Problem using xGEMM (General Matrix-Matrix Product)

[Yoni]

Hi,

I've arrived at a dead-end.

I'm trying to execute matrix multiplication with the GPU.

(see attached VI)

For comparison I did the same matrix multiplication with regular matrix operation (gemm BLAS 3)

which works fine with the same matrices.

I don't get an error I just get all zeros in the output

I checked the heat transfer demo using the same GPU function and it seems to be running ok.

so by now I have no idea what I'm doing wrong.

Thanks

I'd really appreciate any helpful help.

Yoni.

[Yoni]

Found a solution at http://forums.ni.com/t5/LabVIEW/CUDA-Matrix-Multiplication-Fails/m-p/3262686/highlight/false#M951836

turns out its a labview 32bit/Windows 64bit compatibility issue.