#include "blas.h" void axpy_cpu(int N, float ALPHA, float *X, int INCX, float *Y, int INCY) { int i; for(i = 0; i < N; ++i) Y[i*INCY] += ALPHA*X[i*INCX]; } void scal_cpu(int N, float ALPHA, float *X, int INCX) { int i; for(i = 0; i < N; ++i) X[i*INCX] *= ALPHA; } void copy_cpu(int N, float *X, int INCX, float *Y, int INCY) { int i; for(i = 0; i < N; ++i) Y[i*INCY] = X[i*INCX]; } float dot_cpu(int N, float *X, int INCX, float *Y, int INCY) { int i; float dot = 0; for(i = 0; i < N; ++i) dot += X[i*INCX] * Y[i*INCY]; return dot; }