|Sapphire ATI Radeon HD 5850 Video Card 21162-00-50R|
|Reviews - Featured Reviews: Video Cards|
|Written by Olin Coles|
|Thursday, 15 October 2009|
Page 12 of 16
SPECviewperf 10 is a synthetic benchmark designed to be a predictor of application performance and a measure of graphics subsystem performance. SPECviewperf 10 provides the ability to compare performance of systems running in higher-quality graphics modes that use full-scene anti-aliasing, and measures how effectively graphics subsystems scale when running multithreaded graphics content. The SPECopc project group's SPECviewperf 10 is a performance evaluation software requiring OpenGL 1.5 and a minimum of 1GB of system memory. It currently supports 32/64-bit versions of the Microsoft Windows Operating System. Since the SPECviewperf source and binaries have been upgraded to support changes, no comparisons should be made between past results and current results for viewsets running under SPECviewperf 10.
The proe-04 viewset was created from traces of the graphics workload generated by the Pro/ENGINEER 2001 application from PTC. Mirroring the application, draw arrays are used for the shaded tests and immediate mode is used for the wireframe. The gradient background used by the Pro/E application is also included to better model the application workload.
Two models and three rendering modes are measured during the test. PTC contributed the models to SPEC for use in measurement of the Pro/ENGINEER application. The first of the models, the PTC World Car, represents a large-model workload composed of 3.9 to 5.9 million vertices. This model is measured in shaded, hidden-line removal, and wireframe modes. The wireframe workloads are measured both in normal and antialiased mode. The second model is a copier. It is a medium-sized model made up of 485,000 to 1.6 million vertices. Shaded and hidden-line-removal modes were measured for this model.
This viewset includes state changes as made by the application throughout the rendering of the model, including matrix, material, light and line-stipple changes. The PTC World Car shaded frames include more than 100MB of state and vertex information per frame. All state changes are derived from a trace of the running application. The state changes put considerably more stress on graphics subsystems than the simple geometry dumps found in older viewsets.
Unlike the other benchmark tests in this article, the Pro/ENGINEER 2001 targets industrial application and disregards video game performance, although the two overlap. SPECviewperf 10 tests the proe-04 viewset in seven different tests, ranging from shaded to wire- and anti-aliased line views. The results are NOT the average FPS, but are actually the weighted geometric mean for the combined performance of all seven tests.
Judging from the results, there's very little difference in weighted geometric mean between the 13.1 score of NVIDIA's GTS 250, or the 14.0 scores of nearly all ATI Radeon products. But when you look a little closer, you notice that the GTS 250, overclocked GTX 260, and the overclocked ASUS GeForce GTX 285 TOP all score the same 13.1 geometric mean. Consider then that the mid-level Radeon HD 4770 scores a 13.7. while the ATI Radeon HD 4890, 5850, and 5870 all score a solid 14.0 geometric mean.
So what can we infer from these SPECviewperf Pro/ENGINEER tests? From what little can be gathered, it appears that ATI Radeon video cards are generally superior to NVIDIA GeForce products in terms of industrial CAD applications. To be fair these are both consumer-level display adapters, and the NVIDIA Quadro or AMD/ATI FirePro series is designed specifically for workstation graphics.