Manas103 opened a new pull request, #49315:
URL: https://github.com/apache/arrow/pull/49315

   ### Rationale for this change
   Profiling `BM_Tpch_Q1_ExecOnly` in Acero shows a hotspot in 
`BasicDecimal128::Abs()`, and the existing TPC‑H Q1 benchmark mixes data 
generation with execution, making it hard to isolate execution costs. This 
change introduces an exec‑only Q1 benchmark for cleaner profiling and removes 
an avoidable temporary in Abs() to reduce overhead in decimal‑heavy execution. 
It also adjusts TDigest test tolerances on MSVC to align with existing libc++ 
precision behavior.
   
   ### What changes are included in the PR?
   
   - Add `BM_Tpch_Q1_ExecOnly` that pre‑generates the lineitem table and 
benchmarks only plan execution
   - Refactor Q1 setup to build an exec plan from a pre‑generated table source
   - Optimize `BasicDecimal128::Abs()` to use `IsNegative()` directly (avoids 
temporary + `operator<`)
   - Relax TDigest test tolerance on MSVC to match libc++ behavior
   
   ### Are these changes tested?
   
   Yes. I ran the C++ unit test subset labeled `unittest` using CTest with 
4-way parallelism and failure output enabled:
   - `ctest -j4 -L unittest --output-on-failure`
   All 75 tests in that label passed.
   
   ### Are there any user-facing changes?
   No.
   
   Github Issue: 48931
   
   * GitHub Issue: #48931
   


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]

Reply via email to