• Title/Summary/Keyword: Speculative

Search Result 141, Processing Time 0.025 seconds

A Hybrid Value Predictor using Speculative Update of the Predictor Table and Static Classification for the Pattern of Executed Instructions in Superscalar Processors (슈퍼스칼라 프로세서에서 예상 테이블의 모험적 갱신과 명령어 실행 유형의 정적 분류를 이용한 혼합형 결과값 예측기)

  • Park, Hong-Jun;Jo, Young-Il
    • Journal of KIISE:Computing Practices and Letters
    • /
    • v.8 no.1
    • /
    • pp.107-115
    • /
    • 2002
  • We propose a new hybrid value predictor which achieves high performance by combining several predictors. Because the proposed hybrid value predictor can update the prediction table speculatively, it efficiently reduces the number of mispredicted instructions due to stale data. Also, the proposed predictor can enhance the prediction accuracy and efficiently decrease the hardware cost of predictor, because it allocates instructions into the best-suited predictor during instruction fetch stage by using the information of static classification which is obtained from the profile-based compiler implementation. For the 16-issue superscalar processors, simulation results based on the SimpleScalar/PISA tool set show that we achieve the average prediction rates of 73% by using speculative update and the average prediction rates of 88% by adding static classification for the SPECint95 benchmark programs.

Sepculative Updates of a Stride Value Predictor in Wide-Issue Processors (와이드 이슈 프로세서를 위한 스트라이드 값 예측기의 모험적 갱신)

  • Jeon, Byeong-Chan;Lee, Sang-Jeong
    • Journal of KIISE:Computer Systems and Theory
    • /
    • v.28 no.11
    • /
    • pp.601-612
    • /
    • 2001
  • In superscalar processors, value prediction is a technique that breaks true data dependences by predicting the outcome of an instruction in order to exploit instruction level parallelism(ILP). A value predictor looks up the prediction table for the prediction value of an instruction in the instruction fetch stage, and updates with the prediction result and the resolved value after the execution of the instruction for the next prediction. However, as the instruction fetch and issue rates are increased, the same instruction is likely to fetch again before is has been updated in the predictor. Hence, the predictor looks up the stale value in the table and this mostly will cause incorrect value predictions. In this paper, a stride value predictor with the capability of speculative updates, which can update the prediction table speculatively without waiting until the instruction has been completed, is proposed. Also, the performance of the scheme is examined using Simplescalar simulator for SPECint95 benchmarks in which our value predictor is added.

  • PDF

A study on the application of legal design methodology for commercialization of security tokens

  • Sangyub Han;Hokyoung Ryu
    • Journal of the Korea Society of Computer and Information
    • /
    • v.29 no.7
    • /
    • pp.117-128
    • /
    • 2024
  • In this paper, we propose a process for deriving priority tasks using the legal design technique in a situation where there is high uncertainty in the market and legal system regarding the commercialization of security tokens based on blockchain and distributed ledger technology. To issue and distribute securities tokens, we conducted a legal design workshop with participants who applied for innovative financial services (financial regulatory sandbox). During the workshop, participants harmonized their interests and deliberated on readiness, considering both legal and technical factors. The aim was to ascertain the feasibility of identifying prioritized objectives for future endeavors. The legal design technique facilitates consensus-building among stakeholders in an uncertain environment by confirming and adjusting differing perspectives and disagreements based on mutual understanding. The key stages include the empathetic process called "Family Therapy," the "N whys" for problem definition, and the speculative scenario design for problem-solving. This approach distinguishes itself from user-centered design thinking. Given the diverse stakeholders involved, effective facilitation by the facilitator is crucial during the legal design workshop preparation and execution.

An Experimental Approach to Uncanny Valley Hypothesis (Uncanny Valley 가설에 대한 실험적 접근)

  • Jang, Phil-Sik
    • Journal of the Ergonomics Society of Korea
    • /
    • v.26 no.1
    • /
    • pp.47-53
    • /
    • 2007
  • The uncanny valley is a hypothesis about robotics concerning the emotional response of humans to robots and other non-human entities. Although it stands today as one of the robots and synthetic characters, the uncanny valley was speculative and few studies have been performed to test the theory. In two experiments, a total of 183 participants were employed to explore this hypothesis. The results of experiment 1 indicate that the perceived human likeness of a robot is not a key factor causing uncanny valley. And the results of experiments 2 suggest that even if the appearance and motion of a robot become fully human, the emotional response of humans could not reach human-human empathy levels.

Recovery Modules for Speculative Update Branch History (분기 정보의 투기적 사용에 대한 효율적인 복구 기법)

  • Kwak Jong Wook;Kim Ju-Hwan;Jhang Seong Tae;Jhon Chu Shik
    • Proceedings of the Korean Information Science Society Conference
    • /
    • 2005.11a
    • /
    • pp.766-768
    • /
    • 2005
  • 분기 영령어의 예측 정확도는 시스템 전체 성능에 중대한 영향을 미친다. 여러 분기 예측 방식 가운데 하나인 "분기 정보의 투기적 사용" 은 분기 명령어의 가장 최근 기록을 일관되게 사용할 수 있도록 도와줌으로 해서 분기 예측의 정확도 향상에 크게 기여한다. 하지만 이와 같은 기법은 미완료 분기에 대한 히스토리를 투기적으로 사용하는 방식이다. 따라서 사용되는 정보가 올바르지 못할 수 있으며, 이런 경우 적절한 복구 기법을 필요로 한다. 본 논문에서는 분기 정보의 투기적 사용에 대한 필요성과 효율적인 복구 기법을 제안한다. 제안된 기법은 이전 연구와 비교하여 상당한 하드웨어 요구량의 감소를 가져왔으며, 또한 프로그램 수행의 정확성을 해치지 않으면서 최대 $3.3\%$의 성능향상을 보였다.

