Post-Doctoral Researcher F/M Dynamic Parallelization of Sparse Codes for High-Performance Computing and Machine Learning

Most kernels of interest in machine learning and high-performance computing manipulate sparse tensors. Sparse codes are highly irregular and make use of array indirections and dynamic control which jeopardize static automatic parallelization algorithms.

The overall objective of this postdoctoral fellowship is to investigate compiler and runtime algorithms to delay the specialization of the dense code at runtime when the sparse structure is known.

From a dense specification, we seek to compile a code able to specialize itself on the sparse input data. The specialization will involve a set of sub-computations, which are expected to be achievable by standard linear algebra routines (e.g. gemm), using state-of-the art linear algebra libraries.Several issues must be investigated:

• How to specialize the code? In particular, how propagate efficiently the sparsity along the computation flow?
• How to detect library kernels on the specialized code?
• How to enforce a proper scheduling for the parallel runtime?

Points 1 and 2 have been partially addressed by a PhD student.

The postdoctoral fellow will:

• Propose code optimizations and data structures for scaling sparse propagation (point 1)
• Address runtime scheduling (point 3) by relying on existing parallel runtimes
• Validate the complete approach (points 1, 2 and 3) on scientific benchmarks by using sparse tensors from the Florida sparse matrix collection as well as machine learning applications.

This position is funded by the French prioritary research program for exascale computing in France (PEPR NumPEx).

Inria Lyon is a leading research center in computer science and applied mathematics, dedicated to advancing knowledge and technology. We foster innovation, collaboration, and excellence in research and education.

Metadata

Topics: Compilation, High-performance computing, Optimization, Parallel computing, Performance engineering, Runtime performance

Summary

Inria Lyon seeks a Post-Doctoral Researcher for 14 months to optimize dynamic parallelization of sparse codes in high-performance computing and machine learning, focusing on compiler algorithms and scheduling.

Post-Doctoral Researcher F/M Dynamic Parallelization of Sparse Codes for High-Performance Computing and Machine Learning

Full-time

Inria Lyon

Lyon, FR

Inria Lyon seeks a Post-Doctoral Researcher for 14 months to optimize dynamic parallelization of sparse codes in high-performance computing and machine learning, focusing on compiler algorithms and scheduling.

Context & Goals

Most kernels of interest in machine learning and high-performance computing manipulate sparse tensors. Sparse codes are highly irregular and make use of array indirections and dynamic control which jeopardize static automatic parallelization algorithms.

The overall objective of this postdoctoral fellowship is to investigate compiler and runtime algorithms to delay the specialization of the dense code at runtime when the sparse structure is known.

From a dense specification, we seek to compile a code able to specialize itself on the sparse input data. The specialization will involve a set of sub-computations, which are expected to be achievable by standard linear algebra routines (e.g. gemm), using state-of-the art linear algebra libraries.Several issues must be investigated:

• How to specialize the code? In particular, how propagate efficiently the sparsity along the computation flow?
• How to detect library kernels on the specialized code?
• How to enforce a proper scheduling for the parallel runtime?

Points 1 and 2 have been partially addressed by a PhD student.

The postdoctoral fellow will:

• Propose code optimizations and data structures for scaling sparse propagation (point 1)
• Address runtime scheduling (point 3) by relying on existing parallel runtimes
• Validate the complete approach (points 1, 2 and 3) on scientific benchmarks by using sparse tensors from the Florida sparse matrix collection as well as machine learning applications.

This position is funded by the French prioritary research program for exascale computing in France (PEPR NumPEx).

The HiPEAC project has received funding from the Eur