• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.62 no.2
• /
• 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.

• Journal of KIISE:Computer Systems and Theory
• /
• v.33 no.7
• /
• pp.429-439
• /
• 2006

A desktop grid, which is a computing grid composed of idle computing resources in a large network of desktop computers, is a promising platform for compute-intensive distributed computing applications. However, due to reliability and unpredictability of computing resources, effective scheduling of parallel computing applications on such a platform is a difficult problem. This paper proposes a new scheduling method aimed at reducing the total execution time of a parallel application on a desktop grid. The proposed method is based on utilizing the histories of execution behavior of individual computing nodes in the scheduling algorithm. In order to test out the feasibility of this idea, execution trace data were collected from a set of 40 desktop workstations over a period of seven weeks. Then, based on this data, the execution of several representative parallel applications were simulated using trace-driven simulation. The simulation results showed that the proposed method improves the execution time of the target applications significantly when compared to previous desktop grid scheduling methods. In addition, there were fewer instances of application suspension and failure.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.58 no.7
• /
• pp.1443-1449
• /
• 2009

This paper presents a profiling model of a wide-window superscalar microprocessor using multiple branch prediction. The key idea is to apply statistical profiling technique to the superscalar microprocessor with a wide instruction window and a multiple branch predictor. The statistical profiling data are used to obtain a synthetical instruction trace, and the consecutive multiple branch prediction rates are utilized for running trace-driven simulation on the synthesized instruction trace. We describe our design and evaluate it with the SPEC 2000 integer benchmarks. Our performance model can achieve accuracy of 8.5 % on the average.

• Journal of Korea Game Society
• /
• v.6 no.4
• /
• pp.63-70
• /
• 2006

This paper studied various low power structures of texture caches for mobile 3D graphics accelerator to reduce the memory latency of texture data. Also the paper designed the texture cache with the variable threshold values of power mode transition according to the filtering algorithms. In the trace driven simulation, we compared the performance of those structures using Quake game engine as the benchmark. Also the algorithm was proposed and verified by the simulation, which has variable threshold values of power mode transitions according to the selected texture filtering method.

• The Transactions of the Korea Information Processing Society
• /
• v.5 no.10
• /
• pp.2676-2685
• /
• 1998

In order to improve the branch prediction accuracy and to reduce the BTB miss rate, this paper proposes a two-level BTB structure that adds small-sized victim BTB to the convetional BTB. With small cost, two-level BTB can reduce the BTB miss rate as well as improve the prediction accuracy of the hybrid branch prediction strategy which combines dynamic prediction and static prediction. Through the trace-driven simulation of four bechmark programs, the performance improvement by the proposed two-level BTB structure is analysed and validated. Our proposed BTB structure can improve the BTB miss rate by 26.5% and the misprediction rate by 26.75%

• The Transactions of the Korea Information Processing Society
• /
• v.5 no.6
• /
• pp.1652-1659
• /
• 1998

To provide performance gains by reducing the operand referencing latency and data cache bandwidth requirements, we present an operand reference prediction cache (ORPC) which predicts operand value and address translation during the instruction fetch stage. The prediction is verified in the early stage, and thus it minimizes the performance penalty caused by the misprediction. Through the trace-driven simulation of six benchmark programs, the performance improvement by proposed three aRPC stmctures (OfiPC1, OfiPC2. ORPC3)is analysed and validated.

• Proceedings of the Korean Information Science Society Conference
• /
• 1999.10c
• /
• pp.24-26
• /
• 1999

본 논문에서는 주어진 윈도우에 대하여 수퍼스칼라 프로세서의 하드웨어를 구성하는 기본 요소인 인출율과 연산 유닛의 개수로 표현되는 성능 예측 모델을 제시하였다. 이때, 수퍼스칼라 프로세서에서 실행되는 벤치마크 프로그램은 매 싸이클당 각 명령어 개수가 시행되는 확률과 분기 예측 정확도에 의하여 특성화된다. 초기의 실험으로 각종 파라미터를 획득한 후에는 다양한 연산유닛과 인출율을 갖는 수퍼스칼라 프로세서의 성능을 본 논문에서 제안하는 모델에 의하여 간단하게 구할 수 있다. 명령어 자취 모의실험(trace-driven simulation)으로 측정한 성능과 본 논문에서 제안하는 성능 예측 모델에 의한 성능을 비교한 결과, 3.8%의 평균오차를 기록하였다.

• Proceedings of the KIEE Conference
• /
• 1987.07b
• /
• pp.1577-1580
• /
• 1987

This paper proposes a gate and functional level logic simulator which can be run on XENIX O.S. The simulator has hierarchical structure including Hardware Description Language compiler, Waveform Description Language compiler, and Simulation Command Language compiler. The Hardware Description Language compiler generates data structure composed of gate structure, wire structure, condition structure, and event structure. Simulation algorithm is composed of selective trace and event-driven methods. To improve simulation speed, Cross Referenced Linked List Structure ia defined in building the data structure of circuits.

• Journal of the Korea Society for Simulation
• /
• v.8 no.3
• /
• pp.17-28
• /
• 1999

Recently studies have shown that conditional branches can be accurately predicted by recording the path leading up to the branch. But path predictors are more complex and uncompatible with existing pattern branch predictors. In order to solve these problems, we propose a simple path branch predictor(SPBP) that hashes together two most recent branch instruction addresses. In addition, we propose a pattern/path hybrid branch predictor composed of the SPBP and existing pattern branch predictors. Through the trace-driven simulation of six benchmark programs, the performance improvement by the proposed pattern/path hybrid branch prediction is analysed and validated. The proposed predictor can improve the prediction accuracy from 94.21% to 95.03%.

• Journal of KIISE:Computer Systems and Theory
• /
• v.33 no.5
• /
• pp.297-305
• /
• 2006

Trace-driven simulation is widely used for measuring the performance of a microprocessor in its initial design phase. However, since it requires much time and disk space, the statistical simulation has been studied as an alternative method. In this paper, statistical simulations are performed for a high performance superscalar microprocessor with a perceptron-based multiple branch predictor. For the verification, various hardware configurations are simulated using SPEC2000 benchmarks programs as input. As a result, we show that the statistical simulation is quite accurate and time saving for the evaluation of microprocessor architectures with multiple branch prediction.