SemanticBBV: A Semantic Signature for Cross-Program Knowledge Reuse in Microarchitecture Simulation

TL;DR

SemanticBBV introduces a semantic signature framework for cross-program microarchitecture simulation, leveraging deep learning to improve reuse and performance prediction, resulting in significant speedups and broad adaptability.

Contribution

It presents a novel two-stage semantic signature generation method that enhances cross-program reuse and performance sensitivity in microarchitecture simulation.

Findings

Achieves 86.3% average accuracy on SPEC CPU benchmarks.

Enables 7143x simulation speedup with minimal fine-tuning.

Supports cross-program analysis and adaptation to new microarchitectures.

Abstract

For decades, sampling-based techniques have been the de facto standard for accelerating microarchitecture simulation, with the Basic Block Vector (BBV) serving as the cornerstone program representation. Yet, the BBV's fundamental limitations: order-dependent IDs that prevent cross-program knowledge reuse and a lack of semantic content predictive of hardware performance have left a massive potential for optimization untapped. To address these gaps, we introduce SemanticBBV, a novel, two-stage framework that generates robust, performance-aware signatures for cross-program simulation reuse. First, a lightweight RWKV-based semantic encoder transforms assembly basic blocks into rich Basic Block Embeddings (BBEs), capturing deep functional semantics. Second, an order-invariant Set Transformer aggregates these BBEs, weighted by execution frequency, into a final signature. Crucially, this stage is co-trained with a dual objective: a triplet loss for signature distinctiveness and a Cycles Per Instruction (CPI) regression task, directly imbuing the signature with performance sensitivity. Our evaluation demonstrates that SemanticBBV not only matches traditional BBVs in single-program accuracy but also enables unprecedented cross-program analysis. By simulating just 14 universal program points, we estimated the performance of ten SPEC CPU benchmarks with 86.3% average accuracy, achieving a 7143x simulation speedup. Furthermore, the signature shows strong adaptability to new microarchitectures with minimal fine-tuning.