---
title: "CAMP: Context-Aware Mapping and Placement for LLMs on 3D-IMC Arrays"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.07707v1"
permalink: "https://feed.astralor.com/items/itm_aee9445784ea473759c896ad"
published: "2026-11-05T09:27:31.000Z"
score: 60
channel: "tech"
tags: ["LLM","推理效率","CAMP","Context-Aware Mapping","Placement","LLMs","IMC Arrays Large","Language Models"]
---

# CAMP: Context-Aware Mapping and Placement for LLMs on 3D-IMC Arrays

## 速览

Large Language Models (LLMs) incur severe memory-access overheads due to the cost of loading large weight matrices and key-value (KV) caches. Analog In-Memory Computing (AIMC) is an emerging solution that enables comput…

## 关键点

- Large Language Models (LLMs) incur severe memory-access overheads due to the cost of loading large weight matrices and key-value (KV) caches.
- Analog In-Memory Computing (AIMC) is an emerging solution that enables computation directly on static weights stored in memory, substantially reducing energy and latency.
- 3D-IMC further stacks memory arrays into vertical tiers, increasing capacity but revealing a new challenge: how weights are placed in memory determines which matrix-vector multiplications (MVMs) can execute concurrently…

## 全文

Large Language Models (LLMs) incur severe memory-access overheads due to the cost of loading large weight matrices and key-value (KV) caches. Analog In-Memory Computing (AIMC) is an emerging solution that enables computation directly on static weights stored in memory, substantially reducing energy and latency. 3D-IMC further stacks memory arrays into vertical tiers, increasing capacity but revealing a new challenge: how weights are placed in memory determines which matrix-vector multiplications (MVMs) can execute concurrently, affecting latency and throughput. The concurrency aspect of 3D-IMC weight-mapping remains underexplored in the literature, leading to sub-optimal utilization of compute resources on 3D-IMC chips. In this context we propose CAMP (Context-Aware Mapping and Placement), an inference-context-aware weight mapping algorithm for 3D-IMC-based LLM accelerators. CAMP captures the potential resource contention resulting from the architecture, targeted network, and runtime context in a conflict matrix, enabling throughput-optimized weight mapping. This mapping is refined through a profiling-driven feedback loop that efficiently prunes the search space and returns optimized mappings within practical runtimes. CAMP is an offline, software-based solution requiring no hardware changes and improving 3D-IMC compute utilization from 42.4% to 60.3%, delivering up to 2.0x higher 3D-IMC throughput and 1.74x higher end-to-end throughput over state-of-the-art mapping algorithms.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_aee9445784ea473759c896ad