• 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 Korean Institute of Telematics and Electronics A
• /
• v.32A no.4
• /
• pp.93-102
• /
• 1995

This paper introduces a general purpose Associative Processor(AP) which is very efficient for search-oriented applications. The proposed architecture consists of three main functional blocks: Content-Addressable Memory(CAM) arry, row logic, and control section. The proposed AP is a Single-Instruction, Multiple-Data(SIMD) device based on a CAM core and an array of high speed processors. As an application for the proposed hardware, we present a parallel algorithm to solve a global routing problem in the layout process utilizing the processing capabilities of a rudimentary logic and the selective matching and writing capability of CAMs, along with basic algorithms such a minimum(maximum) search, less(greater) than search and parallel arithmetic. We have focused on the simultaneous minimization of the desity of the channels and the wire length by sedking a less crowded channel with shorter wire distance. We present an efficient mapping technique of the problem into the CAM structure. Experimental results on difficult examples, on randomly generated data, and on benchmark problems from MCNC are included.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.19 no.10
• /
• pp.2043-2052
• /
• 1994

This paper proposes a new parallel ASIC architecture for real-time image processing to reduce inter-processing element (inter-PE) communication overhead, called a Sliding Memory Plane (SliM) Image Processor. The Slim Image Processor consists of $3\times3$ processing elements (PEs) connected by a mesh topology. With easy scalability due to the topology. a set of SliM Image Processors can form a mesh-connected SIMD parallel architecture. called the SliM Array Processor. The idea of sliding means that all pixels are slided into all neighboring PEs without interrupting PEs and without a coprocessor or a DMA controller. Since the inter-PE communication and computation occur simultaneously. the inter-PE communication overhead, significant disadvantage of existing machines greatly diminishes. Two I/O planes provide a buffering capability and reduce the date I/O overhead. In addition, using the by-passing path provides eight-way connectivity even with four links. with these salient features. SliM shows a significant performance improvement. This paper presents architectures of a PE and the SliM Image Processor, and describes the design of an instruction set.

• Journal of the Institute of Convergence Signal Processing
• /
• v.13 no.1
• /
• pp.50-55
• /
• 2012

This paper proposes an optima] many-core processor architecture that meets the requirements of low power and high performance for different ultrasonic image resolutions in hand-held ultrasonic devices. To identify the optimal many-core architecture, seven different PE configurations are simulated for processing ultrasonic images in terms of execution performance and energy consumption. Experimental results indicate that the highest energy efficiencies are achieved at PEs=1,024, 64, and 256 for ultrasonic images at $256{\times}256$, $320{\times}240$, and $800{\times}480$ resolutions, respectively. In addition, the maximum area efficiencies are obtained at PEs=256 (for $256{\times}256$ and $800{\times}480$ image resolutions) and 64 (for $320{\times}240$ image resolution).

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.6
• /
• pp.55-64
• /
• 2017

High-capacity, high-definition image applications need to process considerable amounts of data at high speed. Accordingly, users of these applications demand a high-speed parallel execution system. To increase the speed of a parallel execution system, Park (2004) proposed a technique, called MAMS (Multi-Access Memory System), to access data in several execution units without the conflict of parallel processing memories. Since then, many studies on MAMS have been conducted, furthering the technique to MAMS-PP16 and MAMS-PP64, among others. As a memory architecture for parallel processing, MAMS must be constructed in one chip; therefore, a method to achieve the identical functionality as the existing MAMS while minimizing the architecture needs to be studied. This study proposes a method of miniaturizing the MAMS architecture in which the architectures of the ACR (Address Calculation and Routing) circuit and MMS (Memory Module Selection) circuit, which deliver data in memories to parallel execution units (PEs), do not use the MMS circuit, but are constructed as one shift and conditional statements whose number is the same as that of memory modules inside the ACR circuit. To verify the performance of the realized architecture, the study conducted the processing time of the proposed MAMS-PP64 through an image correlation test, the results of which demonstrated that the ratio of the image correlation from the proposed architecture was improved by 1.05 on average.

• Proceedings of the IEEK Conference
• /
• 2005.11a
• /
• pp.1141-1144
• /
• 2005

일반 컴퓨터에서 중앙처리장치와 메모리 사이의 병목 현상인 "Von Neumann Bottleneck"을 보이는데 본 논문에서는 이러한 문제점을 해소하고 검색위주의 응용분야에서 우수한 성능을 보이는 확장 가능한 범용 Associative Processor(AP) 구조를 제안하였다. 본 연구에서는 Associative computing을 효율적으로 수행할 수 있는 명령어 세트를 제안하였으며 다양하고 대용량 응용분야에도 적용할 수 있도록 구조를 확장 가능하게 설계함으로써 유연한 구조를 갖는다. 12 가지의 명령어가 정의되었으며 프로그램이 효율적으로 수행될 수 있도록 명령어 셋을 구성하고 연속된 명령어를 하나의 명령어로 구현함으로써 처리시간을 단축하였다. 제안된 프로세서는 bit-serial, word-parallel로 동작하며 대용량 병렬 SIMD 구조를 갖는 32 비트 범용 병렬 프로세서로 동작한다. 포괄적인 검증을 위하여 명령어 단위의 검증 뿐 아니라 최대/최소 검색, 이상/이하 검색, 병렬 덧셈 등의 기본적인 병렬 알고리즘을 검증하였으며 알고리즘은 처리 데이터의 개수와는 무관한 상수의 복잡도 O(k)를 갖으며 데이터의 비트 수만큼의 이터레이션을 갖는다.

