GeForce RTX 2070, OpenGL backend, Windows 10, 64 bit (N=4096) 0.77 TFLOPS
"Semi-quantitative" plot.
<script src="https://cdn.jsdelivr.net/npm/@tensorflow/tfjs@latest"> </script>
var N = 1024, A,B;
function init() {
A = tf.randomUniform([N, N]);
B = tf.randomUniform([N, N]);
run()
}
function run() {
var ti0 = performance.now(), ti, Tmin = 100000, str = "\n T(ms)= "
for(var i = 0; i < it; i++){
const C = A.matMul(B)
var t = C.dataSync()[0];
ti = performance.now()
dt = ti - ti0
if(Tmin > dt) Tmin = dt
str += Math.round(10*dt)/10 + "\u2003"
ti0 = ti
}
document.getElementById('output').innerText = "N = " + N +
" GFLOPS=" + Math.round(2*N*N*N/Tmin/10000)/100 + str
}