Skip to content

On the Limits of Machine-Learned Ranking for Modern Microarchitectural Policies

Aug 2026 · 0 citations · 30 references
Computer Science

TL;DR

It is shown that high cycle or aggregate ranking accuracy can reflect mastery of easy, high-margin cases while missing the local reversals that carry the most architectural insight and for which cycle-level simulation remains indispensable.

Abstract

Machine-learning predictors estimate processor performance far faster than cycle-level simulation. For design-space exploration, however, the valuable test is not merely reproducing the usual hardware ordering, but identifying how different hardware configurations rank on individual program phases. We evaluate four ML-predictors in two design regimes: \emph{Structural Parameters} (SP), varying hardware resources such as issue width, ROB size, and cache capacity; and \emph{Behavioral Policies} (BP), varying prefetching and replacement algorithms. In the SP regime, aggregate ranking is strong, yet counter-intuitive windows(CIW)---where the configuration expected to be slower is faster---constitute $22.4\%$ of non-tied windows across five pairs with a clear architectural prior. CIW match across these pairs is only $23.3$--$39.9\%$; every point estimate is below the $50\%$ random strict-ordering reference. The BP regime presents a different failure: ground-truth ties cover $37.8\%$ of pair-windows, most strict pairs have margins of only a few cycles, and no model family reliably beats a feature-free majority baseline. NeuroScalar and SimNet fall below that baseline, Concorde is statistically tied with it, and the best selected OneDSE head improves by only $2.1$ percentage points. Accuracy rises mainly at large margins. We further show that this failure is not a matter of model capacity: an information-theoretic analysis reveals that when ranking outcomes depend on hidden microarchitectural state absent from the instruction stream, no trace-based predictor can exceed the Bayes accuracy determined by observable inputs alone. Thus high cycle or aggregate ranking accuracy can reflect mastery of easy, high-margin cases while missing the local reversals that carry the most architectural insight and for which cycle-level simulation remains indispensable.

View source

Similar papers

Preprint Aug 2026

Aneto: Predicting System Performance by Exploiting Cross-Workload Regularity

Aneto is a mechanistic-empirical regression model that estimates the performance-latency sensitivity of any new workload from a single run, enabling first-order CPI prediction under any memory configuration.

Raúl Taranco, Rene Mueller, Michael Giardino · 0 citations
Book Open access Sep 2026

Code Generation from Regression Trees for Microsecond-Scale Decisions in Operating Systems

This work examines the suitability of regression trees for fast (nano- to microsecond-scale) runtime decisions within operating systems, and is able to reduce inference latency by up to an order of magnitude compared to conventional approaches.

B. Friesel, Marcel Lütke Dreimann, Olaf Spinczyk · 0 citations
#artificial intelligence Preprint Sep 2026

PerfReasoning: How Well Do LLMs Reason on Hardware Performance?

PerfReasoning is introduced, a benchmark that evaluates LLMs both as direct performance reasoners and as generators of analytical performance-model code, exposing the gap between plausible architectural reasoning and reliable performance-model construction.

Da Zhao, K. Sankaralingam, Christos Kozyrakis et al. · 0 citations
Preprint Aug 2026

FinHardBench: Can LLMs Generate Latency-Aware Hardware for Financial Computing?

FinHardBench, a benchmark of 33 financial computing tasks, is presented together with three experiments that mirror the real-world FPGA iteration cycle: generating new modules from specifications, tuning system-level configurations across a 6-stage trading pipeline, and adapting existing modules to specification change...

Weimin Fu, He-Jia Zhang, Ming-Hao Shao et al. · 0 citations

Related blog posts

MIT News · Artificial Intelligence Nov 17, 2026

Learning the language of machine learning

By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.

Microsoft Research Blog Nov 16, 2026

TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient

AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.