x86 is irrelevant from an energy efficiency POV Linus Torvalds2011/12/20 01:07 PM
                            ARM vs. x86 is irrelevant from an energy efficiency POV Exophase2011/12/20 07:19 PM
                              ARM vs. x86 is irrelevant from an energy efficiency POV EduardoS2011/12/20 07:40 PM
                                ARM vs. x86 is irrelevant from an energy efficiency POV Exophase2011/12/20 08:02 PM
                                  ARM vs. x86 is irrelevant from an energy efficiency POV Linus Torvalds2011/12/20 08:49 PM
                                    ARM vs. x86 is irrelevant from an energy efficiency POV Exophase2011/12/20 08:59 PM
                                      ARM vs. x86 is irrelevant from an energy efficiency POV Michael S2011/12/21 03:49 AM
                                        ARM vs. x86 is irrelevant from an energy efficiency POV Exophase2011/12/21 10:10 AM
                                      ARM vs. x86 is irrelevant from an energy efficiency POV gallier22011/12/21 06:41 AM
                                        ARM vs. x86 is irrelevant from an energy efficiency POV Wilco2011/12/21 07:43 AM
                                          ARM vs. x86 is irrelevant from an energy efficiency POV Seni2011/12/21 09:28 AM
                                            ARM vs. x86 is irrelevant from an energy efficiency POV Wilco2011/12/21 11:59 AM
                                              Cortex A9 latenciesS. Rao2011/12/21 09:12 PM
                                                Cortex A9 latenciesWilco2011/12/22 04:59 AM
                                            ARM vs. x86 is irrelevant from an energy efficiency POV gallier22011/12/22 01:25 AM
                                        ARM vs. x86 is irrelevant from an energy efficiency POV Exophase2011/12/21 09:42 AM
                                          ARM vs. x86 is irrelevant from an energy efficiency POV gallier22011/12/22 02:02 AM
                                            ARM vs. x86 is irrelevant from an energy efficiency POV Wilco2011/12/22 05:44 AM
                                              ARM vs. x86 is irrelevant from an energy efficiency POV gallier22011/12/22 07:57 AM
                                    (in)visibility of ISA featureshobold2011/12/21 06:27 AM
                              ARM vs. x86 is irrelevant from an energy efficiency POV Linus Torvalds2011/12/20 07:51 PM
                                ARM vs. x86 is irrelevant from an energy efficiency POV Exophase2011/12/20 08:13 PM
                                  ARM vs. x86 is irrelevant from an energy efficiency POV EduardoS2011/12/20 08:41 PM
                                    second to that (NT)Michael S2011/12/21 02:37 AM
                                  ARM vs. x86 is irrelevant from an energy efficiency POV Linus Torvalds2011/12/20 09:03 PM
                                    ARM vs. x86 is irrelevant from an energy efficiency POV Exophase2011/12/20 11:05 PM
                                      ARM vs. x86 is irrelevant from an energy efficiency POV Seni2011/12/21 02:22 AM
                                        ARM vs. x86 is irrelevant from an energy efficiency POV Exophase2011/12/21 09:28 AM
                                          ARM vs. x86 is irrelevant from an energy efficiency POV Seni2011/12/21 10:06 AM
                                            ARM vs. x86 is irrelevant from an energy efficiency POV Exophase2011/12/21 10:33 AM
                                              ARM vs. x86 is irrelevant from an energy efficiency POV Seni2011/12/21 11:03 AM
                                                ARM vs. x86 is irrelevant from an energy efficiency POV Exophase2011/12/21 11:33 AM
                                                  Adding modes for flexible imm. sizesPaul A. Clayton2011/12/21 04:08 PM
                                                  ARM vs. x86 is irrelevant from an energy efficiency POV anonymous2011/12/21 10:57 PM
