fp32 mat4 FMA
x = m * x + c chained in a register with a mat4x4<f32> (a contracting matrix and rotating nonzero forcing keep it stable): 16 FMAs per step with plenty of independent work, exercising the full mat4 x vec4 multiply.
Measured in FLOP/s. Higher values mean better performance. Benchmark your device.
Performance distribution
916 MFLOP/s199 GFLOP/s43.2 TFLOP/s
916 MFLOP/s199 GFLOP/s43.2 TFLOP/s
Performance thresholds
99% of results achieve at least 5.37 GFLOP/s
95% of results achieve at least 45.4 GFLOP/s
90% of results achieve at least 129 GFLOP/s
Median (50th percentile) 1.49 TFLOP/s
Best performer
Highest recorded performance: 43.2 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