Related papers: Accelerating Twisted Mass LQCD with QPhiX
Matrix multiplications between asymmetric bit-width operands, especially between 8- and 4-bit operands are likely to become a fundamental kernel of many important workloads including neural networks and machine learning. While existing SIMD…
While Transformers are dominated by Floating-Point (FP) Matrix-Multiplications, their aggressive acceleration through dedicated hardware or many-core programmable systems has shifted the performance bottleneck to non-linear functions like…
Using medical imaging as case-study, we demonstrate how Intel-optimized TensorFlow on an x86-based server equipped with 2nd Generation Intel Xeon Scalable Processors with large system memory allows for the training of memory-intensive…
We evaluate IBM's Enhanced Cell Broadband Engine (BE) as a possible building block of a new generation of lattice QCD machines. The Enhanced Cell BE will provide full support of double-precision floating-point arithmetics, including…
A modern Fortran implementation of three Dirac operators (Wilson, Brillouin, Susskind) in lattice QCD is presented, based on OpenMP shared-memory parallelization and SIMD pragmas. The main idea is to apply a Dirac operator to $N_v$ vectors…
Quantum Monte Carlo (QMC) techniques are widely used in a variety of scientific problems and much work has been dedicated to developing optimized algorithms that can accelerate QMC on standard processors (CPU). With the advent of various…
Fixed-frequency superconducting quantum processors are one of the most mature quantum computing architectures with high-coherence qubits and simple controls. However, high-fidelity multi-qubit gates pose tight requirements on individual…
Mixed-signal hardware accelerators for deep learning achieve orders of magnitude better power efficiency than their digital counterparts. In the ultra-low power consumption regime, limited signal precision inherent to analog computation…
This short report describes the scaling, up to 1024 software processes and hardware cores, of a distributed simulator of plastic spiking neural networks. A previous report demonstrated good scalability of the simulator up to 128 processes.…
This paper presents a workflow for synthesizing near-optimal FPGA implementations for structured-mesh based stencil applications for explicit solvers. It leverages key characteristics of the application class, its computation-communication…
Transformer-based large language models (LLMs) have demonstrated remarkable performance across a wide range of real-world tasks, but their inference cost remains prohibitively high due to the quadratic complexity of attention and the memory…
We introduce QPU micro-kernels: shallow quantum circuits that perform a stencil node update and return a Monte Carlo estimate from repeated measurements. We show how to use them to solve Partial Differential Equations (PDEs) explicitly…
The main performance bottleneck of gravitational N-body codes is the force calculation between two particles. We have succeeded in speeding up this pair-wise force calculation by factors between two and ten, depending on the code and the…
We present a novel application of the machine learning / artificial intelligence method called boosted decision trees to estimate physical quantities on field programmable gate arrays (FPGA). The software package fwXmachina features a new…
We present the first end-to-end deployment of the Gemma3 family of large language and vision models on a tiled edge dataflow architecture (AMD Ryzen AI NPU). Our work introduces a set of hardware-aware techniques. For prefill, we introduce…
Algorithmic and architecture-oriented optimizations are essential for achieving performance worthy of anticipated energy-austere exascale systems. In this paper, we present an extreme scale FMM-accelerated boundary integral equation solver…
Modern processors deliver higher throughput for lower-precision arithmetic than for higher-precision arithmetic. For matrix multiplication, the Ozaki scheme exploits this performance gap by splitting the inputs into lower-precision…
Neural network accelerators have been widely applied to edge devices for complex tasks like object tracking, image recognition, etc. Previous works have explored the quantization technologies in related lightweight accelerator designs to…
Cornami Mx2 accelerates of Fully Homomorphic Encryption (FHE) applications, enabled by breakthrough work [1], which are otherwise compute limited. Our processor architecture is based on the systolic array of cores with in-memory compute…
No area of computing is hungrier for performance than High Performance Computing (HPC), the demands of which continue to be a major driver for processor performance and adoption of accelerators, and also advances in memory, storage, and…