We start out with synthetic benchmarks, led by 3DMark. We're seeing a fairly linear progression here as the number of CPU cores decreases, with a slightly larger loss between dual- and single-core operations. Compared to our Core 2 Quad results, the decrease in performance is much less dramatic, but it is about as linear.
Here, we see a similar result compared to the 3DMark benchmark, but with larger margins as the number of CPU cores are decreased. On a side note, the Core 2 Quad we benchmarked in the previous article showed no tangible difference between three and four CPU cores, but a quick drop-off in performance when two or fewer CPU cores were active. In retrospect, this was likely attributable to the Core 2 Quad Q6600's split cache.
Both the PCMark memories and productivity benchmarks demonstrate the same story. Let's move on to SiSoftware Sandra.
- Time To Follow-Up
- Test Methodology: How Do You Make It A Fairer Fight?
- Test System And Benchmarks
- Synthetic Benchmarks: 3DMark And PCMark Vantage
- Synthetic Benchmarks: SiSoftware Sandra
- Application Benchmarks: Audio Encoding
- Application Benchmarks: Video Encoding And Image Rendering
- Application Benchmarks: General Usage
- Game Benchmarks
- Multitasking Benchmarks
- Simulated Dual-Core Versus Actual Dual-Core Comparison
- Performance Analysis