Add to My Interests
Remove from My Interests
This talk consists of two parts. In the first part, we explain how we use Tensor Cores to obtain extreme signal-processing performance. Tensor Cores are special-purpose matrix-multiplication units found in the latest GPUs, and are designed to speed up deep learning. However, their use is not limited to deep learning: we show how a single Tesla V100 GPU can achieve speeds of up to 75 TFLOPS on signal-processing algorithms like correlations and beam forming. In the second part of this talk, we explain how we solve the largest computational challenge in the imaging pipeline of modern radio telescopes. We explain how we implemented and optimized the novel Image-Domain Gridding algorithm on GPUs and compare performance and energy efficiencies with other devices. We show that our solution is an ideal candidate for the world's largest radio telescope (the Square Kilometre Array) as it meets the challenging performance and power consumption constraints.
Do Not Sell My Personal Information