“…The test strategy is based on the technique proposed by Raik et al [36] and assumes an external tester and the definition of several test path configurations to exercise all possible communications in the network. Lubaszewski et al [23] proposed a post burn-in testing for both links and routers, which is based on the functional testing of several 2 Â 2 meshes in an N Â N NoC. However, both these techniques are offline and suitable for manufacturing testing using automatic test equipment, and to get a reasonable fault coverage and implementing them in hardware leads to overhead.…”
Section: Router Testingmentioning
confidence: 99%
“…They test each 2 Â 2 mesh using a set of test sequences and patterns. However, as they showed in [23], the 2 Â 2 mesh can give good fault coverage for the links but not for the routers, especially for the routing logics, FIFO's control paths, and arbiters. To obtain higher fault coverage for the routers, they added more than 12 other mesh configurations including 3 Â 1, 1 Â 3, 2 Â 2, and so on.…”
Section: Introductionmentioning
confidence: 99%
“…Recently, Lubaszewski et al [22], [23] proposed a new post burn-in testing for NoCs, which is based on the atspeed functional testing of several 2 Â 2 meshes in an N Â N NoC. They test each 2 Â 2 mesh using a set of test sequences and patterns.…”
Section: Introductionmentioning
confidence: 99%
“…First, we propose a functional test architecture, which can be implemented in routers and NIs with small hardware overhead. Similar to the work in [23], we use test pattern generator (TPG) and test response analyzer (TRA). However, to have minimum performance overhead on the NoC in online mode we take advantage of TPG and TRA in both router and NI.…”
Section: Introductionmentioning
confidence: 99%
“…Moreover, we use TMR for the reliability of testing components added to the router. Unlike the work proposed in [23], we do not use 2 Â 2 meshes to test the entire NoC, but we test each router separately and using its neighbors in online and at-speed functional mode. We use logic and delay fault models and the corresponding system-level failure modes to better tune the test pattern sequences.…”
Abstract-In this work, we propose a distributed functional test mechanism for NoCs which scales to large-scale networks with general topologies and routing algorithms. Each router and its links are tested using neighbors in different phases. The router under test is in test mode while all other parts of the NoC are operational. We use triple module redundancy (TMR) for the robustness of all testing components that are added into the switch. Experimental results show that our functional test approach can detect stuck-at, short and delay faults in the routers and links. Our approach achieves 100 percent stuck-at fault coverage for the data path and 85 percent for the control paths including routing logic, FIFO's control path, and the arbiter of a 5 Â 5 router. We also show that our approach is able to detect delay faults in critical control and data paths. Synthesis results show that the area overhead of our test components with TMR support is 20 percent for covering stuck-at, delay, and short-wire faults and 7 percent for covering only stuck-at and delay faults in the 5 Â 5 router. Simulation results show that our online testing approach has an average latency overhead of 3 percent in PARSEC traffic benchmarks on an 8 Â 8 NoC.
“…The test strategy is based on the technique proposed by Raik et al [36] and assumes an external tester and the definition of several test path configurations to exercise all possible communications in the network. Lubaszewski et al [23] proposed a post burn-in testing for both links and routers, which is based on the functional testing of several 2 Â 2 meshes in an N Â N NoC. However, both these techniques are offline and suitable for manufacturing testing using automatic test equipment, and to get a reasonable fault coverage and implementing them in hardware leads to overhead.…”
Section: Router Testingmentioning
confidence: 99%
“…They test each 2 Â 2 mesh using a set of test sequences and patterns. However, as they showed in [23], the 2 Â 2 mesh can give good fault coverage for the links but not for the routers, especially for the routing logics, FIFO's control paths, and arbiters. To obtain higher fault coverage for the routers, they added more than 12 other mesh configurations including 3 Â 1, 1 Â 3, 2 Â 2, and so on.…”
Section: Introductionmentioning
confidence: 99%
“…Recently, Lubaszewski et al [22], [23] proposed a new post burn-in testing for NoCs, which is based on the atspeed functional testing of several 2 Â 2 meshes in an N Â N NoC. They test each 2 Â 2 mesh using a set of test sequences and patterns.…”
Section: Introductionmentioning
confidence: 99%
“…First, we propose a functional test architecture, which can be implemented in routers and NIs with small hardware overhead. Similar to the work in [23], we use test pattern generator (TPG) and test response analyzer (TRA). However, to have minimum performance overhead on the NoC in online mode we take advantage of TPG and TRA in both router and NI.…”
Section: Introductionmentioning
confidence: 99%
“…Moreover, we use TMR for the reliability of testing components added to the router. Unlike the work proposed in [23], we do not use 2 Â 2 meshes to test the entire NoC, but we test each router separately and using its neighbors in online and at-speed functional mode. We use logic and delay fault models and the corresponding system-level failure modes to better tune the test pattern sequences.…”
Abstract-In this work, we propose a distributed functional test mechanism for NoCs which scales to large-scale networks with general topologies and routing algorithms. Each router and its links are tested using neighbors in different phases. The router under test is in test mode while all other parts of the NoC are operational. We use triple module redundancy (TMR) for the robustness of all testing components that are added into the switch. Experimental results show that our functional test approach can detect stuck-at, short and delay faults in the routers and links. Our approach achieves 100 percent stuck-at fault coverage for the data path and 85 percent for the control paths including routing logic, FIFO's control path, and the arbiter of a 5 Â 5 router. We also show that our approach is able to detect delay faults in critical control and data paths. Synthesis results show that the area overhead of our test components with TMR support is 20 percent for covering stuck-at, delay, and short-wire faults and 7 percent for covering only stuck-at and delay faults in the 5 Â 5 router. Simulation results show that our online testing approach has an average latency overhead of 3 percent in PARSEC traffic benchmarks on an 8 Â 8 NoC.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.