Reimagine graph analytics with the Lucata Pathfinder next-generation computing architecture. The Pathfinder enhances common graph databases or graph engines developed in-house to perform multi-hop analytics, including breadth-first search (BFS), on graph databases with 1 trillion vertices (scale 40) with no data pruning or database sharding. Lucata leverages patented migrating thread technology to treat even massive graph databases as unsharded instances, enabling fast analytics with no MapReduce-like processing.
Pathfinder Powers a New Generation of Graph Analytics
The Lucata Pathfinder hardware platform can power open-source or custom graph databases to achieve previously unattainable performance for graph analytics. The Pathfinder platform leverages Cilk open-source libraries to enable common graph databases such as RedisGraph or in-house developed graph engines to run on the platform. Cilk is a concurrency platform that makes parallel programming a simple extension of serial programming, while Pathfinder performs all memory and thread management behind the scenes.
Lucata Pathfinder can easily scale to meet your needs with no manual reprogramming required; it runs BFS analytics on petabyte-scale graph databases. A Lucata Pathfinder-S chassis features 512 GB of RAM and a minimum of 8 TB of SSD, which allows you to run real-time analytics on a 512 GB graph database with no database sharding while storing up to 8 TBs of graph data in near-memory. Each Pathfinder chassis can support up to eight 100 GBit I/O cards, allowing your graph database engine to ingest data at its maximum rate. A Pathfinder rack seamlessly connects eight Pathfinder chassis, providing 4 TB of RAM and a minimum of 64 TB of SSD. Over 1,000 racks can be interconnected as a single shared memory image, supporting over 4 PB of RAM and 64 PB of SSD.
There is no data pruning required for graph analytics or machine or deep learning training, eliminating the potential for introducing bias during pruning or sharding processes.
Pathfinder is a Smart Choice
The Pathfinder platform is cost-effective. The patented Lucata migratory thread approach to computing means compute threads move to your data rather than moving data to the CPUs. This approach results in much lower interconnect bandwidth requirements between Pathfinder chassis and racks than current approaches to distributed computing clusters require. Migratory thread computing allows Pathfinder chassis to consistently maintain high CPU and RAM utilization rates, lowering your operating costs.
Pathfinder is a new computing paradigm for big data. You can process petabyte-scale datasets in real-time with no data pruning or database sharding. Initially available for graph databases, the Pathfinder platform has the capability to power massive performance gains for a variety of other database types. Pathfinder can also power high-performance machine and AI model training on sparse data.
Pathfinder offers out-of-the-box support for a variety of graph analytics algorithms including:
|Connected Component||K-truss Subgraph|
|Breadth-First Search (BFS)||RandomAccess (GUPS)|
Scalable Shared Memory
Unprecedented performance and scalable to 4 PB of RAM for in-memory databases and data lake acceleration
Removes coherency cost and complexity overheads in shared memory databases for OLTP
Ultra lightweight computational elements for MPP databases combined with Migratory Threads for OLAP enable efficient queries without data movement
Low Power Consumption
60%+ reduction in power consumption for environmentally conscious data science