Related papers: MISO: Exploiting Multi-Instance GPU Capability on …
Mixed-precision algorithms have been proposed as a way for scientific computing to benefit from some of the gains seen for artificial intelligence (AI) on recent high performance computing (HPC) platforms. A few applications dominated by…
Recent breakthroughs in Large-scale language models (LLMs) have demonstrated impressive performance on various tasks. The immense sizes of LLMs have led to very high resource demand and cost for running the models. Though the models are…
Modified Bessel functions of the second kind are widely used in physics, engineering, spatial statistics, and machine learning. Since contemporary scientific applications, including machine learning, rely on GPUs for acceleration, providing…
Ubiquity of AI makes optimizing GPU power a priority as large GPU-based clusters are often employed to train and serve AI models. An important first step in optimizing GPU power consumption is high-fidelity and fine-grain power measurement…
We investigate and characterize the performance of an important class of operations on GPUs and Many Integrated Core (MIC) architectures. Our work is motivated by applications that analyze low-dimensional spatial datasets captured by high…
Meeting both scalability and performance portability requirements is a challenge for any HPC application, especially for adaptively refined ones. In Octo-Tiger, an astrophysics application for the simulation of stellar mergers, we approach…
While Model Predictive Control (MPC) delivers strong performance across robotics applications, solving the underlying (batches of) nonlinear trajectory optimization (TO) problems online remains computationally demanding. Existing…
This study systematically tests a computational power reuse scheme proposed by the open source community disabling specific instruction sets (Fused Multiply Add instructions) through CUDA source code modifications on the NVIDIA CMP 170HX…
One way to write fast programs is to explore the potential parallelism and take advantage of the high number of cores available in microprocessors. This can be achieved by manually specifying which code executes on which thread, by using…
GPUs are essential to accelerating the latency-sensitive deep neural network (DNN) inference workloads in cloud datacenters. To fully utilize GPU resources, spatial sharing of GPUs among co-located DNN inference workloads becomes…
In recent years, the Graphics Processing Unit (GPU) has emerged as a low-cost alternative for high performance computing, enabling impressive speed-ups for a range of scientific computing applications. Early adopters in astronomy are…
GPU underutilization is a significant concern in many production deep learning clusters, leading to prolonged job queues and increased operational expenses. A promising solution to this inefficiency is GPU sharing, which improves resource…
Massive multi-threading in GPU imposes tremendous pressure on memory subsystems. Due to rapid growth in thread-level parallelism of GPU and slowly improved peak memory bandwidth, the memory becomes a bottleneck of GPU's performance and…
Spatial Branch and Bound (B&B) algorithms are widely used for solving nonconvex problems to global optimality, yet they remain computationally expensive. Though some works have been carried out to speed up B&B via CPU parallelization, GPU…
Training LLMs in distributed environments presents significant challenges due to the complexity of model execution, deployment systems, and the vast space of configurable strategies. Although various optimization techniques exist, achieving…
Exploration tasks are essential to many emerging robotics applications, ranging from search and rescue to space exploration. The planning problem for exploration requires determining the best locations for future measurements that will…
The identification, and subsequent discovery, of fast radio transients through blind-search surveys requires a large amount of processing power, in worst cases scaling as $\mathcal{O}(N^3)$. For this reason, survey data are generally…
Collocating deep learning training tasks improves GPU utilization but risks resource contention, severe slowdowns, and out-of-memory (OOM) failures. Accurate memory estimation is essential for robust collocation, and GPU utilization…
Sorting is a primitive operation that is a building block for countless algorithms. As such, it is important to design sorting algorithms that approach peak performance on a range of hardware architectures. Graphics Processing Units (GPUs)…
Collective operations are cornerstones of both HPC applications and large-scale AI training and inference, yet benchmarking them in a systematic and reproducible way remains difficult on modern systems due to the complexity of their…