Indigo Bench is a standalone application based on the Indigo rendering engine, which creates photo-realistic images using what its developers call “unbiased rendering technologies.”
Chaos Group’s V-Ray is a ray-tracing kernel that can be used in 3D Studio Max, Maya, and even the Unreal Engine.
Handbrake is a very popular video-transcoding app. To see how it performs on these chips, we used the latest version—1.2.2 as of this writing—to convert a roughly two-minute 4K source file from an iPhone 6S into a 1920×1080, 30 FPS MKV using the HEVC algorithm implemented in the x265 open-source encoder. We otherwise left the preset at its default settings.
Where the x264 encoder for H.264 video struggled to scale past 8 cores, x265 has no such difficulties. These new Ryzens will bring their video-encoding might to bear again in our streaming tests a bit later.
Computational fluid dynamics (CFD) makes for an interesting and CPU-intensive benchmark. For years and years, we used the Euler3D benchmark from Oklahoma State University’s CASElab, but that benchmark has become more and more difficult to continue justifying in today’s newly-competitive CPU landscape thanks to its compilation with Intel tools (and the resulting baked-in vendor advantage).
We set out to find a more vendor-neutral and up-to-date computational fluid dynamics benchmark than the wizened Euler3D. As it happens, the SPECwpc benchmark includes a CFD test constructed with Microsoft’s HPC Pack, the OpenFOAM toolkit, and the XiFoam solver. More information on XiFoam is available here. SPECwpc allows us to yoke every core and thread of our test systems for this benchmark.
While it’s true that CFD is CPU-intensive, it’s even more memory-bandwidth-intensive, which is why our high-end desktop chips take the first and second positions here with their quad-channel memory controllers. It’s not clear to us why the third-generation Ryzens fall behind their older cousins in this benchmark, but it’s fairly unlikely anyone is going to purchase a dual-channel desktop chip for serious CFD work.
The SPECwpc benchmark also includes a Windows-ready implementation of NAMD. As its developers describe it, NAMD “is a parallel molecular dynamics code designed for high-performance simulation of large biomolecular systems. Based on Charm++ parallel objects, NAMD scales to hundreds of cores for typical simulations and beyond 500,000 cores for the largest simulations.” Our ambitions are considerably more modest, but NAMD seems an ideal benchmark for our many-core single-socket CPUs.
AMD demoed NAMD on stage at Computex this year using a 64-core EPYC “Rome” CPU. That chip put up an incredible performance in that demo, and our results seem to support the veracity of said showing.