M1 Mac Mini best: 1022.61 gflops [numthreads(2, 4, 1)] compute void main(constant float4[] A : register(u0), constant float4[] B : register(u1), device float4[] C : register(u2), float3 threadID : SV_DispatchThreadID)
M1 Mac Mini best: 1022.61 gflops [numthreads(2, 4, 1)] compute void main(constant float4[] A : register(u0), constant float4[] B : register(u1), device float4[] C : register(u2), float3 threadID : SV_DispatchThreadID)