Performance Verification of the AmpereOne CPU Core

📅 2026-08-19
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
本文介绍了AmpereOne CPU核心性能验证方法,通过周期精确的相关性检查、数据驱动的工作负载管理和高频回归系统等手段,确保处理器达到性能目标。
📝 Abstract
As process technology scaling slows, microarchitectural innovation has become the primary driver of performance gains, making pre-silicon Performance Verification (PV) more critical than ever. This paper presents the industrial-scale PV methodology applied across four generations of the AmpereOne custom CPU core, centered on the cycle-accurate correlation of the RTL design against a trace-driven performance model. The methodology integrates data-driven workload curation, a high-frequency daily regression system, and a unified event-stream framework for analysis. We demonstrate this methodology through case studies of the Branch Prediction Unit and L2 Prefetcher, highlighting a hierarchical strategy that first isolates individual units for focused correlation before proceeding to full-core verification. The results demonstrate that this disciplined, iterative process is indispensable for avoiding costly post-silicon bugs and ensuring complex processors meet their performance targets. We end with a look towards the future of PV in the microprocessor industry.
Problem

Research questions and friction points this paper is trying to address.

Performance Verification
microarchitectural innovation
pre-silicon
AmpereOne CPU
Innovation

Methods, ideas, or system contributions that make the work stand out.

Performance Verification
cycle-accurate correlation
data-driven workload curation
unified event-stream framework
🔎 Similar Papers
No similar papers found.
D
Doa'a Al-Otoom
Ampere Computing – Portland, OR, and Raleigh, NC, and Santa Clara, CA, USA
N
Nicholas Kelly
Ampere Computing – Portland, OR, and Raleigh, NC, and Santa Clara, CA, USA
A
Aaron Lindsay
Ampere Computing – Portland, OR, and Raleigh, NC, and Santa Clara, CA, USA
A
Agreen Ahmadi
Ampere Computing – Portland, OR, and Raleigh, NC, and Santa Clara, CA, USA
A
Ananth Kumar
Ampere Computing – Portland, OR, and Raleigh, NC, and Santa Clara, CA, USA
A
Anthony Faubert
Ampere Computing – Portland, OR, and Raleigh, NC, and Santa Clara, CA, USA
B
Benjamin Chaffin
Ampere Computing – Portland, OR, and Raleigh, NC, and Santa Clara, CA, USA
B
Bret Toll
Ampere Computing – Portland, OR, and Raleigh, NC, and Santa Clara, CA, USA
Eric Wallace
Eric Wallace
UC Berkeley
Natural Language ProcessingMachine LearningComputer Security
L
Lucas Crowthers
Ampere Computing – Portland, OR, and Raleigh, NC, and Santa Clara, CA, USA
M
Mark Charney
Ampere Computing – Portland, OR, and Raleigh, NC, and Santa Clara, CA, USA
M
Michael Chin
Ampere Computing – Portland, OR, and Raleigh, NC, and Santa Clara, CA, USA
M
Michael Spradling
Ampere Computing – Portland, OR, and Raleigh, NC, and Santa Clara, CA, USA
S
Scott Witscher
Ampere Computing – Portland, OR, and Raleigh, NC, and Santa Clara, CA, USA
Sriyash Caculo
Sriyash Caculo
Ampere Computing – Portland, OR, and Raleigh, NC, and Santa Clara, CA, USA
S
Syed Fakhri
Ampere Computing – Portland, OR, and Raleigh, NC, and Santa Clara, CA, USA
V
Vivek Kothapalli
Ampere Computing – Portland, OR, and Raleigh, NC, and Santa Clara, CA, USA
W
William Freelove
Ampere Computing – Portland, OR, and Raleigh, NC, and Santa Clara, CA, USA
Mahesh Madhav
Mahesh Madhav
Fellow, Ampere Computing
CPU MicroarchitecturePerformanceWorkload Characterization