  • PDF

Design of Accurate and Efficient Indirect Branch Predictor (정확하고 효율적인 간접 분기 예측기 설계)

  • Paik, Kyoung-Ho;Kim, Eun-Sung
    • Proceedings of the IEEK Conference
    • /
    • 2005.11a
    • /
    • pp.1083-1086
    • /
    • 2005
  • Modern superscalar processors exploit Instruction Level Parallelism to achieve high performance by speculative techniques such as branch prediction. The indirect branch target prediction is very difficult compared to the prediction of direct branch target and branch direction, since it has dynamically polymorphic target. We present a accurate and hardware-efficient indirect branch target predictor. It can reduce the tags which has to be stored in the Indirect Branch Target Cache without a sacrifice of the prediction accuracy. We implement the proposed scheme on SimpleScalar and show the efficiency running SPEC95 benchmarks.

  • PDF

Polyclonal gammopathy related to renal bleeding in a peritoneal dialysis patient

  • Cho, Eun-Mi;Moon, Hye-Hyun;Hwang, Young-Ju;Lee, Seung-Jin;Ko, Cheol Woo;Cho, Min Hyun
    • Clinical and Experimental Pediatrics
    • /
    • v.56 no.7
    • /
    • pp.304-307
    • /
    • 2013
  • Polyclonal gammopathy represents the diffuse activation of B cells and is usually related to inflammation or immune-related diseases. However, the mechanisms leading to polyclonal gammopathy are essentially speculative. Generally, infectious, inflammatory, or various other reactive processes may be indicated by the presence of a broad-based peak or band in the gamma region on serum protein electrophoresis results. A 15-year-old girl, who had been receiving peritoneal dialysis, presented with polyclonal gammopathy and massive gross hematuria. Renal artery embolization was performed, after which the continuous bleeding subsided and albumin-globulin dissociation resolved. This is a rare case of polyclonal gammopathy related to renal bleeding.

An Asynchronous Multiplier Design of Mobile MPEG Application (휴대용 MPEG 응용기기를 위한 비동기식 곱셈기 설계)

  • 나윤석;김견수;홍유표;황인석
    • Proceedings of the Korean Information Science Society Conference
    • /
    • 2001.10c
    • /
    • pp.37-39
    • /
    • 2001
  • 본 논문은 여러 가지 데이터 압축 표준에서 채택하고 있는 이차원 이산 여현 변환과 그 역 변환 (DCT/IDCT)를 위한 효율적인 비동기식 행렬 벡터 곱셈기를 설계하였다. 본 논문에서 제안되어진 곱셈기는 일반적으로 DCT/IDCT의 입력 데이터가 대부분 zero입력이거나 또는 작은 비트수로 표현 가능하다는 점을 이용하여 저전력 고성능 동작을 구현할 수 있도록 설계하였다. 비동기식 설계 방식을 채택하여 Zero입력일 경우 곱셈과정을 생략하고, 정적 회로에 기초한 특정 계산 완료 인지 방식(Speculative Completion Sensing)와 비트 분할된 곱셈기를 이용하여 입력 비트 슬라이스에 대해 동적으로 회로의 계산부분을 활성화/비활성화를 동작을 할 수 있도록 설계되어졌다.

  • PDF

An Enhanced MapReduce Scheduling Scheme Considering Node Load in Distributed Environments (분산 환경에서 노드 부하를 고려한 향상된 맵리듀스 스케쥴링 기법)

  • Hwang, Jaemin;Oh, Hyunkyo;Kim, Cheonjung;Lim, Jongtae;Bok, Kyoungsoo;Yoo, Jaesoo
    • Proceedings of the Korea Contents Association Conference
    • /
    • 2014.11a
    • /
    • pp.11-12
    • /
    • 2014
  • 데드라인을 고려한 스케쥴러는 데드라인 내에 잡을 완료시키기 위해 노드의 실시간 I/O 부하, 데이터 지역성 등을 이용한다. 하지만 데드라인을 만족시키기 위한 기법이 오히려 노드부하를 야기하는 현상이 나타난다. 본 논문에서는 노드의 부하에 따라 맵리듀스 처리 성능이 저하되는 문제점을 해결하기 위해 새로운 스케줄링 기법을 제안한다. 제안하는 스케줄링 기법은 우선 순위에 의해 중지되는 작업의 발생을 감소시키기 위해 동일한 작업을 중복적으로 수행시키는 사행 작업(speculative task)를 처리한다. 맵리듀스 작업의 지연이나 취소를 방지시키기 위해 핫 데이터 청크를 성능이 우수한 노드에 복제한다.

  • PDF

Comprehensive Measures in Real Estate Policy for Housing Market Stabilization (주택시장 안정화를 위한 부동산정책 방향)

  • Lee sun
    • Journal of the Korean Professional Engineers Association
    • /
    • v.38 no.4
    • /
    • pp.7-9
    • /
    • 2005
  • The recent speculation fever in Kangnam and its southern vicnity of Seoul resulted in surging apartment prices. The government is determined to employ more effective anti-speculation policy measures to control the property speculative demand. The Government plans to implement support measures to discourage people from owning multiple homes by reinforcing tax measures. To meet the increasing demand for more large-sized apartments in Seoul, the Government may allow to build more large sized units. By the end of August, 'a comprehensive package tool of real estate policy measures' ,as a real estate controlling guidelines, is scheduled to be presented by the Government. We hope that the package tool will stabilize housing market more effectively and enhance the national economy.

  • PDF