You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
SIMD Vectorization, related to SIMD vectorization using Intel SSE instructions for
matrix-vector and matrix-matrix multiplication.The assignment involves using
GCC, understanding SSE intrinsics, and implementing vectorized versions of
these operations:
1- Vector-Vector Multiplication:
This mode compares the performance of scalar and vectorized implementations
of vector-vector multiplication. The table presents the execution times for
different input sizes (128, 256, 512).
2- Matrix-Vector Multiplication:
This mode compares the performance of scalar and vectorized implementations
of matrix-vector multiplication. The table provides execution times for different
input sizes (128, 256, 512).
3- Matrix-Matrix Multiplication:
This mode compares the performance of scalar and vectorized implementations
of matrix-matrix multiplication. Execution times are reported for different input
sizes (128, 256, 512).