欢迎参与评论，每一条合规评论都是对我们的褒奖。
请 登录 或 快速注册 后发表评论
注明：上一篇由于系统设置及驱动问题因此进行重测。
这几天，我们再次得到一些利用Crysis自带的“CPU Benchmark”进行的处理器测试数据。除了上一篇测试已经提到的Intel QX9650、QX6850还有AMD Phenom X4之外，这次还将看到新加入的AMD Athlon64 X2 5000+、FX62、Intel QX6700等处理器。为了让测试更准确，我们灌入新的操作系统，使用更新的驱动，以及加入了有特别目的的子项目测试。
本次测试旨在说明的是不同核心的性能差异，因此频率都被定制为一样。另外不用零售版本AM2+处理器进行测试的原因是，锁定倍频的零售Phenom X4超频能力极为有限，测试也没有发现ES和零售品有任何性能差异。
由于版面限制，更多测试截图将保留到论坛讨论帖
AMD平台使用即将发布的RD790，而Intel平台则使用P35主板，包括游戏在内的所有设置都是默认。显卡是GeForce8800GTX，驱动是最新的169.02，板载声卡使用了Realtek 1.80驱动，操作系统是Windows XP(DX9)。
设置时，内存均设置为“by SPD”(by SPD= 5-5-5-18)，但CPU-Z侦测Phenom X4平台时会误辩为5-5-7-18，这个问题要等CPU-Z以后的更新解决了。
| 特别说明：为什么Phenom X4的CPU-Z图中内存显示为单通道？
因为此时打开Phenom X4的2个内存控制器，1个内存控制器控制一条内存，这样在执行多任务的表现会更好，但是提升并不是很大，这只是对AMD平台稍做优化而已。 |
第一回合：AMD处理器对抗赛(QX6700为附加赛)
由于版面限制，点击放大图片可看到参考的QX6700成绩
测试成绩：同频QX6700 > Phenom X4 > FX62 > 5000+
L2 Cache较大的FX62赢了5000+，Phenom X4则领先FX62大概21.5%，却落后QX6700达12.7%。值得强调的是，由于AMD处理器固有的内存分频问题，Phenom X4的内存频率是485.9MHz(X2)，而QX6700平台的内存频率是400MHz(X2)。
第二回合：AMD、Intel 4核心对抗赛
由于版面限制，点击放大图片可看到参考的E6850和FX62成绩
测试成绩：同频QX9650 > QX6850 > E6850 > Phenom X4 > FX62
Yorkfield核心的QX9650领先Kentsfield核心的QX6850大约1.4%，差距很小。4核的QX6850则领先2核的E6850达13.7%，对比AMD平台呢？原生4核的Phenom X4领先2核的FX62比率缩减到17.7%(第一回合是21.5%)，但是却远远落后于同频的E6850。
在这个测试中，E6850的得分是70.76，而Phenom X4的得分是64.325，落后达9.1%，如果是对比QX9650，落后的数值要扩大到21.2%。
第三回合：超频、HT Link
由于版面限制，点击放大图片可看到更多成绩
为了让大家更为熟悉Phenom X4的效能情况，我们又进行了多个超频模式。从成绩来看，HT频率对于Phenom X4的实际效能没有帮助，提高CPU频率或者内存效能依然是更好的办法。
全文总结：
进行Crysis CPU Benchmark是对一个全新测试项目的尝试，借助游戏默认设置的测试，我们可以参考到一些已经发布和即将发布处理器产品的实际效能。
对于AMD而言，现阶段依然无法保证在频率之战上面取得胜利。我们知道，几颗所谓零售版AM2+处理器(上面已经标识好对应的型号，如GP9600)的超频情况不容乐观。由于倍频已经锁定，所以通过提高倍频来超频是不现实的想法，而通过外频来呢？最高只能提升至26X～27XMHz。测试所用PhenomX4工程样品可以超过3GHz的情况不会那么容易就出现在零售产品上面，请记住这点。
很多朋友可能会认为是频率限制了Phenom X4效能的发挥，其实不然。参考前面的测试成绩，你可以看到不仅仅是Superpi跑得慢的问题，Phenom X4调节到与同代Intel CPU相同的频率下也无法取得胜利，即便是对比双核的E6850，差距也不小。
Intel平台也并非全无困惑，我们可以看到2核到4核心的提高不如AMD平台来得高，这可能成为AMD宣传中作反复强调的地方。但是Phenom X4对于K8处理器提升虽然更大一些，但是效能却远远落后于同代对手，更不需要提及在超频部分的劣势。
我想问，AMD，Phenom X4原生4核威力何在？11月20日，AMD将正式发布其首款4核桌面处理器，届时，你将会得到更多你想知道的答案。我想知道的，那就是产品的最终定价如何？
Notice: We have done a re-test based on the earlier episode on these CPU due to the driver and system setting reason.