                                                    ARM vs. x86 is irrelevant from an energy efficiency POV Exophase2011/12/21 11:12 PM
                                                      ARM vs. x86 is irrelevant from an energy efficiency POV anonymous2011/12/22 02:27 AM
                                                        ARM vs. x86 is irrelevant from an energy efficiency POV Exophase2011/12/22 08:27 AM
                                                ARM vs. x86 is irrelevant from an energy efficiency POV Brett2011/12/21 11:36 PM
                                            ARM vs. x86 is irrelevant from an energy efficiency POV Wilco2011/12/21 05:34 PM
                                              ARM vs. x86 is irrelevant from an energy efficiency POV Seni2011/12/21 06:53 PM
                                                ARM vs. x86 is irrelevant from an energy efficiency POV Wilco2011/12/22 06:42 AM
                                                  ARM vs. x86 is irrelevant from an energy efficiency POV David Kanter2011/12/22 05:29 PM
                                                    ARM vs. x86 is irrelevant from an energy efficiency POV Exophase2011/12/22 07:17 PM
                                                      ARM vs. x86 is irrelevant from an energy efficiency POV David Kanter2011/12/22 08:23 PM
                                                        ARM vs. x86 is irrelevant from an energy efficiency POV Exophase2011/12/22 09:27 PM
                                                          Confused by AVX....David Kanter2011/12/23 12:05 AM
                                                            Celeron, PentiumMichael S2011/12/23 01:15 AM
                                                            Confused by AVX....S. Rao2011/12/23 01:27 AM
                                                            Confused by AVX....Gabriele Svelto2011/12/23 01:33 AM
                                                              Confused by AVX....David Kanter2011/12/23 12:58 PM
                                                                Confused by AVX....Gabriele Svelto2011/12/23 02:44 PM
                                      Load Single Register (pc-relative, literal load)Michael S2011/12/21 02:55 AM
                                        Load Single Register (pc-relative, literal load)Wilco2011/12/21 08:35 AM
                                          Load Single Register (pc-relative, literal load)Brett2011/12/22 12:20 AM
                                            Load Single Register (pc-relative, literal load)Exophase2011/12/22 08:32 AM
                                              Load Single Register (pc-relative, literal load)iz2011/12/22 05:45 PM
                                        Load Single Register (pc-relative, literal load)Exophase2011/12/21 09:34 AM
                                          Load Single Register (pc-relative, literal load)Wilco2011/12/21 04:29 PM
                                            Load Single Register (pc-relative, literal load)Exophase2011/12/22 08:37 AM
                                              Load Single Register (pc-relative, literal load)Brett2011/12/22 11:59 PM
                                          Load Single Register (pc-relative, literal load)Konrad Schwarz2011/12/27 05:07 AM
                                        Load Single Register (pc-relative, literal load)stubar2011/12/21 03:00 PM
                                          Load Single Register (pc-relative, literal load)Exophase2011/12/21 03:25 PM
                                            Load Single Register (pc-relative, literal load)Wilco2011/12/21 04:30 PM
                                              Load Single Register (pc-relative, literal load)anon2011/12/21 09:20 PM
                                                Load Single Register (pc-relative, literal load)Wilco2011/12/22 05:50 AM
