Introducing WebGPU-Bench: A WebGPU Microbenchmark
- Auto-discovered
Ben Houston
Visit resource ↗Description
Ben Houston's September 2026 article introduces webgpu-bench, the micro-benchmark suite behind Web3D Survey GPU measurements. It targets developers who need device-specific costs for WebGPU shader operations.
Houston contrasts micro-benchmarks with full-scene tests, then describes focused workloads for arithmetic, memory access, and alternate shader implementations. The suite runs in the browser via Web3D Survey and from a Node/Dawn CLI.
Intermediate WebGPU authors who already ship shaders benefit most.
Access is open source: use the survey site for quick comparisons or the CLI in profiling workflows.
Widely linked in WebGPU performance threads as a bridge between tutorials and app-level profiling.
Related resources
- Crystal Shader Breakdown (Cyanilux)
A Cyanilux Shader Graph walkthrough for Unity URP that builds an unlit transparent crystal with object-space Y colour gradients, camera opaque-texture refraction, Fresnel opacity, and HDR glow for bloom.
100% match · <intermediate><blog><developers><node><post><shader><used><via> - Local UVs for Sprites in Sprite Sheet/Atlas (Cyanilux)
Unity shader techniques for per-sprite 0-1 UVs when sprites live in sheets or atlases: C# UV remap with Shader Graph/HLSL, plus URP object-space and renderer-bounds alternatives.
100% match · <code><intermediate><blog><developers><node><post><shader><specific> - Writing Shader Code in Universal RP (v2) (Cyanilux)
Writing Shader Code in Universal RP (v2) is Cyanilux's ShaderLab and HLSL guide for Unity URP (2021, updated 2022).
100% match · <code><blog><developers><explains><node><shader><support><used> - 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 · <code><blog><access><compute><data><device><need><post> - Cyanilux GitHub - URP Blit Renderer Feature
URP_BlitRenderFeature demonstrates a ScriptableRendererFeature that performs full-screen blits in Universal RP - template for custom post effects, copying buffers, or chaining pass
100% match · <intermediate><access><blog><developers><node><post><shader><specific> - New AMD Radeon Developer Tool Suite update brings shader source code, Extended PIX Markers, and command-line capture
New AMD Radeon Developer Tool Suite update brings shader source code, Extended PIX Markers, and command-line capture is a technical blog article by Chris Hesik. AMD GPUOpen…
100% match · <optimization><tool><intermediate><blog><cli><developers><post><shader> - Advanced Shader Delivery expands Public Preview with AMD
DirectX Developer Blog post announcing Advanced Shader Delivery (ASD) expanding public preview to Windows 11 PCs with AMD RDNA GPUs, beyond the ROG Xbox Ally handhelds.
100% match · <code><optimization><intermediate><blog><developers><device><explains><post> - D3D12 Opacity Micromaps
A Microsoft DirectX Developer Blog post by Amar and Adam on Direct3D 12 Opacity Micromaps (OMMs) in DXR Tier 1.2 for cheaper alpha-tested geometry in ray tracing. It covers…
100% match · <code><optimization><blog><cost><developers><micro><post><shader> - Runtime Mipmap Generation
Runtime Mipmap Generation is a February 2026 blog post by Ignacio Castano on generating mipmaps at runtime in spark.js instead of shipping precomputed chains with compressed…
100% match · <code><optimization><blog><developers><device><memory><post><shader> - Vulkan Introduces Roadmap 2026 and New Descriptor Heap Extension
Vulkan Introduces Roadmap 2026 and New Descriptor Heap Extension is a January 2026 Khronos blog post from the Vulkan Working Group announcing VK_EXT_descriptor_heap and the…
100% match · <code><intermediate><blog><access><compute><developers><memory><post> - Dispatching Hundreds of Thousands of Compute Tasks
Dispatching Hundreds of Thousands of Compute Tasks is a March 2026 blog post by Amini Allight on recording huge Vulkan compute command streams for a GPU voxel spring simulation…
100% match · <code><optimization><intermediate><blog><compute><costs><explains><post> - AMD and Microsoft partner on DirectX ML, DirectStorage, and developer tools at GDC 2026
AMD GPUOpen blog post by Alexander Blake-Davies and Joe Rozek summarizing Microsoft GDC 2026 DirectX announcements and AMD's planned Radeon and tool-suite support. It covers…
100% match · <code><tool><intermediate><blog><compute><developers><post><shader> - Simplifying Vulkan One Subsystem at a Time
Simplifying Vulkan One Subsystem at a Time is a February 2026 Khronos blog post by Tobias Hector (AMD / Vulkan Strategy Officer) on cutting Vulkan API complexity through…
100% match · <code><blog><data><developers><explains><memory><post><strategies> - Notes about VK_EXT_custom_resolve
Notes about VK_EXT_custom_resolve is a November 2025 Geek Blight blog post by Ricardo Garcia on Vulkan shader-driven multisample resolve, tied to Igalia work around the Steam…
100% match · <code><optimization><blog><data><explains><post><shader><specific> - Inline vs Pipeline Ray Tracing
Inline vs Pipeline Ray Tracing is a November 2025 Evolve Benchmark blog post by Manon Oomen comparing the two DirectX and Vulkan-style ray-tracing programming models as…
100% match · <code><optimization><blog><access><bench><benchmark><explains><post> - State of GPU Hardware (End of Year 2025)
State of GPU Hardware (End of Year 2025) is a guest blog article by Dmytro Bulatov (Boolka) on asawicki.info.
100% match · <code><optimization><intermediate><blog><access><data><developers><post> - 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…
100% match · <code><optimization><memory><need><specific><suite><tooling><written> - WebGPU and the price of compiling WGSL
WebGPU and the price of compiling WGSL is a blog post by Hugo Daniel introducing a WebGPU diagnostics and compilation-benchmark tool after earlier posts on WGSL limits. It…
100% match · <code><tool><intermediate><blog><benchmark><browser><compute><cost> - A case for learning GPU programming with a compute-first mindset
A case for learning GPU programming with a compute-first mindset is a 2025 blog essay on Maister Graphics Adventures arguing that new GPU programmers should learn compute,…
100% match · <code><optimization><intermediate><blog><compute><device><post><run> - ONNX and DirectML execution provider guide - part 1
This AMD GPUOpen technical article by Hui Zhang is part 1 of a guide to using the ONNX Runtime DirectML execution provider with a native DirectX 12 pipeline.
100% match · <code><optimization><blog><access><compute><data><developers><device>