GPU-Accelerated Rule Ranking

Ranker v5.0

Multi-Armed Bandit ranking with Early Elimination and memory-mapped file loading for 50× faster rule evaluation.

OpenCL GPU MAB Algorithm Memory-Mapped I/O NumPy Optimized

16K+Rules Supported

50×Loading Speed

MABAlgorithm

GPUAccelerated

Overview

Ranker v5.0 answers the question: "Which of my 16,000 rules actually cracks the most hashes?" — without running a full Hashcat session for every rule.

The Multi-Armed Bandit algorithm allocates GPU compute intelligently, spending more trials on promising rules and eliminating poor performers early. Combined with memory-mapped file loading, this achieves a 50× speedup over naive approaches.

Core Features

∞

Multi-Armed Bandit + Early Elimination

Allocates GPU compute to top performers. Low-performing rules eliminated after confidence threshold crossed.

⚡

Memory-mapped file loading

OS-level mmap for near-instant rule file loading. 50× faster than standard file I/O for large rule sets.

∫

NumPy-optimized scoring

Vectorized hit counting and confidence interval math using NumPy broadcasting.

⊞

All Hashcat modes

Compatible with modes 0, 1, 3, 6, 7 and custom corpora.

Ranking Workflow

Step 1

mmap rule files

Map all rule files into virtual memory. Load time: milliseconds even for 16K rules.

Step 2

GPU batch initialization

Compile OpenCL kernel, allocate device buffers for rules and hash corpus.

Step 3

MAB exploration phase

Each rule gets initial trials; bandit algorithm tracks win rates with UCB confidence bounds.

Step 4

Early elimination

Rules whose upper confidence bound falls below threshold are dropped, freeing GPU cycles.

Step 5

Final exploitation

Remaining budget spent on top-k rules for precise hit rate estimates.

Step 6

Export sorted ruleset

Output .rule file sorted descending by hit rate.