Improving Performance for Small Size Problems

The overhead of calling an Intel MKL function for small problem sizes can be significant when the function has a large number of parameters or internally checks parameter errors. To reduce the performance overhead for these small size problems, the Intel MKL direct call feature works in conjunction with the compiler to preprocess the calling parameters to ?gemm functions and directly call or inline special optimized small-matrix kernels that bypass error checking.

To activate the feature, do the following:

• Compile your C or Fortran code with the preprocessor macro depending on whether a threaded or sequential mode of Intel MKL is required by supplying the compiler option as explained below:

  Intel MKL Mode	Macro	Compiler Option
  Threaded	MKL_DIRECT_CALL	-DMKL_DIRECT_CALL
  Sequential	MKL_DIRECT_CALL_SEQ	-DMKL_DIRECT_CALL_SEQ

• For Fortran applications:

  • Enable preprocessor by using the -fpp option for Intel® Fortran Compiler and -Mpreprocess option for PGI* compilers.
  • Include the Intel MKL Fortran include file mkl_direct_call.fi.

Intel MKL skips error checking and intermediate function calls if the problem size is small enough (for example, a dgemm function call with matrix ranks smaller than 50).

• Using MKL_DIRECT_CALL in C Applications
  
• Using MKL_DIRECT_CALL in Fortran Applications
  
• Limitations of the Direct Call