Testing of parallel programs involves two parts-testing of controlflow within the processes and testing of timing-sequence. This paper focuses on thelatter, particularly on the timing-sequence of message-passing parad...Testing of parallel programs involves two parts-testing of controlflow within the processes and testing of timing-sequence. This paper focuses on thelatter, particularly on the timing-sequence of message-passing paradigms. Firstlythe coarse-grained SYN-sequence model is built up to describe the execution of distributed programs. All of the topics discussed in this paper are based on it. Themost direct way to test a program is to run it. A fault-free parallel program shouldbe of both correct computing results and proper SYN-sequence. In order to analyzethe validity of observed SYN-sequence, this paper presents the formal specification(Backus Normal Form) of the valid SYN-sequence. Till now there is little workabout the testing coverage for distributed programs. Calculating the number of thevalid SYN-sequences is the key to coverage problem, while the number of the validSYN-sequences is terribly large and it is very hard to obtain the combination lawamong SYN-events. In order to resolve this problem, this paper proposes an efficienttesting strategy- atomic SYN-event testing, which is to linearize the SYN-sequence(making it only consist of serial atomic SYN-events) first and then test each atomicSYN-event independently. This paper particularly provides the calculating formulaabout the number of the valid SYN-sequences for tree-topology atomic SYN-event(broadcast and combine). Furthermore, the number of valid SYN-sequences also,to some degree, mirrors the testability of parallel programs. Taking tree-topologyatomic SYN-event as an example, this paper demonstrates the testability and communication speed of the tree-topology atomic SYN-event under different numbersof branches in order to achieve a more satisfactory tradeoff between testability andcommunication efficiency.展开更多
文摘Testing of parallel programs involves two parts-testing of controlflow within the processes and testing of timing-sequence. This paper focuses on thelatter, particularly on the timing-sequence of message-passing paradigms. Firstlythe coarse-grained SYN-sequence model is built up to describe the execution of distributed programs. All of the topics discussed in this paper are based on it. Themost direct way to test a program is to run it. A fault-free parallel program shouldbe of both correct computing results and proper SYN-sequence. In order to analyzethe validity of observed SYN-sequence, this paper presents the formal specification(Backus Normal Form) of the valid SYN-sequence. Till now there is little workabout the testing coverage for distributed programs. Calculating the number of thevalid SYN-sequences is the key to coverage problem, while the number of the validSYN-sequences is terribly large and it is very hard to obtain the combination lawamong SYN-events. In order to resolve this problem, this paper proposes an efficienttesting strategy- atomic SYN-event testing, which is to linearize the SYN-sequence(making it only consist of serial atomic SYN-events) first and then test each atomicSYN-event independently. This paper particularly provides the calculating formulaabout the number of the valid SYN-sequences for tree-topology atomic SYN-event(broadcast and combine). Furthermore, the number of valid SYN-sequences also,to some degree, mirrors the testability of parallel programs. Taking tree-topologyatomic SYN-event as an example, this paper demonstrates the testability and communication speed of the tree-topology atomic SYN-event under different numbersof branches in order to achieve a more satisfactory tradeoff between testability andcommunication efficiency.
