Samurai Search vs Vector Search Bench

Search source code, plain text files and PDF files on your iOS device or in iCloud/USB/SMB, preview matched files. or open in your favourite editing/viewing app. Supports flexible search options, including regular expressions (for plain text files). Files searched can be selected from standard or custom text file types or a filename pattern may be specified. Search files and folders can be selected from On My iPad, iCloud Drive or external file providers (e.g SMB/USB folder). Saved search files and folders are retained by the app where possible. iCloud files in selected iCloud Drive folders that match the file type (file extension) criteria or pattern, will be synced to device prior to searching. Searching text files is extremely fast. PDF search speed depends on content. It can be slow.

Vector Search Bench is a high-signal, no-nonsense benchmark suite for vector similarity search on iPhone. Measure how fast and stable your device can score embeddings using the CPU (Accelerate/vDSP) versus the Apple Neural Engine (Core ML)—with real metrics you can trust. What you can benchmark Exact Top-K vector search (dot-product similarity) CPU path: Accelerate / vDSP optimized scoring NPU path: Core ML Dense inference tuned for Neural Engine scheduling Query-by-query execution with repeatable timing Intricate performance metrics Latency distribution: median, p95 Throughput: QPS Recall@K vs CPU reference (sanity check) Memory footprint and dataset sizing knobs Built for real-world AI systems