SYSMark 2004 SE
As usual, we will test the performance of our systems in “general-purpose” applications with the SYSMark 2004 SE testing suite. This benchmark emulates the user’s work in popular applications with multi-tasking of the operating system actively involved.
The applications intended for creation and processing of digital content are very well-optimized for multi-processor environments. Therefore, the performance of our dual-core processors appears higher than that of the single-core ones. At the same time, the dual-core AMD processors easily outperform Intel Pentium Extreme Edition and Intel Pentium D.
The performance in office application doesn’t get that much faster due to the second core. Nevertheless, the dual-core newcomer, Athlon 64 FX-60, wins the first prize in this test. It is evidently explained by the small frequency difference between the dual- and single-core AMD processors. If we take a look at the performance of the Intel processors, we will notice that the dual-core CPUs fall behind their single-core counterparts.
It is true, while the performance difference between the Athlon 64 FX-60 and Athlon 64 FX-57 is only 7.5%, the clock frequencies of the Pentium Extreme Edition 955 and Pentium 4 670 differ by 10%. Moreover, the slightly better design of the AMD’s dual-core architecture also plays an important role here. Toledo (and Manchester) CPUs, unlike Presler and Smithfield, do not use a system bus to arrange communication between the cores, i.e. they use up the platform resources in a more efficient way.