Nexus: Efficient and Scalable Multi-Cell mmWave Baseband Processing with Heterogeneous Compute

TL;DR

NEXUS is presented, the first system to realize real-time, virtualized multi-cell mmWave baseband processing on a single server with heterogeneous compute resources, and introduces a novel framework for sharing Intel's ACC100 eASIC across multiple CPU cores via virtual functions (VFs).

Abstract

The rapid adoption of 5G New Radio (NR), particularly in the millimeter-wave (mmWave) spectrum, imposes stringent demands on the flexibility, scalability, and efficiency of baseband processing. While virtualized Radio Access Networks (vRANs) enable dynamic spectrum sharing across cells, compute resource allocation for baseband processing, especially in multi-cell deployments with heterogeneous workloads, remains underexplored. In this paper, we present NEXUS, the first system to realize real-time, virtualized multi-cell mmWave baseband processing on a single server with heterogeneous compute resources. NEXUS integrates software-based digital signal processing pipelines with hardware-accelerated LDPC decoding, and introduces a novel framework for sharing Intel's ACC100 eASIC across multiple CPU cores via virtual functions (VFs). For single-cell operation, NEXUS employs a random forest (RAF)-based model that predicts the most energy-efficient resource allocation for the given cell configuration with microsecond-level inference latency and high accuracy. For multi-cell scenarios, NEXUS introduces a power-aware scheduler that incorporates a lightweight contention model to adjust resource allocation strategies under concurrent execution. Through extensive evaluation across various Frequency Range 2 (FR2) cell configurations, we show that NEXUS supports up to 16 concurrent cells under full load, achieving 5.37Gbps aggregate throughput, while reducing the multi-cell scheduling search space by orders of magnitude. These results demonstrate that virtualized, resource-aware baseband processing is both practical and efficient for next-generation vRAN systems.

Figures (8)

• Figure 1: Overview of Nexus: (a) Nexus virtualizes multi-cell mmWave PHY processing on a single server with heterogeneous compute by sharing a set of CPU cores and a pool of ACC100 virtual functions (VFs) in a power-aware manner. (b) Resource allocation strategies for a single cell are characterized by combinations of CPU cores and VFs.
• Figure 2: Region of resource allocations, where integer points in the shaded area represent valid CPU core and VF allocations satisfying \ref{['eq:core-union']}--\ref{['eq:core-vf-mapping']}.
• Figure 3: Power consumption of ACC100 with multiple VFs.
• Figure 4: Power-latency trade-off space for Nexus across heterogeneous cell configurations. Each point represents a distinct resource allocation. Labeled dots indicate the most and second most energy-efficient options that Nexus is likely to select.
• Figure 5: Nexus single-cell scheduler's predictions with $MCS=18$. Confidence heatmaps are thresholded at $\tau=0.5$ (black dashed line). Each green/red dot corresponds to measured 99.9th processing latency outcomes from executing Nexus over 20K frames.