CAD-SYS // ULTSQL-KERNEL v1.0.32
COORD: X: 0000 | Y: 0000
JITTER: 0.08ms
View on pub.dev GitHub Repository
EMPIRICALLY MEASURED & AUDITED

Transparent Performance Audit

Zero simulated metrics. Every single datapoint below was generated by automated benchmark runs executed on physical hardware, measuring ULTSQL (Pure Dart & Standalone AOT Native Binary) directly against SQLite3 (native C).

Physical Test Rig Specifications

Verified Test Environment
Machine (Hardware Model)
ASUS ROG Strix G16 (2023)
Model: G614JU / AC Power
Processor (CPU)
13th Gen Intel Core i7-13650HX
14 Cores (6P + 8E), 20 Threads, up to 4.9 GHz
System Memory (RAM)
16 GB DDR5 (4800 MHz)
High-speed dual-channel memory
Storage Subsystem
Micron 2400 NVMe SSD (PCIe Gen4)
Direct file I/O with ARIES Write-Ahead Log
Host OS & Toolchain
Windows 11 Home 64-bit
Dart SDK 3.12.2 / Standalone AOT Binary
ULTSQL v1.0.32 (Pure Dart & Standalone AOT) vs SQLite 3.50.4 (C/FFI)
Measured from live automated test run
โšก Native Standalone Binary
AOT COMPILED STANDALONE BINARY

Native Head-to-Head: UltSQL vs Native C SQLite 3

Zero Dart VM, zero JIT, and zero Dart SDK overhead. We benchmarked the standalone native AOT executable (ultsql.exe / ultsql) directly against the native C library SQLite 3 (sqlite3.dll v3.50.4) on an NVMe SSD using a pure Python 3 harness across 50,000 rows.

Benchmark Workload Unit โšก Native UltSQL (ultsql.exe) ๐Ÿชถ Native SQLite 3 (sqlite3.dll) Empirical Result
1. Bulk Ingest (Transaction Batch) rows/s 3,357,282 1,710,922 ๐Ÿ† 1.96x faster
2. CREATE INDEX on age (B+Tree) ms 2.739 8.197 ๐Ÿ† 2.99x faster
3. Point Lookup by PK (Prepared) ยตs/query 0.682 3.474 ๐Ÿ† 5.09x faster
4. Range Aggregate (age 30โ€“40) ms 0.222 1.475 ๐Ÿ† 6.64x faster
5. Full-scan GROUP BY Aggregate ms 0.692 8.951 ๐Ÿ† 12.93x faster
6. Indexed In-Place UPDATE ms 0.108 3.203 ๐Ÿ† 29.66x faster
7. Indexed DELETE ms 0.028 19.992 ๐Ÿ† 714.00x faster
8a. Auto-Commit (synchronous = NORMAL) tx/s 519,481 94,437 ๐Ÿ† 5.50x faster
8b. Relaxed Durability (synchronous = OFF) rows/s 4,545,455 657,895 ๐Ÿ† 6.91x faster
9. DROP TABLE Catalog Cleanup ms 0.004 0.916 ๐Ÿ† 229.05x faster

Durability Semantics & Crash Safety Verification

Durability Distinctions: Comparing buffered group-commit writes against SQLite's default per-commit fsync() (which yields ~1,064 tx/s due to NVMe disk sync latency) is not apples-to-apples. Under matching WAL durability (PRAGMA synchronous = NORMAL), SQLite reaches 94,437 tx/s, while UltSQL achieves 519,481 tx/s. When disk synchronization is relaxed entirely (synchronous = OFF), SQLite achieves 657,895 rows/s on disk and 1.32M rows/s in memory, while UltSQL's batch group-commit reaches 4.55M rows/s.

Out-of-Process Crash Safety Proof: UltSQL is rigorously verified with an out-of-process crash harness (test/out_of_process_crash_test.dart) executing kill -9 / taskkill /F abruptly mid-batch. In both single-crash and multi-cycle recovery tests, 100% of acknowledged committed transactions survive, the Write-Ahead Log replays cleanly, and relational SQL correctness is verified against standardized SQL logic conformance suites.

Reproduce Native Comparison (Python 3, No Dart Needed)
# Clone and run the native benchmark script (requires only Python 3 + bundled sqlite3)
git clone https://github.com/ompatel3158/ULTSQL.git
cd ULTSQL
python tool/benchmarks/benchmark_native_sqlite_vs_ultsql.py

Comprehensive Workload Audit Table

Empirical statistical medians across 3 timed runs per workload.

Workload Benchmark Unit โšก ULTSQL (Pure Dart) SQLite (Native C/FFI) Winner / Speedup

Reproduce These Benchmarks On Your Machine

Clone the repository and run the open-source benchmark harness directly via Dart:

Terminal (PowerShell / Bash)
# 1. Clone ULTSQL
git clone https://github.com/ompatel3158/ULTSQL.git
cd ULTSQL

# 2. Run automated comparative benchmark harness (relational, nosql, kv, vector)
dart run tool/benchmarks/run_all.dart --rows 50000 --runs 3 --big 200000

# Results will be generated and saved to web_site/data/benchmarks.json
ESC
โœ“ Copied