Author: Leo Corelli
-
NVIDIA Rubin CPX: GDDR7 Prefill Offload Reshapes TCO
NVIDIA Rubin CPX moves prefill to a GDDR7-backed accelerator, disaggregating inference to cut HBM exposure, densify liquid-cooled racks, and improve…
-
Quantum subsurface radar moves from lab to field
Quantum subsurface radar is leaving the lab and entering real field trials, promising cleaner maps at the same power when…
-
iPhone 17 camera and security shift
iPhone 17 camera is the headline change this cycle, backed by a quieter but consequential security shift called Memory Integrity…
-
Tensor G5 puts Gemini on‑device in Google’s Pixel 10
Tensor G5 anchors Google’s assistant‑first Pixel 10, bringing more of Gemini’s intelligence directly onto the phone for instant, private, and…
-
NVIDIA’s AI Networking Playbook: From Scale-Across to Low-Latency Stacks
AI performance is no longer just about the GPU; it’s increasingly limited by the network. Recognizing this, NVIDIA has released…
-
Denser On-Prem AI Hardware: How Blades + NVMe Redefine Racks, Power, and Cooling
Denser on-prem AI hardware is collapsing the data center footprint and widening the I/O firehose, forcing organizations to completely rethink…
-
Quantum-Enhanced Subsurface Radar: From Lab Bench to Field Trials
Introduction Quantum-enhanced subsurface radar has moved from theoretical ideas to working prototypes with a clear path to field trials. Lab…
-
Hot Chips 2025 Accelerator Shift: Reasoning, Memory, and Integration
At Hot Chips 2025, Google, AMD, and NVIDIA each presented new accelerator designs. For data‑center architects, the signal was less…
-
The Hardening of the AI Infrastructure Stack
Executive Summary Performance leadership will hinge on end-to-end bandwidth orchestration—within packages and across racks—rather than peak FLOPs. The hardened stack…