This work observes that a large fraction of the computations performed by Deep Neural
Networks (DNNs) are intrinsically ineffectual as they involve a multiplication where one of …

The Single Instruction Multiple Data (SIMD) architecture, supported by various high-
performance computing platforms, efficiently utilizes data-level parallelism. The SIMD model …

Modern scientific discovery is driven by an insatiable demand for computing performance.
The HPC community is targeting development of supercomputers able to sustain 1 ExaFlops …

This paper presents Warped-Compression, a warp-level register compression scheme for
reducing GPU power consumption. This work is motivated by the observation that the …

To aid application characterization and architecture design space exploration, researchers
and engineers have developed a wide range of tools for CPUs, including simulators …

General-purpose GPUs have been widely utilized to accelerate parallel applications. Given
a relatively complex programming model and fast architecture evolution, producing efficient …

If-conversion is a fundamental technique for vectorization. It accounts for the fact that in a
SIMD program, several targets of a branch might be executed because of divergence …

We address the problem of applying powerful pattern recognition algorithms based on
kernels to efficient visual tracking. Recently S. Avidan,(2001) has shown that object …

Convolutional neural networks (CNNs) outperform traditional machine learning algorithms
across a wide range of applications, such as object recognition, image segmentation, and …

A generally used GPU programming methodology is that adjacent threads access data in
neighbor or specific-stride memory addresses and perform computations with the fetched …