Related papers: ZMCintegral-v5.1: Support for Multi-function Integ…
An analog integrated circuit has been designed, in a BiCMOS 0.8 micron technology, for the feasability study of the signal processing of the AMS RICH photomultiplier tubes. This low power, three channel gated integrator includes its own…
The paper presents investigations on the implementation and performance of the finite element numerical integration algorithm for first order approximations and three processor architectures, popular in scientific computing, classical CPU,…
In this paper we present a new release of the FIESTA program (Feynman Integral Evaluation by a Sector decomposiTion Approach). FIESTA5 is performance-oriented - we implemented improvements of various kinds in order to make Feynman integral…
Recent results in language understanding using neural networks have required training hardware of unprecedentedscale, with thousands of chips cooperating on a single training run. This paper presents techniques to scaleML models on the…
GPU runtimes are historically implemented in CUDA or other vendor specific languages dedicated to GPU programming. In this work we show that OpenMP 5.1, with minor compiler extensions, is capable of replacing existing solutions without a…
Feynman loop integrals are a key ingredient for the calculation of higher order radiation effects, and are responsible for reliable and accurate theoretical prediction. We improve the efficiency of numerical integration in sector…
This paper presents a new major release of the program FIESTA (Feynman Integral Evaluation by a Sector decomposiTion Approach). The new release is mainly aimed at optimal performance at large scales when one is increasing the number of…
A merge tree is a topological descriptor of a real-valued function. Merge trees are used in visualization and topological data analysis, either directly or as a means to another end: computing a 0-dimensional persistence diagram,…
Tensor processing units (TPUs), specialized hardware accelerators for machine learning tasks, have shown significant performance improvements when executing convolutional layers in convolutional neural networks (CNNs). However, they…
With multi-core processors a ubiquitous building block of modern supercomputers, it is now past time to enable applications to embrace these developments in processor design. To achieve exascale performance, applications will need ways of…
In this report, we introduce InternVL 1.5, an open-source multimodal large language model (MLLM) to bridge the capability gap between open-source and proprietary commercial models in multimodal understanding. We introduce three simple…
Most previous 3D IC research focused on stacking traditional 2D silicon layers, so the interconnect reduction is limited to inter-block delays. In this paper, we propose techniques that enable efficient exploration of the 3D design space…
Matrix-accelerated stencil computation is a hot research topic, yet its application to three-dimensional (3D) high-order stencils and HPC remains underexplored. With the emergence of matrix units on multicore CPUs, we analyze matrix-based…
Finetuning large language models (LLMs) is essential for task adaptation, yet today's serving stacks isolate inference and finetuning on separate GPU clusters -- wasting resources and under-utilizing hardware. We introduce FlexLLM, the…
Functional aspects as well as the influence of integration technology on the system behavior have to be considered in the 3D integration design process of micro systems. Therefore, information from different physical domains has to be…
Maximizing the performance potential of the modern day GPU architecture requires judicious utilization of available parallel resources. Although dramatic reductions can often be obtained through straightforward mappings, further performance…
In this paper we solve on GPUs massive problems with large amount of data, which are not appropriate for solution with the SIMD technology. For the given problem we consider a three-level parallelization. The multithreading of CPU is used…
Inspired by the fact that humans use diverse sensory organs to perceive the world, sensors with different modalities are deployed in end-to-end driving to obtain the global context of the 3D scene. In previous works, camera and LiDAR inputs…
One of the most important and commonly used operations in many linear algebra functions is matrix-matrix multiplication (GEMM), which is also a key component in obtaining high performance of many scientific codes. It is a computationally…
We present a novel 4.5B parameter small language model that can handle multiple input and output modalities, including text, images, videos, and audio. Despite its small size, the model achieves near state-of-the-art performance on a…