Cohet: A CXL-Driven Coherent Heterogeneous Computing Framework with Hardware-Calibrated Full-System Simulation
Yanjing Wang, Lizhou Wu, Sunfeng Gao, Yibo Tang, Junhui Luo, Zicong Wang, Yang Ou, Dezun Dong, Nong Xiao, Mingche Lai

TL;DR
Cohet introduces a novel CXL-based framework for coherent heterogeneous computing, enabling unified memory sharing between CPUs and XPUs, supported by a full-system simulator, leading to significant performance improvements over PCIe-based systems.
Contribution
This work presents the first CXL-driven coherent heterogeneous computing framework and a cycle-level simulator, advancing research and development in CXL-based systems.
Findings
CXL.cache reduces latency by 68%.
CXL increases bandwidth by 14.4x over DMA.
CXL-NIC outperforms PCIe-NIC in RAO and RPC tasks.
Abstract
Conventional heterogeneous computing systems built on PCIe interconnects suffer from inefficient fine-grained host-device interactions and complex programming models. In recent years, many proprietary and open cache-coherent interconnect standards have emerged, among which compute express link (CXL) prevails in the open-standard domain after acquiring several competing solutions. Although CXL-based coherent heterogeneous computing holds the potential to fundamentally transform the collaborative computing mode of CPUs and XPUs, research in this direction remains hampered by the scarcity of available CXL-supported platforms, immature software/hardware ecosystems, and unclear application prospects. This paper presents Cohet, the first CXL-driven coherent heterogeneous computing framework. Cohet decouples the compute and memory resources to form unbiased CPU and XPU pools which share a…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsParallel Computing and Optimization Techniques · Advanced Data Storage Technologies · Cloud Computing and Resource Management
