Sql-Rewrite

−46% or −2%? Rule-Based Rewriters Only Work at Home

On TPC-H 10GB, a state-of-the-art learned rewriter cuts mean execution time from 69.84s to 37.57s — a 46% win. On DSB 10GB, the same rewriter takes 32.62s to 31.93s — a 2.1% non-event. The gap isn’t query difficulty; it’s whether the benchmark is in the rewriter’s training distribution. “Rule-based systems are stable and reliable” is often a benchmark artifact, not an engineering fact.

Just Asking an LLM to Rewrite SQL Does Almost Nothing

On TPC-H 10GB, asking GPT-4o to rewrite SQL takes mean execution time from 78.81s down to 74.92s — almost nothing. Swap in an open 14B model, feed it plans, add a reward, fine-tune once, and the same workload drops to 29.67s. Whether LLMs can help SQL rewriting is not a question about model strength; it’s a question about whether you’re willing to give the model the signals it actually needs.