https://bhargav.work/Computer Architecture & Performance Engineer based in Pune, India. Experience across IBM Power, AMD Ryzen, and Qualcomm Hexagon DSP. Writing about processor performance, memory systems, and AI-assisted engineering. 2026-11-07T17:07:32+05:30 D K Bhargav Achary https://bhargav.work/ Jekyll © 2026 D K Bhargav Achary /assets/img/favicons/favicon.ico /assets/img/favicons/favicon-96x96.png 2026-11-03T12:00:00+05:30 2026-11-04T10:03:03+05:30 https://bhargav.work/posts/why-a-fast-computer-can-still-feel-slow/ D K Bhargav Achary

Performance Analysis 101 - Part 1 You click something and there is a small delay. You change a browser tab and it takes a moment. A webpage is scrolling smoothly, then suddenly it catches somewhere. Or maybe you ask an AI application something… and wait before anything even starts happening. We normally put all of this into one simple statement: “My computer is slow.” But… what does that act...

2026-11-01T00:00:00+05:30 2026-11-01T00:00:00+05:30 https://bhargav.work/posts/beyond-the-chat-window/ D K Bhargav Achary

At IBM, I won the Bobathon as a solo-member team within ISDL. The event involved hundreds of teams, including teams with multiple members. That experience belongs alongside some rather ordinary uses of AI in my life: working on software projects, configuring my router and camera, organising financial information and reminders, tracking health-related information, and revamping both my personal...

2025-05-19T00:00:00+05:30 2026-09-06T15:32:43+05:30 https://bhargav.work/posts/the-nvidia-nvlink-fusion/ D K Bhargav Achary

Imagine if your brain and your hands had to write letters to each other before doing anything - now imagine if they just shared thoughts instantly. That is the kind of architectural shift NVLink Fusion brings to heterogeneous computing. At Computex 2025, NVIDIA unveiled NVLink Fusion, opening its proprietary interconnect fabric to semi-custom third-party silicon. By enabling CPUs and GPUs to s...

2025-04-29T00:00:00+05:30 2026-09-06T15:01:43+05:30 https://bhargav.work/posts/llms-on-edge-devices/ D K Bhargav Achary

M-series, Snapdragon X Elite, AMD Phoenix, Intel Meteor Lake - the most powerful SoCs ever made for consumers. But even they struggle with running large language models locally. Here’s why edge AI inference hits roadblocks, and what the future holds. How Apple, AMD, Intel, and Qualcomm hit the limits of on-device AI - and what it really takes to run LLMs locally 1. From WWDC Hype to Edge AI...

2024-12-12T00:00:00+05:30 2026-09-06T14:10:30+05:30 https://bhargav.work/posts/the-apple-intellgence-saga/ D K Bhargav Achary

In my recent blog, “Apple Intelligence: The Seamless AI in Apple’s Ecosystem”, I was brimming with optimism. Apple had unveiled its latest marvel, Apple Intelligence, and the potential for seamless integration, enhanced productivity, and smarter devices felt like a turning point. The promise of a future where AI wasn’t just an add-on but a cornerstone of the Apple ecosystem had me captivated. ...