skills.rest
sirius-db
sirius-dbOFFICIAL
Explore all skills by this author →
GitHub

tpcds-benchmark

Execute TPC-DS benchmarks across Legacy Sirius, Super Sirius, and DuckDB CPU engines.

1.0k|109|Updated Jun 19, 2024
Search Tags:#performance#sql#benchmark#gpu#duckdb#sirius#tpcds
One-click install
npx skills add https://github.com/sirius-db/sirius --skill tpcds-benchmark
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: tpcds-benchmark
Source: https://github.com/sirius-db/sirius/tree/main/.claude/skills/tpcds-benchmark
Command: npx skills add https://github.com/sirius-db/sirius --skill tpcds-benchmark

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the process of running TPC-DS benchmarks across different SQL engines, enabling performance comparisons and identifying potential issues.

Core Features & Use Cases

  • Multi-Engine Benchmarking: Execute TPC-DS queries on Legacy Sirius, Super Sirius, and DuckDB CPU.
  • Data Generation: Create TPC-DS datasets in DuckDB or Parquet formats.
  • Result Analysis: Compare query execution times and identify GPU fallback or errors.
  • Use Case: Compare the performance of Super Sirius against a DuckDB CPU baseline for a specific set of TPC-DS queries to understand GPU acceleration benefits.

Quick Start

Generate TPC-DS data for scale factor 1 in parquet format.

Frequently Asked Questions about tpcds-benchmark

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run TPC-DS benchmarks to compare GPU and CPU SQL query performance?▼

Yes, you can generate TPC-DS datasets in either DuckDB or Parquet formats. This allows you to create the necessary test data at your desired scale factor before executing the benchmark queries across the different SQL engines.

What is the best way to identify GPU fallback issues during SQL benchmark execution?▼

To identify GPU fallback during SQL benchmark execution, the tool analyzes query runs across Sirius engines and provides detailed output logs that flag execution errors and instances where GPU acceleration falls back to standard processing.

Does this benchmarking process support DuckDB CPU as a baseline for TPC-DS queries?▼

Yes, DuckDB CPU is supported as a baseline for TPC-DS queries. The benchmarking process runs the standard TPC-DS workload against DuckDB CPU alongside Legacy Sirius and Super Sirius to measure comparative execution times.

How do I generate TPC-DS data for scale factor 1 in Parquet format?▼

To generate TPC-DS data for scale factor 1 in Parquet format, you can use the provided scripts to quickly create the dataset. This prepares the required data files for subsequent multi-engine SQL query benchmarking.

Why does my TPC-DS query fail when running across different SQL engines?▼

TPC-DS query failures across different SQL engines are captured in the detailed output logs. The benchmarking tool identifies execution errors and GPU fallback instances, providing timing results to help analyze performance discrepancies and failures.

Related Skills

Explore More Software Engineering Skills→
sirius-dbsirius-db
1.0k

dataset-manager

Generate and optimize TPC-H Parquet datasets with cudf or pyarrow.

Official
Advanced
kindoflukekindofluke

tpcds-benchmark

Automate TPC-DS benchmarking across SQL engines and compile comparative results.

Community
Advanced
sirius-dbsirius-db
1.0k

validate

Diagnose incorrect Sirius GPU query results against a DuckDB CPU baseline.

Official
Advanced
pilotspacepilotspace
2

gpu-bench

Benchmark GPU-accelerated Moon workloads against CPU baselines in CUDA environments.

Official
Intermediate