Skip to content
STIMSMITH

Translation Buffer

CodeArtifact

The Translation Buffer is a co-simulation component for coverage-guided processor verification that converts a bounded fuzzer-generated test vector into a deterministic endless instruction stream. It is implemented as a customized ring-buffer-like structure that supports cyclic reading, enabling an RTL core and a reference instruction set simulator to consume the same instruction stream despite differences such as RTL pipelining.

First seen 5/25/2026
Last seen 5/26/2026
Evidence 4 chunks
Wiki v1

WIKI

Overview

The Translation Buffer is an essential component in a cross-level processor verification co-simulation setup. In the described flow, a coverage-guided fuzzer generates bounded test vectors, and the Translation Buffer transforms those vectors into an endless instruction stream for execution by both the RTL core under test and a reference instruction set simulator (ISS). This supports co-simulation of the RTL core and ISS while helping decouple the setup from micro-architecture-specific optimizations such as pipelining. [Translation Buffer role]

Purpose

READ FULL ARTICLE →

NEIGHBORHOOD

No graph connections found for this entity yet. It may appear in future ingestion runs.

explore full graph →

RELATIONSHIPS

4 connections
The Translation Buffer is a novel component introduced in the paper to transform test vectors into instruction streams.
Instruction Stream Generation uses → 100% 2e
The Translation Buffer transforms test vectors into endless instruction streams.
pipelining uses → 90% 2e
The Translation Buffer helps decouple the co-simulation from pipelining-related micro-architecture specifics.
Co-Simulation part of → 100% 1e
The Translation Buffer is a component of the co-simulation framework.