fp32 fma() builtin
The fp32 scalar test with the explicit fma(x, a, b) builtin in place of x * a + b. WGSL lets the compiler contract the latter into an FMA; similar timing is consistent with similar lowering but does not prove contraction.
Measured in FLOP/s. Higher values mean better performance. Benchmark your device.
Performance distribution
1.34 GFLOP/s335 GFLOP/s83.8 TFLOP/s
1.34 GFLOP/s335 GFLOP/s83.8 TFLOP/s
Performance thresholds
99% of results achieve at least 7.13 GFLOP/s
95% of results achieve at least 96 GFLOP/s
90% of results achieve at least 225 GFLOP/s
Median (50th percentile) 2.7 TFLOP/s
Best performer
Highest recorded performance: 83.8 TFLOP/s. View benchmark profile.
Recorded 9/14/2026, 2:52:24 PM
WebGPU device
Vendornvidia
Device—
Architectureblackwell
Description—
WebGL device
VendorGoogle Inc. (NVIDIA)
RendererANGLE (NVIDIA, NVIDIA GeForce RTX 5090 (0x00002B85) Direct3D11 vs_5_0 ps_5_0, D3D11)
Browser
NameChrome
Version153.0.0.0
Operating system
NameWindows
Version10