TIDES
Tiered block-sparse tensor contraction with a streaming transpose on GPUs.
Open Source
Tiered block-sparse tensor contraction with a streaming transpose on GPUs.
STTID: High-Performance Sparse Tensor-Train Interpolative Decomposition.
RedSan: A Redundant Memory Instruction Sanitizer for GPU Programs.
SymProp: Scaling Sparse Symmetric Tucker Decomposition via Symmetry Propagation.
A hierarchical parallel tensor infrastructure for sparse and structured tensor computing.
A parallel sparse tensor algorithm benchmark suite spanning CPUs and GPUs.
A parallel tensor infrastructure for data analysis and tensor kernels.
Adaptive tensor memoization support for CP decomposition.
Input-adaptive and in-place dense tensor-times-matrix multiplication.
A sparse matrix-vector multiplication auto-tuner.