Filter Bank Benchmark Summary

This file details a summary of how the numbers were obtained for this benchmark.

Benchmark Description lines of code # of constructs in the program Number of filters in the expanded graph
filters pipelines splitjoins feedbackloops
Filterbank 8 channel Filterbank 650 9 3 1 1 51
Benchmark 250 MHz RAW processor C on a 2.2 GHz Intel Pentium IV
StreamIt on 16 tiles C on a single tile
Utilization # of tiles used MFLOPS Throughput (per 105 cycles) Throughput (per 105 cycles) Throughput (per 105 cycles)
Filterbank 41% 16 644 256.4 8.9 7.0

StreamIt Number Calculations

No StreamIt numbers were available.

C Code Single Tile Raw Number Calculations

first iteration done at 0x1610688 (23135880 cycles)
second iteration done at 0x2c1ccfd (46255357 cycles) (delta=23119477)
third iteration done at 0x4229372 (69374834 cycles) (delta=23119477)
Based on these cycle counts, each iteration takes 23119477 min/23119477 max cycles (average = 23119477).

2048 outputs every 23119477 cycles normalized to 10^5 cycles, 2048*(100000/23119477) = 8.85833 outputs / 10^5 cycles.

C Code Number Calculations

Performing 10,000 iterations at 2048 outputs/iteration.
Runtime for 10,000 iterations is 133.46 seconds.

Number of cycles per iteration: 10^4 iterations/ 133.46 second * 2048 outputs / 1 iteration * 1 second / 2.2*10^9 cycles * 10^5 cycles = 6.9752 outputs / 10^5 cycles.