The Definitive Guide toAI Data Centers
Ask the GuideAboutAccount
GuideGlossaryGPU

GPU · Graphics Processing Unit

A massively parallel processor that became the workhorse of AI training and inference.

Current numbers

~1.08 TB/speak single-submission throughput at 92.2% GPU utilization and 9.9M IO/s (Volumez on AWS) in MLPerf Storage v1.0as of Sep 2024 · register ↗
3.6 TB/sNVLink 6 per-GPU bandwidth (Rubin); 900 GB/s Hopper, 1.8 TB/s Blackwell — ~260 TB/s per NVL72 rackas of H2 2026 (announced) · register ↗
0.5–5 GB/s/GPUDGX H200 SuperPOD shared-storage read guidelines: 0.5, 1, and 5 GB/s per GPU for Good, Better, and Best performance, with 4 GB/s/GPU recommended for computer-vision workloadsas of Apr 2025 · register ↗

← All terms