• Journal of the Korean Institute of Telematics and Electronics A
• /
• v.33A no.10
• /
• pp.186-194
• /
• 1996

The SliM (sliding memory plane) array processor has been proposed to alleviate disadvantages of existing mesh-connected SIMD(single instruction stream- multiple data streams) array processors, such as the inter-PE(processing element) communication overhead, the data I/O overhead and complicated interconnections. This paper presents the deisgn and implementation of SliM image processor ASIC (application specific integrated circuit) chip consisting of mesh connected 5 X 5 PE. The PE architecture implemented here is quite different from the originally proposed PE. We have performed the front-end design, such as VHDL (VHSIC hardware description language)modeling, logic synthesis and simulation, and have doen the back-end design procedure. The SliM ASIC chip used the VTI 0.8$\mu$m standard cell library (v8r4.4) has 55,255 gates and twenty-five 128 X 9 bit SRAM modules. The chip has the 326.71 X 313.24mil$^{2}$ die size and is packed using the 144 pin MQFP. The chip operates perfectly at 25 MHz and gives 625 MIPS. For performance evaluation, we developed parallel algorithms and the performance results showed improvement compared with existing image processors.

• Proceedings of the IEEK Conference
• /
• 2002.06b
• /
• pp.129-132
• /
• 2002

AE64000 is the 64-bit high-performance microprocessor that ADC Co. Ltd. is developing for an embedded environment. It has a 5-stage pipeline and uses Havard architecture with a separated instruction and data caches. It also provides SIMD-like DSP and FP operation by enabling the 8/16/32/64-bit MAC operation on 64-bit registers. AE64000 processor implements the EISC ISA and uses the instruction folding mechanism (Instruction Folding Unit) that effectively deals with LERI instruction in EISC ISA. But this unit makes branch prediction behavior difficult. In this paper, we designs a branch predictor optimized for AE64000 Pipeline and develops a AES4000 simulator that has cycle-level precision to validate the performance of the designed branch predictor. We makes TAC(Target address cache) and BPT(branch prediction table) seperated for effective branch prediction and uses the BPT(removed indexed) that has no address tags.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.10
• /
• pp.1-12
• /
• 2014

This paper implements and improves the performance of high computational subtractive clustering algorithm using a single instruction, multiple data (SIMD) based many-core processor. In addition, this paper implements five different processing element (PE) architectures (PEs=16, 64, 256, 1,024, 4,096) to select an optimal PE architecture for the subtractive clustering algorithm by estimating execution time and energy efficiency. Experimental results using two different medical images and three different resolutions ($128{\times}128$, $256{\times}256$, $512{\times}512$) show that PEs=4,096 achieves the highest performance and energy efficiency for all the cases.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.43 no.2 s.308
• /
• pp.1-11
• /
• 2006

In this paper, we propose a new register file architecture called the Register File Extension for Multi-words or Long-word Operation (RFEMLO) to accelerate both symmetric and asymmetric cryptographic algorithms. Based on the idea that most of cryptographic algorithms heavily use multi-words or long-word operations, RFEMLO allows multiple contiguous registers to be specified as a single operand. Thus, a single instruction can specify a SIMD-style multi-word operation or a long-word operation. RFEMLO can be applied to general purpose processors by adding instruction set for multi-words or long-word operands and functional units for additional instruction set. To evaluate the performance of RFEMLO, we use Simplescalar/ARM 3.0 (with gcc 2.95.2) and run detailed simulations on various symmetric and asymmetric cryptographic algorithms. By applying RFEMLO, we could get maximum 62% and 70% reductions in the total instruction count of symmetric and asymmetric cryptographic algorithms respectively. Also, performance results show that a speedup of 1.4 to 2.6 can be obtained in symmetric cryptographic algorithms and a speedup of 2.5 to 3.3 can be obtained for asymmetric cryptographic algorithms when we apply RFEMLO to a processor with an in-order pipeline. We also found that RFEMLO can effectively improve the performance of these cryptographic algorithms with much less cost compared to issue-width increase available in Superscalar implementations. Moreover, the RFEMLO can also be applied to Superscalar processor, leading to additional 83% and 138% performance gain in symmetric and asymmetric cryptographic algorithms.