In this paper, we propose a new efficient FFT algorithm for OFDM/DMT applications and present. its pipeline implementation results. Since the proposed algorithm is based on the radix-4 butterfly unit, the processing r...
详细信息
In this paper, we propose a new efficient FFT algorithm for OFDM/DMT applications and present. its pipeline implementation results. Since the proposed algorithm is based on the radix-4 butterfly unit, the processing rate can be twice as fast as that based on the radix-2(3) algorithm. Also, its implementation is more area-efficient than the implementation from conventional radix-4 algorithm due to reduced number of nontrivial multipliers like using the radix-2(3) algorithm. In order to compare the proposed algorithm with the conventional radix-4 algorithm, the 64-point MDC pipelined FFT processor based on the proposed algorithm was implemented. After the logic synthesis using 0.35mum CMOS technology, the logic gate count for the processor with the proposed algorithm is only about, 70% of that for the processor with the conventional radix-4 algorithm. Since the proposed algorithm can achieve higher processing rate and better efficiency than the conventional algorithm, it is very suitable for the OFDM/DMT applications such as the WLAN, DAB/DVB, and ADSL/VDSL systems(1).
Authenticated encryption schemes which resist misuse of nonce at some desired level of privacy are two-pass or Mac-then-Encrypt constructions (inherently inefficient but provide full privacy) and online constructions ...
详细信息
Authenticated encryption schemes which resist misuse of nonce at some desired level of privacy are two-pass or Mac-then-Encrypt constructions (inherently inefficient but provide full privacy) and online constructions like McOE, sponge-type authenticated encryptions (such as duplex) and COPA. Only the last one is almost parallelizable except that for associated data processing, the final block-cipher call is sequential (it needs to wait for the encryption of all the previous ones). In this paper, we design a new online secure authenticated encryption, called ELmD or Encrypt-Linear mix-Decrypt, which is completely (two-stage) parallel (even in associated data) and fully pipeline implementable. It also provides full privacy when associated data is not repeated. Like COPA, our construction is based on EME, an Encrypt-Mix-Encrypt type SPRP construction (secure against chosen plaintext and ciphertext). But unlike EME, we have used an online computable efficient linear mixing instead of a non-linear mixing. We have also provided the hardware implementation of the construction and compare the performance with similar constructions like COPA and EME2.
THE AUTHORS' CHIP MULTIPROCESSOR (CMP) DESIGN MIXES COARSE- AND FINE-GRAINED RECONFIGURABILITY TO INCREASE CORE AVAILABILITY OF SAFETY-CRITICAL EMBEDDED SYSTEMS IN THE PRESENCE OF HARD ERRORS. THE AUTHORS IDENTIFI...
详细信息
THE AUTHORS' CHIP MULTIPROCESSOR (CMP) DESIGN MIXES COARSE- AND FINE-GRAINED RECONFIGURABILITY TO INCREASE CORE AVAILABILITY OF SAFETY-CRITICAL EMBEDDED SYSTEMS IN THE PRESENCE OF HARD ERRORS. THE AUTHORS IDENTIFIED WHICH GRANULARITY MIXES MAXIMIZE FAULT TOLERANCE AND MINIMIZE PERFORMANCE AND ENERGY OVERHEADS. THEIR APPROACH CAN TOLERATE 3 TIMES MORE HARD ERRORS THAN CORE REDUNDANCY AND 1.5 TIMES MORE THAN A COARSE-GRAINED SOLUTION.
Instruction cache misses are the critical performance bottleneck in the execution of recent workloads such as Web applications written in JavaScript and server applications. Although various instruction prefetchers ha...
详细信息
Instruction cache misses are the critical performance bottleneck in the execution of recent workloads such as Web applications written in JavaScript and server applications. Although various instruction prefetchers have been proposed to reduce the misses, the requirements for both high miss coverage and small hardware cost are not satisfied. In this article, we propose a novel method that improves the instruction fetch throughput not by instruction prefetching but by dynamically configuring the fetch pipeline structure. Our scheme switches between the normal pipeline and newly introduced miss-assuming pipeline, which does not degrade the fetch throughput even when L1 instruction cache misses occur. Our method achieves high instruction fetch throughput with simple hardware and small cost unlike previously proposed prefetchers. Our evaluation results using Web and database workloads show that our method improves the performance by 16.6 percent and 8.6 percent on average, compared to that with noprefetching and the state-of-the-art instruction prefetcher, PIF, respectively, and achieves as much as 79.0 percent of the performance of the processor with a perfect instruction cache.
A machine learning (ML) design framework is proposed for adaptively adjusting clock frequency based on propagation delay of individual instructions. A random forest model is trained to classify propagation delays in r...
详细信息
A machine learning (ML) design framework is proposed for adaptively adjusting clock frequency based on propagation delay of individual instructions. A random forest model is trained to classify propagation delays in real time, utilizing current operation type, current operands, and computation history as ML features. The trained model is implemented in Verilog as an additional pipeline stage within TigerMIPS processor. The modified system is experimentally tested at the gate level in 45 nm CMOS technology, exhibiting simultaneously a speedup of 70 percent and an energy reduction of 30 percent with coarse-grained ML classification as compared with the baseline TigerMIPS. A speedup of 89 percent is demonstrated with finer granularities with a simultaneous 15.5 percent reduction in energy consumption.
Several geometric distortions are present in remotely sensed images depending on the type of sensors and the object being observed. It is often desirable to compensate for these distortions and store the images in ref...
详细信息
Several geometric distortions are present in remotely sensed images depending on the type of sensors and the object being observed. It is often desirable to compensate for these distortions and store the images in reference to a standard coordinate system. Digital techniques for correction are versatile and introduce a minimum of radiometric errors. The main problems to be considered in this area are the determination of the corrective transformation, resampling, and the management of the large quantities of data. This correspondence considers the last problem. It is shown here that, by a judicious rearrangement of the input data, considerable reductions in the required memory capacity can be achieved. The rearrangement can be accomplished in several stages. The method presented here is amenable to pipeline implementation for processing a continuous stream of images. It can also be used on a relatively small computer with the staging being in time sequence rather than hardware. Examples are shown to illustrate the reductions in overall cost depending on the relative cost of memory and the peripheral devices.
Background: The Marine Genomics project is a functional genomics initiative developed to provide a pipeline for the curation of Expressed Sequence Tags ( ESTs) and gene expression microarray data for marine organisms....
详细信息
Background: The Marine Genomics project is a functional genomics initiative developed to provide a pipeline for the curation of Expressed Sequence Tags ( ESTs) and gene expression microarray data for marine organisms. It provides a unique clearing-house for marine specific EST and microarray data and is currently available at http://www. ***. Description: The Marine Genomics pipeline automates the processing, maintenance, storage and analysis of EST and microarray data for an increasing number of marine species. It currently contains 19 species databases ( over 46,000 EST sequences) that are maintained by registered users from local and remote locations in Europe and South America in addition to the USA. A collection of analysis tools are implemented. These include a pipeline upload tool for EST FASTA file, sequence trace file and microarray data, an annotative text search, automated sequence trimming, sequence quality control (QA/QC) editing, sequence BLAST capabilities and a tool for interactive submission to GenBank. Another feature of this resource is the integration with a scientific computing analysis environment implemented by MATLAB. Conclusion: The conglomeration of multiple marine organisms with integrated analysis tools enables users to focus on the comprehensive descriptions of transcriptomic responses to typical marine stresses. This cross species data comparison and integration enables users to contain their research within a marine-oriented data management and analysis environment.
暂无评论