Search Results - single instruction multiple data parallel computation model

A GPU-based numerical manifold method for modeling the formation of the excavation damaged zone in deep rock tunnels by Liu, Quanshen, Xu, Xiangyu, Wu, Zhijun

“…In this study, combined with the zero–thickness cohesive element (ZE) model and explicit integration method, a parallelization technique based on graphics processing units (GPU…”
Get full text

Splitwise: Efficient Generative LLM Inference Using Phase Splitting by Patel, Pratyush, Choukse, Esha, Zhang, Chaojie, Shah, Aashaka, Goiri, Inigo, Maleki, Saeed, Bianchini, Ricardo

“…Generative large language model (LLM) applications are growing rapidly, leading to large-scale deployments of expensive and power-hungry GPUs…”
Get full text

Max-PIM: Fast and Efficient Max/Min Searching in DRAM by Zhang, Fan, Angizi, Shaahin, Fan, Deliang

“…Recently, in-DRAM computing is becoming one promising technique to address the notorious 'memory-wall' issue for big data processing…”
Get full text

A flexible algorithm for calculating pair interactions on SIMD architectures by Páll, Szilárd, Hess, Berk

“… In order to reach high performance on modern CPU and accelerator architectures, single-instruction multiple-data (SIMD…”
Get full text

PISA: Efficient Precision-Slice Framework for LLMs with Adaptive Numerical Type by Yang, Ning, Wang, Zongwu, Sun, Qingxiao, Lu, Liqiang, Liu, Fangxin

“…Large language models (LLMs) have transformed numerous AI applications, with on-device deployment becoming increasingly important for reducing cloud computing costs and protecting user privacy…”
Get full text

McPAL: Scaling Unstructured Sparse Inference with Multi-Chiplet HBM-PIM Architecture for LLMs by Liu, Shiwei, Huang, Zhirui, Yu, Jiangnan, Liu, Qi, Chen, Chixiao

“…Large language models (LLMs) have gained significant attention recently. However, executing LLM is memory-bound due to the extensive memory accesses. Process-in-memory (PIM…”
Get full text

KVO-LLM: Boosting Long-Context Generation Throughput for Batched LLM Inference by Li, Zhenyu, Lyu, Dongxu, Wang, Gang, Chen, Yuzhou, Chen, Liyan, Li, Wenjie, Jiang, Jianfei, Sun, Yanan, He, Guanghui

“…With the widespread deployment of long-context large language models (LLMs), efficient and high-quality generation is becoming increasingly important…”
Get full text

A Novel Wavefront-Based High Parallel Solution for HEVC Encoding by Chen, Keji, Sun, Jun, Duan, Yizhou, Guo, Zongming

“… On data level, optimal single-instruction-multiple-data algorithms are designed for the enhanced coding tools, i.e…”
Get full text

MIMDRAM: An End-to-End Processing-Using-DRAM System for High-Throughput, Energy-Efficient and Programmer-Transparent Multiple-Instruction Multiple-Data Computing by Oliveira, Geraldo F., Olgun, Ataberk, Yaglikci, Abdullah Giray, Bostanci, F. Nisa, Gomez-Luna, Juan, Ghose, Saugata, Mutlu, Onur

“…, 16,384-262,144-bit-wide) data-parallel operations, in a single-instruction multiple-data (SIMD) fashion. However, DRAM rows' large and rigid granularity limit the effectiveness and applicability of PUD in three ways…”
Get full text

PHCG: Optimizing Simulink Code Generation for Embedded System With SIMD Instructions by Su, Zhuo, Wang, Dongyan, Yu, Zehong, Yang, Yixiao, Jiang, Yu, Wang, Rui, Chang, Wanli, Li, Wen, Cui, Aiguo, Sun, Jiaguang

“… In this article, we propose PHCG, an optimized code generator for the Simulink model with single-instruction-multiple-data (SIMD…”
Get full text

PairGraph: An Efficient Search-space-aware Accelerator for High-performance Concurrent Pairwise Queries by Fu, Yutao, Long, Zhongtian, Zhang, Yu, He, Zirui, Zhao, Jin, Niu, Qiyuan, Wang, Zixiao, Jin, Hai

“…Pairwise queries have been widely used in many applications. Although several approaches have been recently proposed to accelerate a single query, they still…”
Get full text

Pipirima: Predicting Patterns in Sparsity to Accelerate Matrix Algebra by 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 storage, it causes several challenges, too…”
Get full text

PacQ: A SIMT Microarchitecture for Efficient Dataflow in Hyper-asymmetric GEMMs by Yin, Ruokai, Li, Yuhang, Panda, Priyadarshini

“… During deployment on single-instruction-multiple-threads (SIMT) architectures, weights are stored in low-precision integer (INT…”
Get full text

PIMGCN: A ReRAM-Based PIM Design for Graph Convolutional Network Acceleration by Yang, Tao, Li, Dongyue, Han, Yibo, Zhao, Yilong, Liu, Fangxin, Liang, Xiaoyao, He, Zhezhi, Jiang, Li

“…Graph Convolutional Network (GCN) is a promising but computing- and memory-intensive learning model…”
Get full text

A parallel algorithm for generating bicompatible elimination orderings of proper interval graphs by Panda, B.S., Das, Sajal K.

“… (Single Instruction Stream Multiple Data Stream Concurrent Read Concurrent Write Parallel Random Access Machine…”
Get full text

EDGE: Event-Driven GPU Execution by Hetherington, Tayler Hicklin, Lubeznov, Maria, Shah, Deval, Aamodt, Tor M.

“… supporting latency-sensitive streaming tasks. This paper proposes an event-driven GPU execution model, EDGE, that enables non-CPU devices to directly launch preconfigured tasks on a GPU without CPU interaction…”
Get full text

Occamy: Memory-efficient GPU Compiler for DNN Inference by Lee, Jaeho, Jeong, Shinnung, Song, Seungbin, Kim, Kunwoo, Choi, Heelim, Kim, Youngsok, Kim, Hanjun

“…This work proposes Occamy, a new memory-efficient DNN compiler that reduces the memory usage of a DNN model without affecting its accuracy…”
Get full text

Soter: Analytical Tensor-Architecture Modeling and Automatic Tensor Program Tuning for Spatial Accelerators by Wang, Fuyu, Shen, Minghua, Ding, Yufei, Xiao, Nong

“…Spatial accelerator is a specialized hardware to provide noticeable performance speedup for tensor computations…”
Get full text

Offloaded MPI message matching: an optimistic approach by Garcia, Jeronimo S., Di Girolamo, Salvatore, Kosta, Sokol, Olmos, J.J. Vegas, Nudelman, Rami, Hoefler, Torsten, Bloch, Gil

“… In this work, we propose a bin-based MPI message approach, Optimistic Tag Matching, explicitly designed for the lightweight, highly parallel architectures typical of on-path SmartNICs…”
Get full text

Accelerating Geostatistical Modeling and Prediction With Mixed-Precision Computations: A High-Productivity Approach With PaRSEC by Abdulah, Sameh, Cao, Qinglei, Pei, Yu, Bosilca, George, Dongarra, Jack, Genton, Marc G., Keyes, David E., Ltaief, Hatem, Sun, Ying

“… models and optimization of parameters. Spatial data are assumed to possess properties of stationarity or non-stationarity via a kernel fitted to a covariance matrix…”
Get full text