Sparse Convolution (SpC) powers 3D point cloud networks widely used in autonomous driving and AR/VR. SpC builds a kernel map that stores mappings between input voxel coordinates, output coordinates, and weight offsets, then uses this map to compute feature vectors for output coordinates. Our work identifies three key properties of voxel coordinates: they are integer-valued, bounded within a limited spatial range, and geometrically continuous-neighboring voxels on the same object surface are highly likely to exist at small spatial offsets from each other. Prior SpC engines do not fully exploit these properties and suffer from high pre-processing and post-processing overheads during kernel map construction. To address this, we design Spira, the first voxel-property-aware SpC engine for GPUs. Spira proposes: (i) a high-performance one-shot search algorithm that builds the kernel map with no preprocessing and high memory locality, (ii) an effective packed-native processing scheme that accesses packed voxel coordinates at low cost, (iii) a flexible dual-dataflow execution mechanism that efficiently computes output feature vectors by adapting to layer characteristics, and (iv) a network-wide parallelization strategy that builds kernel maps for all SpC layers concurrently at network start. Our evaluation shows that Spira significantly outperforms prior SpC engines by 1.71x on average and up to 2.31x for end-to-end inference, and by 2.13x on average and up to 3.32x for layer-wise execution across diverse layer configurations.

Respiratory insufficiency is a medic symptom in which a person gets a reduced amount of oxygen in the blood. This paper reports the experience of building SPIRA: an intelligent system for detecting respiratory insufficiency from voice. It compiles challenges faced in two succeeding implementations of the same architecture, summarizing lessons learned on data collection, training, and inference for future projects in similar systems.

Two University of Washington students just released a SMS COVID-19 tracker and have plans for a coronavirus screening tool. Nikolas Ioannou and Sage Khanuja are the teenagers behind Spira, which debuted the text-based service this week. Users will receive daily coronavirus updates, including information on deaths, cases, recoveries, and even reminders for hand washing and staying home. The data comes from Worldometer, a site that pulls numbers from official government reports and reliable news sources. The young entrepreneurs are also working on a COVID-19 screening tool that encourages people who may be experiencing flu-like symptoms to answer a quick questionnaire.

If you're single and your New Year's resolution was to rev up the romance, then Sunday, Jan. 5 might be the best day to immerse yourself in dating apps. Dubbed "Dating Sunday" or "Singles Sunday," the superficial holiday is the busiest online dating day of the year, according to several dating apps and websites. The date falls at the intersection of several cultural influences, making it "the perfect trifecta" for singles looking to find love, according to Julie Spira, a cyber-dating expert and author of "The Perils of Cyber-Dating." "You have people recovering from a breakup or who were down during the holidays, you have all those New Year's resolutions, and you have the clock ticking down to Valentine's Day," Spira said. The date also falls toward the tail-end of "cuffing season," where otherwise promiscuous adults seek to be tied down by a relationship. Young adults are often working during the weekdays and out socializing on Saturday, so Sundays tend to be the busiest day of the week for web dating throughout the year in general.