Articles: CPU

Bookmark and Share

Pages: [ 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 ]

Application Tests

In Autodesk 3ds max 2014 we benchmark the speed of mental ray rendering of a complex 3D scene.

The final rendering is a type of application that can run easily on multiple processing cores. Most of its computations are integer. AMD’s multicore FX series CPUs are especially effective at such loads, so it is no wonder that the FX-9370 and FX-9590 deliver high performance. Being 7% and 15% faster than their predecessor FX-8350, the new processors from AMD compete successfully with the top-end LGA1150 products. The FX-9370 is about as fast as the Core i7-4770 whereas the flagship FX-9590 is 8% ahead of the fastest Haswell-based CPU.

In Adobe’s After Effects CC we measure the speed of classic rendering of a 3D video with a set of filters and special effects.

Rendering video effects in this Adobe application is somewhat different from 3D rendering but can also be easily carried out in parallel on multiple processing cores. The FX-9370 and FX-9590 are not as impressive as in the previous test. Still, the FX-9370 is ahead of the comparably priced Core i5-4670K whereas the FX-9590 is as good as the flagship quad-core Haswell with Hyper-Threading support.

The performance in Adobe Premiere Pro CC is measured as the time it takes to render a Blu-ray project with HDV 1080p25 video into H.264 format and apply special effects to it.

As a matter of fact, AMD’s Socket AM3+ processors are good enough for a broad range of applications that create high multithreaded loads but such applications are usually meant to run on workstations. Adobe Premier Pro CC is a good example. The FX-9370 and FX-9590 don’t show anything exceptional here but, being 6% and 11% ahead of the FX-8350, they are quite comparable to the Haswell-based Core i5 and Core i7 products. To be precise, the FX-9370 and FX-9590 are faster than the Core i5-4670K but slower than the Core i7-4770K, which agrees with AMD’s official pricing.

The test scenario for Adobe Photoshop Lightroom 5.3 includes post-processing and exporting into JPEG format of two hundred 12-megapixel RAW images captured with a Nikon D300.

Batch-processing of photographs is also an appropriate task for AMD’s Vishera-based CPUs. Working at increased clock rates, the new FX-9370 and FX-9590 handle this job as efficiently as the fastest LGA1150 products.

We benchmark performance in Adobe Photoshop CC using our custom test that is based on the Retouch Artists Photoshop Speed Test and consists of typical processing of four 24-megapixel images captured with a digital camera.

The FX-9370 and FX-9590 don’t find this test agreeable. The senior model falls behind the Core i5-4670K by as much as 26%. The fact is that Photoshop doesn’t always make good use of multiple processing cores. Moreover, this application often needs floating-point processing and the Piledriver design has only one floating-point subunit per each two x86 cores.

In our ABBYY FineReader 11.0 test we convert a scanned document with lots of formulas and images into a text format.

FineReader 11 is optimized for multicore CPUs, yet the top-end 8-core processors from AMD can’t match the quad-core Core i7-4770K with its Hyper-Threading technology. Anyway, the FX-9370 and FX-9590 deliver high performance here and seem to be absolutely worth the money.

The processors’ performance in cryptographic tasks is measured with the built-in benchmark of the popular TrueCrypt utility that uses triple AES-Twofish-Serpent encryption. Besides optimizations for multi-core CPUs, it supports the AES instructions.

AMD processors have always been good at encryption. The FX-9370 and FX-9590 push the performance bar even higher up. They are 8% and 16%, respectively, faster than the FX-8350 and this performance boost helps them beat not only the Core i5-4670K but also the Core i7-4770K. The FX-9590 is up to 25% ahead of the senior Haswell-based model.

To test the processors’ performance at data archiving we use WinRAR 5.0. Using maximum compression rate, we archive a 1.7GB folder with multiple files.

The WinRAR developers have managed to optimize their application for multicore CPUs, yet this is not enough for high archiving performance. Memory subsystem speed is important as well. AMD processors are inferior to their Intel opponents in cache latency as well as effective memory bandwidth. That’s why the 8-core FX-9370 and FX-9590 can only beat the quad-core i5-4670K here just because the latter lacks Hyper-Threading.

In order to measure how fast the tested CPUs can transcode video into H.264 format we used x264 FHD Benchmark 1.0.1 (64 bit). It measures the time it takes the x264 coder to convert an MPEG-4/AVC video recorded in 1920x1080@50fps resolution with default settings. The results have high practical value because the x264 codec is part of popular transcoding utilities such as HandBrake, MeGUI, VirtualDub, etc. We regularly update the coder used in this performance test. This time around, we use version r2358, which supports all contemporary instruction sets including AVX2.

When encoding HD video, the AMD FX-9370 is 17% ahead of the Core i5-4670K whereas the FX-9590 is about as fast as the Core i7-4770K. So again, AMD’s new FX series processors deliver good performance in applications that are optimized for multicore CPUs.

Encoding video with a bare coder is hardly a real-life application, so we want to check out the speed of video transcoding with the popular free tool Freemake Video Converter 4.1.0. It uses the FFmpeg library and is based on the x264 coder too, but features certain optimizations. We disable CUDA for this test to create maximum load on the CPUs’ computing cores but enable DXVA optimizations.

This picture is somewhat different from what we’ve seen in the previous test. Intel’s Core i5-4670K seems to be more confident, outperforming the FX-9370. In the same way, the FX-9590 is slightly slower than its market opponent Core i7-4770K.

Pages: [ 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 ]


Comments currently: 140
Discussion started: 02/25/14 01:59:38 AM
Latest comment: 01/07/17 08:37:07 AM

View comments

Add your Comment