Copertina

Characterizing and Optimizing LLM Inference Workloads on CPU-GPU Coupled Architectures

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Vellaisamy, Prabhu, Labonte, Thomas, Chakraborty, Sourav, Turner, Matt, Sury, Samantika, Shen, John Paul
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Distributed, Parallel, and Cluster Computing Artificial Intelligence Hardware Architecture Performance
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Profiling Concurrent Vision Inference Workloads on NVIDIA Jetson -- Extended
di: Chakraborty, Abhinaba, et al.
Pubblicazione: (2025)

Characterizing CPU-Induced Slowdowns in Multi-GPU LLM Inference
di: Chung, Euijun, et al.
Pubblicazione: (2026)

GigaAPI for GPU Parallelization
di: Suvarna, M., et al.
Pubblicazione: (2025)

Parallelizing a modern GPU simulator
di: Huerta, Rodrigo, et al.
Pubblicazione: (2025)

Optimizing Attention on GPUs by Exploiting GPU Architectural NUMA Effects
di: Choudhary, Mansi, et al.
Pubblicazione: (2025)

Massimult: A Novel Parallel CPU Architecture Based on Combinator Reduction
di: Nicklisch-Franken, Jurgen, et al.
Pubblicazione: (2024)

Compiler Support for Speculation in Decoupled Access/Execute Architectures
di: Szafarczyk, Robert, et al.
Pubblicazione: (2025)

Fusing Depthwise and Pointwise Convolutions for Efficient Inference on GPUs
di: Qararyah, Fareed, et al.
Pubblicazione: (2024)

Dissecting the NVIDIA Hopper Architecture through Microbenchmarking and Multiple Level Analysis
di: Luo, Weile, et al.
Pubblicazione: (2025)

Optimized thread-block arrangement in a GPU implementation of a linear solver for atmospheric chemistry mechanisms
di: Ruiz, Christian Guzman, et al.
Pubblicazione: (2024)

Cloud to Edge: Benchmarking LLM Inference On Hardware-Accelerated Single-Board Computers
di: Renney, Harri, et al.
Pubblicazione: (2026)

ZipServ: Fast and Memory-Efficient LLM Inference with Hardware-Aware Lossless Compression
di: Fan, Ruibo, et al.
Pubblicazione: (2026)

Performance Analysis of HPC applications on the Aurora Supercomputer: Exploring the Impact of HBM-Enabled Intel Xeon Max CPUs
di: Ibeid, Huda, et al.
Pubblicazione: (2025)

UPMEM Unleashed: Software Secrets for Speed
di: Chmielewski, Krystian, et al.
Pubblicazione: (2025)

Experimental Assessment of Containers Running on Top of Virtual Machines
di: Aqasizade, Hossein, et al.
Pubblicazione: (2024)

Exploring and Evaluating Real-world CXL: Use Cases and System Adoption
di: Wang, Xi, et al.
Pubblicazione: (2024)

Can Asymmetric Tile Buffering Be Beneficial?
di: Wang, Chengyue, et al.
Pubblicazione: (2025)

Exploiting long vectors with a CFD code: a co-design show case
di: Blancafort, Marc, et al.
Pubblicazione: (2024)

Simopt -- Simulation pass for Speculative Optimisation of FPGA-CAD flow
di: Wadhwa, Eashan, et al.
Pubblicazione: (2024)

On Optimizing Locality of Graph Transposition on Modern Architectures
di: Esfahani, Mohsen Koohi, et al.
Pubblicazione: (2025)

ODIN-Based CPU-GPU Architecture with Replay-Driven Simulation and Emulation
di: Dorairaj, Nij, et al.
Pubblicazione: (2026)

DCC: Data-Centric Compilation of Machine Learning Kernels for Processing-In-Memory Architectures
di: Yang, Peiming, et al.
Pubblicazione: (2025)

PyGim: An Efficient Graph Neural Network Library for Real Processing-In-Memory Architectures
di: Giannoula, Christina, et al.
Pubblicazione: (2024)

Evaluation of computational and energy performance in matrix multiplication algorithms on CPU and GPU using MKL, cuBLAS and SYCL
di: Torres, L. A., et al.
Pubblicazione: (2024)

The Hitchhiker's Guide to Programming and Optimizing Cache Coherent Heterogeneous Systems: CXL, NVLink-C2C, and AMD Infinity Fabric
di: Wang, Zixuan, et al.
Pubblicazione: (2024)

Taming Asynchronous CPU-GPU Coupling for Frequency-aware Latency Estimation on Mobile Edge
di: Chen, Jiesong, et al.
Pubblicazione: (2026)

ARKV: Adaptive and Resource-Efficient KV Cache Management under Limited Memory Budget for Long-Context Inference in LLMs
di: Lei, Jianlong, et al.
Pubblicazione: (2026)

Vector-Centric Machine Learning Systems: A Cross-Stack Approach
di: Jiang, Wenqi
Pubblicazione: (2025)

Chopper: A Multi-Level GPU Characterization Tool & Derived Insights Into LLM Training Inefficiency
di: Kurzynski, Marco, et al.
Pubblicazione: (2025)

Wattlytics: A Web Platform for Co-Optimizing Performance, Energy, and TCO in HPC Clusters
di: Afzal, Ayesha, et al.
Pubblicazione: (2026)

Performance and Power: Systematic Evaluation of AI Workloads on Accelerators with CARAML
di: John, Chelsea Maria, et al.
Pubblicazione: (2024)

TAPA: A Scalable Task-Parallel Dataflow Programming Framework for Modern FPGAs with Co-Optimization of HLS and Physical Design
di: Guo, Licheng, et al.
Pubblicazione: (2022)

SCAR: Scheduling Multi-Model AI Workloads on Heterogeneous Multi-Chiplet Module Accelerators
di: Odema, Mohanad, et al.
Pubblicazione: (2024)

Exploring the Efficiency of 3D-Stacked AI Chip Architecture for LLM Inference with Voxel
di: Liu, Yiqi, et al.
Pubblicazione: (2026)

Systematic Characterization of LLM Quantization: A Performance, Energy, and Quality Perspective
di: Shi, Tianyao, et al.
Pubblicazione: (2025)

Microbenchmark-Driven Analytical Performance Modeling Across Modern GPU Architectures
di: Jarmusch, Aaron, et al.
Pubblicazione: (2026)

Performance Modeling and Workload Analysis of Distributed Large Language Model Training and Inference
di: Kundu, Joyjit, et al.
Pubblicazione: (2024)

Ultra Ethernet's Design Principles and Architectural Innovations
di: Hoefler, Torsten, et al.
Pubblicazione: (2025)

Optimizing ML Concurrent Computation and Communication with GPU DMA Engines
di: Agrawal, Anirudha, et al.
Pubblicazione: (2024)

Spira: Exploiting Voxel Data Structural Properties for Efficient Sparse Convolution in Point Cloud Networks
di: Adamopoulos, Dionysios, et al.
Pubblicazione: (2025)