                                                  Load Single Register (pc-relative, literal load)anon2011/12/22 06:11 AM
                                                    Load Single Register (pc-relative, literal load)Wilco2011/12/22 07:25 AM
                                      ARM vs. x86 is irrelevant from an energy efficiency POV Linus Torvalds2011/12/21 08:18 PM
                                        ARM vs. x86 is irrelevant from an energy efficiency POV Wilco2011/12/22 06:07 AM
                                          ARM vs. x86 is irrelevant from an energy efficiency POV Linus Torvalds2011/12/22 10:56 AM
                                            idle philosophizing about localityhobold2011/12/23 08:26 AM
                                              Streaming needs regularity, not locality (NT)Rohit2011/12/23 01:32 PM
                                                Streaming needs regularity, not localityiz2011/12/24 12:38 AM
                                                Streaming needs regularity, not localityhobold2011/12/24 04:49 AM
                                                  Streaming needs regularity, not localityRohit2011/12/24 08:52 AM
                                                  Streaming needs regularity, not localityEBFE2011/12/25 06:30 PM
                                                    Streaming needs regularity, not localityRohit2011/12/25 09:42 PM
                                                      Streaming needs regularity, not localityEBFE2011/12/25 11:49 PM
                                                        Streaming needs regularity, not localityRohit2011/12/26 09:53 AM
                                    ARM vs. x86 is irrelevant from an energy efficiency POV mpx2011/12/21 02:57 AM
                                      ARM vs. x86 is irrelevant from an energy efficiency POV John Yates2011/12/26 10:46 AM
                                        Apollo Computer's DN10KBrett2011/12/26 06:56 PM
                                          Apollo Computer's DN10Kpeter huisken2011/12/27 07:40 AM
                                    ARM vs. x86 is irrelevant from an energy efficiency POV gallier22011/12/21 06:56 AM
                              ALU with shift; post-adjust, memcpyMichael S2011/12/21 03:22 AM
                                ALU with shift; post-adjust, memcpyExophase2011/12/21 09:02 AM
                                  memcpyMichael S2011/12/21 10:36 AM
                                    memcpyExophase2011/12/21 11:15 AM
                                    memcpyWilco2011/12/21 06:06 PM
                                      memcpyanon2011/12/21 09:15 PM
                                      memcpyMichael S2011/12/22 12:12 AM
                                        memcpyWilco2011/12/22 06:20 AM
                          Other x86 uop tricksDavid Kanter2011/12/20 07:21 PM
                            Other x86 uop tricksanon2011/12/20 07:35 PM
                              Other x86 uop tricksMichael S2011/12/21 03:55 AM
                            Other x86 uop tricksanon2011/12/20 07:53 PM
                            Other x86 uop tricksExophase2011/12/20 07:54 PM
                      stwxMichael S2011/12/17 10:46 AM
                        stwxWilco2011/12/17 11:33 AM
                          stwxMichael S2011/12/17 01:12 PM
            ARM vs. x86 is irrelevant from an energy efficiency POV mpx2011/12/16 11:06 AM
              ARM vs. x86 is irrelevant from an energy efficiency POV Linus Torvalds2011/12/16 11:17 AM
                Reason for shared decoderPaul A. Clayton2011/12/16 11:45 AM
                  Reason for shared decoderanon2011/12/16 06:37 PM
                    Reason for shared decodermpx2011/12/17 06:20 AM
                      Reason for shared decoderanon2011/12/17 04:19 PM
                        Reason for shared decodermpx2011/12/18 07:21 AM
