Ravi Teja Mullapudi

Learn More
This paper presents the design and implementation of PolyMage, a domain-specific language and compiler for image processing pipelines. An image processing pipeline can be viewed as a graph of interconnected stages which process images successively. Each stage typically performs one of point-wise, stencil, reduction or data-dependent operations on image(More)
The Halide image processing language has proven to be an effective system for authoring high-performance image processing code. Halide programmers need only provide a high-level strategy for mapping an image processing pipeline to a parallel machine (a <i>schedule</i>), and the Halide compiler carries out the mechanical task of generating platform-specific(More)
Current de-facto parallel programming models like OpenMP and MPI make it difficult to extract <i>task-level dataflow parallelism</i> as opposed to <i>bulk-synchronous parallelism</i>. Task parallel approaches that use point-to-point synchronization between dependent tasks in conjunction with dynamic scheduling dataflow runtimes are thus becoming attractive.(More)
Electromagnetic interference (EMI) control is one of the most significant challenges for emerging consumer, automotive, Internet of things (IoT) and wearable systems. This paper demonstrates miniaturized and integrated nanostructures for component-level EMI isolation and external EMI shielding in ultra-miniaturized electronic systems. Multi-layered(More)
Piezoelectric materials are widely used for microscale sensors and actuators but can pose material compatibility challenges. This paper reports a post-CMOS compatible fabrication process for piezoelectric sensors and actuators on silicon using only standard CMOS metals. The piezoelectric properties of aluminum nitride (AlN) deposited on titanium (Ti) by(More)
  • 1