Why you can trust Tom's Hardware Our expert reviewers spend hours testing and comparing products and services so you can choose the best for you. Find out more about how we test.
Performance Results: LuxMark, SPECviewperf, Cinema4D and Blender
LuxMark v.3.1
The latest version of LuxMark is based on an updated LuxRender 1.5 render engine, which specifically incorporates OpenCL optimizations that invalidate comparisons to previous versions of the benchmark.
We tested all three scenes available in the 64-bit benchmark: LuxBall HDR (with 217,000 triangles), Neumann TLM-102 SE (with 1,769,000 triangles), and Hotel Lobby, with 4,973,000 triangles).
Radeon VII is the first-place finisher in LuxMark's LuxBall HDR workload, beating the Turing-based Titan RTX and Volta-based Titan V thanks to a substantial memory bandwidth advantage. It doesn't fare quite as well in the subsequent tests, which are more compute-intensive.
With that said, Radeon VII also scores better than GeForce RTX 2080, its primary competition, in the Neumann TLM-201 SE and Hotel Lobby tests.
SPECviewperf 13
The most recent version of SPECviewperf employs traces from Autodesk 3ds Max, Dassault Systemes Catia, PTC Creo, Autodesk Maya, Autodesk Showcase, Siemens NX, and Dassault Systemes SolidWorks. Two additional tests, Energy and Medical, aren’t based on a specific application, but rather on datasets typical of those industries.
Oil and gas workloads tend to involve very large datasets, which play into Radeon VII's 16GB of HBM2 at 1 TB/s. The same goes for a certain medical applications. And in those tests, AMD's flagship is faster than GeForce RTX 2080.
Catia and NX, specifically, respond well to the professional driver optimizations that benefit Nvidia's Titan cards. AMD's Radeons are quite a bit slower in both benchmarks. However, the Radeon VII and Radeon RX Vega 64 make easy work of GeForce RTX 2080.
Cinema4D
ProRender is a physically-based GPU render engine. Unlike Arion Render, which we tested in our Titan RTX review, it utilizes OpenCL instead of CUDA.
Blender
Per AMD's recommendation, we tested Radeon VII and Radeon RX Vega 64 using Blender v.2.79b. In order to get CUDA acceleration from GeForce RTX 2080, we had to use v.2.80.
Rendering the bmw27_GPU test file using our Core i7-8700K took 5:16, regardless of the graphics card we had installed. Switching over to GPU acceleration through OpenCL or CUDA brought those times down significantly. Although Radeon VII trails GeForce RTX 2080, it definitely improves upon Radeon RX Vega 64's performance.
MORE: Best Graphics Cards
MORE: Desktop GPU Performance Hierarchy Table
MORE: All Graphics Content
Orange Pi teams up with Huawei to create a SBC for AI development — Huawei Ascend chip delivers 8/20 TOPS of AI performance
Modder creates an awesome modular kinetic PC case — 3D-printed gears, wood, and acrylic combine to generate mesmerizing continual movements
AMD makes CPU and GPU comeback in latest Steam Hardware Survey — Red Team regains lost ground from Nvidia and Intel