                          Reason for shared decoderanon2011/12/18 08:30 AM
                          Reason for shared decoderKira2011/12/18 09:00 PM
                ARM vs. x86 is irrelevant from an energy efficiency POV mpx2011/12/17 05:40 AM
                  ARM vs. x86 is irrelevant from an energy efficiency POV Linus Torvalds2011/12/17 12:06 PM
                    ARM vs. x86 is irrelevant from an energy efficiency POV mpx2011/12/17 03:17 PM
        ARM vs. x86 is irrelevant from an energy efficiency POV Wilco2011/12/16 12:10 AM
          ARM vs. x86 is irrelevant from an energy efficiency POV David Kanter2011/12/16 04:19 AM
          ARM vs. x86 is irrelevant from an energy efficiency POV Linus Torvalds2011/12/16 10:14 AM
          ARM vs. x86 is irrelevant from an energy efficiency POV Eugene Nalimov2011/12/16 11:07 AM
            ARM vs. x86 is irrelevant from an energy efficiency POV Michael S2011/12/18 07:25 AM
              ARM vs. x86 is irrelevant from an energy efficiency POV Linus Torvalds2011/12/18 12:48 PM
                ARM vs. x86 is irrelevant from an energy efficiency POV Michael S2011/12/18 04:01 PM
                  ARM vs. x86 is irrelevant from an energy efficiency POV Linus Torvalds2011/12/18 05:21 PM
                    ARM vs. x86 is irrelevant from an energy efficiency POV Linus Torvalds2011/12/18 07:56 PM
      x86 compatibility is not as important as Microsoft compatibilityBrett2011/12/15 08:13 PM
      You're completley missing the pictureDaniel Bizo2011/12/16 08:12 AM
        Missed referencesDaniel Bizo2011/12/16 08:16 AM
          Missed referencesnone2011/12/16 09:17 AM
            Missed referencesDaniel Bizo2011/12/16 09:29 AM
    ARM vs. x86 is irrelevant from an energy efficiency POV Gabriele Svelto2011/12/15 12:55 PM
    ARM vs. x86 is irrelevant from an energy efficiency POV someone2011/12/15 01:19 PM
  AMD's Mobile StrategyDavid Kanter2011/12/15 06:13 PM
    AMD's Mobile StrategyMark Pillsbury2011/12/15 08:14 PM
      AMD's Mobile Strategybakaneko2011/12/15 08:57 PM
      AMD's Mobile StrategyDavid Kanter2011/12/15 10:53 PM
    AMD's new GPU ISA less efficient?Paul A. Clayton2011/12/15 08:33 PM
      AMD's new GPU ISA less efficient?bakaneko2011/12/15 09:03 PM
      AMD's new GPU ISA less efficient?Rohit2011/12/15 09:09 PM
  AMD's Mobile StrategyIan Ollmann2011/12/16 09:21 AM
    AMD's Mobile StrategyMegol2011/12/16 09:33 AM
    AMD's Mobile StrategyDan Fay2011/12/16 07:02 PM
      AMD's Mobile StrategyMichael S2011/12/17 09:22 AM
        AMD's Mobile StrategyMegol2011/12/17 10:10 AM
          AMD's Mobile StrategyWilco2011/12/17 11:18 AM
        AMD's Mobile StrategyDan Fay2011/12/17 11:45 AM
    AMD's Mobile StrategyEduardoS2011/12/17 07:43 AM
      AMD's Mobile StrategyMichael S2011/12/17 11:55 AM
  AMD's Mobile StrategyBill Henkel2011/12/16 06:54 PM
    6 GHz 2-core water-cooled processorTom P2011/12/19 07:48 PM
      6 GHz 2-core water-cooled processorBill Henkel2011/12/19 08:21 PM
        6 GHz 2-core water-cooled processorgallier22011/12/20 01:31 AM
          "Benefit" of smaller market sharePaul A. Clayton2011/12/20 09:45 AM
            scalability of flash SSDSeni2011/12/20 11:22 AM
              USB drive price-point practical?Paul A. Clayton2011/12/20 12:49 PM
                USB drive price-point practical?Seni2011/12/20 02:02 PM
                  A minor comment on utilityPaul A. Clayton2011/12/20 03:19 PM
                    A minor comment on utilitySeni2011/12/20 03:35 PM
                    A minor comment on utilityFoo_2011/12/21 07:06 AM
                      100" Big screen.pH72011/12/26 12:37 PM
                USB drive price-point practical?David Hess2011/12/20 05:25 PM
                  USB drive price-point practical?iz2011/12/20 06:08 PM
                    USB drive price-point practical?David Hess2011/12/21 07:54 AM
                      USB drive price-point practical?iz2011/12/21 11:21 PM
