• 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.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.44 no.2
• /
• pp.61-71
• /
• 2007

The instruction level parallelism, which has been used to improve the performance of processors, expose its limit. The change of a control flow by a branch miss prediction is one of the obstacles that restrict the instruction level parallelism. The single chip multiprocessors have been developed to utilize the thread level parallelism. However, we could not use the maximum performance of the single chip multiprocessor in case of executing the coded programs without considering the multi-thread. In order to overcome the two performance degradation factors, in this paper, we suggest the concurrent branch execution method that applies to the multi-path execution method at a single chip multiprocessor. We executes all two flows of the conditional branch using the idle core processor. Through this, we can improve the processor's efficiency with blocking the control flow termination by the branch instruction and reducing the idle time. We analyze the effects of concurrent branch execution proposed in this paper through the simulation. As a result of that, concurrent branch execution reduces about 20% of idle time and improves the maximum 10% of the branch prediction accuracy. We show that our scheme improves the overall performance of maximum 39% compared to the normal single chip multiprocessor and maximum 27% compared to the superscalar processor.

• Journal of the Korea Computer Industry Society
• /
• v.7 no.3
• /
• pp.171-178
• /
• 2006

Value prediction of instruction issue width in superscalar processor is a technique to obtain performance gains by supplying earlier source values of its data dependent instructions using predicted value of a instruction. In this paper, the mean performance improvement by predictor as well as prediction accuracy and prediction rate are moaned and assessed by comparison and analysis of value predictor that instruction issue width(4,8,16) in parallel and run by predicting value, which is for performance improvements of ILP[4]. The experiment result show the superiority hight performance of 8-issue.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.10c
• /
• pp.688-690
• /
• 2002

고성능 슈퍼스칼라 프로세서에서는 명령어 수준 병렬성(Instruction Level Parallelism, ILP)의 장애인 명령어간의 종속 관계 중 데이터 종속관계를 극복하기 위해 값 예측기를 이용하여 모험적으로 명령어들을 실행한다. 값 예측 시에 필요한 테이블 참조와 값 예측 실패 시 실행되는 잘못된 명령어의 실행은 프로세서의 부가적인 전력 소모를 요구한다. 본 논문에서는 값 예측기와 Cai-Lim의 전력모델을 슈퍼스칼라 프로세서 사이클 수준 시뮬레이터인 SimpleScalar 3.0 툴셋에 삽입하여 전력 소모량을 측정하고 분석한다.

• International Journal of Control, Automation, and Systems
• /
• v.1 no.3
• /
• pp.339-350
• /
• 2003

In this paper, we propose a simultaneous multithreading (SMT) architecture that improves instruction throughput by exploiting instruction level parallelism (ILP) and thread level parallelism (TLP). The proposed architecture issues and completes instructions belonging to the same thread in exact program order. The issue and completion policy greatly reduces the design complexity and hardware cost of our architecture, compared with others that employ out-of-order issue and completion. On the other hand, when the instructions belong to different threads, the issue and completion orders for those instructions may not necessarily be identical to the fetch order. The processor issues instructions simultaneously from multiple threads to functional units by exploiting ILP and TLP, and by dynamic resource sharing. That parallel execution notably improves performance and resource utilization with minimal additional hardware cost over the conventional superscalar processors. This paper proposes an SMT architecture with grouping as well as one without grouping. Without grouping, all threads dynamically and flexibly share most resources. On the other hand, in the SMT architecture with grouping, in which resources and threads are divided into several groups for design simplification, resources are shared only among threads belonging to the same group as those resources. Simulation results show that our processors with four and eight threads improve performance by three or more times over the conventional superscalar processor with comparable execution resources and policies, and that reasonable grouping reduces the design complexity of SMT processors with little negative effect on performance.

