ReadMeFeed / Community knowledge

#gpu-performance

Real questions. Useful conversations. Find the people who know your stack.

Article0 replies2,499 followingPosted 24 May 2026, 16:29 UTC78K views3,288 votes

Diagnosing Illustrator GPU Performance Artifacts and Crashes

Step-by-step diagnostic guide for Illustrator GPU rendering artifacts, freezes, and slowdowns, with driver checks, VRAM tests, and escalation thresholds.

Community & Careers · Guide

Tasadduq Burneyowner

Started24 May 2026, 16:29 UTC

Level 38Owner35,775 rep points

Community & Careers

Article0 replies2,272 followingPosted 28 Jul 2025, 18:29 UTC102.7K views1,003 votes

When to Use Double Precision in OpenCL: Detection, Trade‑offs, and a Practical Fallback Pattern

OpenCL double‑precision is optional. Learn how to detect cl_khr_fp64 support, understand the performance trade‑offs, and use a simple fallback to single precision when the extension is missing.

Community & Careers · Blog

opencl double-precision cl-khr-fp64

Community & Careers

Article0 replies4,543 followingPosted 12 Aug 2026, 07:53 UTC72.7K views3,479 votes

Reducing Draw Calls in PixiJS with cacheAsBitmap

Learn how to use PixiJS cacheAsBitmap to collapse complex container hierarchies into single draw calls, improving GPU performance for static UI and backgrounds.

Community & Careers · Blog

game-optimization

pixijs gpu-performance

Community & Careers

Article0 replies2,754 followingPosted 14 Jul 2026, 03:31 UTC112.6K views2,791 votes

Your GPU Is Bored: Fixing Input Pipelines with tf.data

If your GPU idles between training steps, the input pipeline is the likely culprit. Here's how to order tf.data transformations — interleave, map, cache, prefetch — to keep the hardware fed.

Community & Careers · Blog

input-pipeline

tensorflow tf-data

Community & Careers

Article0 replies3,766 followingPosted 15 Jan 2026, 20:40 UTC72.6K views853 votes

Your GPU Is Starving: Fixing TensorFlow Input Pipelines with tf.data

Low GPU utilization usually means your input pipeline, not your model, is the bottleneck. Here's how to fix it with tf.data prefetch, parallel map, and cache — in the right order.

Community & Careers · Blog

input-pipeline

tensorflow tf-data

Community & Careers

Article0 replies796 followingPosted 07 Jul 2026, 19:47 UTC37.9K views1,458 votes

Your GPU Is Waiting on Your Data: Fixing TensorFlow Input Pipelines with tf.data

GPUs idle while CPU-bound data loading runs in lockstep with training. A well-ordered tf.data pipeline — shuffle, map, batch, prefetch with AUTOTUNE — overlaps preparation with execution and recovers the wasted budget.

Community & Careers · Blog

input-pipeline

tensorflow tf-data

Community & Careers

Question0 answers1 comment1,088 followingPosted 27 Dec 2022, 06:57 UTC22.5K views3,241 votes

owner commented

BufferAttribute vs InterleavedBuffer: performance trade‑offs on diverse GPUs

Goal Identify the attribute layout that yields the lowest GPU‑side latency when rendering large, frequently updated geometries across a range of desktop and mobile GPUs. Constraints Three.js BufferGeometry supports both separate BufferAttribute objects and a single InterleavedBuffer with multiple InterleavedBufferAttribute views. Driver hints (StaticDraw, Dy

Community & Careers · Editorial question

buffergeometry

threejs interleavedbuffer