Benchmarking Confidential Computing Performance on NVIDIA Blackwell GPUs

arXiv:2608.26575 · cs.DC, cs.CR · Submitted 2026-08-27 · Read on arXiv

cs.DC, cs.CR

Submitted: 2026-08-27

Updated: 2026-09-01

Comments: 23 pages, 3 figures, 22 tables

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Decode — 50× in this paper · explained in 2 episodes
• Core — 8× in this paper · explained in 2 episodes
• KV cache — 8× in this paper · explained in 3 episodes
• NVIDIA Confidential Computing — 6× in this paper
• Trusted Execution Environment — 4× in this paper
• Benchmarking — 2× in this paper · explained in 3 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Communication Overhead — 1× in this paper · explained in 2 episodes
• GPU System Processor — 1× in this paper
• Quantization — 1× in this paper · explained in 12 episodes
• Security Protocol and Data Model — 1× in this paper
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• SGLang: Efficient Execution of Structured Language Model Programs
• Efficient Memory Management for Large Language Model Serving with PagedAttention
• Blueprint, Bootstrap, and Bridge: A Security Look at NVIDIA GPU Confidential Computing

Related papers

• iScheduler: Reinforcement Learning-Driven Continual Optimization for Large-Scale Resource Investment Problems
• Load Balancing with Evolving Workloads in Large-Scale Language Model Serving
• Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation
• SAMM: Sharded Automated Market Maker
• InferScale: GPU-Native KV Injection for Personalized LLM Serving
• Vigil: Accountable Liveness against Selective Silence