Related papers: nvidia-pcm: A D-Bus-Driven Platform Configuration …
Characterizing and predicting the training performance of modern machine learning (ML) workloads on compute systems with compute and communication spread between CPUs, GPUs, and network devices is not only the key to optimization and…
ModeSwitch-LLM is a lightweight request-boundary controller for improving single-GPU large language model inference efficiency by routing each request to an appropriate fixed inference mode. Instead of relying on one static serving…
Large language models (LLMs) are becoming increasingly capable at small parameter scales. At the same time, conventional cloud-centric deployment introduces challenges around data privacy, latency, and cost that are acute in operational…
Processing-In-Memory (PIM) is a novel approach that augments existing DRAM memory chips with lightweight logic. By allowing to offload computations to the PIM system, this architecture allows for circumventing the data-bottleneck problem…
With the increasing diversity of heterogeneous architecture in the HPC industry, porting a legacy application to run on different architectures is a tough challenge. In this paper, we present OpenMP Advisor, a first of its kind compiler…
In this paper, we develop a low-order three-dimensional finite-element solver for fast multiple-case crust deformation analysis on GPU-based systems. Based on a high-performance solver designed for massively parallel CPU based systems, we…
GPUs are the most popular platform for accelerating HPC workloads, such as artificial intelligence and science simulations. However, most microarchitectural research in academia relies on GPU core pipeline designs based on architectures…
Every year, novel NVIDIA GPU designs are introduced. This rapid architectural and technological progression, coupled with a reluctance by manufacturers to disclose low-level details, makes it difficult for even the most proficient GPU…
Repeated off-chip memory accesses to DRAM drive up operating power for data-intensive applications, and SRAM technology scaling and leakage power limits the efficiency of embedded memories. Future on-chip storage will need higher density…
GPU architectures have become popular for executing general-purpose programs. Their many-core architecture supports a large number of threads that run concurrently to hide the latency among dependent instructions. In modern GPU…
NVIDIA's Multi-Instance GPU (MIG) is a feature that enables system designers to reconfigure one large GPU into multiple smaller GPU slices. This work characterizes this emerging GPU and evaluates its effectiveness in designing…
This paper presents a GPU implementation of two foreground object segmentation algorithms: Gaussian Mixture Model (GMM) and Pixel Based Adaptive Segmenter (PBAS) modified for RGB-D data support. The simultaneous use of colour (RGB) and…
NVMe SSD hardware has witnessed widespread deployment as commodity and enterprise hardware due to its high performance and rich feature set. Despite the open specifications of various NVMe protocols by the NVMe Express group and NVMe being…
Hardware performance monitoring (HPM) is a crucial ingredient of performance analysis tools. While there are interfaces like LIKWID, PAPI or the kernel interface perf\_event which provide HPM access with some additional features, many…
The most important way to achieve higher performance in computer systems is through heterogeneous computing, i.e., by adopting hardware platforms containing more than one type of processor, such as CPUs, GPUs, and FPGAs. Several types of…
Effective performance profiling and analysis are essential for optimizing training and inference of deep learning models, especially given the growing complexity of heterogeneous computing environments. However, existing tools often lack…
The practical deployment of diffusion-based Neural Video Compression (NVC) faces critical challenges, including severe information loss, prohibitive inference latency, and poor temporal consistency. To bridge this gap, we propose DiffVC-RT,…
As heterogeneous supercomputing architectures leveraging GPUs become increasingly central to high-performance computing (HPC), it is crucial for computational fluid dynamics (CFD) simulations, a de-facto HPC workload, to efficiently utilize…
In this paper we implemented the algorithm we developed in [1] called 3DPIFCM in a parallel environment by using CUDA on a GPU. In our previous work we introduced 3DPIFCM which performs segmentation of images in noisy conditions and uses…
Real-world applications are now processing big-data sets, often bottlenecked by the data movement between the compute units and the main memory. Near-memory computing (NMC), a modern data-centric computational paradigm, can alleviate these…