官方机啥样？看英特尔Nehalem-EX样机超详评测(1)(29)
| SiSoftware Sandra Pro Business 2010 | ||||
|---|---|---|---|---|
| 测试对象 | 双路Intel Westmere-EP Xeon X5680 3.33GHz |
DELL PowerEdge M910 四路Intel Nehalem-EX Xeon E7540 2.0GHz |
四路Intel Nehalem-EX Xeon X7560 2.27GHz 超线程关闭 |
四路Intel Nehalem-EX Xeon X7560 2.27GHz |
|
Memory Bandwidth Benchmark 内存带宽测试 |
||||
| Aggregate Memory Performance | 35.2GB/s | 33.86GB/s | 57.84GB/s | 65.76GB/s |
| Int Buff'd iSSE2 Memory Bandwidth | 35.2GB/s | 33.86GB/s | 57.87GB/s | 65.76GB/s |
| Float Buff'd iSSE2 Memory Bandwidth | 35.18GB/s | 33.85GB/s | 57.81GB/s | 65.77GB/s |
|
Memory Latency Benchmark(Random) 内存延迟测试(随机) |
||||
|
Memory(Random Access) Latency (越小越好) |
82ns | 192ns | 148ns(min) | 149ns(min) |
|
Speed Factor (越小越好) |
64.60 | 98.10 | 96.40 | 94.50 |
| Internal Data Cache | 4clocks | 4clocks | 3clocks | 3~4clocks |
| L2 On-board Cache | 10clocks | 10clocks | 9clocks | 9~10clocks |
| L3 On-board Cache | 60clocks | 84clocks | 56~57clocks | 66~70clocks |
|
Memory Latency Benchmark(Linear) 内存延迟测试(线性) |
||||
|
Memory(Linear Access) Latency (越小越好) |
7ns | 41ns | 40ns(min) | 36ns(min) |
|
Speed Factor (越小越好) |
5.50 | 20.70 | 19.50 | 20.20 |
| Internal Data Cache | 4clocks | 4clocks | 3clocks | 3~4clocks |
| L2 On-board Cache | 11clocks | 10clocks | 9clocks | 9~10clocks |
| L3 On-board Cache | 13clocks | 34clocks | 27~28clocks | 27~28clocks |
|
Cache and Memory Benchmark 缓存及内存测试 |
||||
| Cache/Memory Bandwidth | 195.6GB/s | 315GB/s | 410.41GB/s | 510.58GB/s |
|
Speed Factor (越小越好) |
35.20 | 34.80 | 23.60 | 26.90 |
| Internal Data Cache | 744.49GB/s | 919.66GB/s | 973.74TB/s | 1.3TB/s |
| L2 On-board Cache | 611GB/s | 749GB/s | 1.32TB/s | 909.27GB/s |
| L3 On-board Cache | 159GB/s | 336.6GB/s | - | 571.35GB/s |
总带宽有所下降，延迟也有所下降~随机缓存延迟甚至降到了Westmere-EP的水平，不过线性访问延迟变化不大。
评论暂时关闭