Modal Releases Comprehensive GPU Glossary Covering Hardware to Software Stack
charles_irl · x · 2026-08-01
Modal and @charlesirl have released a highly-praised GPU Glossary, recognized by the developer community as an excellent resource for guiding beginners into lower-level details.
The resource systematically categorizes core GPU concepts across several dimensions:
- Device Hardware: Including Streaming Multiprocessors (SM), Tensor Cores, Tensor Memory Accelerator (TMA), and various cache architectures.
- Device Software & Programming Model: Covers the CUDA programming model, SASS/PTX instruction sets, Thread/Warp/Block hierarchies, and Memory Hierarchy.
- Host Software Stack: Features CUDA Driver/Runtime APIs, NVML, Nsight Systems, and essential libraries like cuBLAS, cuDNN, and CUTLASS.
- Performance: Dives into optimization metrics like the Roofline Model, Compute-bound vs. Memory-bound, Occupancy, and Warp Divergence.
More from Infra
- Stanford Prof. Mark Horowitz on AI Cluster Hardware Design Costs Post-Moore's Law — jwt0625 · 2026-08-01
- Privacy-focused AI platform Venice secures own ASN, moves to self-owned bare-metal infrastructure — 0xAllen_ · 2026-08-01
- Power Bottlenecks to Persist Through 2030: Hyperscaler AI Infrastructure Partnerships Explained — BenBajarin · 2026-08-01
- Why Doesn't NVIDIA Make a Budget AI Card? Community Debates — Aggravating-Push-207 · 2026-08-01
- MediaTek's AI Pivot: Data Center Chip Revenue to Exceed $2 Billion This Year — firstadopter · 2026-08-01
- antirez looks into deploying LLMs on DGX Spark — antirez · 2026-08-01