GPU Integrity Check Stress
Does your GPU compute correctly under load? Repeats a deterministic calculation, checks it against a CPU reference and verifies patterns in video memory. Detect-only.
GPU Integrity Check
This canvas shows the animated graphics workload used to stress the GPU. It is decorative; results are listed in the metrics below.
- FPS
- –
- 1% LOW
- –
- FRAME TIME
- –
- SCORE
- –
- TIME
- 0:00
- LOAD
- –
- ERRORS
- 0
Before you start
GPU stress tests can significantly increase GPU load, temperature, power draw and fan speed.
Stop the test if your system becomes unstable, overheats, crashes or behaves unexpectedly. Do not run extreme tests on hardware with known cooling problems. This website cannot guarantee hardware safety.
This is a deliberately punishing test. It can push your GPU to its thermal and power limits for minutes.
- Laptops: plug in the charger and make sure the vents are clear.
- Make sure your GPU is cooled properly. Do not run this with known fan or cooling problems.
- Save your work and close other important tabs. A weak or overheated GPU can make the screen flicker or the graphics driver reset, which may close apps.
- You can stop at any time with the Stop button or the Escape key. The test also stops itself if frames take more than two seconds.
Long run: this test keeps the GPU busy for five minutes or more, so your computer will get warm. Laptops should be plugged in. You can stop at any time with the Stop button.
Does your GPU compute correctly under load? Repeats a deterministic calculation, checks it against a CPU reference and verifies patterns in video memory. Detect-only.
About this test
Repeats a deterministic integer calculation on the GPU under load, checks the results against a CPU reference and verifies patterns written to video memory. It is detect-only: it reports mismatches and does not diagnose their cause.
It cannot see temperature, clocks or power, and WebGL cannot exercise tensor or ray-tracing hardware.
How to read the results
0 errors means a PASS for this run at this load; it does not prove the GPU is stable forever. One or more errors is a FAIL. The cause could be an overclock, overheating, a driver problem or faulty memory. Lower any overclock, check cooling and run again. Repeated errors at stock settings suggest a hardware fault.
Frequently asked questions
What kind of errors does it find?
Wrong answers to a calculation with a known result, and pattern mismatches in video memory. These are signs of instability that a frame-rate test can miss.
Is a pass a guarantee?
No. It means no errors were seen in this run. Run it a few times, especially after a change.
What should I do after a fail?
Reset overclocks to default, check temperatures and cooling, update the driver and run again. If it still fails, the card may be faulty.
Why does it need a high load?
Marginal hardware often only misbehaves when hot or at full power.
Does it run in the background?
No. Keep the tab in the foreground until the test ends.
Share feedback about this test
Did it work for you? Tell us your GPU or device, your browser and what you saw. Your email address is never shown.