                  USB drive price-point practical?Ungo2011/12/20 06:36 PM
                    USB drive price-point practical?David Hess2011/12/21 07:48 AM
              scalability of flash SSDEduardoS2011/12/20 03:50 PM
                scalability of flash SSDSeni2011/12/20 06:41 PM
                  scalability of flash SSDEduardoS2011/12/20 06:50 PM
                    scalability of flash SSDSeni2011/12/20 07:24 PM
                      scalability of flash SSDEduardoS2011/12/20 07:51 PM
                        scalability of flash SSDanon2011/12/21 04:03 AM
                          scalability of flash SSDanon2011/12/21 05:21 AM
                            scalability of flash SSDEduardoS2011/12/21 01:32 PM
                              scalability of flash SSDanon2011/12/21 03:49 PM
                                scalability of flash SSDEduardoS2011/12/21 04:58 PM
                                  scalability of flash SSDanon2011/12/21 09:00 PM
                                    scalability of flash SSDEduardoS2011/12/22 02:58 AM
                                    scalability of flash SSDRicardo B2011/12/22 08:36 AM
              scalability of flash SSDWes Felter2011/12/20 05:53 PM
                scalability of flash SSDSeni2011/12/20 06:24 PM
                scalability of flash SSDiz2011/12/20 06:29 PM
        6 GHz 2-core water-cooled processorExophase2011/12/20 09:05 AM
          6 GHz 2-core water-cooled processorEduardoS2011/12/20 03:58 PM
            6 GHz 2-core water-cooled processorExophase2011/12/20 06:13 PM
              6 GHz 2-core water-cooled processorEduardoS2011/12/20 06:43 PM
                6 GHz 2-core water-cooled processorExophase2011/12/21 11:36 AM
                  6 GHz 2-core water-cooled processorSeni2011/12/21 12:11 PM
                    6 GHz 2-core water-cooled processorExophase2011/12/21 12:26 PM
                  Diatomic Helium? (NT)Paul A. Clayton2011/12/21 03:50 PM
                    Sorry, should have read further in thread! (NT)Paul A. Clayton2011/12/21 03:52 PM
      6 GHz 2-core water-cooled processorsomeone2011/12/20 10:09 AM
        Per-core licensing fees.mpx2011/12/21 03:07 AM
    AMD's Mobile StrategyDoug Siebert2011/12/20 06:39 PM
  AMD's Mobile Strategy (NT)yundy2011/12/16 09:19 PM
  ARM transition is irrelevant from an economic POV Azazel2011/12/18 12:23 AM
  AMD's Mobile Strategypk2011/12/21 07:51 AM
    AMD's Mobile StrategyDavid Kanter2011/12/21 10:55 AM
      Samsung's fab technologyMark Roulo2011/12/21 11:34 AM
      AMD's Mobile StrategyAzazel2011/12/21 09:45 PM
        AMD's Mobile StrategyEduardoS2011/12/22 02:59 AM
          AMD's Mobile StrategyAzazel2011/12/22 10:03 PM
            AMD's Mobile StrategyEduardoS2011/12/22 11:51 PM
            AMD's Mobile StrategyVincent Diepeveen2011/12/24 11:15 AM
  AMD's Mobile StrategyAndrew Maizels2011/12/21 11:30 AM
  AMD's Mobile StrategyMr. Camel2011/12/27 09:50 AM
    AMD's Mobile StrategyMike C2011/12/27 11:01 PM
  Need for DifferentiationBill Henkel2011/12/29 12:22 PM
    Need for DifferentiationBrett2011/12/29 09:53 PM
      Need for DifferentiationVincent Diepeveen2011/12/30 11:29 AM
      Requested software features already in productCharles2011/12/30 09:35 PM
        Requested software features already in productSanjay B2012/01/11 04:45 PM
          Requested software features already in productBrett2012/01/11 10:18 PM
    Need for DifferentiationDavid Kanter2011/12/30 01:23 AM
      Need for DifferentiationVincent Diepeveen2011/12/30 11:17 AM
      Need for DifferentiationBill Henkel2012/01/03 07:01 PM
        Need for DifferentiationDavid Kanter2012/01/03 08:34 PM
    Need for DifferentiationVincent Diepeveen2011/12/30 11:09 AM
    L4 CacheBill Henkel2011/12/30 05:55 PM
      L4 CacheDavid Kanter2011/12/30 09:34 PM
        L4 CacheEduardoS2011/12/31 03:42 PM
          L4 CacheExophase2011/12/31 05:37 PM
      Need for speedDoug Siebert2011/12/31 01:07 PM
