Copertina

Adaptive Cache Pollution Control for Large Language Model Inference Workloads Using Temporal CNN-Based Prediction and Priority-Aware Replacement

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Liu, Songze, Du, Hongkun, Wang, Shaowen
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Hardware Architecture Performance
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

DEER: Deep Runahead for Instruction Prefetching on Modern Mobile Workloads
di: Vahdatniya, Parmida, et al.
Pubblicazione: (2025)

Characterizing and Optimizing Realistic Workloads on a Commercial Compute-in-SRAM Device
di: Zhang, Niansong, et al.
Pubblicazione: (2025)

An Analytical Cost Model for Fast Evaluation of Multiple Compute-Engine CNN Accelerators
di: Qararyah, Fareed, et al.
Pubblicazione: (2025)

Enhancing Instruction Prefetching via Cache and TLB Management
di: Jamet, Alexandre Valentin, et al.
Pubblicazione: (2026)

The Bicameral Cache: a split cache for vector architectures
di: Rebolledo, Susana, et al.
Pubblicazione: (2024)

A Review on Proprietary Accelerators for Large Language Models
di: Park, Sihyeong, et al.
Pubblicazione: (2025)

Accelerating LLM Inference via Dynamic KV Cache Placement in Heterogeneous Memory System
di: Fang, Yunhua, et al.
Pubblicazione: (2025)

Understanding the Performance Horizon of the Latest ML Workloads with NonGEMM Workloads
di: Karami, Rachid, et al.
Pubblicazione: (2024)

Towards CPU Performance Prediction: New Challenge Benchmark Dataset and Novel Approach
di: Liu, Xiaoman
Pubblicazione: (2024)

Simulation-Driven Evaluation of Chiplet-Based Architectures Using VisualSim
di: Ali, Wajid, et al.
Pubblicazione: (2025)

GreenMalloc: Allocator Optimisation for Industrial Workloads
di: Dakhama, Aidan, et al.
Pubblicazione: (2025)

PipeWeave: Synergizing Analytical and Learning Models for Unified GPU Performance Prediction
di: Zhang, Kaixuan, et al.
Pubblicazione: (2026)

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

SAHM: State-Aware Heterogeneous Multicore for Single-Thread Performance
di: Wadle, Shayne, et al.
Pubblicazione: (2025)

Makinote: An FPGA-Based HW/SW Platform for Pre-Silicon Emulation of RISC-V Designs
di: Perdomo, Elias, et al.
Pubblicazione: (2024)

OPTIMA: Design-Space Exploration of Discharge-Based In-SRAM Computing: Quantifying Energy-Accuracy Trade-Offs
di: Seyedfaraji, Saeed, et al.
Pubblicazione: (2024)

Improving the Serving Performance of Multi-LoRA Large Language Models via Efficient LoRA and KV Cache Management
di: Zhang, Hang, et al.
Pubblicazione: (2025)

Data-Driven Power Modeling and Monitoring via Hardware Performance Counter Tracking
di: Mazzola, Sergio, et al.
Pubblicazione: (2025)

WaveTune: Wave-aware Bilinear Modeling for Efficient GPU Kernel Auto-tuning
di: Zhang, Kaixuan, et al.
Pubblicazione: (2026)

Gem5-AcceSys: Enabling System-Level Exploration of Standard Interconnects for Novel Accelerators
di: Liu, Qunyou, et al.
Pubblicazione: (2025)

Cleaning up the Mess: Re-Evaluating the Real-System Modeling Accuracy of Ramulator 2.0
di: Bostanci, F. Nisa, et al.
Pubblicazione: (2025)

A TRRIP Down Memory Lane: Temperature-Based Re-Reference Interval Prediction For Instruction Caching
di: Kao, Henry, et al.
Pubblicazione: (2025)

3RSeT: Read Disturbance Rate Reduction in STT-MRAM Caches by Selective Tag Comparison
di: Cheshmikhani, Elham, et al.
Pubblicazione: (2025)

CXL-Interference: Analysis and Characterization in Modern Computer Systems
di: Mao, Shunyu, et al.
Pubblicazione: (2024)

JSPIM: A Skew-Aware PIM Accelerator for High-Performance Databases Join and Select Operations
di: Tajdari, Sabiha, et al.
Pubblicazione: (2025)

Towards Automated and Predictive Network-Level Energy Profiling in Reconfigurable IoT Systems
di: Bocus, Mohammud J., et al.
Pubblicazione: (2025)

Heterogeneous Memory Benchmarking Toolkit
di: Ghaemi, Golsana, et al.
Pubblicazione: (2025)

ETM2: Empowering Traditional Memory Bandwidth Regulation using ETM
di: Zuepke, Alexander, et al.
Pubblicazione: (2026)

Recurrent CircuitSAT Sampling for Sequential Circuits
di: Ardakani, Arash, et al.
Pubblicazione: (2025)

Introducing the Arm-membench Throughput Benchmark
di: Burth, Cyrill, et al.
Pubblicazione: (2025)

Enhancing software-hardware co-design for HEP by low-overhead profiling of single- and multi-threaded programs on diverse architectures with Adaptyst
di: Graczyk, Maksymilian, et al.
Pubblicazione: (2025)

SPEC CPU2026: Characterization, Representativeness, and Cross-Suite Comparison
di: Li, Ruihao, et al.
Pubblicazione: (2026)

Single 32-bit Sub-Channel DDR5 DIMMs: Architecture, Performance Bounds, and Standardisation
di: Ke, Chih-Hua
Pubblicazione: (2026)

Regular-Dead on Arrival: Characterizing and Protecting Against Dead-Entry TLB Misses in GPU Microarchitectures
di: Anik, Shafayat Mowla, et al.
Pubblicazione: (2026)

AI Load Dynamics--A Power Electronics Perspective
di: Li, Yuzhuo, et al.
Pubblicazione: (2025)

ONNXim: A Fast, Cycle-level Multi-core NPU Simulator
di: Ham, Hyungkyu, et al.
Pubblicazione: (2024)

LightningSimV2: Faster and Scalable Simulation for High-Level Synthesis via Graph Compilation and Optimization
di: Sarkar, Rishov, et al.
Pubblicazione: (2024)

Range, Not Precision: Block-Floating-Point Half-Precision FFT and SAR Imaging on Apple Silicon
di: Bergach, Mohamed Amine
Pubblicazione: (2026)

Accelerating Transistor-Level Simulation of Integrated Circuits via Equivalence of RC Long-Chain Structures
di: Tang, Ruibai, et al.
Pubblicazione: (2025)

A Quantitative Analysis and Guidelines of Data Streaming Accelerator in Modern Intel Xeon Scalable Processors
di: Kuper, Reese, et al.
Pubblicazione: (2023)