ECO MDA ED Edwin Chiu Unlock Granular CPU Insights: PMU Support on GKE is now generally available When examining workload performance, CPU utilization, a staple of any monitoring dashboard, tells you if your processor is busy, but it…
AI TCH ED Edwin Chiu Beyond grep for coding agents For AI agents operating in codebases of all sizes, we want to be efficient with our token usage, not just for costs, but for time and…
TCH AI ED Edwin Chiu Further explorations in GCP Axion performance with ffmpeg We further explore the performance of C4A and N4A GCP Axion instances and examine the possible role of compilers for easy optimization…
AI TCH ED Edwin Chiu Debugging Assembly: How Gemini helped us root cause a production issue Recently, we faced a critical issue where the trail led directly to memmove.s — the low-level assembly implementation behind Go’s copy()…
ED Edwin Chiu Initial look at Axion based N4A compute performance TL;DR: Google’s new Axion-based N4A instances deliver nearly 2x the raw performance of comparable current-gen x86 instances in…
