Groups | Search | Server Info | Login | Register
Groups > comp.compilers > #3713
| Path | csiph.com!weretis.net!feeder9.news.weretis.net!news.misty.com!news.iecc.com!.POSTED.news.iecc.com!nerds-end |
|---|---|
| From | Derek <derek@shape-of-code.com> |
| Newsgroups | comp.compilers |
| Subject | Re: Paper: Magellan: Autonomous Discovery of Novel Compiler Optimization Heuristics with AlphaEvolve |
| Date | Sun, 01 Feb 2026 17:37:42 +0000 |
| Organization | Compilers Central |
| Sender | johnl%iecc.com |
| Approved | comp.compilers@iecc.com |
| Message-ID | <26-02-001@comp.compilers> (permalink) |
| References | <26-01-006@comp.compilers> |
| MIME-Version | 1.0 |
| Content-Type | text/plain; charset="UTF-8" |
| Injection-Info | gal.iecc.com; posting-host="news.iecc.com:2001:470:1f07:1126:0:676f:7373:6970"; logging-data="28218"; mail-complaints-to="abuse@iecc.com" |
| Keywords | optimize |
| Posted-Date | 01 Feb 2026 21:48:02 EST |
| X-submission-address | compilers@iecc.com |
| X-moderator-address | compilers-request@iecc.com |
| X-FAQ-and-archives | http://compilers.iecc.com |
| In-Reply-To | <26-01-006@comp.compilers> |
| Xref | csiph.com comp.compilers:3713 |
Show key headers only | View raw
John, A paper with "novel" in the title is a major red flag. > This Google paper describes an AI approach to invent new compiler > optimizations. No they don't. They use an LLM to select the tuning parameters for a well established optimization, function inlining. > surpass expert baselines. In LLVM function inlining, Magellan synthesizes > new heuristics that outperform decades of manual engineering for both > binary-size reduction and end-to-end performance. "... the continued Gemini-3-Pro run achieves consistent positive speedups beyond 0%, ultimately surpassing the hand- tuned baseline by 0.61%." Figure 3/4 suggests a much bigger improvement, until the reader realises that the comparison is not against human generated rules. Results given to two decimal places and no error bars! > In register allocation, > it learns a concise priority rule for live-range processing that matches > intricate human-designed policies on a large-scale workload. This sentence in the abstract goes undiscussed in the paper, which only looks at inlining.
Back to comp.compilers | Previous | Next — Previous in thread | Find similar
Paper: Magellan: Autonomous Discovery of Novel Compiler Optimization Heuristics with AlphaEvolve John R Levine <johnl@taugh.com> - 2026-01-30 10:53 -0500 Re: Paper: Magellan: Autonomous Discovery of Novel Compiler Optimization Heuristics with AlphaEvolve Derek <derek@shape-of-code.com> - 2026-02-01 17:37 +0000
csiph-web