        Need for speedAlex M2012/01/06 03:38 PM
          Need for speedDoug Siebert2012/01/06 07:51 PM
        Need for speedTom J2012/01/10 04:44 PM
          Need for speedrwessel2012/01/10 05:30 PM
      L4 CacheRicardo B2011/12/31 02:25 PM
        L4 CacheBill Henkel2012/01/03 06:33 PM
          L4 CacheDavid Kanter2012/01/03 08:54 PM
            L4 Cache--not quite that bad?Paul A. Clayton2012/01/04 01:10 PM
              L4 Cache--not quite that bad?David Kanter2012/01/04 04:59 PM
                L4 Cache--not so bad (for Intel/IBM perhaps)Paul A. Clayton2012/01/04 08:01 PM
                L4 CacheBill Henkel2012/01/05 05:50 PM
                  Integration class price/performance tradeoffs?Paul A. Clayton2012/01/06 03:26 PM
                    Integration class price/performance tradeoffs?David Kanter2012/01/06 06:29 PM
                      InterposersMark Roulo2012/01/09 09:43 AM
                        InterposersDavid Kanter2012/01/10 12:13 PM
                    Integration class price/performance tradeoffs?Bill Henkel2012/01/06 06:52 PM
                      Beware of invention-stealing time travelers :-)Paul A. Clayton2012/01/06 08:31 PM
                        AMD PrototypePoindexter2012/01/07 06:20 AM
                    L4 Cache with Silicon InterposerTom J2012/01/08 05:50 PM
              L4 Cache--not quite that bad?rwessel2012/01/04 07:20 PM
                Temptation for expensive optimizationsPaul A. Clayton2012/01/04 08:20 PM
            L4 CacheDan Fay2012/01/04 05:51 PM
              L4 CacheRicardo B2012/01/04 06:39 PM
                L4 CacheDan Fay2012/01/04 06:57 PM
              L4 CacheKevin G2012/01/06 09:02 AM
          L4 CacheRicardo B2012/01/04 06:29 PM
            L4 CacheMichael S2012/01/05 07:21 AM
              L4 CacheRicardo B2012/01/05 11:01 AM
              L4 CacheRicardo B2012/01/06 06:06 AM
                L4 CacheMichael S2012/01/06 07:35 AM
                  Non-latency advantagesPaul A. Clayton2012/01/06 03:04 PM
                    Non-latency advantagesRicardo B2012/01/06 06:12 PM
                      Tag check delay??Paul A. Clayton2012/01/06 07:05 PM
                        Tag check delay??Ricardo B2012/01/06 08:18 PM
                          Thanks for sharingPaul A. Clayton2012/01/06 08:46 PM
            L4 Cachesomeone2012/01/08 05:06 PM
              L4 CacheRicardo B2012/01/08 06:28 PM
      L4 CacheVincent Diepeveen2012/01/08 02:11 PM
        L4 CacheJouni Osmala2012/01/09 03:24 AM
  Value of x86 in ServersGeorge Baker2012/01/04 10:55 AM
    Value of x86 in ServersDavid Kanter2012/01/05 02:40 AM
      Value of x86 in Serversrwessel2012/01/05 03:27 AM
        Value of x86 in ServersDavid Kanter2012/01/05 04:49 AM
      Value of x86 in ServersKira2012/01/09 05:22 PM
        Value of x86 in ServersJoel2012/01/09 09:20 PM
    Value of x86 in ServersDan Fay2012/01/05 09:03 AM
    Value of x86 in ServersAlex M2012/01/06 04:23 PM
    Value of x86 in ServersTom J2012/01/10 04:25 PM
      Value of x86 in Serversanon2012/01/11 12:44 PM
        Value of x86 in ServersGregory2012/01/12 06:11 PM
          x86 complexity or high-performance complexity?Paul A. Clayton2012/01/12 06:52 PM
          Value of x86 in ServersMichael S2012/01/13 06:39 AM
            Value of x86 in ServersRicardo B2012/01/13 03:14 PM
              Value of x86 in ServersMichael S2012/01/14 12:22 PM
  Heterogeneous ComputingAlex M2012/01/06 05:10 AM
    Thoughput != SIMDPaul A. Clayton2012/01/06 05:10 PM
  AMD's Processor StrategyJason Chan2012/01/10 06:06 AM
    AMD's Processor StrategyMark Roulo2012/01/10 06:21 PM
      AMD's Processor StrategyMegol2012/01/11 03:51 AM
        AMD's Processor StrategyDavid Hess2012/01/11 10:46 AM
    AMD's Processor StrategyAzazel2012/01/12 09:46 PM
      AMD's Processor StrategyVincent Diepeveen2012/01/13 06:28 AM
Reply to this Topic
Name:
Email:
Topic:
Body: No Text
How do you spell purple?