GeForce GT 710 ~9 GFLOPS (N=1024) ~22 GFLOPS (N=2048) 22.8 GFLOPS (N=4096).
<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()
}
async function run() {
var ti0 = performance.now()
const C = A.matMul(B)
await C.data();
var ti = performance.now()
document.getElementById('output').innerText = "N = " + N +
" time = " + Math.round(10*(ti - ti0))/10 +
"ms GFLOPS=" + Math.round(N*N*N/(ti - ti0)/10000)/100
}
First "synchronous" script is a bit faster
on AMD APU 120/130 ms for N = 1024.