Synthetic Benchmarks (Cont.)

Now we will grab some sample information from Everest Ultimate Edition and get some feedback on the central processing performance. Lavalys was nice enough to allow us to evaluate their software for our reviews. We really like the wealth of information this utility gives us and we thank Lavalys for their support. On top of that it will allow us to show you some extra performance figures to give you a second opinion about the raw power of the Intel Core 2 Extreme QX6700 quad core processor. Again we will compare it to our Core 2 Duo E6300 raised to 2.66GHz. It is always good to have an extra angle on the performance.

Lavalys Everest Ultimate 2006

Everest Ultimate Edition is the cutting-edge benchmarking and diagnostics tool to maximize security, performance, and troubleshooting capabilities for home and home office PC environments, PC professionals and consulting firms as well as OEM partners and configuration centers worldwide. During system optimizations and tweaking it provides essential system and overclock information, advanced hardware monitoring and diagnostics capabilities to check the effects of the applied settings. We are using Everest Ultimate Edition together with the Core 2 Extreme QX6700 for checking the performance.

CPU Queen Benchmark

This simple integer benchmark focuses on the branch prediction capabilities and the misprediction penalties of the CPU. It finds the solutions for the classic queen problem on a chessboard. At the same clock speed theoretically the processor with the shorter pipeline and smaller misprediction penalties will attain higher benchmark scores. The CPU Queen test uses only the basic x86 instructions, it consumes very low system memory and it is HyperThreading, multi-processor (SMP) and multi-core (CMP) aware.

Results Interpretation: Higher index values are better. - C2E QX6700 at 2.66GHz

Results Interpretation: Higher index values are better. - C2D E6300 at 2.66GHz

Looking at the above results we notice that our Core 2 Duo E6300 clocked at 2.66GHz delivers a very nice score of 5406 points, which is on par with the E6700 dual core processor which features 4MB cache. But that isn't a match for the quad core QX6700 processor which almost doubles the score and hits 9220 points. A nice result and even a bit better then the reference score available in Everest, the only difference is the mainboard where we did use the newer version of Intel's own 975X Express based version.

CPU PhotoWorxx Benchmark

The following test is an integer benchmark which performs different common tasks used during digital photo processing. It performs several tasks on e very large RGB image. This benchmark stresses the integer arithmetic and multiplication execution units of the CPU and also the memory subsystem. Due to the fact that this test performs high memory read/write traffic, it cannot effectively scale in situations where more than two processing threads are used. The CPU PhotoWorxx benchmark used only the basic x86 instructions and it is HyperThreading, multi-processor and multi-core aware.

Results Interpretation: Higher index values are better. - C2E QX6700 at 2.66GHz

Results Interpretation: Higher index values are better. - C2D E6300 at 2.66GHz

Our Core 2 Extreme QX6700 quad core processor is delivering stunning results as it is beating to already enlisted QX6700 reference score by a large margin. When comparing however we can see that this benchmark is less predictable as the QX6700 doesn't double at all the score of our evenly clocked Core 2 Duo E6300. It is however somehow linked to the limitation of this benchmark which has some scaling issues when more than two processing threads are running. In this case it is impacting the quad core processor the most as it will work in general with more threads than a dual core processor.

CPU ZLib Benchmark

Our next CPU test is an integer benchmark which measures combined CPU and memory subsystem performance through the public ZLib compression library. ZLib is designed as a free, general purpose, legally unencumbered lossless data compression library for use on virtually any computer hardware and operating system. The ZLib data format is itself portable across platforms. ZLib's memory footprint is also independent of the input data and can be reduced, if necessary, but at some cost in compression. The CPU ZLib test uses only the basic x86 instructions and it is HyperThreading, multi-processor and multi-core aware.

Results Interpretation: Higher index values are better. - C2E QX6700 at 2.66GHz

Results Interpretation: Higher index values are better. - C2D E6300 at 2.66GHz

Again a decent improvement reported when it comes to the ZLib compression library performance. We spot that the Core 2 Extreme QX6700 is almost doubling the performance of the E6300 processor. This is no real surprise as compression is mainly a processing intensive task that can be threaded. This clearly shows the potential of the quad core technology as designed by Intel. We also notice that it is the first time that our overclocked Core 2 Duo E6300 gets beaten by the default clocked E6700 processor. The only reason that can explain this resides with the cache of the CPU, where the E6300 only has 2MB and the E6700 has twice as much which is clearly in favor when running the ZLib compression.