1997 Fiscal Year Final Research Report Summary
Parallelising Compiler for a Declarative Language
| Project/Area Number |
07458062
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
計算機科学
|
|---|
| Research Institution | KYUSYU UNIVERSITY |
|---|
Principal Investigator |
AMAMIYA Makoto KYUSYU UNIVERSITY Graduate School of Information Science & Electrical Engineering Professor, 大学院・システム情報科学研究科, 教授 (90202697)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
TSURUTA Naoyuki KYUSYU UNIVERSITY Graduate School of Information Science & Electrical Engineerin, 大学院・システム情報科学研究科, 助手 (60227478)
MINE Tsunenori KYUSYU UNIVERSITY Graduate School of Information Science & Electrical Engineerin, 大学院・システム情報科学研究科, 助教授 (30243851)
MURAKAMI Kazuaki KYUSYU UNIVERSITY Graduate School of Information Science & Electrical Engineerin, 大学院・システム情報科学研究科, 助教授 (10200263)
TANIGUCHI Hideo KYUSYU UNIVERSITY Graduate School of Information Science & Electrical Engineerin, 大学院・システム情報科学研究科, 助教授 (70253507)
TANIGUCHI Rinichro KYUSYU UNIVERSITY Graduate School of Information Science & Electrical Engineerin, 大学院・システム情報科学研究科, 教授 (20136550)
|
|---|
| Project Period (FY) |
1995 – 1997
|
| Keywords | Declarative Parallel Language / Prallel Processing / Fine-grain Multi-threading / Parallelizing Compiler / Dataflow |
|---|
| Research Abstract |
We have implemented a dataflow declarative language on stock (non-dataflow) machines.
・Practical Compiler
The compiler has two phases : machine-independent phase and machine independent phase. The former generates a fine-grain virtual machine code, called DVMC (Datarol Virtual Machine Code). The latter optimizes the DVMC and translates it to the suitable code for a particular target machine. Since our source language supports non-strictness, frequent dynamic scheduling, which may incur heavy overhead on stock machines, will occur during the program execution. However, our compiler can find an appropriate execution order of a program, so that the frequency of useless dynamic scheduling may be reduced. In addition, our runtime system provides an efficient execution environment even if a program has potential points of dynamic scheduling.
・Experiment Environment for Fine-grain parallelism
In our implementation, we have built a virtual machine which supports fine-grain parallel execution. We have also developed an interpreter of this fine-grain virtual machine. The interpreter provides an interactive execution environment of fine-grain multithread programs. Since the interpreter is augmented with GUI,we can visually check the fine-grain execution.
|
