Skip to content
STIMSMITH

LLM-based Processor Verification: A Case Study for Neuromorphic Processor

Paper
First seen 8/17/2026
Last seen 8/17/2026
Evidence 12 chunks

NEIGHBORHOOD

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

explore full graph →

RELATIONSHIPS

35 connections
riscv-dv mentions → 95% 2e
The paper mentions RISCV-DV as a testing tool for RISC-V processors.
LLM-based Test Generation uses → 98% 2e
The paper employs LLM-based test generation as its primary verification technique.
GPT-3.5 uses → 99% 2e
The paper uses GPT-3.5 as the primary LLM for test generation.
neuromorphic processor evaluates → 98% 2e
The paper evaluates LLM-based verification on a neuromorphic processor.
Chip-Chat mentions → 90% 2e
The paper mentions Chip-Chat as a related tool for hardware logic design using ChatGPT.
ChipGPT mentions → 90% 2e
The paper mentions ChipGPT as a related tool for hardware logic design using ChatGPT.
Xuantie-C910 evaluates → 98% 2e
The paper evaluates Xuantie-C910 as the RISC-V processor under verification.
constrained random generation mentions → 95% 2e
The paper mentions constrained random generation as an existing test generation technique.
coverage-directed test generation mentions → 95% 2e
The paper mentions CDG as an existing simulation-based verification approach.
Coverage-Directed Test Selection mentions → 95% 2e
The paper mentions coverage-directed test selection as an existing approach.
simulation-based verification uses → 95% 2e
The paper relies on simulation-based verification as the underlying approach.
RTL Simulation uses → 95% 2e
The paper uses RTL-level simulation as part of its verification workflow.
Lei Wang authored by → 100% 2e
Lei Wang is listed as a corresponding author of the paper.
block coverage uses → 95% 2e
The paper uses block coverage as a verification metric.
expression coverage uses → 95% 2e
The paper uses expression coverage as a verification metric.
toggle coverage uses → 95% 2e
The paper uses toggle coverage as a verification metric.
ISA coverage uses → 95% 2e
The paper uses ISA coverage to measure how many instructions are tested.
Prompt Engineering uses → 90% 2e
The paper uses prompt engineering to guide LLM test generation.
LLM-based verification workflow introduces → 98% 2e
The paper proposes and introduces the LLM-based verification workflow for DSA verification.
assembly test generation uses → 95% 2e
The paper uses assembly test generation for the neuromorphic processor verification.
C program test generation uses → 95% 2e
The paper uses C program test generation for RISC-V processor verification.
iterative test refinement uses → 90% 2e
The paper uses iterative test refinement through multiple rounds of LLM interaction.
Raven mentions → 95% 2e
The paper mentions RAVEN as a testing tool for ARM processors.
random test generation mentions → 90% 1e
The paper mentions random test generation as an existing approach.
National University of Defense Technology authored by → 100% 1e
Several authors of the paper are affiliated with National University of Defense Technology.
Some authors of the paper are affiliated with University of Electronic Science and Technology of China.
Defense Innovation Institute authored by → 100% 1e
Some authors of the paper are affiliated with Defense Innovation Institute.
Code Coverage uses → 95% 1e
The paper uses code coverage as an index to evaluate verification progress.
hardware-aware test generation uses → 90% 1e
The paper employs hardware-aware test generation targeting specific processor function units.
GPT-4 mentions → 90% 1e
The paper mentions GPT-4 as the latest version of the GPT family.
Codex mentions → 90% 1e
The paper mentions Codex as an LLM fine-tuned on code repositories.
DAVE mentions → 90% 1e
The paper mentions DAVE as the first LLM work in hardware design.
Novelty-Driven Verification mentions → 90% 1e
The paper mentions novelty-driven verification as a related approach.
TrueNorth mentions → 90% 1e
The paper mentions TrueNorth as an example neuromorphic processor.
Chao Xiao authored by → 100% 1e
Chao Xiao is listed as a primary author of the paper.