• The Journal of the Acoustical Society of Korea
• /
• v.36 no.6
• /
• pp.425-435
• /
• 2017

In this paper, we propose optimization methods for speeding the feedforward network of deep neural networks using NEON SIMD (Single Instruction Multiple Data) parallel instructions and multi-core parallelization on the multi-core ARM processor. As the result of the optimization using SIMD parallel instructions, we present the amount of speed improvement and arithmetic precision stage by stage. Through the optimization using SIMD parallel instructions on the single core, we obtain $2.6{\times}$ speedup over the baseline implementation using C compiler. Furthermore, by parallelizing the single core implementation on the multi-core, we obtain $5.7{\times}{\sim}7.7{\times}$ speedup. The results we obtain show the possibility for applying the arithmetic-intensive deep neural network technology to applications on mobile devices.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2011.11a
• /
• pp.18-20
• /
• 2011

최근 컴퓨터 비전의 활용 영역이 증가함에 따라 컴퓨터 비전의 대표적인 라이브러리인 openCV의 사용 또한 증가하는 추세이다. openCV 에는 컴퓨터 비전 알고리즘의 특성상 massive 한 연산을 수행해야 하는 부분이 상당수 존재한다. 본 논문은 이러한 연산량의 부담을 줄임으로써 openCV 의 성능 향상을 위한 아키텍처를 연구한다. openCV 의 massive 한 연산은 라이브러리 함수에 있는 내부 반복문에서 발생하기 때문에, 본 논문은 반복문의 특성을 분석하고 이를 가속할 수 있는 아키텍처가 무엇인지 연구한다. 결론적으로 반복문의 각 iteration 이 독립적일 경우에는 SIMD (Single Instruction Multiple Data)와 SIMT (Single Instruction Multiple Thread)이 적합하며 반복문의 각 iteration 이 의존적일 경우에는 MIMD (Multiple Instruction Multiple Data)를 바탕으로 하는 파이프라인 아키텍처가 적합하다.

• Journal of the Korea Society for Simulation
• /
• v.11 no.2
• /
• pp.67-75
• /
• 2002

This paper proposes a parallel simulation algorithm for bounded Petri nets in a single processor, which exploits the SIMD(Single Instruction Multiple Data)-type parallelism. The proposed algorithm is based on a data packing scheme which packs multiple bytes data in a single register, thereby being manipulated simultaneously. The parallelism can reduce simulation time of bounded Petri nets in a single processor environment. The effectiveness of the algorithm is demonstrated by presenting speed-up of simulation time for two bounded Petri nets.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2014.01a
• /
• pp.1-4
• /
• 2014

Although physical modeling synthesis is becoming more and more efficient in rich and natural high-quality sound synthesis, its high computational complexity limits its use in portable devices. This constraint motivated research of single-instruction multiple-data many-core architectures that support the tremendous amount of computations by exploiting massive parallelism inherent in physical modeling synthesis. Since no general consensus has been reached which grain sizes of many-core processors and memories provide the most efficient operation for sound synthesis, design space exploration is conducted for seven processing element (PE) configurations. To find an optimal PE configuration, each PE configuration is evaluated in terms of execution time, area and energy efficiencies. Experimental results show that all PE configurations are satisfied with the system requirements to be implemented in portable devices.

• KIISE Transactions on Computing Practices
• /
• v.23 no.8
• /
• pp.498-503
• /
• 2017

SIMD (Single Instruction Multiple Data) is a representative parallelization architecture that processes multiple data loaded in a SIMD register with a single instruction. Quicksort is a sorting algorithm that picks an element as a pivot from the array and reorders the array such that all elements having the values less than the pivot value are located in the left side on the pivot as well as all elements having the value greater than the pivot value are located in the right side on the pivot and then the algorithm performs the same task on both sublist recursively. In this paper, we propose an efficient Quicksort algorithm applying the SIMD instructions which minimally invokes conditional branches to avoid the performance degradation incurred by branch misprediction in a pipeline architecture. In addition, we improve the performance of the Quicksort algorithm by fetching data into a SIMD register as a byte unit to apply VBP (Vertical Bit Parallel) and the early pruning technique.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.8 no.1
• /
• pp.117-123
• /
• 2012

