The proposed LDPC decoder has a partially parallel
architecture with 16 BNUs, 16 CNUs and exchange messages
with 16 shared memory modules. Each CNU reads the
memory from the address generated by the AGU and
processes the operation. After completing each operation, the
message to be delivered is stored in the same address. It is
crucial for the AGU to generate precise addresses without
causing any memory access conflict. Therefore, we propose a
novel approach which enables us to parallelize processing
with 16 shared memories without any conflict. Also, we
propose a highly efficient AGU design which generates
addresses based on an Index matrix. Furthermore, to support
two data rates with a minimal area overhead, most of the
blocks are reconfigurable so that they can be commonly used
for both modes.
The proposed LDPC decoder has a partially parallelarchitecture with 16 BNUs, 16 CNUs and exchange messageswith 16 shared memory modules. Each CNU reads thememory from the address generated by the AGU andprocesses the operation. After completing each operation, themessage to be delivered is stored in the same address. It iscrucial for the AGU to generate precise addresses withoutcausing any memory access conflict. Therefore, we propose anovel approach which enables us to parallelize processingwith 16 shared memories without any conflict. Also, wepropose a highly efficient AGU design which generatesaddresses based on an Index matrix. Furthermore, to supporttwo data rates with a minimal area overhead, most of theblocks are reconfigurable so that they can be commonly usedfor both modes.
การแปล กรุณารอสักครู่..
