We didn’t run our entire benchmark suite for this little project. After all, our main goal in running tests was to verify that what we were seeing in CPUz and Everest was correct.
|Processor||AMD Phenom II X4 810 (Deneb) 2.6 GHz, 4 MB L3 cache|
|AMD Phenom II X2 720 Black Edition (Deneb) 2.8 GHz, 6 MB L3 cache|
|Cooler||Thermalright Ultra 120 Extreme|
|Motherboard||ASRock M3A790GXH/128M (Socket AM3) 790GX/SB750|
|Hard Drive||Western Digital VelociRaptor WD3000GLFS 300 GB 10,000 RPM SATA 3 Gb/s HDD|
|Graphics Card||Zotac GeForce GTX 260 Core 216 896 MB|
|Power Supply||Cooler Master UCP 1100 W|
|System Software and Drivers|
|Operating System||Microsoft Windows Vista Ultimate Edition x64 Service Pack 1|
|DirectX ||DirectX 10|
|Platform Driver||Catalyst 9.3|
|Graphics Driver||GeForce 185.63|
|Mainconcept Reference 1.6.1||MPEG-2 to H.264, 28 second HDTV clip (1920x1080)|
|TMPGEnc 4.0 XPress||DivX 6.8.5, Xvid 1.2.1 Video: Terminator 3 SE DVD (720x576) 5 min. Audio: Dolby Digital, 48000 Hz, 6-channel, English|
|Lame 3.98||64-bit .exe, Audio CD "Terminator II SE," 53 min., .wav to .mp3 @ 160 kbps|
|WinRAR 3.80||Compression = Best, Benchmark: THG Workload|
In Mainconcept, an extra 2 MB of cache buys a second off of the encoding job's time. But the addition of a fourth core to the X3 knocks 41 seconds off of the same task. Clearly, in applications able to take advantage of multiple cores, turning an X3 into an X4 yields more performance than getting a slightly higher overclock, for instance.
Again, we see the cache help a little bit. But the 2.8 GHz Phenom II X3 turns in better times for the latest version of Xvid due to its clock speed advantage over the X4 810. In DivX 6.8.5, the fourth core helps AMD's Phenom II X4 810 turn in better times. But a combination of four cores and an extra 200 MHz shows the unlocked X3 720 in the most favorable light.
Clock speed reigns supreme here, and LAME doesn't care about more cache or a fourth core.
WinRAR is the only application that we ran able to demonstrate the gains of an extra 2 MB of L3 cache. Because the app is also threaded, the quad-core X4 810 ends up performing close to the quicker X3 720.