ScienceMark Membench | ||
| 处理器 | 单路E5430 | 双路E5430 |
| 内存技术参数 | 2GB FBD ECC DDR2-667 SDRAM x4 | 2GB FBD ECC DDR2-667 SDRAM x4 |
| L1带宽(MB/s) | 55953.82 | 55688.67 |
| L2带宽(MB/s) | 16745.33 | 16730.90 |
| 内存带宽(MB/s) | 4460.41 | 4479.89 |
| L1 Cache Latency(ns) | ||
| 32 Bytes Stride | 1.13 | 1.13 |
| L1 Algorithm Bandwidth(MB/s) | ||
| Compiler | 25048.56 | 25244.97 |
| REP MOVSD | 25460.85 | 25451.67 |
| ALU Reg Copy | 12883.48 | 12826.15 |
| MMX Reg Copy | 25375.93 | 25348.59 |
| SSE PAlign | 48260.40 | 48552.33 |
| SSE2 PAlign | 55953.82 | 55688.67 |
| L2 Cache Latency(ns) | ||
| 4 Bytes Stride | 1.13 | 1.13 |
| 16 Bytes Stride | 1.50 | 1.50 |
| 64 Bytes Stride | 4.51 | 4.51 |
| 256 Bytes Stride | 4.51 | 4.51 |
| 512 Bytes Stride | 4.89 | 4.89 |
| L2 Algorithm Bandwidth(MB/s) | ||
| Compiler | 11885.44 | 11882.42 |
| REP MOVSD | 12529.20 | 12530.11 |
| ALU Reg Copy | 8605.95 | 8590.76 |
| MMX Reg Copy | 13438.48 | 13403.55 |
| SSE PAlign | 16745.33 | 16715.36 |
| SSE2 PAlign | 16738.86 | 16730.90 |
| Memory Latency(ns) | ||
| 4 Bytes Stride | 1.13 | 1.13 |
| 16 Bytes Stride | 4.89 | 4.51 |
| 64 Bytes Stride | 19.55 | 19.17 |
| 256 Bytes Stride | 61.28 | 60.90 |
| 512 Bytes Stride | 68.42 | 68.04 |
| Memory Algorithm Bandwidth(MB/s) | ||
| Compiler | 3131.23 | 3184.41 |
| REP MOVSD | 3181.92 | 3220.63 |
| ALU Reg Copy | 2751.90 | 2780.84 |
| MMX Reg Copy | 2936.99 | 2966.63 |
| MMX Reg 3dNow | --- | --- |
| MMX Reg SSE | 3976.80 | 4022.10 |
| SSE PAlign | 4274.10 | 4320.64 |
| SSE PAlign SSE | 4392.84 | 4443.62 |
| SSE2 PAlign | 4282.16 | 4321.07 |
| SSE2 PAlign SSE | 4389.19 | 4442.27 |
| MMX Block 4kb | 4030.85 | 4062.40 |
| MMX Block 16kb | 4454.26 | 4476.12 |
| SSE Block 4kb | 4043.62 | 4083.46 |
| SSE Block 16kb | 4460.41 | 4476.69 |
最后我们来看看处理器数量对于测试结果的影响。表格左侧的数据是使用单颗Intel至强E5430处理器的测试成绩，表格右侧的数据是使用两颗Intel至强E5430处理器的测试成绩。在同样内存容量的情况下，双处理器系统的性能提升非常有限，双路系统对于内存延迟的降低起到了一定的作用，同时也略微提高了内存带宽。不过两者在大多数测试中的成绩互有胜负，并看不出明显的性能提升。
