- Benchmarking GPU pipeline stages
The work measures isolated rendering pipeline stages with a custom Unity 6000.2.9 engine loop, custom render pipeline, DX12, and the DXC shader compiler instead of profiling a full production scene.
100% match
· <optimization><advanced><blog><mroz><benchmarks><custom><il2cpp><nsight> - Optimizing camera overhead to the absolute minimum
The motivating example renders waterfall occlusion with an orthographic depth texture and a shader that compares obstacle depth against surface positions.
100% match
· <optimization><advanced><blog><mroz><camera><costs><culling><custom> - Drawing Thousands of Meshes with DrawMeshInstanced / Indirect (Toqoz)
Toqoz's November 2019 toqoz.fyi post walks through drawing very large mesh counts in Unity with Graphics.DrawMeshInstanced and Graphics.DrawMeshInstancedIndirect, with C# samples,
100% match
· <advanced><blog><culling><custom><data><frustum><identical><occlusion> - Optimizing whole frame - case study
Every pass uses a fixed camera angle, DX12, and Nsight Graphics so frame comparisons stay apples-to-apples.
97% match
· <optimization><blog><mroz><camera><culling><editor><nsight><unity> - How to properly profile your game
Opening stories show GPU-bound teams celebrating CPU particle wins, camera-angle skew in captures, and missed spike frames.
93% match
· <optimization><blog><mroz><builtin><camera><culling><drawer><occlusion> - Procedural Pixels Blog
Blog focused on Unity rendering, GPU/CPU profiling, and production optimization case studies.
89% match
· <optimization><blog><mroz><benchmarks><culling><occlusion><savings><unity> - Optimizing mannequin
Optimizing mannequin is a December 2025 post on the peterstrahle.dev blog about performance work for the Quest VR title Mannequin, with lessons carried from Vampire: The…
83% match
· <optimization><blog><culling><custom><data><editor><occlusion><scenes> - Using grid to speed up dynamic collisions
The solver already handles velocity integration, static SDF colliders, iterative dynamic collisions, constraints, and invalid-position correction with Burst-compiled Unity Jobs.
80% match
· <optimization><blog><mroz><culling><overhead><profiler><scenes><unity> - Profiling the GPU in Unity Editor
The workflow targets Windows with DirectX 11 or 12 and an NVIDIA GPU (the author uses an RTX 3060).
76% match
· <optimization><blog><mroz><editor><prerequisites><profiler><nsight><unity> - Optimizing Based On Analysis - Game Optimization - Episode 8
[video] Optimizing Based On Analysis - Game Optimization - Episode 8 is a free YouTube episode by Ben Cloward that applies prior PIX captures to concrete Unity URP and Unreal…
73% match
· <optimization><drawer><editor><profiler><unity><urp> - Analyze Your Game With PIX - Game Optimization - Episode 7
Analyze Your Game With PIX - Game Optimization - Episode 7 is a YouTube video by Ben Cloward on using Microsoft PIX for GPU frame capture and timeline analysis inside a larger…
73% match
· <optimization><costs><frames><release><unity><urp> - Modern rendering culling techniques
Modern rendering culling techniques is a technical blog article by Nikita Krupitskas.
Technical blog post by Nikita Krupitskas surveying culling techniques used in modern…
71% match
· <optimization><blog><culling><dense><frustum><occlusion><scenes> - Software occlusion culling in Block Game
Software occlusion culling in Block Game is a January 2026 Eniko Fox blog post on a CPU depth-buffer occlusion culler for an FNA block/chunk game aimed at weak integrated…
71% match
· <optimization><blog><culling><final><frustum><occlusion> - Texture Baking - Trading VRAM for GPU performance
The case study starts with a procedural rock material built in Shader Graph: bevel edge detection on normal maps, triplanar wood and mud, and many texture samples that leave the GPU texture unit st…
66% match
· <optimization><advanced><blog><mroz><nsight><profiler><unity> - How to profile the rendering - GPU profiling basics
It separates profilers from Frame Debugger and RenderDoc, which debug resources without per-draw durations.
64% match
· <optimization><blog><mroz><frames><nsight><scenes><unity> - Rendering 90,000 particles in Unity: what actually costs CPU and GPU time
A Burst job simulates gravity, noise, pull, drag, and bounce for large CPU particle counts before draw.
64% match
· <optimization><blog><mroz><costs><drawer><scenes><unity><urp> - How to properly profile mobile GPU using ARM Streamline
Streamline streams continuous GPU performance counters from a USB-connected phone, but raw counter values and missing API labels make frames hard to interpret out of the box.
60% match
· <optimization><blog><mroz><custom><frames><profiler> - Efficiently sorting gigabytes: the Deferred Merge Sort
Efficiently sorting gigabytes: the Deferred Merge Sort is a Superluminal engineering post by Jelle van der Beek on timestamp-ordering huge profiler capture streams with bounded…
60% match
· <optimization><advanced><blog><algorithm><costs><data><profiler> - Rendering into texture - the most important TA skill
It restates vertex and fragment roles and the levers artists actually control beyond hardware rasterization.
58% match
· <blog><mroz><culling><custom><frustum><unity><urp> - Introducing WebGPU-Bench: A WebGPU Microbenchmark
Blog post introducing webgpu-bench, a WebGPU micro-benchmark suite used by Web3D Survey to measure arithmetic, memory access, operation costs, and compute strategies.
58% match
· <optimization><blog><benchmarks><costs><data>
