1. 2048 bit RISCV Vector
2. dual vector and scalar load/store
3. RVA22 profile compliance
4. Andes Matrix Multiply
5. Private L2 cache
6. 16 core cluster
above are the special unique feature of AX46MPV.
AX46MPV have better vector performance due to major improvement in the memory subsystem, matrix engine and wider VLEN. AI computation uses a lot of data, and the dual load/store engine can greatly increase the memory bandwidth.
The private L2 cache and the dual scalar load/store also increase the scalar capability greatly, boost the specint2006 benchmark much higher than Cortex A55. The RVA22 support increase Linux SW compatibility. That makes the AX46MPV the ideal A55 replacement.
Malicious vote manipulation is expressly forbidden in this voting event. The organizers reserve the right to evaluate the fairness and accuracy of the voting results. AspenCore retains the authority to interpret the rules of this event.
