- How to Think About GPUs
How to Think About GPUs is a free online chapter from How To Scale Your Model by Jacob Austin, Swapnil Patil, Adam Paszke, and Reiner Pope.
100% match
· <optimization><advanced><blog><access><bandwidth><book><concrete><hierarchy> - Blackwell: Nvidia’s Massive GPU
This is a June 2025 Chips and Cheese architecture deep dive by Chester Lam measuring Nvidia's largest consumer Blackwell GPU, focused on GB202 configurations such as the RTX PRO…
85% match
· <optimization><advanced><blog><access><bandwidth><behavior><caches><hierarchies> - niagara: Cooking geometry
[video] niagara: Cooking geometry is a multi-hour live coding stream by Arseny Kapoulkine on the niagara project, focused on making scene loading faster by caching optimized…
71% match
· <optimization><advanced><access><caches><concrete><hot><profiling> - No Graphics API
No Graphics API is a December 2025 long-form essay by Sebastian Aaltonen arguing that modern bindless GPUs no longer need the retained-mode complexity of DirectX 12, Vulkan, and…
60% match
· <optimization><advanced><blog><caches><pointer><systems><types> - Bindless Oriented Graphics Programming
Bindless Oriented Graphics Programming is a technical blog post by Alex Tardif on alextardif.com.
60% match
· <optimization><advanced><blog><access><loops><streaming><virtual> - Learning About GPUs Through Measuring Memory Bandwidth
Learning About GPUs Through Measuring Memory Bandwidth is a Traverse Research / Evolve blog article by Manon Oomen on designing microbenchmarks that isolate GPU load and store…
60% match
· <optimization><advanced><blog><bandwidth><caches><hierarchy><profiling> - CUDA Ray Tracing 2x Faster Than RTX: My CUDA Ray Tracing Journey
This is a long-form technical blog post by Karim Sayed documenting a CUDA path tracer based on Ray Tracing in One Weekend and comparing it with GPSnoopy's RayTracingInVulkan RTX…
60% match
· <optimization><advanced><blog><access><beat><concrete><layout> - CUDA Tile IR
CUDA Tile IR is an NVIDIA open-source GitHub repository for an MLIR-based intermediate representation and compiler stack aimed at tile-based CUDA kernel optimization on NVIDIA…
58% match
· <optimization><advanced><hierarchy><patterns><published><types> - GPU Side Input
GPU Side Input is a short technical talk by Timothy Lattis on the Neokineogfx channel about reading controller and keyboard state from GPU shaders late in the frame to cut…
58% match
· <optimization><advanced><access><caches><concrete><hot> - How to optimize your Niagaras - Paweł Charzyński || 11Bit Studios ||
How to optimize your Niagaras is a Game Industry Conference 2024 talk by Pawel Charzynski of 11Bit Studios on Unreal Engine Niagara VFX optimization from Frostpunk 2…
56% match
· <optimization><concrete><patterns><systems><types> - Casey Muratori – The Big OOPs: Anatomy of a Thirty-five-year Mistake – BSC 2025
Casey Muratori - The Big OOPs: Anatomy of a Thirty-five-year Mistake is a Better Software Conference 2025 talk by Casey Muratori on how object-oriented hierarchy modeling shaped…
56% match
· <general><access><hierarchies><hierarchy><systems> - Ghost of Yōtei – tech deep dive
This PlayStation Blog post by Adrian Bentley, Director of Programming at Sucker Punch Productions, is a long-form tech deep dive into systems behind Ghost of Yotei on PlayStation…
54% match
· <general><optimization><advanced><blog><concrete><streaming><systems> - Quantization from the ground up
Long-form ngrok blog article by Sam Rose that explains model quantization from first principles, focused on how large language models are compressed.
52% match
· <general><optimization><blog><access><patterns><systems> - AMD GPU-Initiated I/O
AMD GPU-Initiated I/O is a March 2026 systems blog post by Abdelhadi exploring direct AMD GPU to NVMe communication instead of CPU-driven storage I/O.
It explains NVMe queues…
48% match
· <optimization><advanced><blog><access><dma><systems> - Vulkan memory barriers and image layouts explained
Vulkan memory barriers and image layouts explained is a long RasterGrid technical article by Daniel Rakos clarifying pipeline barriers, memory visibility, and image layout…
48% match
· <optimization><advanced><blog><access><behavior><layout> - Rendering Engine Architecture Conference (REAC)
Virtual conference on the craft of building real-time rendering engines - architecture, workflows, tooling, and product/engine tradeoffs rather than single algorithms.
46% match
· <general><advanced><patterns><streaming><virtual> - Memory-Efficient BVHs with Merged Nodes for Hardware Ray Tracing
Memory-Efficient BVHs with Merged Nodes for Hardware Ray Tracing.
46% match
· <optimization><advanced><bandwidth><hierarchies><layout> - Revealing NVIDIA Closed-Source Driver Command Streams for CPU-GPU Runtime Behavior Insight
Revealing NVIDIA Closed-Source Driver Command Streams for CPU-GPU Runtime Behavior Insight recovers hardware command streams from NVIDIA's closed-source userspace driver by…
46% match
· <optimization><advanced><behavior><dma><systems> - Even Faster asin() Was Staring Right At Me
Even Faster asin() Was Staring Right At Me is a March 2026 follow-up blog post on 16BPP.net that further optimizes a Cg-style arcsine polynomial approximation for CPU ray…
46% match
· <optimization><blog><concrete><hot><systems> - HIP Threads: GPU power for teams without GPU experts
AMD GPUOpen Learn article by Alexander Blake-Davies, Kelvin Lui, Chas Boyd, Marko Savic, and Daniel McIntosh introducing HIP Threads, a C++ concurrency library for AMD GPUs.
46% match
· <optimization><blog><multithreaded><patterns><profiling>