Next, use a spreadsheet analysis to assess compute requirements. Load the system input parameters on the left side of the spreadsheet and analyze compute parameters on the right side. It is useful to tabulate the numbers of processor cycles required by each loop body in the original MATLAB model of the Hough Transform. Given an AI Engine compute capacity of 32 MACs/cycle for int16 data types, you can process two MACs/pixel per \(\theta\) value in real time. Based on these vector estimates, the spreadsheet indicates to process 5.7 cycles per pixel to meet the 220 MP/s throughput objective. This equals 45 cycles for the vector processor with eight-lane single‑instruction multiple‑data (SIMD) execution. The compute bound for the vector processor is high at 5000 MP/s. Assuming an 8-cycle read-modify-write instruction to update histogram tables, throughput becomes limited by the scalar unit. With 32 tiles, throughput reaches only 39 MP/s. Even with 128 tiles, reaching the 220 MP/s target is impossible.