Overview / Usage

This code performs the following tasks:

1. Matrix Creation: It generates two 1024x1024 random matrices, A and B, using NumPy with values of type float32.
2. Matrix Multiplication: It multiplies these two matrices using oneapi.matmul, which leverages Intel's OneAPI for optimized matrix multiplication.
3. Timing: It measures the time taken to perform the matrix multiplication by recording the start and end times.
4. Result Display: It prints the first 5 elements of the resulting matrix C and the time taken for the operation.

Essentially, it demonstrates how to perform matrix multiplication on large matrices and optimize the operation using Intel OneAPI.

Repository

https://github.com/tao011110/OneAPI/blob/master/mul.py