Complex matrix inverse III: CUDA

Here is cuinverse_kernel.cu

__global__ void cgeMatrixInverse_kernel(cuFloatComplex *invA , cuFloatComplex *A , int N , cuFloatComplex *Work)
{

int i;
int idx = blockDim.x * blockIdx.x + threadIdx.x;

cuFloatComplex * ThreadWorkSpace;

ThreadWorkSpace = Work + idx*cgeMatrixInverse_WorkSpace()*N*N;

for(i=0;i<N*N;i++) A[ i + idx*N*N ] =  A[i];

A[ idx*N*N ] = make_cuFloatComplex( (float) idx , 1./sqrtf(2));

cgeMatrixInverse(invA + idx*N*N , A + idx*N*N , N , ThreadWorkSpace);


}

_______________________

and my makefile is

#  edit the path of your working directory
BASE_PATH = /home/rcabrera/Documents/source/c/inverseCUDA

#

CUDA_PATH = /usr/local/cuda

CC = gcc
NVCC    := $(CUDA_PATH)/bin/nvcc

CUDA_INCLUDE_PATH = /usr/local/cuda/include
CUDA_LIB_PATH := $(CUDA_PATH)/lib64
CUDA_LIBS = -lcuda -lcudart

a.out: main.cu cuinverse_kernel.cu cumatrixtools.h
$(NVCC)  -I$(CUDA_INCLUDE_PATH) -L$(CUDA_LIB_PATH) $(CUDA_LIBS) -lm  main.cu -o a.out

# $(NVCC) -deviceemu  -I$(CUDA_INCLUDE_PATH) -L$(CUDA_LIB_PATH) $(CUDA_LIBS) -lm  main.cu -o a.out

clean :
rm -f a.out