|AMD FX-8150 Bulldozer Processor|
|Reviews - Featured Reviews: Processors|
|Written by David Ramsey|
|Wednesday, 12 October 2011|
Page 5 of 18
AIDA64 Extreme Edition Tests
AIDA64 Extreme Edition is the evolution of Lavalys' "Everest Ultimate Edition". Hungarian developer FinalWire acquired the rights to Everest in late November 2010, and renamed the product "AIDA64". The Everest product was discontinued and FinalWire is offering 1-year license keys to those with active Everest keys.
AIDA64 is a full 64-bit benchmark and test suite utilizing MMX, 3DNow! and SSE instruction set extensions, and will scale up to 32 processor cores. An enhanced 64-bit System Stability Test module is also available to stress the whole system to its limits. For legacy processors all benchmarks and the System Stability Test are available in 32-bit versions as well. Additionally, AIDA64 adds new hardware to its database, including 300 solid-state drives. On top of the usual ATA auto-detect information the new SSD database enables AIDA64 to display flash memory type, controller model, physical dimensions, and data transfer performance data. AIDA64 v1.00 also implements SSD-specific SMART disk health information for Indilinx, Intel, JMicron, Samsung, and SandForce controllers.
All of the benchmarks used in this test— Memory reads and writes, Queen, Photoworxx, ZLib, hash, and AES— rely on basic x86 instructions, and consume very little system memory while also being aware of Hyper-Threading, multi-processors, and multi-core processors. Of all the tests in this review, AIDA64 is the one that best isolates the processor's performance from the rest of the system. While this is useful in that it more directly compares processor performance, readers should remember that virtually no "real world" programs will mirror these results.
Although I'm using the same physical memory on both the AMD and Intel systems, I'm running it at different speeds: the officially supported maximum on each platform, which is 1333MHz for the Intel Core i5 and AMD Phenom II 1100T, and DDR3-1866 for the FX-8150. Let's see how this plays out in AIDA64's memory throughput tests:
And...not that well. While the FX-8150 shows a huge improvement in memory throughput over its predecessor, the Core I5 2500K still easily wins, even doubling the write throughput performance. This is an interesting result considering the higher frequency of the FX-8150 memory subsystem.
The Queen and Photoworxx tests are synthetic benchmarks that iterate the function many times and over-exaggerate 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.
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, so quad-core processors with Hyper-Threading have no real advantage. The AIDIA64 Photoworxx benchmark performs the following tasks on a very large RGB image:
The Intel processor produces the highest scores in both benchmarks, but the differences are interesting: at stock clocks speeds, the 2500K and FX-8150 are neck and neck, with the 1100T actually very slightly in the lead. Overclocking the Intel results in a decisive win, with the Intel CPU coming in about 18% above the AMD.
In the Photoworxx benchmark, the FX-8150 is much faster than the 1100t, even faster than its two extra cores would lead you to believe. The Intel processor still wins, although not by as large a margin as it did in the Queen benchmark, and the very high overclocks for both processors produce only minor improvements in their scores.
In the ZLib test, the AMD CPUs leap ahead of the Intel 2500K, with even the previous-generation 1100T beating the stock-clocked 2500K. In the Hash test, the difference is even more profound: the Intel CPU simply can't keep up with the AMD CPUs here.
Intel's Clarksdale and subsequent CPUs have dominated the AES test due to their Advanced Encryption Standard New Instructions (AES-NI), which dramatically accelerate AES code. AMD's own implementation of AES-NI makes its first appearance in Bulldozer-based CPUs, and in the ASUS motherboard turns in slightly better scores than the Intel CPU, although the score in the MSI motherboard is, oddly, about 11% lower. Overclocking has a minimal effect on this benchmark in either case, and the Phenom II X6-1100T, which does without AES-NI, just can't compete.
So far, we've seen the Intel and AMD CPUs slug it out and swap wins in these tests. Let's move on to the PCMark Vantage benchmark.