This paper implements mobile Worldwide Interoperability for Microwave Access (WiMAX) receiver using Software Defined Radio (SDR) technology. SDR system is difficult to implement on the mobile handset because of restrictions that are computing power and under space constraints. The implemented receiver processes mobile WiMAX software modem on Open Multimedia Application Platform (OMAP) System on Chip (SoC) and Field Programmable Gate Array (FPGA). OMAP SoC is composed of ARM processor and Digital Signal Processor (DSP). ARM processor supports Single Instruction Multiple Data (SIMD) instruction which could operate on a vector of data with a single instruction and DSP is powerful image and video accelerators. For this reason, we suggest the possibility of SDR technology in the mobile handset. In order to verify the performance of the mobile WiMAX receiver, we measure the software modem runtime respectively. The experimental results show that the proposed receiver is able to do real-time signal processing.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.27 no.3
• /
• pp.413-426
• /
• 2017

In this paper, we propose an adder that can be applied to data encrypted with a fully homomorphic encryption scheme and an addition method with improved performance that can be applied when adding multiple data. The proposed arithmetic adder is based on the Kogge-Stone Adder method with the optimal circuit level among the existing hardware-based arithmetic adders and suitable to apply the cryptographic SIMD (Single Instruction for Multiple Data) function on encrypted data. The proposed multiple addition method does not add a large number of data by repeatedly using Kogge-Stone Adder which guarantees perfect addition result. Instead, when three or more numbers are to be added, three numbers are added to C (Carry-out) and S (Sum) using the full-adder circuit implementation. Adding with Kogge-Stone Adder is only when two numbers are finally left to be added. The performance of the proposed method improves dramatically as the number of data increases.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.2
• /
• pp.65-77
• /
• 2009

This paper proposes fast image processing algorithms using SSE (Streaming SIMD Extensions) instructions. The CPU's supporting SSE instructions have 128bit XMM registers; data included in these registers are processed at the same time with the SIMD (Single Instruction Multiple Data) mode. This paper develops new SIMD image processing algorithms for Mean filter, Sobel horizontal edge detector, and Morphological erosion operation which are most widely used in automated optical inspection systems and compares their processing times. In order to objectively evaluate the processing time, the developed algorithms are compared with OpenCV 1.0 operated in SISD (Single Instruction Single Data) mode, Intel's IPP 5.2 and MIL 8.0 which are fast image processing libraries supporting SIMD mode. The experimental result shows that the proposed algorithms on average are 8 times faster than the SISD mode image processing library and 1.4 times faster than the SIMD fast image processing libraries. The proposed algorithms demonstrate their applicability to practical image processing systems at high speed without commercial image processing libraries or additional hardwares.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.729-730
• /
• 2006

multimedia applications has been targeted for exploiting single instruction multiple data extensions to instruction architectures for the most of the modern microprocessor. In this paper, the newest video coding standard, H.264/AVC baseline profile decoder has been implemented and optimized exploiting INTEL MMX technology to show the overall system speedup by the SIMD style coding

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.10C
• /
• pp.1460-1468
• /
• 2004

In this paper, we developed a low-area and low-cost SIMD MAC/MAS(Single Instruction Multiple Data Multiply and ACcumulate/Multiply And Subtract) for multimedia that is used much in real life. We compared the result of this research with a previously developed more large and high performance SIMD MAC/MAS. This paper is consist of 5 parts, which are an introduction, the contents of designing SIMD MAC/MAS hardware, a special qualities for previous works, the result of synthesis and conclusion. The design result reduced by size 32% of whole hardware than 64 bit SIMD MAC/MAS block of designed for high performance. This improved ISA (Instruction Set Architecture) to be suitable to embedded DSP(Digital Signal Processor), and shortened bit range of 64-bit data to 32-bit and implement more optimally.