Archive Home arrow Reviews: arrow Processors arrow AMD Phenom-II X4-840 CPU HDX840WFGMBOX
AMD Phenom-II X4-840 CPU HDX840WFGMBOX E-mail
Reviews - Featured Reviews: Processors
Monday, 03 January 2011
Table of Contents: Page Index
AMD Phenom-II X4-840 CPU HDX840WFGMBOX
Features and Specifications
Closer Look: Phenom-II X4-840
Testing and Results
AIDA64 Extreme Edition v1.1 Benchmark Tests
Passmark PerformanceTest
PCMark Vantage Benchmark Tests
SiSoftware Sandra
Cinebench R11.5 Benchmarks
Street Fighter IV Benchmark
Video Transcoding Tests
AMD Phenom-II X4-840 Final Thoughts
AMD Phenom-II X4-840 Conclusion

AIDA64 Extreme Edition v1.1 Benchmark Tests

In November, 2010, FinalWire acquired and discontinued Lavalys EVEREST, updated it, and released it as AIDA64. AIDA64 is an industry leading system diagnostics and benchmarking solution for enthusiasts PC users, based on the award-winning EVEREST Technology. During system optimizations and tweaking it provides essential system and overclock information, advanced hardware monitoring and diagnostics capabilities to check the effects of the applied settings. CPU, FPU and memory benchmarks are available to measure the actual system performance and compare it to previous states or other systems. Furthermore, complete software, operating system and security information makes AIDA64 a comprehensive system diagnostics tool that offers a total of 100 pages of information about your PC.

All of the benchmarks used in our test bed rely on basic x86 instructions and consume very low system memory while also being aware of HyperThreading, multi-processors, and multi-core processors. While the AIDA64 CPU tests really only compare the processor performance more than it measures platforms, it still offers a glimpse into what kind of power each platform possesses.

Queen and Photoworxx tests are synthetic benchmarks that operate the function many times and over-exaggerate by several magnitudes what the real-world performance would be like. The Queen benchmark focuses on the branch prediction capabilities and misprediction penalties of the CPU. It does this by finding possible solutions to the classic queen problem on a chessboard. At the same clock speed theoretically the processor with the shorter pipeline and smaller misprediction penalties will attain higher benchmark scores.

Phenom_II_X4_840_AIDA1.png

In the Queen tests, the Phenom-II X4-840 gives about a 2.8% increase over the Athlon-II X4-645, just what we would expect from the 3% bump in clock speed. When overclocked, the X4-840 increases its own performance by almost 23% and comes within a few thousand points of both the Core i7-920 and the Core i5-2500K.

Like the Queen benchmark, the Photoworxx tests for penalties against pipeline architecture. The synthetic Photoworxx benchmark stresses the integer arithmetic and multiplication execution units of the CPU and also the memory subsystem. Due to the fact that this test performs high memory read/write traffic, it cannot effectively scale in situations where more than two processing threads are used. The AIDA64 Photoworxx benchmark performs the following tasks on a very large RGB image:

  • Fill
  • Flip
  • Rotate90R (rotate 90 degrees CW)
  • Rotate90L (rotate 90 degrees CCW)
  • Random (fill the image with random colored pixels)
  • RGB2BW (color to black & white conversion)
  • Difference
  • Crop

I have noticed over time that the Photoworxx test, unlike most of the other AIDA64 tests, depends a lot on the L3 cache. In this test more than any other, the CPUs that have an L3 cache perform a lot better than those that do not. Curiously, the Phenom-II X4-840 falls slightly behind the Athlon-II X4-645 in the Photoworxx test, although at an interval of less than 1%. When overclocked to 3.9GHz, the performance increases by over 20%.

The Zip Library test measures combined CPU and memory subsystem performance through the public ZLib compression library. ZLib is designed as a free lossless data compression library for use on virtually any computer hardware and operating system. The ZLib data format is itself portable across platforms and has a footprint independent of input data that can be reduced at some cost in compression.

Phenom_II_X4_840_AIDA2.png

In the ZLib integer test, the Phenom-II X4-840 comes out just over 3% ahead of the X4-645, which is right where it should be. When overclocked, performance is increased by over 22.5% and the Phenom-II X4-840 at 3.9GHz reaches a ZLib performance above that of the much more expensive, but stock clocked, Intel Core i7 and i5 CPUs.

