arXiv subjects

Karima Ma

Publications and source records attributed to Karima Ma.

4 recordsLinked to original sources

arXiv2026

Vectorizing Recurrences over Semirings

Recurrences are ubiquitous in signal and image processing, bioinformatics, numerical computing, combinatorial optimization, and many other domains. Because recurrences seem inherently sequential, they are often implemented serially and thus do not leverage vector instructions in modern hardware. This leaves much of the available, often highly parallel, hardware underutilized. In this paper, we present an algebra of recurrences over semirings and study algebraic identities that enable vectorization. Using our algebraic framework, we present a number of vectorizing transformations that yield efficient, vectorized implementations across various settings. These transformations naturally extend to 2D recurrences and mutual recurrences. We implement the recurrence algebra and the vectorizing transformations in a compiler called VecRec.VecRec compiles recurrence programs to efficient vectorized C++ implementations. The generated kernels can achieve up to an order-of-magnitude speedup over serial implementations across a wide variety of recurrences. A case study in bioinformatics shows that they are competitive with, and in many cases better than, existing libraries with manually-crafted vectorization.

cs.PL↗

arXiv2026

Finding Fast Filters

Processing images, video, and audio often requires running large finite impulse response (FIR) filters with strict performance and latency requirements. Prior methods for fast filter approximations are special cases or combinations of a few key techniques: multi-rate and recurrent filtering, and decomposing filters into sums or cascades. We unify these techniques as primitives within a single design language for fast 1D and 2D filters. Given a target filter to approximate, we automatically search this program space, fitting continuous parameters with gradient descent, to generate a Pareto frontier of algorithms that trade off performance with quality. Our system produces substantially higher-quality and faster filter approximations than have been previously described for several popular imaging and audio filters. Furthermore we demonstrate how to automatically lower programs in this design space to optimized, vectorized, parallel, C++ code which is fused for data locality.

cs.GR↗

arXiv2024

Sketching With Your Voice: "Non-Phonorealistic" Rendering of Sounds via Vocal Imitation

We present a method for automatically producing human-like vocal imitations of sounds: the equivalent of "sketching," but for auditory rather than visual representation. Starting with a simulated model of the human vocal tract, we first try generating vocal imitations by tuning the model's control parameters to make the synthesized vocalization match the target sound in terms of perceptually-salient auditory features. Then, to better match human intuitions, we apply a cognitive theory of communication to take into account how human speakers reason strategically about their listeners. Finally, we show through several experiments and user studies that when we add this type of communicative reasoning to our method, it aligns with human intuitions better than matching auditory features alone does. This observation has broad implications for the study of depiction in computer graphics.

cs.GR↗

arXiv2023

Efficient Automatic Scheduling of Imaging and Vision Pipelines for the GPU

We present a new algorithm to quickly generate high-performance GPU implementations of complex imaging and vision pipelines, directly from high-level Halide algorithm code. It is fully automatic, requiring no schedule templates or hand-optimized kernels. We address the scalability challenge of extending search-based automatic scheduling to map large real-world programs to the deep hierarchies of memory and parallelism on GPU architectures in reasonable compile time. We achieve this using (1) a two-phase search algorithm that first 'freezes' decisions for the lowest cost sections of a program, allowing relatively more time to be spent on the important stages, (2) a hierarchical sampling strategy that groups schedules based on their structural similarity, then samples representatives to be evaluated, allowing us to explore a large space with few samples, and (3) memoization of repeated partial schedules, amortizing their cost over all their occurrences. We guide the process with an efficient cost model combining machine learning, program analysis, and GPU architecture knowledge. We evaluate our method's performance on a diverse suite of real-world imaging and vision pipelines. Our scalability optimizations lead to average compile time speedups of 49x (up to 530x). We find schedules that are on average 1.7x faster than existing automatic solutions (up to 5x), and competitive with what the best human experts were able to achieve in an active effort to beat our automatic results.

cs.PL↗