CORDIC-based LMMSE equalizer for Software Defined Radio

Senthilvelan, Murugappan; Hormigo, Javier; Chun, Joon Hwa; Sima, Mihai; Iancu, Daniel; Schulte, Michael; Glossner, John

doi:10.1109/icsamos.2010.5642051

Cited by 1 publication

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This analysis resulted in CORDIC ISA extensions that speedup computation within a single CORDIC iteration including the conditional-add-subtract, shift-conditional-add-subtract, lookup-conditional-add-subtract instructions [17]. While these ISA extensions could be implemented with incremental hardware changes within the existing SIMD vector functional unit and have low memory overhead implementations for hyperbolic functions compared to the baseline implementations that use large lookup tables, they did not demonstrate significant performance improvement [17].…”

Section: Isa Extensions For a Single Cordic Iterationmentioning

confidence: 95%

“…Additional details regarding the CORDIC functional units and the impact of the CORDIC ISA extensions on power dissipation of wireless algorithms are presented by Senthilvelan [17]. The designs are synthesized with a clock constraint of 600 MHz to match the clock speed of the SB3000.…”

Section: Hardware Synthesis Estimatesmentioning

confidence: 99%

“…An analytical methodology using instruction-type profiling and instruction power-consumption measurements from real hardware was employed to estimate the power consumption of wireless algorithms [17]. Previous experiments indicate this power model is accurate to within about 10% when modeling the power dissipation of computeintensive wireless communication algorithms.…”

Section: Power Consumption Estimatesmentioning

confidence: 99%

“…To study the effect of the CORDIC algorithm on the LDPC decoding, a software-only implementation of the CORDIC algorithm using the SB3000 instruction set was created [17]. The software-only implementation of the CORDIC algorithm has hand-optimized assembly functions for rotation and vectoring in each coordinate system.…”

Section: Software-only Cordic Algorithmmentioning

confidence: 99%

See 3 more Smart Citations

CORDIC instructions for LDPC decoding on SDR platforms

Senthilvelan

Iancu

et al. 2011

Analog Integr Circ Sig Process

Self Cite

View full text Add to dashboard Cite

Wireless protocols strive to increase spectral efficiency and achieve high data throughput. Low-density parity-check (LDPC) codes are advanced forward error correction (FEC) codes that use iterative decoding techniques to achieve close to the Shannon capacity. Due to their superior performance, state-of-art wireless protocols, such as WiMAX and LTE Advanced, are adopting LDPC codes. LDPC codes come with the high cost of drastically increased computational effort for decoding. Among the proposed decoding algorithms, the belief propagation (BP) algorithm leads to a good approximation of an optimal decoder; however, it uses compute-intensive hyperbolic trigonometric functions. To reduce the computational complexity, typical LDPC decoder implementations use simplified algorithms, such as the min-sum algorithm, at the expense of reduced signal processing performance. Efficient and accurate methods to compute hyperbolic trigonometric functions can facilitate the use of the BP algorithm in real-time LDPC decoder implementations. This paper investigates hyperbolic COordinate Rotation DIgital Computer (CORDIC) instruction set architecture (ISA) extensions for software-defined radio (SDR) processors to compute the hyperbolic trigonometric functions for LDPC decoding efficiently. The CORDIC ISA extensions are evaluated on the low-power multi-threaded Sandbridge Sandblaster TM SB3000 platform. The computational performance, numerical accuracy, hardware estimates, power consumption estimates, and memory requirements with the CORDIC ISA extensions are compared to a baseline implementation without these extensions on the SB3000.

show abstract

Section: Isa Extensions For a Single Cordic Iterationmentioning

confidence: 95%

Section: Hardware Synthesis Estimatesmentioning

confidence: 99%

Section: Power Consumption Estimatesmentioning

confidence: 99%

Section: Software-only Cordic Algorithmmentioning

confidence: 99%

See 2 more Smart Citations