• 전기학회논문지
• /
• 제61권10호
• /
• pp.1502-1507
• /
• 2012

In order to overcome the hardware complexity and power consumption problems, recently the multi-core architecture has been prevalent. For hardware simplicity, usually RISC processor is adopted as the unit core processor. However, if the performance of unit core processor is enhanced, the overall performance of the multi-core processor architecture can be further increased. In this paper, out-of-order superscalar processor is utilized for the multi-core processor architecture. Using SPEC 2000 benchmarks as input, the trace-driven simulation has been performed for the out-of-order superscalar cores between 2 and 16 extensively. As a result, the 16-core out-of-order superscalar processor for the window size of 16 resulted in 17.4 times speed up over the single-core out-of-order superscalar processor, and 50 times speed up over the single core RISC processor. When compared for the same number of cores on the average, the multi-core out-of-order superscalar processor performance achieved 3.2 times speed up over the multi-core RISC processor and 1.6 times speed up over the multi-core in-order superscalar processor.

• 한국컴퓨터정보학회논문지
• /
• 제20권9호
• /
• pp.1-10
• /
• 2015

In this paper, we propose a new variable latency L1 data cache architecture for multi-core processors. Our proposed architecture extends the traditional variable latency cache to be geared toward the multi-core processors. We added a specialized data structure for recording the latency of the L1 data cache. Depending on the added latency to the L1 data cache, the value stored to the data structure is determined. It also tracks the remaining cycles of the L1 data cache which notifies data arrival to the reservation station in the core. As in the variable latency cache of the single-core architecture, our proposed architecture flexibly extends the cache access cycles considering process variation. The proposed cache architecture can reduce yield losses incurred by L1 cache access time failures to nearly 0%. Moreover, we quantitatively evaluate performance, power, energy consumption, power-delay product, and energy-delay product when increasing the number of cache access cycles.

• JSTS:Journal of Semiconductor Technology and Science
• /
• 제14권3호
• /
• pp.284-299
• /
• 2014

Coarse-grained reconfigurable architecture (CGRA)-based multi-core architecture aims at achieving high performance by kernel level parallelism (KLP). However, the existing CGRA-based multi-core architectures suffer from much energy and performance bottleneck when trying to exploit the KLP because of poor resource utilization caused by insufficient flexibility. In this work, we propose a new ring-based sharing fabric (RSF) to boost their flexibility level for the efficient resource utilization focusing on the kernel-stream type of the KLP. In addition, based on the RSF, we introduce a novel inter-CGRA reconfiguration technique for the efficient pipelining of kernel-stream on CGRA-based multi-core architectures. Experimental results show that the proposed approaches improve performance by up to 50.62 times and reduce energy by up to 50.16% when compared with the conventional CGRA-based multi-core architectures.

• JSTS:Journal of Semiconductor Technology and Science
• /
• 제15권2호
• /
• pp.307-311
• /
• 2015

In this paper, we propose an efficient fault-recovery technique for CGRA (Coarse-Grained Reconfigurable Architecture) based multi-core architecture. The proposed technique is intra/inter-CGRA co-reconfiguration technique based on a ring-based sharing fabric (RSF) and it enables exploiting the inherent redundancy and reconfigurability of the multi-CGRA for fault-recovery. Experimental results show that the proposed approaches achieve up to 73% fault recoverability when compared with completely connected fabric (CCF).

• 대한전자공학회논문지SD
• /
• 제46권10호
• /
• pp.46-52
• /
• 2009

현재 개발되고 있는 Shader 프로세서는 처리 성능을 높이기 위하여 Multi-Core, Multi-Thread를 채택하고 있다. 또한 Shader 프로세서에서 각 수행 단계별 마다 IP를 따로 구현하지 않고 하나의 Core IP를 다양한 목적으로 사용할 수 있도록 설계하고 있다. 본 논문에서는 이러한 목적에 맞게 Shader-Core를 이용하여 연산이 가능하고, Multi-Core, Multi-Thread 기반에서 픽셀의 병렬처리가 가능하도록 고안된 Vector 기반의 Rasterization알고리즘을 제안한다. 이를 통하여 동일 조건의 기존 알고리즘에 비하여 약 2%의 연산량을 가지면서 각 픽셀이 독립적으로 연산이 가능하도록 하였다.

