TalyhVitaliy/GPUOptimizationForGameDev.md

Forked from silvesthu/GPUOptimizationForGameDev.md

Created June 30, 2025 07:19

Star (0) You must be signed in to star a gist
Fork (0) You must be signed in to fork a gist

Learn more about clone URLs
Clone this repository at <script src="https://gist.github.com/TalyhVitaliy/20fd7993e82c0658f716d1924761ea10.js"></script>
Save TalyhVitaliy/20fd7993e82c0658f716d1924761ea10 to your computer and use it in GitHub Desktop.

Download ZIP

GPU Optimization for GameDev

Raw

GPUOptimizationForGameDev.md

GPU Optimization for GameDev

Graphics Pipeline / GPU Architecture Overview

2011 - A trip through the Graphics Pipeline 2011
2015 - Life of a triangle - NVIDIA's logical pipeline
2015 - Render Hell 2.0
2016 - How bad are small triangles on GPU and why?
2017 - GPU Performance for Game Artists
2019 - Understanding the anatomy of GPUs using Pokémon
2020 - GPU ARCHITECTURE RESOURCES
2020 - All the pipelines - journey through the GPU

By Author

Emil Persson @Humus
- Blog
- 2013 - Low-Level Thinking in High-Level Shading Languages
- 2014 - Low-Level Shader Optimization for Next-Gen and DX11
- 2018 - Rule of optimization
Matt Pettineo @mynameismjp
- Blog
- 2018 - Breaking Down Barriers
- 2019 - Half The Precision, Twice The Fun: Working With FP16 In HLSL
- 2021 - The Shader Permutation Problem
- 2022 - GPU Memory Pools in D3D12
- 2025 - To Early-Z, or Not To Early-Z
Louis Bavoil @louisbavoil
- D3D11 Vendor Hacks
- 2018 - The Peak-Performance-Percentage Analysis Method for Optimizing Any GPU Workload
- 2018 - Fixing the Hyperdrive: Maximizing Rendering Performance on NVIDIA GPUs (Presented by NVIDIA)
- 2019 - Optimizing DX12/DXR GPU Workloads using Nsight Graphics: GPU Trace and the Peak-Performance-Percentage (P3) Method (Presented by NVIDIA)
- 2020 - Optimizing Compute Shaders for L2 Locality using Thread-Group ID Swizzling
- 2021 - Dana Elifaz - The Next Level of Optimization Advice with Nsight Graphics: GPU Trace
- 2022 - Optimizing Ray Tracing GPU Workloads using Nsight Graphics: GPU Trace and Nsight Systems
Rys Sommefeldt @ryszu
- Blog
- 2018 - Understanding GPU context rolls
Michal Drobot @michaldrobot
- Blog
- 2014 - Low Level Optimizations for GCN – Digital Dragons 2014 - Video
- 2014 - GCN Execution Patterns in Full Screen Passes
- 2014 - ShaderFastLibs
Kostas Anagnostou @KostasAAA
- Blog
- 2018 - DD2018: Kostas Anagnostou - Experiments in GPU occlusion culling
- 2020 - GPU architecture resources
- 2020 - GPU architecture resources (twitter thread)
- 2020 - What is shader occupancy and why do we care about it?
- 2020 - To z-prepass or not to z-prepass
- 2022 - Shader tips and tricks
- 2023 - Low-level thinking in high-level shading languages 2023
- 2025 - The hidden cost of shader instructions
- 2025 - Async compute all the things
Matthäus G. Chajdas @NIV_Anteru
- Blog
- 2018 - Introduction to compute shaders
- 2018 - More compute shaders
- 2018 - Even more compute shaders
Matthijs De Smedt @anji_nl
- 2016 - PC GPU Performance Hot Spots
Maurizio Cerrato @speedwago
- 2019 - GPU Architectures
Sebastian Aaltonen @SebAaltonen
- 2017 - Optimizing GPU occupancy and resource usage with large thread groups
- 2018 - DD2018: Sebastian Aaltonen - GPU based clay simulation and ray tracing tech in Claybook
- 2018 - This is how I managed to port Claybook from consoles to ~4x slower handheld
Layla Mah @MissQuickstep
- 2013 - The AMD GCN Architecture - A Crash Course
- 2013 - Powering the Next Generation of Graphics: The AMD GCN Architecture
Sven Andersson @andsve
- Blog
- 2014 - Real-time Rendering Blogs
Fabian Giesen @rygorous
- Blog
- 2010 - Finish your derivations, please
- 2011 - A trip through the Graphics Pipeline 2011
Timothy Lottes @NOTimothyLottes
- 2016 - Understanding Memory Coalescing on GCN
- 2017 - ADVANCED SHADER PROGRAMMING ON GCN
- 2018 - Engine Optimization Hot Lap
- 2024 - Fixing The GPU
Robert Menzel @renderpipeline
- Blog
- 2012 - Low-Level GPU Documentation
RasterGrid @rastergrid
- Blog
- 2021 - Understanding GPU caches
Adam Sawicki @Reg__
- Blog
- 2020 - A Better Way to Scalarize a Shader
- 2021 - Efficient Use of GPU Memory in Modern Games
Matías N. Goldberg @matiasgoldberg
- Blog
- 2020 - A little clarification on modern shader compile times
- 2022 - The road to 16-bit floats GPU is paved with our blood
Francesco Cifariello Ciardi @FCifaCiar
- Blog
- 2018 - INTRO TO GPU SCALARIZATION
Sébastien Lagarde @SebLagarde
- Blog
- 2014 - Inverse trigonometric functions GPU optimization for AMD GCN architecture
Bart Wronski @BartWronsk
- Blog
- 2014 - GCN – two ways of latency hiding and wave occupancy
- 2021 - Is this a branch?
Elizabeth Baumel @Icetigris
- 2016 - Tightening Up the Graphics: Tools and Techniques for Debugging and Optimization
Anton Schreiner @antonschrein
- Blog
- 2019 - What's up with my branch on GPU?
Jendrik Illner @jendrikillner
- Blog
- Graphics Programming Weekly Article Database Not specifically on optimization. Have a search bar.
Hans-Kristian @Themaister
- Blog
- 2024 - Modernizing Granite’s mesh rendering
Graham Wihlidal @gwihlidal
- Blog
- 2016 - Optimizing the Graphics Pipeline With Compute
Alexandre Sabourin @AlexSneezeKing
- Blog
- 2024 - Harnessing Wave Intrinsics For Good (And Evil) Video
Chips and Cheese @chipsandcheese9
- Blog
- RDNA4
  - 2025 - AMD's RDNA4 Architecture (Video)
  - 2025 - RDNA 4's "Out-of-Order" Memory Accesses
  - 2025 - Dynamic Register Allocation on AMD's RDNA 4 GPU Architecture
  - 2025 - RDNA 4’s Raytracing Improvements

