• International Journal of Advanced Culture Technology
• /
• v.9 no.4
• /
• pp.282-287
• /
• 2021

A multicore system must be able to take full advantage of the program's instruction and data parallelism. This study introduces the data replication technique as a support technique to maximize the program's instruction and data parallelism. Instruction level parallelism can be limited by data dependency. In this case, if data is replicated to each processor core and used, instruction level parallelism can be used to the maximum. The technique proposed in this study can maximize the performance improvement effect when applied to scientific applications such as matrix multiplication operation.

• Journal of Korea Game Society
• /
• v.8 no.2
• /
• pp.69-76
• /
• 2008

In this paper, we present the architecture of graphics processor and its instruction format for the mobile device. In addition, we introduce tile shader data structure for the on/off-line compilation based on the OpenGL ES 2.0 and a new optimization method based on the ILP(Instruction-Level Parallelism). This paper shows where a processor with the sane core clock is being used, the shader instruction resulted from the compile structure and method in this paper is approximately 1.5 to 2 times faster than a code based on the single instruction.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.2 s.34
• /
• pp.87-95
• /
• 2005

value prediction in high performance micro processors is a technique that exploits Instruction Level Parallelism(ILP) by predicting the outcome of an instruction and by breaking and executing true data dependences. In this paper, the mean Performance improvements by predictor according to a point of time for update of each table as well as prediction accuracy and Prediction rate are measured and assessed by comparison and analysis of value predictor that issues in parallel and run by predicting value, which is for Performance improvements of ILP in micro Processor. For the verification of its validity the SPECint95 benchmark through the simulation is compared by making use of execution driven system.

• Proceedings of the IEEK Conference
• /
• 2003.07d
• /
• pp.1355-1358
• /
• 2003

This paper presents performance analysis of the embedded application, called EEMBC consisting of 5 categories and total 34 applications. We measured various performance metrics, such as code sizes, TLP(Thread Level Parallelism) using OpenMP API and ILP(Instruction Level Parallelism) on ARM-modeled SimpleScalar in detail. We show that the embedded applications have the similar characteristics as integer applications to deliver low ILP and TLP in our environment. They have many small loops, which result in large instruction overhead in TLP and loop control overhead in ILP.

• Journal of the Korean Society of Industry Convergence
• /
• v.20 no.1
• /
• pp.1-7
• /
• 2017

Most conventional processors execute program instructions in a sequential manner. On the other hand, VLIW processor can execute multiple instructions at the same time. It exploits instruction level parallelism to improve system performance. To that end, program code should be rearranged to VLIW instruction format by a compiler. The compiler determine an optimal execution order of instructions of a program code. This instruction ordering is also called instruction scheduling. The scheduling is an algorithm that decides the execution order for instruction codes in loop parts of a program so that the instruction level parallelism can be maximized. In this research, we apply an existing scheduling algorithm to a VLIW FCC and describe analysis results to further improve its performance. And, we present a solution to solve some limitation of the existing scheduling technique. By using our solution, FCC's performance can be improved upto 32% compared to the existing scheduling only setting.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.4
• /
• pp.1-9
• /
• 2019

LRR(Loose Round Robin) warp scheduling policy for GPU architecture results in high warp-level parallelism and balanced loads across multiple warps. However, traditional LRR policy makes multiple warps execute long latency operations at the same time. In cases that no more warps to be issued under long latency, the throughput of GPUs may be degraded significantly. In this paper, we propose a new warp scheduling policy which utilizes latency hiding, leading to more utilized memory resources in high performance GPUs. The proposed warp scheduler prioritizes memory instruction based on GTO(Greedy Then Oldest) policy in order to provide reduced memory stalls. When no warps can execute memory instruction any more, the warp scheduler selects a warp for computation instruction by round robin manner. Furthermore, our proposed technique achieves high performance by using additional information about recently committed warps. According to our experimental results, our proposed technique improves GPU performance by 12.7% and 5.6% over LRR and GTO on average, respectively.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.11 no.3
• /
• pp.31-43
• /
• 2015

In this paper, we discuss a code generation technique for custom transport triggered architecture (TTA) from a high-level language structure. This methodology is implemented by using TTA-based Co-design Environment (TCE) tool. The results show how the scheduler exploits instruction level parallelism in the custom target architecture and source program. Thus, the scheduler generates parallel TTA instructions using lower cycle counts than the sequential scheduling algorithm. Moreover, we take Tensilica tool to make a comparison with TCE. Because of the efficiency of TTA, TCE takes less execution cycles compared to Tensilica configurations. Finally, this paper shows that it requires only 7 cycles to generate the parallel TTA instruction set for implementing Cyclic Redundancy Check (CRC) applications as an input design, and presents the code generation technique to move complexity from the processor software to hardware architecture. This method can be applicable lots of channel Codecs like CRC and source Codecs like High Efficiency Video Coding (HEVC).

• Journal of KIISE:Computer Systems and Theory
• /
• v.27 no.8
• /
• pp.741-751
• /
• 2000

To achieve high performance by exploiting instruction level parallelism aggressively in superscalar processors, it is necessary to overcome the limitation imposed by control dependences and data dependences which prevent instructions from executing parallel. Value prediction is a technique that breaks data dependences by predicting the outcome of an instruction and executes speculatively its data dependent instruction based on the predicted outcome. In this paper, a hybrid value prediction scheme with dynamic classification mechanism is proposed. We design a hybrid predictor by combining the last predictor, a stride predictor and a two-level predictor. The choice of a predictor for each instruction is determined by a dynamic classification mechanism. This makes each predictor utilized more efficiently than the hybrid predictor without dynamic classification mechanism. To show performance improvements of our scheme, we simulate the SPECint95 benchmark set by using execution-driven simulator. The results show that our scheme effect reduce of 45% hardware cost and 16% prediction accuracy improvements comparing with the conventional hybrid prediction scheme and two-level value prediction scheme.

• The Transactions of the Korea Information Processing Society
• /
• v.5 no.5
• /
• pp.1172-1184
• /
• 1998

ILP(Instruction Level Parallelism) processors use code reordering algorithms to expose parallelism in a given sequential program. When applied to a loop, this algorithm produces a software-pipelined loop. In a software-pipelined loop, each iteration contains a sequence of parallel instructions that are composed of data-independent instructions collected across from several iterations. For vector loops, however the software pipelining technique can not expose the maximum parallelism because it schedules the program based only on data-dependencies. This paper proposes to schedule differently for vector loops. We develop an algorithm to detect vector loops at object code level and suggest a new vector scheduling algorithm for them. Our vector scheduling improves the performance because it can schedule not only based on data-dependencies but on loop structure or iteration conditions at the object code level. We compare the resulting schedules with those by software-pipelining techniques in the aspect of performance.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.723-724
• /
• 2006

Exploiting the instruction level parallelism encountered with the limit. Single chip multiprocessor was introduced to overcome the limit of traditional processor using the instruction level parallelism. Also, a branch miss prediction is one of the causes that reduce the processor performance. In order to overcome the problems, in this paper, we make single chip multiprocessor having the idle core execute the two control flow of conditional branch. This scheme is a kind of multi-path execution technique based on single chip multiprocessor architecture.