24 July 2018 in IEEE Transactions on Neural Networks and Learning Systems
Deep learning (DL) is a new machine learning (ML) methodology that has found successful implementations in many application domains. However, its usage in communications systems has not been well explored. This paper investigates the use of the DL in modulation classification, which is a major task in many communications systems. The DL relies on a massive amount of data and, for research and applications, this can be easily available in communications systems. Furthermore, unlike the ML, the DL has the advantage of not requiring manual feature selections, which significantly reduces the task complexity in modulation classification. In this paper, we use two convolutional neural network (CNN)-based DL models, AlexNet and GoogLeNet. Specifically, we develop several methods to represent modulated signals in data formats with gridlike topologies for the CNN. The impacts of representation on classification performance are also analyzed. In addition, comparisons with traditional cumulant and ML-based algorithms are presented. Experimental results demonstrate the significant performance advantage and application feasibility of the DL-based approach for modulation classification.
27 February 2016 in BMC Bioinformatics
Background: HMMER software suite is widely used for analysis of homologous protein and nucleotide sequences with high sensitivity. The latest version of hmmsearch in HMMER 3.x, utilizes heuristic-pipeline which consists of MSV/SSV (Multiple/Single ungapped Segment Viterbi) stage, P7Viterbi stage and the Forward scoring stage to accelerate homology detection. Since the latest version is highly optimized for performance on modern multi-core CPUs with SSE capabilities, only a few acceleration attempts report speedup. However, the most compute intensive tasks within the pipeline (viz., MSV/SSV and P7Viterbi stages) still stand to benefit from the computational capabilities of massively parallel processors. Results: A Multi-Tiered Parallel Framework (CUDAMPF) implemented on CUDA-enabled GPUs presented here, offers a finer-grained parallelism for MSV/SSV and Viterbi algorithms. We couple SIMT (Single Instruction Multiple Threads) mechanism with SIMD (Single Instructions Multiple Data) video instructions with warp-synchronism to achieve high-throughput processing and eliminate thread idling. We also propose a hardware-aware optimal allocation scheme of scarce resources like on-chip memory and caches in order to boost performance and scalability of CUDAMPF. In addition, runtime compilation via NVRTC available with CUDA 7.0 is incorporated into the presented framework that not only helps unroll innermost loop to yield upto 2 to 3-fold speedup than static compilation but also enables dynamic loading and switching of kernels depending on the query model size, in order to achieve optimal performance. Conclusions: CUDAMPF is designed as a hardware-aware parallel framework for accelerating computational hotspots within the hmmsearch pipeline as well as other sequence alignment applications. It achieves significant speedup by exploiting hierarchical parallelism on single GPU and takes full advantage of limited resources based on their own performance features. In addition to exceeding performance of other acceleration attempts, comprehensive evaluations against high-end CPUs (Intel i5, i7 and Xeon) shows that CUDAMPF yields upto 440 GCUPS for SSV, 277 GCUPS for MSV and 14.3 GCUPS for P7Viterbi all with 100 % accuracy, which translates to a maximum speedup of 37.5, 23.1 and 11.6-fold for MSV, SSV and P7Viterbi respectively. The source code is available at https://github.com/Super-Hippo/CUDAMPF.
1 December 2021 in Chinese Physics B
Signal transduction is an important and basic mechanism to cell life activities. The stochastic state transition of receptor induces the release of signaling molecular, which triggers the state transition of other receptors. It constructs a nonlinear sigaling network, and leads to robust switchlike properties which are critical to biological function. Network architectures and state transitions of receptor affect the performance of this biological network. In this work, we perform a study of nonlinear signaling on biological polymorphic network by analyzing network dynamics of the Ca2+-induced Ca2+ release (CICR) mechanism, where fast and slow processes are involved and the receptor has four conformational states. Three types of networks, Erdös–Rényi (ER) network, Watts–Strogatz (WS) network, and BaraBási–Albert (BA) network, are considered with different parameters. The dynamics of the biological networks exhibit different patterns at different time scales. At short time scale, the second open state is essential to reproduce the quasi-bistable regime, which emerges at a critical strength of connection for all three states involved in the fast processes and disappears at another critical point. The pattern at short time scale is not sensitive to the network architecture. At long time scale, only monostable regime is observed, and difference of network architectures affects the results more seriously. Our finding identifies features of nonlinear signaling networks with multistate that may underlie their biological function.
26 April 2018 in IEEE Transactions on Parallel and Distributed Systems
Biological sequence alignment is an important research topic in bioinformatics and continues to attract significant efforts. As biological data grow exponentially, however, most of alignment methods face challenges due to their huge computational costs. HMMER, a suite of bioinformatics tools, is widely used for the analysis of homologous protein and nucleotide sequences with high sensitivity, based on profile hidden Markov models (HMMs). Its latest version, HMMER3, introduces a heuristic pipeline to accelerate the alignment process, which is carried out on central processing units (CPUs) and highly optimized. Only a few acceleration results are reported on the basis of HMMER3. In this paper, we propose a five-tiered parallel framework, CUDAMPF++, to accelerate the most computationally intensive stages in HMMER3's pipeline, multiple/single segment Viterbi (MSV/SSV), on a single graphics processing unit (GPU) without any loss of accuracy. As an architecture-aware design, the proposed framework aims to fully utilize hardware resources via exploiting finer-grained parallelism (multi-sequence alignment) compared with its predecessor (CUDAMPF). In addition, we propose a novel method that proactively sacrifices L1 Cache Hit Ratio (CHR) to get improved performance and scalability in return. A comprehensive evaluation shows that the proposed framework outperforms all existing work and exhibits good consistency in performance regardless of the variation of query models or protein sequence datasets. For MSV (SSV) kernels, the peak performance of CUDAMPF++ is 283.9 (471.7) GCUPS on a single K40 GPU, and impressive speedups ranging from $1.8\times (1.7\times)$ to $168.3\times (160.7\times)$ are achieved over the CPU-based implementation (16 cores, 32 threads).