LLVM-IR Instruction Latency Estimation Using Deep Neural Networks for a Software–Hardware Interface for Multi-Many-Cores

This study  presents a method for estimating the latency of each LLVM-IR instruction to enable effective parallelization in model-based development.  In recent embedded systems, such as in-vehicle electronic control, multi-many-core processors are utilized for the hardware, and model-based development for software.  In the design of these systems, the degree of parallelism in the software and accuracy of performance estimation in the early design stages of the model-based development can be improved by estimating the performance of the blocks in the models and utilizing the estimate for parallelization.  Research is therefore being performed on a software performance estimation technique that uses IEEE2804-2019 hardware feature description called Software-Hardware Interface for Multi-many-core (SHIM).  In SHIM, each LLVM-IR instruction is associated with an execution cycle of the target processor.  Several types of assembly instruction sequences are generated for the target processor from a given LLVM-IR instruction; thus, it is not easy to estimate the number of execution cycles.  In this study, we propose a method that uses deep neural networks to estimate execution cycles for each LLVM-IR instruction.  It can be observed that our method obtains a better estimation of LLVM-IR instruction latency compared with previous methods in experiments using the Raspberry Pi3 Model B+.