By Organization

AMD
- GPU Open
  - Events Presentations
  - AMD GPU architecture programming documentation (Instruction Set Architecture)
    - Reading AMD GPU ISA
    - Machine-readable ISA documentation
  - 2014 - Vertex Shader Tricks
  - 2016 - Getting the Most Out of Delta Color Compression
  - 2016 - Leveraging asynchronous queues for concurrent execution
  - 2016 - AMD GCN Assembly: Cross-Lane Operations
  - 2017 - Wave Programming in D3D12 and Vulkan
  - 2017 - D3D12 and Vulkan Done Right
  - 2017 - Deep Dive: Asynchronous Compute
  - 2018 - Optimize your engine using compute @ 4C Prague 2018 | (Youtube)
  - 2018 - Optimization with Radeon GPU Profiler - A Vulkan Case Study
  - 2019 - DirectX 12 Optimization Techniques in Capcom’s RE ENGINE
  - 2019 - A BLEND OF GCN OPTIMIZATION AND COLOR PROCESSING
  - 2019 - AMD GPU Performance Revealed
  - 2019 - Triangles Are Precious
  - 2020 - Let’s build
    - Optimizing for the Radeon™ RDNA Architecture Video
    - From Source to ISA: A Trip Down the Shader Compiler Pipeline Video
  - 2020 - CONCURRENCY MODEL IN EXPLICIT GRAPHICS APIS
  - 2021 - Understanding Graphs in Radeon GPU Profiler and GPUView
  - 2022 - Let's talk about (GPU) crashes
  - 2022 - Compute Shaders @ GIC
  - 2023 - Occupancy explained
  - 2024 - Occupancy explained through Insert picture the AMD RDNA architecture
  - 2024 - Mesh shaders: optimization and best practices
- GCN
  - 2013 - GCN3 Instruction Set Architecture
  - 2019 - AMD GCN ISA: a first dive
  - 2020 - Understanding AMD GPU ISA Video
- RDNA
  - 2019 - INTRODUCING RDNA ARCHITECTURE
  - 2019 - RDNA Architecture
  - 2020 - "RDNA 1.0" Instruction Set Architecture
  - 2020 - "RDNA 2" Instruction Set Architecture
  - 2022 - "RDNA3" Instruction Set Architecture
  - 2024 - "RDNA3.5" Instruction Set Architecture
  - 2025 - "RDNA4" Instruction Set Architecture
  - RDNA Performance Guide
- OpenCL
  - 2013 - AMD Accelerated Parallel Processing OpenCL Programming Guide
- Radeon GPU Analyzer / Radeon Raytracing Analyzer
- Driver Stack
Nvidia
- Developer Blog and Talks
  - Advanced API Performance on various topics
  - 2012 - GPU Performance Analysis and Optimization
  - 2015 - Constant Buffers without Constant Pain
  - 2016 - Practical DirectX 12
  - 2016 - Reading Between The Threads: Shader Intrinsics
  - 2016 - DX12 Do's And Don'ts
  - 2016 - High-Performance, Low-Overhead Rendering with OpenGL and Vulkan
  - 2019 - Tips and Tricks: Ray Tracing Best Practices
  - 2020 - Optimizing Graphics Applications using Nsight Systems and Nsight Graphics
  - 2020 - RTX Ray Tracing Best Practices
  - 2021 - Advanced API Performance
  - 2022 - Best Practices for Using NVIDIA RTX Ray Tracing (Updated)
  - 2023 - Practical Tips for Optimizing Ray Tracing
  - 2023 - Avoiding Stalls and Hitches in DirectX 12
  - 2023 - How to Improve Shader Performance by Resolving LDC Divergence
  - 2024 - Shader Debugging Made Easy with NVIDIA Nsight Graphics
- Pascal
  - 2016 - NVIDIA GeForce GTX 1080 Whitepaper
  - 2023 - Tuning CUDA Applications for Pascal
- Turing
  - 2018 - NVIDIA Turing Architecture In-Depth
  - 2018 - NVIDIA TURING GPU ARCHITECTURE
  - 2023 - Tuning CUDA Applications for Turing
- Ampere
  - 2020 - NVIDIA AMPERE GA102 GPU ARCHITECTURE
  - 2023 - Tuning CUDA Applications for NVIDIA Ampere GPU Architecture
- Ada
  - 2022 - NVIDIA ADA GPU ARCHITECTURE
  - 2022 - SHADER EXECUTION REORDERING
  - 2023 - Tuning CUDA Applications for NVIDIA Ada GPU Architecture
- Blackwell
  - 2025 - NVIDIA RTX BLACKWELL GPU ARCHITECTURE
- CUDA
  - 2014 - CUDA Pro Tip: Optimized Filtering with Warp-Aggregated Atomics
  - 2017 - CUDA kernel-level experiments in NVIDIA Nsight on Issue Efficiency, Memory Statistics, Pipe Utilization, etc.
- Driver Stack
- Misc
  - Pack/Unpack shader utility in donut
Apple
Intel
Arm
Microsoft
- DirectX-Specs
- 2019 - New in D3D12 – background shader optimizations
Khronos Group
- Vulkan Documentation - Github
  - Performance samples - Github
- 2019 - Optimising a AAA Vulkan Title on Desktop
- 2020 - Vulkan Ray Tracing Best Practices for Hybrid Rendering
GDC
- Advanced Graphics Summit Not specifically on optimization
Digital Dragon
- Video Not specifically on optimization
Graphics Programming Conference
- Video Not specifically on optimization
(JP) CEDEC
- 2016 - GPU最適化入門
  - (Book) マンガとイラストでわかる! GPU最適化入門
SIGGRAPH
- Advances in Real-Time Rendering in Games Not specifically on optimization
- 2009 - From Shader Code to a Teraflop: How Shader Cores Work
- 2020 - LOW-LEVEL OPTIMIZATIONS IN THE LAST OF US PART II
CMU
- 2017 - Parallel Computer Architecture and Programming
- 2017 - Parallel Computer Architecture and Programming Tsinghua ver. - Video

