Learning Series
AI & ML
LLM Inference Introduction In Progress
4 articlesConcepts behind LLM inference - the end-to-end inference flow, the KV cache and attention variants, numeric precision, GPU kernels in Triton, and FlashAttention
LLM Inference Serving In Progress
5 articlesChallenges and solutions in serving LLMs - PagedAttention, FlashAttention in practice, FlashInfer, continuous batching, CUDA Graphs, and agentic/MoE workloads
CPU ISA for ML
1 articleA guide to CPU instruction-set features for ML workloads - the VNNI layout and Intel AMX/TPP performance on Granite Rapids
Hardware & Architecture
CPU Microarchitecture
1 articleA deep dive into CPU microarchitecture on Intel Granite Rapids - cache coherence and MESI, hardware/software prefetching, and IOMMU-based device isolation
CXL Series
1 articleA complete guide on CXL (Compute Express Link) technology and its applications
Performance Engineering
GPU Performance Profiling In Progress
4 articlesPractical tools and workflows for profiling GPU utilization, memory usage, and performance bottlenecks
Performance Profiling Completed
2 articlesA practical guide to Linux performance profiling - perf stat/record internals and adding custom /proc counters
Systems Software
Locking primitives
2 articlesA complete guide on different locking primitives used in Linux Kernel, C, and C++