Visible to Intel only — GUID: kcp1652887199838
Ixiasoft
1. About the 4G Turbo-V Intel® FPGA IP
2. Getting Started with 4G Turbo-V IP
3. Designing with the 4G Turbo-V Intel® FPGA IP
4. 4G Turbo-V Intel® FPGA IP Functional Description
5. 4G Turbo-V Intel FPGA IP User Guide Document Archive
6. Document Revision History for the 4G Turbo-V Intel® FPGA IP User Guide
Visible to Intel only — GUID: kcp1652887199838
Ixiasoft
4.1.5. Throughput Calculations
The downlink accelerator has buffers between two neighboring subcomponents, so that all sub-components can process in parallel at the same time.
The overall throughput can be calculated as
Throughput= K/max(L(crc), L(encoder), L(subblock-interleaver), L(pruning))*freq. (bits per second).
Example 1: K = 6144, Kπ = 6176, E = 18444, freq. = 300 MHz
L(crc) = 776 cycles
L(encoder) = 782 cycles
L(subblock-interleaver) = 814 cycles
L(pruning) = 786 cycles
L(output) = 815 cycles
Throughput(downlink) = 6144/815*300M = 2262 Mbps
Example 2: K = 40, Kπ= 64, E = 132, freq. = 300 MHz
L(crc) = 13 cycles
L(encoder) = 19 cycles
L(subblock-interleaver) = 50 cycles
L(pruning) = 22 cycles
L(output) = 52 cycles
Throughput(downlink) = 40/52*300M = 231 Mbps