arXiv subjects

Maaz Bin Safeer Ahmad

Publications and source records attributed to Maaz Bin Safeer Ahmad.

4 recordsLinked to original sources

arXiv2026

Pushing Tensor Accelerators Beyond MatMul in a User-Schedulable Language

Tensor accelerators now represent a growing share of compute resources in modern CPUs and GPUs. However, they are hard to program, leading developers to use vendor-provided kernel libraries that support tensor accelerators. As a result, the usage of tensor accelerators is limited to the provided interface, mainly designed for traditional ML and scientific computing workloads. In this paper, we show that tensor accelerators can improve the performance of applications beyond simple variants of MatMul. For example, many image processing pipelines are linear transformations over matrices in disguise and can therefore utilize such specialized hardware. This is nonetheless hindered by the difficulties in programming tensor accelerators. We tackle this problem with compiler-based techniques. We use the Halide user-schedulable language and express operations as Halide algorithms succinctly. To this end, we implement a flexible tensor instruction selector based on equality saturation. The tensor instruction selector supports both CPU- and GPU-attached tensor accelerators and works with existing scheduling operations (e.g., producer-consumer fusion). Together, this enables developers to write diverse accelerator-leveraging applications in a few dozen lines. Using our system, we demonstrate the potential of tensor accelerators beyond their traditional domains. We implement several image processing pipelines (e.g., filtering, resampling, and denoising) in our system and evaluate them against non-accelerator-leveraging baselines. We show that these pipelines can achieve significant speedups. For example, a downsampling routine is sped up by $6.1\times$ by utilizing Tensor Cores on an Nvidia RTX 4070 GPU.

cs.PL↗

arXiv2023

Zero-shot CAD Program Re-Parameterization for Interactive Manipulation

Parametric CAD models encode entire families of shapes that should, in principle, be easy for designers to explore. However, in practice, parametric CAD models can be difficult to manipulate due to implicit semantic constraints among parameter values. Finding and enforcing these semantic constraints solely from geometry or programmatic shape representations is not possible because these constraints ultimately reflect design intent. They are informed by the designer's experience and semantics in the real world. To address this challenge, we introduce a zero-shot pipeline that leverages pre-trained large language and image model to infer meaningful space of variations for a shape. We then re-parameterize a new constrained parametric CAD program that captures these variations, enabling effortless exploration of the design space along meaningful design axes.

cs.GR↗

arXiv2018

Automatically Leveraging MapReduce Frameworks for Data-Intensive Applications

MapReduce is a popular programming paradigm for developing large-scale, data-intensive computation. Many frameworks that implement this paradigm have recently been developed. To leverage these frameworks, however, developers must become familiar with their APIs and rewrite existing code. Casper is a new tool that automatically translates sequential Java programs into the MapReduce paradigm. Casper identifies potential code fragments to rewrite and translates them in two steps: (1) Casper uses program synthesis to search for a program summary (i.e., a functional specification) of each code fragment. The summary is expressed using a high-level intermediate language resembling the MapReduce paradigm and verified to be semantically equivalent to the original using a theorem prover. (2) Casper generates executable code from the summary, using either the Hadoop, Spark, or Flink API. We evaluated Casper by automatically converting real-world, sequential Java benchmarks to MapReduce. The resulting benchmarks perform up to 48.2x faster compared to the original.

cs.DB↗

arXiv2016

Leveraging Parallel Data Processing Frameworks with Verified Lifting

Many parallel data frameworks have been proposed in recent years that let sequential programs access parallel processing. To capitalize on the benefits of such frameworks, existing code must often be rewritten to the domain-specific languages that each framework supports. This rewriting-tedious and error-prone-also requires developers to choose the framework that best optimizes performance given a specific workload. This paper describes Casper, a novel compiler that automatically retargets sequential Java code for execution on Hadoop, a parallel data processing framework that implements the MapReduce paradigm. Given a sequential code fragment, Casper uses verified lifting to infer a high-level summary expressed in our program specification language that is then compiled for execution on Hadoop. We demonstrate that Casper automatically translates Java benchmarks into Hadoop. The translated results execute on average 3.3x faster than the sequential implementations and scale better, as well, to larger datasets.

cs.PL↗