Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper audits the energy observability of the ASUS Ascent GX10, a flagship edge AI system based on NVIDIA's GB10 SoC, finding a complete lack of CPU energy counters or power rail monitors exposed through supported software interfaces. It demonstrates that on-device per-process energy attribution, crucial for optimizing agentic AI workloads, is impossible on this platform without unsupported interfaces or external metering. The authors propose a hardware requirements specification for energy-attributed AI and suggest interim calibration methods.
NVIDIA's flagship edge AI hardware has a glaring "energy blind spot," lacking the necessary telemetry to attribute energy consumption at the process level, hindering efforts to optimize the energy efficiency of complex agentic AI workloads.
Agentic AI workloads - where a single user goal triggers multi-step orchestration, tool calls, retries, and failure recovery - are being targeted for edge deployment, with NVIDIA, Dell, HP, ASUS, MSI, Acer, and Gigabyte all shipping GB10-based desktop AI systems in 2026. We recently demonstrated that orchestration structure dominates agentic energy cost, with workflows consuming 4.33x more energy per successful goal than linear baselines and OOI reaching 7.63x for multi-step reasoning tasks. Separately, Rajat et al. show that CPU-side processing accounts for up to 90.6% of total latency and 44% of total dynamic energy in agentic workloads. We report a systematic energy-observability audit of the ASUS Ascent GX10 (GB10 SoC) and find that the platform exposes no CPU energy counter, no INA power-rail monitor, no IPMI/BMC, and no SCMI powercap protocol through any supported software interface. The only on-device energy telemetry is instantaneous GPU power via NVML. We further discover that the MediaTek firmware already computes per-rail energy internally via an undocumented ACPI interface (SPBM), but NVIDIA states there are"no plans to expose CPU rail information."On-device per-process energy attribution - as performed on x86 via RAPL - is therefore not reproducible on this platform through supported interfaces. We formalize a hardware requirements specification for energy-attributed AI, propose an interim calibration bridge using external DC metering combined with GPU subtraction, and identify a standards-track path via SCMI powercap. Our findings motivate the low-carbon computing community to demand energy observability as a first-class hardware requirement.