Programming Language Assisted Waveform Analysis: A Case Study on the Instruction Performance of SERV

04/12/2023
by   Lucas Klemmer, et al.
0

RISC-Vs growing traction leads to the release of new RISC-V cores on a near monthly basis. In this growing and diverse ecosystem, understanding the performance and other properties of a RISC-V core is of great importance since selecting the best fitting core is mandatory for a successful project. Analyzing RISC-V cores by hand is not possible due to the ever-increasing number of available cores and available software benchmarks might not be fine-grained enough to understand a core completely. Programming and powerful programming languages have proven to provide the productivity that is required to keep pace with these fast developments. In this paper we present a case study in which we use WAWK, a front-end for the open-source Waveform Analysis Language, to analyze the performance of all instructions of SERV, a well known bit-serial RISC-V core. With WAWK, only a few lines of code are necessary to calculate the respective metric on the waveform generated during simulation.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset

Sign in with Google

×

Use your Google Account to sign in to DeepAI

×

Consider DeepAI Pro