These days we using the Crysis built-in benchmark to do some more test on Intel QX9650, QX6850, QX6700, AMD Phenom X4, AMD Athlon64 X2 5000+ and FX62 again. For more accuracy we re-install the whole OS, using the newest driver, and adding some subitem tests.
The test focus on the difference of core architecture, so all the frequency are set to the same. Because the retail version phenom X4 have limited OC ability(multiplier locked) so that we have to use engineering sample.(we can't find any difference except the locked multiplier between ES and retail version)
The same as before, in AMD test bed we are using the up-coming RD790 mobo. And in Intel test bed we are using P35. Including games, all the setting are in default. We are using GF 8800GTX,Driver is 169.02 WHQL. integrated Soundcard using Realtek 1.80 driver, and OS is XP SP2(DX9).
We set all the memory to "By SPD"(by SPD= 5-5-5-18). But when we are using the Phenom X4 platform, CPU-z wrongly detected the timing as 5-5-7-18. Please wait for the CPU-Z's further update.
|
Why CPU-Z shows Phenom X4 only have single channel? |
Round one: A64X2 5000+ VS. A64FX62 VS. Phenom X4 VS. QX6700
click to see scores of QX6700
QX6700 > Phenom X4 > FX62 > 5000+
Having a bigger L2 cache, FX62 beats 5000+. And the average score of Phenom X4 is 21.5% more than FX62. But, Phenom X4 losing this round coz its final score less than QX6700 for 12.7%. We have to stress that because of the architecture difference, AMD have the memory frequency demultiplication difference between Intel systems: Phenom X4's memory frequency is 485.9MHz (x2),and QX6700 is 400MHz(x2).
Round two: AMD quad core VS. Intel quad core
Click to see E6850 and FX62 score as a refrence
QX9650 > QX6850 > E6850 > Phenom X4 > FX62 (same frequency)
Yorkfield QX9650 only have little improvement compare to Kentsfield QX6850, only 1.4%. But quad core QX6850 beats E6850 by 13.7% improvement.
Comparing to the AMD side: native quad core Phenom X4 wining FX62 by only having 17.7% improvement, Far less than E6850.
comparing to QX9650, Phenom X4 have a huge gap(21.2% less)
Round three: Overclocking, and HT link
Click to see more
For finding more info to detect the Phenom X4 performance, we continue on several OC test. From the final score, the HT frequency have no actual boost on Phenom X4's performance.
Final thoughts:
Testing using Crysis CPU Benchmark is a new try, We hope this test can show the CPU's actual performance.
With these score AMD can't win this fight easily. We know that the OC ability of these retail version AM2+ CPUs are limited. We can not use the multiplier to OC, and using FSB to OC only can boost up the frequency for 26X～27XMHz. Pls remember that a easily-OC-to-3GHz-PhenomX4 wont sell on market.
It is not the Frequency limiting the Phenom X4. Just read all the score for reference, Even OC to the same frequency Phenom still can not win. Compare to dual core E6850 it still have a performance gap.
But the test also show some bad news for Intel: the dual-core-to-quad-core improvement are more less than AMD's job. AMD is catching up and Intel still using their last generation advantage.
We want to ask AMD: where's native quad core's advantage? Nov.20 Phenom X4 will begin selling, at that time we will know more.