high performance computing on graphics processing units: hgpu.org

Scientific workloads have traditionally exploited high levels of sparsity to accelerate computation and reduce memory requirements. While deep neural networks can be made sparse, achieving practical speedups on GPUs is difficult because these applications have relatively moderate levels of sparsity that are not sufficient for existing sparse kernels to outperform their dense counterparts. In this […]

With AMD reinforcing their ambition in the scientific high performance computing ecosystem, we extend the hardware scope of the Ginkgo linear algebra package to feature a HIP backend for AMD GPUs. In this paper, we report and discuss the porting effort from CUDA, the extension of the HIP framework to add missing features such as […]

A commonly occurring computation idiom in neural networks is to perform some pointwise operations on the result of a matrix multiplication. Such a sequence of operations is typically represented as a computation graph in deep learning compilers. When compiling to a GPU target, these computations can be individually mapped to manually tuned implementations provided by […]

To meet the surging demand for high-speed computation in an era of stagnating increase in performance per processor, systems designers resort to aggregating many and even heterogeneous processors into single systems. Automatic parallelization tools relieve application developers of the tedious and error prone task of programming these heterogeneous systems. For these tools, there are two […]

The Boolean satisfiability problem, abbreviated as SAT, is the backbone of many applications in VLSI design automation and verification. Over the years, many SAT solvers, both complete and incomplete, have been developed. Complete solvers are usually based on the DPLL (Davis–Putnam–Logemann–Loveland) algorithm, which is a backtracking algorithm. Industrial strength problems are very large and make […]

The introduction of accelerator devices such as graphics processing units (GPUs) has had profound impact on molecular dynamics simulations and has enabled order-of-magnitude performance advances using commodity hardware. To fully reap these benefits, it has been necessary to reformulate some of the most fundamental algorithms, including the Verlet list, pair searching and cut-offs. Here, we […]

High-performance tensor programs are crucial to guarantee efficient execution of deep learning models. However, obtaining performant tensor programs for different operators on various hardware platforms is notoriously difficult. Currently, deep learning systems rely on vendor-provided kernel libraries or various search strategies to get performant tensor programs. These approaches either require significant engineering efforts in developing […]

Fast and stable fluid simulations are an essential prerequisite for applications ranging from computer aided aerodynamic design of automobiles or airplanes to simulations of physical effects in CGI to research in meteorology. Recent differentiable fluid simulations allow gradient based methods to optimize e.g. fluid control systems in an informed manner. Solving the partial differential equations […]

We apply the SYCL programming model to the Rodinia benchmark suite, describe the transformations from the OpenCL implementations to the SYCL implementations, and evaluate the benchmarks on microprocessors with a CPU and an integrated GPU. The publicly available implementations of the benchmark suite will track the development of the SYCL compilers, and provide programs for […]

Compilers play a pivotal role in the software development process for microprocessors, by automatically translating high-level programming languages into machinespecific executable code. For a long time, while processors were scalar, compilers were regarded as a black box among the software community, due to their successful internal encapsulation of machine-specific details. Over a decade ago, major […]

The requirements and responsibilities assumed by software have increasingly rendered it to be large and complex. Testing to ensure that software meets all its requirements and is free from failures is a difficult and time-consuming task that necessitates the use of large test suites, containing many test cases. Time needed to compile and execute large […]

We propose a universal method for the evaluation of generalized standard materials that greatly simplifies the material law implementation process. By means of automatic differentiation and a numerical integration scheme, AutoMat reduces the implementation effort to two potential functions. By moving AutoMat to the GPU, we close the performance gap to conventional evaluation routines and […]