computing environment - High variety of workloads - Ever-increasing set of primitives (over 500 aten kernels) - Interpreter methods not delivering generalized performance 2 Why TVM? XTVM for Speech Synthesis

and etc ● Collaborations between Arm NN/ACL/CMSIS-NN and TVM ○ Integrate optimized ACL/CMSIS-NN kernels into TVM? ○ Implement Arm NN generic backend in TVM for more flexibility with the runtime plugins