Suchergebnisse - "Mathematics of computing Mathematical software Mathematical software performance"

Finding the Pareto Frontier of Low-Precision Data Formats and MAC Architecture for LLM Inference von Crafton, Brian, Peng, Xiaochen, Sun, Xiaoyu, Lele, Ashwin, Zhang, Bo, Khwa, Win-San, Akarvardar, Kerem

“… To accelerate AI applications, numerous data formats and physical implementations of matrix multiplication have been proposed, creating a complex design space …”
Volltext

An Input-Aware Sparse Tensor Compiler Empowered by Vectorized Acceleration von He, Xianhao, Wang, Haotian, Zhang, Jiapeng, Yang, Wangdong, Chronopoulos, Anthony Theodore, Li, Kenli

“… Sparsity is widely prevalent in real-world applications, yet existing compiler optimizations and code generation techniques for sparse computations remain …”
Volltext

FeKAN: Efficient Kolmogorov-Arnold Networks Accelerator Using FeFET-based CAM and LUT von Yu, Xuliang, Qian, Yu, Yin, Xunzhao, Zhuo, Cheng, Zhao, Liang

“… Kolmogorov-Arnold networks (KANs) have emerged as a promising alternative to MLP due to their adaptive learning capabilities for complex dependencies through …”
Volltext

Optimized Polynomial Multiplier Architectures for Post-Quantum KEM Saber von Basso, Andrea, Roy, Sujoy Sinha

“… Saber is one of the four finalists in the ongoing NIST post-quantum cryptography standardization project. A significant portion of Saber's computation time is …”
Volltext

InnerSP: A Memory Efficient Sparse Matrix Multiplication Accelerator with Locality-Aware Inner Product Processing von Baek, Daehyeon, Hwang, Soojin, Heo, Taekyung, Kim, Daehoon, Huh, Jaehyuk

“… Sparse matrix multiplication is one of the key computational kernels in large-scale data analytics. However, a naive implementation suffers from the overheads …”
Volltext

Tackling the Matrix Multiplication Micro-Kernel Generation with Exo von Castello, Adrian, Bellavita, Julian, Dinh, Grace, Ikarashi, Yuka, Martinez, Hector

“… The optimization of the matrix multiplication (or GEMM) has been a need during the last decades. This operation is considered the flagship of current linear …”
Volltext

Pipirima: Predicting Patterns in Sparsity to Accelerate Matrix Algebra von Bakhtiar, Ubaid, Joo, Donghyeon, Asgari, Bahar

“… While sparsity, a feature of data in many applications, provides optimization opportunities such as reducing unnecessary computations, data transfers, and …”
Volltext

ReSMiPS: A ReRAM-based Sparse Mixed-precision Solver with Fast Matrix Reordering Algorithm von Fu, Yuyang, Li, Jiancong, Chen, Jia, Zhou, Zhiwei, Zhou, Houji, Peng, Wenlong, Li, Yi, Miao, Xiangshui

“… The solution of sparse matrix equations is essential in scientific computing. However, traditional solvers on digital computing platforms are limited by memory …”
Volltext

SSpMV: A Sparsity-aware SpMV Framework Empowered by Multimodal Machine Learning von Lin, Shengle, Liu, Chubo, Ding, Yan, Zhou, Joey Tianyi, Li, Kenli, Yang, Wangdong

“… Sparse Matrix-Vector Multiplication (SpMV) is an essential sparse operation in scientific computing and artificial intelligence. Efficiently adapting SpMV …”
Volltext

A Tensor Algebra Compiler for Sparse Differentiation von Shaikhha, Amir, Huot, Mathieu, Hashemian, Shideh

“… Sparse tensors are prevalent in many data-intensive applications. However, existing automatic differentiation (AD) frameworks are tailored towards dense …”
Volltext

SFLU: Synchronization-Free Sparse LU Factorization for Fast Circuit Simulation on GPUs von Zhao, Jianqi, Wen, Yao, Luo, Yuchen, Jin, Zhou, Liu, Weifeng, Zhou, Zhenya

“… Sparse LU factorization is one of the key building blocks of sparse direct solvers and often dominates the computing time of circuit simulation programs …”
Volltext

JITSPMM: Just-in-Time Instruction Generation for Accelerated Sparse Matrix-Matrix Multiplication von Fu, Qiang, Rolinger, Thomas B., Huang, H. Howie

“… Achieving high performance for Sparse Matrix-Matrix Multiplication (SpMM) has received increasing research attention, especially on multi-core CPUs, due to the …”
Volltext

pSyncPIM: Partially Synchronous Execution of Sparse Matrix Operations for All-Bank PIM Architectures von Baek, Daehyeon, Hwang, Soojin, Huh, Jaehyuk

“… Recent commercial incarnations of processing-in-memory (PIM) maintain the standard DRAM interface and employ the all-bank mode execution to maximize bank-level …”
Volltext

Accelerating Fourier and Number Theoretic Transforms using Tensor Cores and Warp Shuffles von Durrani, Sultan, Chughtai, Muhammad Saad, Hidayetoglu, Mert, Tahir, Rashid, Dakkak, Abdul, Rauchwerger, Lawrence, Zaffar, Fareed, Hwu, Wen-mei

“… The discrete Fourier transform (DFT) and its specialized case, the number theoretic transform (NTT), are two important mathematical tools having applications …”
Volltext

Seer: Predictive Runtime Kernel Selection for Irregular Problems von Swann, Ryan, Osama, Muhammad, Sangaiah, Karthik, Mahmud, Jalal

“… Modern GPUs are designed for regular problems and suffer from load imbalance when processing irregular data. Prior to our work, a domain expert selects the …”
Volltext

SpV8: Pursuing Optimal Vectorization and Regular Computation Pattern in SpMV von Li, Chenyang, Xia, Tian, Zhao, Wenzhe, Zheng, Nanning, Ren, Pengju

“… Sparse Matrix-Vector Multiplication (SpMV) plays an important role in many scientific and industry applications, and remains a well-known challenge due to the …”
Volltext

SpMMPlu: A Compiler Plug-in with Sparse IR for Efficient Sparse Matrix Multiplication von Yang, Tao, Zhou, Yiyuan, Tang, Qidong, Xu, Feng, Ma, Hui, Zhao, Jieru, Jiang, Li

“… Sparsity is becoming arguably the most critical dimension to explore for efficiency and scalability as deep learning models grow significantly larger …”
Volltext

Bridging the semantic gaps of GPU acceleration for scale-out CNN-based big data processing: Think big, see small von Mingcong Song, Yang Hu, Yunlong Xu, Chao Li, Huixiang Chen, Jingling Yuan, Tao Li

“… Convolutional Neural Networks (CNNs) have substantially advanced the state-of-the-art accuracies of object recognition, which is the core function of a myriad …”
Volltext

Generating Portable High-Performance Code via Multi-Dimensional Homomorphisms von Rasch, Ari, Schulze, Richard, Gorlatch, Sergei

“… We address a key challenge in programming high-performance applications - achieving portable performance, i.e., the same source code achieves a consistent, …”
Volltext

Sparso: Context-driven optimizations of sparse linear algebra von Hongbo Rong, Jongsoo Park, Lingxiang Xiang, Anderson, Todd A., Smelyanskiy, Mikhail

“… The sparse matrix is a key data structure in various domains such as high-performance computing, machine learning, and graph analytics. To maximize performance …”
Volltext