Hardware Reference
In-Depth Information
consumption, and therefore heat generation as well. Eventually, it was determined that the power
penalty was too great, causing Intel to drop back to a more efficient design in its newer Core
microarchitecture processors. Rather than solely increase clock rates, performance was increased by
combining multiple processors into a single chip, thus improving the effective instruction efficiency
even further. This began the push toward multicore processors.
One thing is clear in all of this confusion: Raw clock speed is not a good way to compare chips,
unless they are from the same manufacturer, model, and family.
To fairly compare various CPUs at different clock speeds, Intel originally devised a specific series
of benchmarks called the
Intel Comparative Microprocessor Performance
(iCOMP) index. The
iCOMP index benchmark was released in original iCOMP, iCOMP 2.0, and iCOMP 3.0 versions.
The iCOMP 2.0 index was derived from several independent benchmarks as an indication of relative
processor performance. The benchmarks balance integer with floating-point and multimedia
performance.
The iCOMP 2.0 index comparison for Pentium 75 through Pentium II 450 is available in Chapter 3 of
Upgrading and Repairing PCs,
19
th
Edition, found in its entirety on the disc packaged with this
book.
Until recently, Intel and AMD have rated their latest processors using the commercially available
BAPCo SYSmark benchmark suites. SYSmark is an application-based benchmark that runs various
scripts to do actual work using popular applications. Many companies use it to test and compare PC
systems and components. The SYSmark benchmark is a much more modern and real-world
benchmark than the iCOMP benchmark Intel previously used, and because it is available to anybody,
the results can be independently verified. You can purchase the SYSmark benchmark software from
BAPCo at
www.bapco.com
or from FutureMark at
www.futuremark.com
.
The most recent version of the SYSmark benchmark—SYSmark 2012—has become controversial
because AMD, NVIDIA, and VIA resigned from BAPco in 2011. These companies withdrew from
BAPco because they believe that this version of the SYSmark benchmark is optimized for Intel
processors rather than being processor neutral.
AMD's recent processor designs have emphasized the role of the integrated GPU and heterogenous
computing (the use of both CPU and GPU for calculations) in its consumer-level designs, while Intel,
though its recent processors include integrated GPUs, stresses CPU performance in its designs.
Meanwhile, VIA emphasizes ultra-low power consumption and optimization for basic computer
tasks. SYSmark 2012's application mix (see
Table 3.7
) puts little emphasis on AMD and VIA's
strengths. As several technology columnists have noted, Intel, AMD, and VIA are no longer pursuing
the same goals in processor design, so a common benchmark might no longer make much sense.
Table 3.7. Scenarios and Software Used by SYSmark 2012
