Low-latency SIMD architecture for multiple iterative decoders arranged in parallel
A decoder and iterative technology, applied in the field of decoders, can solve problems such as aggravated delay, additional chip space, and shortcomings.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0018] Example methods, apparatus, and other embodiments associated with low-latency architectures for high-throughput iterative decoders are described herein. In one embodiment, the architecture includes a Single Instruction Multiple Data (SIMD) architecture. Processing latency for iterative decoders is reduced by controlling the decoders to independently start decoding sequences at the granularity of iterations rather than waiting for multiple decoders to start together. By introducing the ability for a decoder to start a new decoding sequence at an iteration while other decoders are within the decoding sequence, the maximum latency is reduced to one iteration.
[0019] Thus, iterative decoders, such as error correction decoders (eg, Low Density Parity Check (LDPC) decoders, Soft Output Viterbi Algorithm (SOVA) decoders), can be implemented in a low-latency architecture with a single controller. A single controller operates with a finer granularity. In this way, architectu...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


