Search arXivSearch

arXiv · 2411.02282

CXL-DMSim: A Full-System CXL Disaggregated Memory Simulator With Comprehensive Silicon Validation

Abstract

Compute eXpress Link (CXL) has emerged as a key enabler of memory disaggregation for future heterogeneous computing systems to expand memory on-demand and improve resource utilization. However, CXL is still in its infancy stage and lacks commodity products on the market, thus necessitating a reliable system-level simulation tool for research and development. In this paper, we propose CXL-DMSim, an open-source full-system simulator to simulate CXL disaggregated memory systems with high fidelity at a gem5-comparable simulation speed. CXL-DMSim incorporates a flexible CXL memory expander model along with its associated device driver, and CXL protocol support with CXL.io and CXL.mem. It can operate in both app-managed mode and kernel-managed mode, with the latter using a dedicated NUMA-compatible mechanism. The simulator has been rigorously verified against a real hardware testbed with both FPGAand ASIC-based CXL memory devices, which demonstrates the qualification of CXL-DMSim in simulating the characteristics of various CXL memory devices at an average simulation error of 3.4%. The experimental results using LMbench and STREAM benchmarks suggest that the CXL-FPGA memory exhibits a ~2.88x higher latency than local DDR while the CXL-ASIC latency is ~2.18x; CXL-FPGA achieves 45-69% of local DDR memory bandwidth, whereas the number for CXLASIC is 82-83%. The study also reveals that CXL memory can significantly enhance the performance of memory-intensive applications, improved by 23x at most with limited local memory for Viper key-value database and approximately 60% in memorybandwidth-sensitive scenarios such as MERCI. Moreover, the simulator's observability and expandability are showcased with detailed case-studies, highlighting its great potential for research on future CXL-interconnected hybrid memory pool.

Explore related subjects

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Yanjing Wang, Lizhou Wu, Wentao Hong, Yang Ou, Zicong Wang, Sunfeng Gao, Jie Zhang, Sheng Ma, Dezun Dong, Xingyun Qi, Mingche Lai, Nong Xiao. 2026-01-11. CXL-DMSim: A Full-System CXL Disaggregated Memory Simulator With Comprehensive Silicon Validation. https://doi.org/10.1109/tcad.2025.3607145

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

ASTRA: Toward Agentic AI for Intelligent Device-Network-Cloud Synergy in Next-Generation Mobile Communication

The evolution toward next-generation mobile communication systems demands intelligence-native networks capable of autonomously adapting to user intent, yet the prevailing 3GPP protocol-driven device-network-cloud (DNC) architecture imposes three structural bottlenecks: protocol-constrained decision spaces confining optimization to predefined parameter subsets, cascaded information asymmetry from lossy interface compression that strips semantic context and causes intent miscalibration, and inherently reactive coordination mechanisms that trigger actions only after performance degradation. This paper proposes an autonomous agentic AI paradigm named Agentic Synergy for Telecommunication Resource Autonomy (ASTRA), which introduces a three-tier agent layer, including device agent, network agent, and cloud agent, decoupling network intelligence from the underlying hardware infrastructure. These agents collaborate through bidirectional semantic channels, including semantic intent messages, capability abstraction messages, global directives, and peer coordination, executing a six-phase cycle of perceive, reason and predict, communicate, decide, act, and learn that transforms reactive protocol-driven operations into proactive, intent-calibrated optimization over the full decision space. Validated through system-level simulations in two representative scenarios, ASTRA achieves a 13.1\% average throughput gain in dense-crowd cell selection by redistributing UEs from congested cells via semantic load exchange, and an 18.2\% passive handover reduction in high-speed mobility through predictive trajectory-aware coordination, providing initial evidence that the proposed agentic framework accesses solution regions structurally inaccessible under protocol-constrained architectures.

cs.ET

A Closed-Form Molecule-Release Rule for Diffusion-Based Molecular Communications with Ligand Receptors

The number of molecules released per bit is a fundamental design variable of diffusion-based molecular communication (MC), and ligand-receptor reception breaks the more-is-better intuition. Too few molecules leave the bound-receptor observations buried in binding noise, while too many amplify the accumulated intersymbol interference and saturate the finite receptor population, again making the observations indistinguishable. Reliability therefore peaks in an interior operating region whose location seems to require an exhaustive search over the channel dynamics. In this paper, we show that this search can be obviated for a biologically plausible receiver that compares consecutive bound-receptor counts without channel state information or a decision threshold. We derive a closed-form transmission rule, which sets the number of molecules released per bit such that the receptor dissociation constant equals the geometric mean of the two bit-conditioned received concentration levels, prove that it exactly minimizes the bit error probability of a memoryless binomial receptor model, and express it in the physical channel parameters through an Euler--Maclaurin evaluation of the interference. Time-domain Monte Carlo sweeps of the channel and receptor parameters, corroborated by particle-based simulations, show that the empirically optimal release count coincides with the prediction or lies above it by a small factor.

cs.ET

Composability rather than computation sets the cost of an analog EML hardware fabric

The operator eml(x, y) = exp(x) - ln(y) with the constant 1 generates the elementary functions, a continuous counterpart to NAND. Whether it yields a useful fabric had not been asked of hardware. We ask in network models, circuit simulation and SkyWater 130 nm layout. Four bipolar junctions evaluate the operator for 13 fJ, beating a width-matched digital datapath by 4-134x. The fabric assembled from them is not cheap: it loses to resource-matched baselines, and over the reals its grammar excludes trigonometry. Amplifiers holding those junctions' operating points take 74.5% of a cell's current, so a cell costs 3000 times what they spend. Extracted non-idealities cost 2.6x when a cell must hold a value and nothing when it need only be repeatable. Sharing them across cells recovers two of the three orders. The premise was that a universal primitive licenses a uniform machine. It survives in the primitive and fails in the machine.

cs.ET