NMX Data Miner™

NMX Data Miner™ allows engineering groups to diagnose any bottleneck suspected of hampering IC development effectiveness.

Examples of bottlenecks, or causal factors, include:

• EDA tools, flows and libraries the design team uses
• Specification stability
• Engineering skills,
• Differences among design sites
• IP quality
• Overall management.

Users analyze causal factors by creating a custom template that describes the causal factor, such as the name and version of the particular EDA tool suspected of causing problems in the design flow. Once project teams capture the data on a handful of IC projects, Data Miner reveals whether statistical relationships exist between the suspected causal factor and the particular performance metric of interest, including productivity, project duration, time-to-tapeout, development throughput, development cost and spin count.

The column chart below illustrates an example of Data Miner’s diagnostic stability of the chip’s design specification. It shows the results of analyzing 34 projects from a particular IC product development organization. Upon the completion of each project, the project manager characterized the stability of the chip’s design specification (as either Below Average, Average or Above Average).

Data Miner then grouped the projects into their respective bins and plotted the average project duration for each bin. The results show a clear relationship between spec stability, which is the independent variable, and project duration, which is the dependent variable. The next step in the root cause analysis would be to examine the impact of spec stability on a range of other performance metrics including, productivity, spin count, throughput, development cost, etc.

Data Miner’s capabilities provide organizations with a powerful vehicle for defining which factors they suspect are causing efficiency problems and rapidly verifying their hypotheses. It is the first true data mining tool available to IC development organizations that demand production-proven software for quantitatively diagnosing bottlenecks and improving their development capability.

Data Miner stores the user’s project data and performance metrics in a robust database. Data and metrics for each IC project can be captured throughout the project lifecycle, and results are instantaneously accessible to any individual granted the appropriate access privileges. A full range of statistical analysis tools together with a suite of graphical and tabular reporting tools enable rapid data mining and root cause diagnosis of all project data.