Matrix multiplication. 2D register blocking v.6i benchmark

WebGL2-compute based NxN matrix multiplication C = A x B Shader v.6 benchmark. Fixed random A, B 1024x1024 buffers are used for calculations, therefore You can set new N value (up to N=1024, multiple of 128). Tile size TS = 128 and work-per-thread = 8. FLOPS = 2 N3 / time. Random CGPU and CGPU - CCPU are shown.

calculating
N=

Intel i3-8100, D3D11     ~99 GFLOPS (N=1024).

I re-run all programs many times (press "Run" button) and try to choose "representative" values. Results differ very much on different GPUs.


SGEMM in WebGL2-compute     updated 27 June 2019