Matrix multiplication. Shader v.4_8i benchmark

WebGL2-compute based NxN matrix multiplication C = A x B Wider data-types v.4_8 benchmark. Fixed random A, B 1024x1024 buffers are used for calculations, therefore You can set new N value (up to N=1024, multiple of TS). Tile size (local_size_x,y) TS = 32. it - number of iterations. FLOPS = 2 N3 / time. Random CGPU and CGPU - CCPU are shown.


Intel i3-8100   38.5 GFLOPS (N=1024, TS=32).

GEMM in WebGL2-compute     updated 27 June 2019