Game Graphics Study

Graphics Studies Compilation

GPU Crash Debugging

2018 - Aftermath: Advances in GPU Crash Debugging
2020 - (JP) Device Removal の処方箋, 補足資料
2023 - GPU Crash Debugging in Unreal Engine: Tools, Techniques, and Best Practices | Unreal Fest 2023

GPU Database

GPU Specs Database by techpowerup
GPU database by Matthäus G. Chajdas
GPUInfo by Sascha Willems For Vulkan, OpenGL, OpenGL ES
D3d12infoDB by Dmytro Bulatov Database based on D3d12info in Tools section below
- Feature Table
(JP) GPU Spec Database by HYPERでんち

Tools

Online Shader Compiler
- Compiler Explorer (godbolt) Support DXC, AMD RGA
- Shader Playground Support DXC, FXC, glslang, hlsl2glsl, hlslparser, IntelShaderAnalyzer, AMD RGA, slang, XShaderCompiler
Microsoft
Nvidia
AMD
- Radeon Developer Tool Suite
  - Radeon GPU Profiler (RGP) Low-level optimization tool
  - Radeon Memory Visualizer (RMV)
  - Radeon Developer Panel (RDP)
    - Driver Experiments Low-level control of the AMD Adrenalin driver
  - Radeon GPU Analyzer (RGA) Offline compiler and performance analysis tool
  - Radeon Raytracing Analyzer (RRA)
  - Radeon GPU Detective (RGD) Post-mortem analysis of GPU crashes
    - 2024 - Post-Mortem GPU Crash Analysis With AMD Radeon GPU Detective (RGD)
  - 2024 - Game Optimization with The Radeon Developer Tool Suite
- GPU Reshape On-the-fly instrumentation of GPU operations with instruction level validation of potentially undefined behavior
  - 2024 - Introducing GPU Reshape - Video
Intel
- Intel Graphics Performance Analyzers
Other related tools
- RenderDoc Graphics debugger that allows quick and easy single-frame capture and detailed introspection
- APITrace Trace OpenGL, Direct3D, and DirectDraw APIs calls to a file and replay
- PerfTest A simple GPU shader memory operation performance test tool. Results on a wide range of GPUs are already available
- D3d12info by Adam Sawicki Get GPU information through DXGI and Direct3D 12 (D3D12) + AMD AGS, NVAPI, WinAPI, and some other sources

Thanks JoseEmilio-ARM for ARM part.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment