Intel MKL also contains a number of BLAS-like extensions:

  • Triangular GEMM routines: Compute a matrix-matrix product but update only the upper or lower triangular part of the result matrix
  • Batched GEMM routines: Perform multiple GEMM operations in parallel
  • Packed GEMM routines: Amortize internal packing costs across multiple GEMM operations

Sparse BLAS (Levels 1, 2, 3) & Solvers

In addition to the standard Sparse BLAS APIs, Intel MKL also supports unique two-stage inspector-executor Sparse BLAS APIs for higher performance. For clusters, use the included implementation of the PARDISO* sparse solver, iterative sparse solver, or a distributed version of the solver. Tackle large-scale sparse eigenvalue problems with the highly robust and scalable Extended Eigensolver (based on the FEAST eigenvalue solver).

See Performance Benchmarks


See below for further notes and disclaimers.1

Ready to Get Started?



英特尔的编译器针对非英特尔微处理器的优化程度可能与英特尔微处理器相同(或不同)。这些优化包括 SSE2、SSE3 和 SSSE3 指令集和其他优化。对于在非英特尔制造的微处理器上进行的优化,英特尔不对相应的可用性、功能或有效性提供担保。该产品中依赖于微处理器的优化仅适用于英特尔微处理器。某些非特定于英特尔微架构的优化保留用于英特尔微处理器。关于此通知涵盖的特定指令集的更多信息,请参阅适用产品的用户指南和参考指南。

通知版本 #20110804