• Journal of KIISE:Computer Systems and Theory
• /
• v.29 no.7
• /
• pp.401-410
• /
• 2002

Control independence has been put forward as a new significant source of instruction-level parallelism for superscalar processors. In branch prediction mechanisms, all instructions after a mispredicted branch have to be squashed and then instructions of a correct path have to be re-fetched and re-executed. This paper presents a new branch misprediction recovery mechanism to reduce the number of instructions squashed on a misprediction. Detection of control independent instructions is accomplished with the help of the static method using a profiling and the dynamic method using a control flow of program sequences. We show that the suggested branch misprediction recovery mechanism improves the performance by 2~7% on a 4-issue processor, by 4~15% on an 8-issue processor and by 8~28% on a 16-issue processor.

• Journal of Practical Agriculture & Fisheries Research
• /
• v.14 no.1
• /
• pp.3-22
• /
• 2012

Control independence has been put forward as a significant new source of instruction-level parallelism for superscalar processors. In branch prediction mechanisms, all instructions after a mispredicted branch have to be squashed and then instructions of a correct path have to be re-fetched and re-executed. This paper presents a new branch misprediction recovery mechanism to reduce the number of instructions squashed on a misprediction. Detection of control independent instructions is accomplished with the help of the static method using a profiling and the dynamic method using a control flow of program sequences. We show that the suggested branch misprediction recovery mechanism improves the performance by 2~7% on a 4-issue processor, by 4~15% on an 8-issue processor and by 8~28% on a 16-issue processor.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.2
• /
• pp.899-902
• /
• 2005

Pipeline hazard due to branch instructions is the major factor of the degradation on the performance of microprocessors. Branch target buffer predicts whether a branch will be taken or not and supplies the address of the next instruction on the basis of that prediction. If the branch target buffer predicts correctly, the instruction flow will not be stalled. This leads to the better performance of microprocessor. In this paper, the architecture of a tag memory that branch target buffer and TLB can share is presented. Because the two tag memories used for branch target buffer and TLB each is replaced by single shared tag memory, we can expect the smaller ship size and the faster prediction. This hared tag architecture is more advantageous for the microprocessors that uses more bits of address and exploits much more instruction level parallelism.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.2
• /
• pp.497-511
• /
• 1999

Recently, many parallel processing technologies were developed, ILP(Instruction level Parallelism) processor's performance have been growed very rapidly. especially, EPIC(Explicitly Parallel Instruction computing) architectures attempt to enhance the performance in the predicated execution and speculative execution with the hardware. In this paper to improve the code scheduling possibility by applying to the characteristics of EPIC architectures, a new register allocation algorithm is proposed. And we proves that proposed register allocation algorithm is more efficient scheme than the conventional scheme when predicated execution is applied to our scheme by experiments. In experimental results, it shows much more performance enhancement, about 19% in proposed scheme than the conventional scheme. So, our scheme is verified that it is an effective register allocation method.

• Journal of KIISE:Computer Systems and Theory
• /
• v.30 no.10
• /
• pp.569-578
• /
• 2003

Data dependencies are one of major hurdles to limit ILP(Instruction Level Parallelism), so several related works have suggested that the limit imposed by data dependencies can be overcome to some extent with use of the data value prediction. Hybrid value predictor can obtain the high prediction accuracy using advantages of various predictors, but it has a defect that same instruction has overlapping entries in all predictor. In this paper, we propose a new hybrid value predictor which achieves high performance by using the information of static and dynamic classification. The proposed predictor can enhance the prediction accuracy and efficiently decrease the prediction table size of predictor, because it allocates each instruction into single best-suited predictor during the fetch stage by using the information of static classification. Also, it can enhance the prediction accuracy because it selects a best- suited prediction method for the “Unknown”pattern instructions by using the dynamic classification mechanism. Simulation results based on the SimpleScalar/PISA tool set and the SPECint95 benchmarks show the average correct prediction rate of 85.1% by using the static classification mechanism. Also, we achieve the average correction prediction rate of 87.6% by using static and dynamic classification mechanism.