Core 2 Duo processors: shock and tremor
Date: 14.07.2006
|
|
Author: Vladimir Romanchenko, Andrey Kuzin, Dmitriy Sofronov
Introduction
This day can be set as the official date marking the start of a new
epoch of Intel Core 2 Extreme and Intel
Core 2 Duo family processors built on the base of the Conroe
core. Indeed, it is just on this day onwards Intel's new architecture
of which all have been talking for at least the past half a year will
be acquiring the official status of a retail product and starts taking
its legitimate place in our desktop systems.
In fact, we can't talk solely about the processor debut of the
Conroe core, because by tradition Intel has presented a comprehensive
solution new processors combined with the new family of
Intel 965 chipsets which will be the basis for various platform
solutions like gaming PCs, entertainment systems, office computers,
etc.
Nevertheless, our today's material is devoted solely to the
practical aspect of research into the real capabilities of the
new-generation processors to start with, those in
combination with the flagship "desktop" Intel 975X chipset. In fact,
with this review we are opening a course of research works devoted to
the capabilities of Core 2 Duo processors in various environments - in
combination with various motherboards based on various chipsets, video
cards, and other components.
As the very first tests of new processors have shown, there is
indeed much to investigate. Even the heading of today's article chosen
not for the sake of a witticism: at long last, the manufacturer of
processors has gladdened us with not the traditional 10-20% but a
two-fold performance boost combined with a real reduction in the chip
temperature.
We hope the readers will forgive us the so emotional
introduction especially when they see the results of tests. Anyway,
before we move on to the lab let me give you a more detailed account of
the specifications of today's tests. At least, to understand then how
such impressive results come out at the benchmarks.
 For the first time, the details of the Core 2 Duo architecture
was announced at IDF Spring 2006. It's just when we came to know the
new improvements of the Core architecture. In fact, the names of the
new processor brands by Intel for desktop PCs - Core 2 Duo
and Core 2 Extreme - became known some time later,
in May 2006. Once exhaustive information on chips with the working name
Conroe has appeared, it makes sense to publish a consolidated
theoretical material on the new generation of the Core micro
architecture. Those who for some reasons have missed the article Evolution
of the multi-core Intel Core processor architecture: Conroe,
Kentsfield.., or already forgot its main theses, should
refresh the information, which will help us easier to comprehend the
test results.
 Today, we'd better mention the key specifications of Core 2
Duo and Core 2 Extreme inherited from Intel Pentium M and enriched with
the best developments of the NetBurst architecture and a number of
brand-new technologies:
- The Intel Wide Dynamic Execution - a technology that allows
executing greater number of instructions executed per cycle, thus
improving the efficiency of running applications and reducing the power
consumption. Each core of the processor is now able executing up to
four instructions simultaneously using the 14-stage pipeline
- The Intel Intelligent Power Capability - a technology that
enables specific components of the chip only when needed, which gives a
substantial reduction in the power consumption on the whole.
- The Intel Advanced Smart Cache - a technology of using the
common L2 cache memory by all the cores, which gives an overall
reduction in the power consumption, and at the same time one of the
processor cores may use up the whole cache memory once the other core
is disabled dynamically
- The Intel Smart Memory Access - a technology for the memory
subsystem optimization that reduces the response time and increases the
bandwidth of the memory subsystem
- The Intel Advanced Digital Media Boost - a technology that
allows processing 128-bit SSE, SSE2, and SSE3 commands widely used in
multimedia and graphic applications in one cycle
 Additionally to these, the core uses the most recent 65-nm
process technology introduced for the manufacture of new dual-core
chips, which has given an additional saving in the power consumption
and allows raising the boundary clock speed of the chips (of course, as
compared to the "next of kin" which offer a similar micro architecture
Intel Core Duo family processors). The speeds of Core 2 Duo
amount to 800 or 1066 MHz, the L1 cache for each core is 32 K for data
and instructions, respectively; the capacity of the total distributed
L2 cache is 2 MB or 4 MB.
Finally, what is left is to sort out with the specific
questions. The pinout of the new processors is clear - it is the
well-know LGA775. On the other hand, the marking of the processors has
undergone essential changes. We can't say the combination of the letter
prefix with a 4-digit index that follows it is so unexpected,
especially that the mobile Core and Core Duo processors have been
marked this way for at least half a year. Anyway, such designation is
new for the desktop platforms.
This is what stands behind the new 5-character marking of
Intel processors for desktop and mobile systems. The letter index at
the beginning of the marking classified the TDP of the processor,
without any relation to the form factor:
- X - TDP over 75W
- E - TDP of 50W and higher
- T - TDP within 25W to 49W
- L - TDP within 15W to 24W
- U - TDP of about 14W and less
In its turn, the 4-digit index also has a meaning. In the
general case, the higher the 4-digit number in the CPU marking is, the
higher performance and power consumption it offers. At the same time,
the first digit means the belonging of the chip to a certain product
family, and the second one stands for the respective ranking within the
family. Therefore, the greater the figure is, the higher is the
performance of the chip.
Here are a few examples of how the marking of modern
processors looks and what stands behind the notation:
- Core 2 Extreme X6800 2.93 GHz, 4 MB L2 cache,
1066 MHz FSB
- Core 2 Duo E6600 2.4 GHz, 4 MB L2 cache, 1066
MHz FSB
- Core 2 Duo E6400 2.13 GHz, 2 MB L2 cache, 1066
MHz FSB
- Core Duo T2500 2 GHz, 2 MB L2 cache, 667 MHz
FSB
- Core Duo U2500 1.06 GHz, 2 MB L2 cache, 533 MHz
FSB
Needless to say, such method of chip marking has no connection
to the PR ratings of AMD processors which pretend for some relative
correspondence to some MHz of a reference CPU; all is much simpler: the
greater the figure is, the higher is the performance of the chip.
Perhaps, after the infamous finish of the discredited system of
performance rating that takes only the clock speed into account, this
is the only method of real-time "rough" estimation of overall
properties of the chip, without going deep into the detailed
specifications. As regards the new method of marking Intel chips that
has come as a replacement to the formerly used 3-digit combination, we
finally can breathe with relief: now the graphics and the processors by
all the main players of the market offer a similar structure of names -
now all depends on who will be the first to to move to 5-digit numbers.
;-)
This is about all with the introduction, and we now move on to
describing the test setup and the tests.
 |
Top Stories: |
 |
 |
|
MoBo:
| |
|
|
VGA Card:
|
|
|
|
CPU & Memory:
|
|
