Combined archive of the CUDA Handbook blog and Nicholas Wilt's Substack, Parallel Programmer. New posts on Substack are mirrored here shortly after they go live.
- Fusing SIMD Operator Chains [Substack] — August 27, 2026
- Vibe-Coding Optimized Binary Search [Substack] — August 26, 2026
- A Toolchain, If We Can Keep It* [Substack] — August 23, 2026
- Subsuming ISA Advancements [Substack] — August 18, 2026
- A Wild Ride With Claude [Substack] — August 11, 2026
- More Updates To The CUDA Handbook [Substack] — August 4, 2026
- Yoda Notation, I Use; Do You? [Substack] — July 31, 2026
- Update on The CUDA Handbook Updates [Substack] — July 28, 2026
- The CUDA Handbook: Now Available Exclusively On The Website [Substack] — July 8, 2026
- Hyperion, Dan Simmons, And Life [Substack] — March 20, 2026
- Most Popular Posts of 2025 [Substack] — January 1, 2026
- Safety-Critical CUDA [Substack] — December 17, 2025
- Return on Investment (c. 1993) [Substack] — December 17, 2025
- Curiously Recurring What? [Substack] — December 12, 2025
- SRAM Scaling: Beginning of the End? [Substack] — November 26, 2025
- Perennial Technical Reads [Substack] — November 19, 2025
- Fun New Project: itch-order-simd [Substack] — November 14, 2025
- This ML Workload Runs 30x Faster With AVX-512 [Substack] — October 19, 2025
- CUDA Error Handling: A Definitive Guide [Substack] — October 13, 2025
- A Missive From The RISC/CISC War [Substack] — October 7, 2025
- 3rd Largest Element: SIMD Edition [Substack] — September 30, 2025
- k'th Largest Element [Substack] — September 26, 2025
- Writing Code For The Next Guy [Substack] — September 25, 2025
- A Paean To Struct-Based Interfaces [Substack] — September 16, 2025
- Sometimes It's Best To Flip A Coin [Substack] — September 12, 2025
- For Want Of A Bit [Substack] — August 15, 2025
- Why We Need SIMD (The Real Reason) [Substack] — August 13, 2025
- Caches and Abstractions [Substack] — July 16, 2025
- cudaGetLastError(): Its Raison D'Etre [Substack] — June 30, 2025
- Asynchronous Error Handling Is Hard [Substack] — June 29, 2025
- Why Does CUDA Have a Current Device? [Substack] — June 27, 2025
- Finding and Fixing Direct3D [Substack] — April 25, 2025
- Run For The Hills [Substack] — April 24, 2025
- 1997: Joining DirectX [Substack] — March 13, 2025
- APUs: When and Why They Work [Substack] — March 8, 2025
- Fun with Popcount [Substack] — March 8, 2025
- Return On Investment [Substack] — February 21, 2025
- AMD's GPU Software: A Software Architect's Take [Substack] — February 17, 2025
- Standardized or Proprietary? [Substack] — February 9, 2025
- Implications of Google v. Oracle [Substack] — February 8, 2025
- The Implementation Is The Spec: CUDA Edition [Substack] — January 26, 2025
- The Implementation Is The Spec: DLL Hell Edition [Substack] — January 23, 2025
- How To Become A Co-Inventor [Substack] — January 7, 2025
- Book Review: The NVIDIA Way [Substack] — January 5, 2025
- Go To Statement Considered Occasionally Useful [Substack] — January 2, 2025
- Why Archaea? [Substack] — December 27, 2024
- Kicking off the Parallel Programmer [Substack] — December 26, 2024
- Coming soon [Substack] — December 10, 2024
- What’s Next For Intel? No One Knows [Blog] — December 4, 2024
- Reflections On The Downfall of Intel [Blog] — August 6, 2024
- The Utility of Futility [Substack] — October 16, 2023
- CUDA Graphs, ROI, and API Adoption [Blog] — September 27, 2018
- Don't Move The Data! [Substack] — October 6, 2017
- Managed Memory And Segmentation [Substack] — August 28, 2017
- Managed Memory: Belated Comments on Implementation [Blog] — August 6, 2017
- Ten Years Later: CUDA Succeeded Despite... [Substack] — June 14, 2017
- Ten Years Later: Why CUDA Succeeded [Substack] — June 2, 2017
- Warp Synchrony and The First Law of CUDA Development [Substack] — May 18, 2017
- Why does CUDA CUdeviceptr use unsigned int instead of void? [Blog] — August 12, 2013
- Floating point: CPU and GPU differences [Blog] — August 8, 2013
- Final Manuscript Submitted [Blog] — February 19, 2013
- On the Home Stretch…25 kLOC? [Blog] — February 7, 2013
- N-Body Update: Multi-GPU [Blog] — November 20, 2012
- N-Body: Multithreaded SSE [Blog] — November 12, 2012
- N-Body: FP Atomics v. Recomputation [Blog] — November 2, 2012
- Multithreaded SSE Timings [Blog] — October 30, 2012
- Rough Cuts [Blog] — October 29, 2012
- N-Body: CUDA Versus Old-School SSE [Blog] — October 12, 2012
- Stream Callbacks [Blog] — September 18, 2012
- Streaming Multiprocessors – updated! [Blog] — August 30, 2012