The AES integer benchmark measures CPU performance using AES data encryption. It utilizes Vincent Rijmen, Antoon Bosselaers and Paulo Barreto's public domain C code in ECB mode and consumes 48 MB of memory.

Phenom_II_X4_840_AIDA3.png

While I normally like to put both of the Everest integer performance tests on one graph, the Core i5-2500K made that impossible this time. With the new Sandy Bridge and Lynnfield series of processors, Intel made some major changes to the way their CPUs handle AES compression. This new processing is a boon to webmasters everywhere, as well as anyone who deals with compressed files on a regular basis. With that in mind, the Core i5 processor completely destroys the competition in the AES test. The Phenom-II X4-840, while not competing in any way with the Core i5 processor, does outpace the Core i7-920 processor, even when both processors are at stock speeds. It also outperforms the Athlon-II X4-645 by 3% and boosts its own performance by over 22% when overclocked to 3.9GHz.

Phenom_II_X4_840_AIDA4.png

The floating point tests take us straight back to the normal 3% increase in performance for the Phenom-II X4-840 over the Athlon-II X4-645. All three tests, the 32-bit, 64-bit, and 128-bit keep almost exactly the same level of increase, lending validity to the tests. All three floating point numbers are increased by about 22.5% when the Phenom-II X4-840 is overclocked to 3.9GHz. Interestingly enough, in the 32-bit Julia and 64-bit Mandel tests, the overclocked X4-840 outperforms the stock Core i7-920, although it doesn't reach the Core i5-2500K levels. The 128-bit SinJulia tests show the Intel CPUs still on top, even after overclocking. Still, it's not a bad performance for a CPU set to release at $102.



 

Comments 

 
# You tell it like it isBernardP 2011-01-04 06:09
Congrats for telling it like it is. I have read another review that glosses over the renaming trickery.

However... the Phenom II 840 is not "a wolf in sheep's clothing", as you say, but more of a sheep in wolf's clothing :-)

It should be called a Athlon II 650, without a doubt. This renaming brings shame to AMD.

No doubt we will see the likes of HP and Acer peddling this Phalse Phenom to the gullible masses.
Report Comment
 
 
# Marketing at it's finestComputer Ed 2011-01-04 07:52
That in the end was the reason for it. My sources at AMD hinted that the name change was asked for by the partners. However as I understand it the 800 series will be the replacement as it where for the Athlon II line.

On a different note I am curious how many people complained when the the i5 was moved from the quad core as it originally released to a dual? Did anyone cry foul then?
Report Comment
 
 
# I agreeHank 2011-01-04 12:10
I mentioned in my review of the i5-2500K that I was glad for the newer transparency with the Sandy Bridge CPUs where all i5 chips are quad-core with no hyperthreading. It's disappointing that they don't have hyperthreading, but at least we know what to expect when buying an i5 this time.
Report Comment
 
 
# What about the "real" Phenom II?Olle P 2011-01-14 06:37
I think the most intriguing result of this test is how little extra performance is gained by adding 6MB L3 cache and hiking up the clock speed from 3.2 to 3.6 GHz (the specs of the 975).

The difference in actual results is mostly way below the 12.5% expected by the clock speed alone.

Seems like the only reason for spending the extra money on a "real" Phenom II X4 is to get a Black Edition with better overclocking.
Report Comment
 
 
# replyNormal 2011-01-20 14:17
@Olle P

Do not forget the L3 cache is suited for memory intensive tasking.
So just a clockspeed application a faster Athlon will beat a lower clocked Phenom,but whenever memory (Cache) comes in play a slower Phenom will beat an even higher clocked Athlon handsdown.
That's why in certain games the smaller P2X2 560 will beat the Athlon 2X4 645 .
Report Comment
 
 
# MrDavid Richmond 2011-05-20 10:24
I built a new pc around a 840 cpu.I was going to use a i3 clarkdale originally but when I went to buy the supplyer only had the new sandybridge as I was on a tight budget I took the amd route instead.A great choice fsst at most tasks and cheap.
Report Comment
 

Comments have been disabled by the administrator.

Search Benchmark Reviews
QNAP Network Storage Servers

Follow Benchmark Reviews on FacebookReceive Tweets from Benchmark Reviews on Twitter