Provides an auto-parallelizing Python compiler that generates low-level MPI code, enabling high-performance computing (HPC) capabilities directly from Python without requiring code rewrites or complex framework integrations. This platform accelerates data processing and analytics workloads by 10x to 100x compared to traditional tools like Spark, Ray, or Dask, while supporting popular libraries such as Pandas and NumPy for seamless integration.
Funding
$25.5M raised to dateRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.
Founders
Product
Problem
Existing data processing frameworks like Spark, Ray, and Dask often suffer from performance bottlenecks and require complex configurations, hindering the efficient scaling of Python-based data analytics and AI workloads. Rewriting code or integrating intricate frameworks is often necessary to achieve high-performance computing (HPC) capabilities.
Solution
Bodo provides an auto-parallelizing Python compiler that directly generates low-level MPI code, enabling native HPC performance from Python without code rewrites or complex framework integrations. This approach bypasses the inefficiencies of traditional frameworks, delivering 10x to 100x faster performance on data processing and analytics workloads. The compiler supports popular libraries such as Pandas and NumPy, ensuring seamless integration with existing Python workflows. Bodo binaries are infrastructure-agnostic, scaling from a single laptop to cloud environments as cores are added, without requiring additional code.
Target Audience
The primary target audience includes data scientists, machine learning engineers, and HPC professionals who use Python for data analytics, AI, and other computationally intensive tasks.
Features
- Automatic compiler parallelization and MPI code generation for high-performance execution
- Comprehensive support for Pandas and NumPy APIs, allowing existing code to run without modification
- Compiler optimizations for sequential CPU performance, maximizing resource utilization
- Enhanced support for data science and machine learning libraries
- Python UDF compilation and optimization
- Scalable I/O for leading data formats and databases
- Automatic filter pushdown to reduce data transfer overhead
- Portable compilation with LLVM, enabling deployment on various platforms