Deep learning models with convolutional and recurrent networks are now ubiquitous and
analyze massive amounts of audio, image, video, text and graph data, with applications in …

This paper introduces Tiramisu, a polyhedral framework designed to generate high
performance code for multiple platforms including multicores, GPUs, and distributed …

Deep Neural Networks (DNNs) have emerged as the core enabler of many major
applications on mobile devices. To achieve high accuracy, DNN models have become …

Futhark is a purely functional data-parallel array language that offers a machine-neutral
programming model and an optimising compiler that generates OpenCL code for GPUs …

Tensor computations overwhelm traditional general-purpose computing devices due to the
large amounts of data and operations of the computations. They call for a holistic solution …

Data locality and parallelism are critical optimization objectives for performance on modern
multi-core machines. Both coarse-grain parallelism (eg, multi-core) and fine-grain …

Purely functional, embedded array programs are a good match for SIMD hardware, such as
GPUs. However, the naive compilation of such programs quickly leads to both code …

Deep learning frameworks automate the deployment, distribution, synchronization, memory
allocation, and hardware acceleration of models represented as graphs of computational …

Previous research has used program transformation to introduce parallelism and to exploit
data locality. Unfortunately, these two objectives have usually been considered …

In recent years the computing landscape has seen an increasing shift towards specialized
accelerators. Field programmable gate arrays (FPGAs) are particularly promising for the …