The 64-bit version of Windows Vista operating system is for about 10.9 percent faster than 32-bit Vista, according to the GeekBench benchmark for 32-bit and 64-bit Windows platforms.
Both 32-bit and 64-bit tests were done on a budget AMD Sempron 2800+ powered desktop PC, featuring Asus K8U-X motherboard with 512MB of main memory.
The 32-bit Windows Vista Ultimate achived 99.8 GeekBench points, while the 64-bit version of the same OS gained 110.7 points. The higher number of points is better. This Windows Vista 32-bit vs 64-bit benchmark consist of measuring integer performance, floating point performance, as same as memory and stream performance.
| Windows Vista Ultimate | 32-Bit | 64-Bit |
| Integer Performance |
||
| Emulate 6502 | ||
| single-threaded scalar |
47 | 45.8 |
| multi-threaded scalar |
46.7 | 62.1 |
| Blowfish |
||
| single-threaded scalar |
106.5 | 118.7 |
| multi-threaded scalar |
106.5 | 119.6 |
| bzip2 Compress |
||
| single-threaded scalar |
160.1 | 172.3 |
| multi-threaded scalar |
157.6 | 95.3 |
| bzip2 Decompress |
||
| single-threaded scalar |
129.1 | 139.4 |
| multi-threaded scalar |
133.6 | 143.9 |
| Floating Point Performance |
||
| Mandelbrot |
||
| single-threaded scalar |
108 | 77.6 |
| multi-threaded scalar |
108.1 | 98 |
| Dot Product |
||
| single-threaded scalar |
50.9 | 150.9 |
| multi-threaded scalar |
50.6 | 150.2 |
| single-threaded vector |
124.4 | 196.5 |
| multi-threaded vector |
122.2 | 196.6 |
| JPEG Compress |
||
| single-threaded scalar |
104.8 | 103.9 |
| multi-threaded scalar |
105 | 103.1 |
| JPEG Decompress |
||
| single-threaded scalar |
97.8 | 115.3 |
| multi-threaded scalar |
97.9 | 114.4 |
| Memory Performance |
||
| Read Sequential |
||
| single-threaded scalar |
139.2 | 137.6 |
| multi-threaded scalar |
143.3 | 142.7 |
| Write Sequential |
||
| single-threaded scalar |
110 | 109.9 |
| multi-threaded scalar |
116 | 115.1 |
| Stdlib Allocate |
||
| single-threaded scalar |
129.2 | 92.2 |
| multi-threaded scalar |
126.9 | 92 |
| Stdlib Write |
||
| single-threaded scalar |
40.9 | 88.2 |
| multi-threaded scalar |
42.1 | 96.8 |
| Stdlib Copy |
||
| single-threaded scalar |
59.7 | 100.3 |
| multi-threaded scalar |
66.4 | 105.5 |
| Stream Performance |
||
| Stream Copy |
||
| single-threaded scalar |
103.9 | 106.2 |
| multi-threaded scalar |
104.5 | 106.2 |
| single-threaded vector |
97.3 | 96.3 |
| multi-threaded vector |
95.7 | 95.1 |
| Stream Scale |
||
| single-threaded scalar |
118 | 118.3 |
| multi-threaded scalar |
115.3 | 116.1 |
| single-threaded vector |
97.2 | 98.9 |
| multi-threaded vector |
95.6 | 97.1 |
| Stream Add |
||
| single-threaded scalar |
95.1 | 97.8 |
| multi-threaded scalar |
91.5 | 93.3 |
| single-threaded vector |
107.4 | 108 |
| multi-threaded vector |
103.4 | 103.7 |
| Stream Triad |
||
| single-threaded scalar |
84.1 | 90.2 |
| multi-threaded scalar |
81.3 | 87 |
| single-threaded vector |
86.4 | 87 |
| multi-threaded vector |
83.1 | 83.2 |
| OVERALL: | 99.8 | 110.7 |
