Module optimized

Module optimized 

Source
Expand description

Optimized sparse matrix implementations with SIMD acceleration and buffer pooling.

This module provides high-performance matrix storage formats optimized for sublinear-time algorithms with focus on minimizing memory allocation overhead and maximizing cache efficiency.

Structs§

BufferPool
High-performance buffer pool for reducing allocation overhead.
BufferPoolStats
Buffer pool statistics.
OptimizedCSRStorage
Optimized CSR storage with SIMD acceleration and buffer pooling.
OptimizedMatrixStats
Performance statistics for optimized matrix operations.
ParallelCSRStorage
Parallel CSR storage for multi-threaded operations.
StreamingMatrix
Memory-efficient matrix representation for extremely large problems.

Functions§

get_global_buffer
Get a buffer from the global pool.
return_global_buffer
Return a buffer to the global pool.