Jetson/Graphics Performance

< Jetson
Revision as of 13:44, 21 June 2014 by Deppman (talk | contribs) (GPGPU Capabilities)
Jump to: navigation, search

The Jetson TK1 SOC

The Tegra K1 SOC in the Jetson TK1 is targeted for embedded GPGPU applications as well as general purpose use in power-constrained devices such as super-phones, tablets, laptops, set-top boxes, and low-power desktop computers.

GPGPU Capabilities

The Tegra K1 SOC GPU provides excellent GPGPU performance. Nvidia claims Tegra TK1 can attain 326 GFLOPS, whereas its closest contemporary competitor, the SnapDragon 805, may achieve estimated 200 GFLOPS. Imagination Technologies announced a PowerVR GX6650 which they claim can challenge the Tegra K1 performance. However, this design favors FP16 operations which may limit its usefulness for GPGPU tasks. In any event, public bench marks have not been made available, and the deign may not be available in consumer devices until 2015. By that time, Erista, the Maxwell successor to the Tegra K1, should be available.

NVidia have a strong ecosystem and experience in the GPGPU space. NVidia leapt over the competition by using the same Kepler GPU architecture that it has used for years to power the worlds fastest desktop GPUs and super computers. This allows them to leverage high-quality existing code to provide superior breadth of capabilities, including OpenGL ES 3.0, CUDA 6, OpenCL 1.2, OpenGL 4.4, and a bevy of other GPGPU tools.

In my testing, GPGPU tasks have required by far the highest power draw. Typical non-GPGPU applications, including demanding OpenGL games, rarely required more than 5W for the SOC + RAM. The GPGPU tests, however, could push the SOC + RAM numbers to 9W.

Frames Per Seconds (FPS) Comparisons

More details soon.

Power Consumption

According to my testing, graphics performance on the Jeston TK1 is about on par with Intel HD 4600 graphics, but with superior OpenGL and GPGPU capabilities. Power draw for graphic-intensive tasks has been surprisingly low. It appears that typical graphical applications probably default to lower-power FP16 operations. GPGPU tasks, by comparison, do increase power draw significantly.

More details soon.