Related papers: DGEMM without FP64 Arithmetic - Using FP64 Emulati…
This study presents a comprehensive multi-level analysis of the NVIDIA Hopper GPU architecture, focusing on its performance characteristics and novel features. We benchmark Hopper's memory subsystem, highlighting improvements in the L2…
Fast Multipole Methods (FMM) are a fundamental operation for the simulation of many physical problems. The high performance design of such methods usually requires to carefully tune the algorithm for both the targeted physics and the…
Most research in quantum computing today is performed against simulations of quantum computers rather than true quantum computers. Simulating a quantum computer entails implementing all of the unitary operators corresponding to the quantum…
Learning the parameters of Partially Observable Markov Decision Processes (POMDPs) from limited data is a significant challenge. We introduce the Fuzzy MAP EM algorithm, a novel approach that incorporates expert knowledge into the parameter…
This paper presents an efficient approach for multiplierless implementation for eight-point DCT approximation, which based on coordinate rotation digital computer (CORDIC) algorithm. The main design objective is to make critical path of…
Efficient exploitation of exascale architectures requires rethinking of the numerical algorithms used in many large-scale applications. These architectures favor algorithms that expose ultra fine-grain parallelism and maximize the ratio of…
The generic matrix multiply (GEMM) function is the core element of high-performance linear algebra libraries used in many computationally-demanding digital signal processing (DSP) systems. We propose an acceleration technique for GEMM based…
As GPU architectures rapidly evolve to meet the growing demands of exascale computing and machine learning, the performance implications of architectural innovations remain poorly understood across diverse workloads. NVIDIA Blackwell (B200)…
Motivated by the increasing interest in the posit numeric format, in this paper we evaluate the accuracy and efficiency of posit arithmetic in contrast to the traditional IEEE 754 32-bit floating-point (FP32) arithmetic. We first design and…
Deep Forest is a prominent machine learning algorithm known for its high accuracy in forecasting. Compared with deep neural networks, Deep Forest has almost no multiplication operations and has better performance on small datasets. However,…
Frugal computing is becoming an important topic for environmental reasons. In this context, several techniques have been proposed to reduce the storage of scientific data by dedicated compression methods specially tailored for arrays of…
It remains a challenge to run Deep Learning in devices with stringent power budget in the Internet-of-Things. This paper presents a low-power accelerator for processing Deep Neural Networks in the embedded devices. The power reduction is…
In this paper we develop the first fine-grained rounding error analysis of finite element (FE) cell kernels and assembly. The theory includes mixed-precision implementations and accounts for hardware-acceleration via matrix multiplication…
Iterative methods on irregular grids have been used widely in all areas of comptational science and engineering for solving partial differential equations with complex geometry. They provide the flexibility to express complex shapes with…
Sparse Matrix-Matrix multiplication is a key kernel that has applications in several domains such as scientific computing and graph analysis. Several algorithms have been studied in the past for this foundational kernel. In this paper, we…
Deep neural networks (DNNs) demand a very large amount of computation and weight storage, and thus efficient implementation using special purpose hardware is highly desired. In this work, we have developed an FPGA based fixed-point DNN…
Tucker decomposition is one of the most popular models for analyzing and compressing large-scale tensorial data. Existing Tucker decomposition algorithms usually rely on a single solver to compute the factor matrices and core tensor, and…
Training large Mixture-of-Experts (MoE) models remains computationally prohibitive due to their extreme compute and memory demands. Although low-precision training promises to accelerate computation and reduce memory footprint, existing…
Modern datacenters increasingly rely on low-power, single-slot inference accelerators to balance performance, energy efficiency, and rack density constraints. The NVIDIA T4 GPU has become widely deployed due to strong performance per watt…
State-of-the-art generic low-precision training algorithms use a mix of 16-bit and 32-bit precision, creating the folklore that 16-bit hardware compute units alone are not enough to maximize model accuracy. As a result, deep learning…