一种基于贝叶斯网络的随机测试方法在Cache一致性验证中的设计与实现

A Bayesian network based test generation method for Cache coherency protocol verification

随着集成电路设计复杂度指数级增长,功能验证已经越来越成为大规模芯片设计的瓶颈,而在多核处理器中,Cache一致性协议十分复杂,验证难度大。针对Cache一致性协议验证提出基于模拟验证的一种基于贝叶斯网络的随机测试生成方法,解决Cache一致性协议状态空间爆炸的问题。首先分析了Cache一致性协议及基于贝叶斯网络推理的CDG方法,并将CDG方法应用于Cache一致性的验证。以FT处理器中的Cache一致性协议验证为例,对比伪随机测试,使用CDG方法将覆盖率提高近30%。

As the complexity of integrated circuit design increases exponentially, functional verification has become a bottleneck in large-scale chip design. And in multi-core processor design, Cache coherency protocols are very complex and difficult to verify. We propose a random test generation method based on Bayesian network for simulation-based verification to solve the state space explosion problem of Cache coherency protocols. We discuss the Cache coherency protocol, analyze the coverage directed test generation （CDG） method based on Bayesian network reasoning, and apply the method to Cache consistency verification. Taking the verification of the Cache coherence protocol of the FT processor as an example, the results show that the CDG method can increase coverage by nearly 30% in comparison with the pseudo-random test.