[2606.31238] A Multi-Dimensional, Per-Pass Empirical Study of the LLVM Optimization Pipeline

Skip to main content

arXiv is now an independent nonprofit!<br>Learn more<br>&times;

Search arXiv

Press Enter to search &middot; Advanced search

-->

Computer Science > Software Engineering

arXiv:2606.31238 (cs)

[Submitted on 30 Jun 2026]

Title:A Multi-Dimensional, Per-Pass Empirical Study of the LLVM Optimization Pipeline

Authors:Federico Bruzzone, Walter Cazzola<br>View a PDF of the paper titled A Multi-Dimensional, Per-Pass Empirical Study of the LLVM Optimization Pipeline, by Federico Bruzzone and 1 other authors

View PDF<br>HTML (experimental)

Abstract:Quantifying the marginal impact of individual optimization passes underpins phase ordering, pass selection, optimization design, and analysis of pass/hardware interactions. In LLVM -- the standard backend for C/C++, Rust, and ML stacks via MLIR -- interactions among optimization passes, measurement noise, and pipeline scale make this difficult. We present a systematic, empirical study of the LLVM -O3 optimization pipeline. We decompose the pipeline into cumulative per-pass prefixes. We then measure execution time, compile time, binary size, hardware counters, and RAPL energy across 84,750 measurements covering 113 cumulative prefixes of the -O3 pipeline evaluated on 30 PolyBench/C kernels under rigorous noise mitigation. On these compute-bound affine kernels, the pipeline is non-monotone (6.6-9.7% of transitions regress) and strongly back-loaded (the median non-regressing kernel needs 84.8% of the pipeline for 80% of its speedup). Most gains are driven by a small Pareto-dominant core of passes, while the final -O3 configuration is Pareto-dominated on (size, speedup) for 29 of 30 kernels. We further show that IR instruction count is an unreliable predictor of runtime, that runtime-targeted passes are de facto energy-targeted (30-60% savings), and that the search-free idealized-additive upper bound on losses due to phase interference is 46.35%. These findings enable more informed pass pruning, cost-model calibration, and autotuning.

Comments:<br>13 pages, 11 figures

Subjects:

Software Engineering (cs.SE); Performance (cs.PF); Programming Languages (cs.PL)

ACM classes:<br>D.3.4; C.1; C.4

Cite as:<br>arXiv:2606.31238 [cs.SE]

(or<br>arXiv:2606.31238v1 [cs.SE] for this version)

https://doi.org/10.48550/arXiv.2606.31238

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

Submission history<br>From: Federico Bruzzone [view email]<br>[v1]<br>Tue, 30 Jun 2026 07:10:48 UTC (6,775 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled A Multi-Dimensional, Per-Pass Empirical Study of the LLVM Optimization Pipeline, by Federico Bruzzone and 1 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.SE

next >

new<br>recent<br>| 2026-06

Change to browse by:

cs<br>cs.PF<br>cs.PL

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

loading...

Data provided by:

Bookmark

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .

Which authors of this paper are endorsers? |<br>Disable MathJax (What is MathJax?)

Major funding support from