Skip to content

workgroup 256

65,536 scalar elements, one per invocation, with 16 multiply-add steps each. Only workgroup size (256) changes; the input, arithmetic and output count match. Reports elements/s.

Measured in element/s. Higher values mean better performance. Benchmark your device.

Performance distribution

 
3.17 Melement/s380 Melement/s45.7 Gelement/s

Performance thresholds

99% of results achieve at least 8.53 Melement/s

95% of results achieve at least 270 Melement/s

90% of results achieve at least 628 Melement/s

Median (50th percentile) 4.97 Gelement/s

Best performer

Highest recorded performance: 45.7 Gelement/s. View benchmark profile.

Recorded 9/23/2026, 4:10:52 AM

WebGPU device
Vendornvidia
Device—
Architectureblackwell
Description—
WebGL device
VendorGoogle Inc. (NVIDIA)
RendererANGLE (NVIDIA, NVIDIA GeForce RTX 5070 Ti (0x00002C05) Direct3D11 vs_5_0 ps_5_0, D3D11)
Browser
NameChrome
Version153.0.0.0
Operating system
NameWindows
Version10