• 한국인터넷방송통신학회논문지
• /
• 제12권5호
• /
• pp.123-128
• /
• 2012

최근에 이르러 디지털 시스템의 성능을 극대화하기 위하여, 멀티코어 프로세서가 상용화 되어 널리 이용되고 있다. 이러한 멀티코어 프로세서를 구성하는 단위 코어의 성능을 높이면, 적은 개수의 코어를 가지고 시스템의 성능을 크게 향상시킬 수가 있다. 본 논문에서는 순차실행 방식의 수퍼스칼라를 단위 코어로 하는 멀티코어 프로세서 아키텍쳐를 제안하였다. 그리고, 윈도우 크기가 4에서 16이고 2-코어에서 16-코어로 구성되는 멀티코어 수퍼스칼라 프로세서에 대하여, SPEC 2000 벤치마크를 입력으로 하는 광범위한 모의실험을 수행하였다. 모의실험 결과, 윈도우의 크기가 16일 때 16-코어 수퍼스칼라 프로세서는 1-코어 수퍼스칼라 프로세서보다 8.4배의 성능 향상을 가져왔다. 또한, 같은 코어 개수를 가진 멀티 코어 수퍼스칼라 프로세서의 성능이 멀티코어 RISC 프로세서의 성능의 2 배를 기록하였다.

• Journal of applied mathematics & informatics
• /
• 제41권6호
• /
• pp.1317-1326
• /
• 2023

Today's computers, desktops and laptops were build with multi-core architecture. Developing and running serial programs in this multi-core architecture fritters away the resources and time. Parallel programming is the only solution for proper utilization of resources available in the modern computers. The major challenge in the multi-core environment is the designing of parallel algorithm and performance analysis. This paper describes the design and performance analysis of parallel algorithm by taking the Knight Tour problem as an example using OpenMP interface. Comparison has been made with performance of serial and parallel algorithm. The comparison shows that the proposed parallel algorithm achieves good performance compared to serial algorithm.

• JSTS:Journal of Semiconductor Technology and Science
• /
• 제16권6호
• /
• pp.736-744
• /
• 2016

Network on chip (NoC) is an emerging technology in the field of multi core interconnection architecture. The routers plays an essential components of Network on chip and responsible for packet delivery by selecting shortest path between source and destination. State-of-the-art NoC designs used routing table to find the shortest path and supports four ports for packet transfer, which consume high power consumption and degrades the system performance. In this paper, the multi port multi core router architecture is proposed to reduce the power consumption and increasing the throughput of the system. The shared buffer is employed between the multi ports of the router architecture. The performance of the proposed router is analyzed in terms of power and current consumption with conventional methods. The proposed system uses Modelsim software for simulation purposes and Xilinx Project Navigator for synthesis purposes. The proposed architecture consumes 31 mW on CPLD XC2C64A processor.

• 전기학회논문지
• /
• 제62권2호
• /
• pp.252-256
• /
• 2013

In order to overcome the complexity and performance limit problems of superscalar processors, the multi-core architecture has been prevalent recently. Usually, the number of cores mostly used for the multi-core processor architecture ranges from 2 to 16. However in the near future, more than 32-cores are likely to be utilized, which is called as many-core processor architecture. Using SPEC 2000 benchmarks as input, the trace-driven simulation has been performed for the 32 to 1024 many-core architectures extensively. For 1024-cores, the average performance scores 15.7 IPC, but the performance increase rate is saturated.

• JSTS:Journal of Semiconductor Technology and Science
• /
• 제15권6호
• /
• pp.615-628
• /
• 2015

CGRA (Coarse-Grained Reconfigurable Architecture) based multi-core architecture can be considered as a suitable solution for the fault-tolerant computing. However, there have been a few research projects based on fault-tolerant CGRA without exploiting the strengths of CGRA as well as their works are limited to single CGRA. Therefore, in this paper, we propose two approaches to enable exploiting the inherent redundancy and reconfigurability of the multi-CGRA for fault-recovery. One is a resilient inter-CGRA fabric that is ring-based sharing fabric (RSF) with minimal interconnection overhead. Another is a novel intra/inter-CGRA reconfiguration technique on RSF for maximizing utilization of the resources when faults occur. Experimental results show that the proposed approaches achieve up to 94% faulty recoverability with reducing area/delay/power by up to 15%/28.6%/31% when compared with completely connected fabric (CCF).