Use Automatic Vectorization

Automatic vectorization is supported on IA-32and Intel® 64 architectures. The information below will guide you in setting up the auto-vectorizer.

Vectorization Speedup

Where does the vectorization speedup come from? Consider the following sample code, where a, b, and c are integer arrays:

for (i=0;i<=MAX;i++)
   c[i]=a[i]+b[i];

If vectorization is not enabled, and you compile using the O1, -no-vec- (Linux), or /Qvec- (Windows) option, the compiler processes the code with unused space in the SIMD registers, even though each register can hold three additional integers. If vectorization is enabled (compiled using O2 or higher options), the compiler may use the additional registers to perform four additions in a single instruction. The compiler looks for vectorization opportunities whenever you compile at default optimization (O2) or higher.

Note

This option enables vectorization at default optimization levels for both Intel® microprocessors and non-Intel microprocessors. Vectorization may call library routines that can result in additional performance gain on Intel® microprocessors than on non-Intel microprocessors. The vectorization can also be affected by certain options, such as /arch (Windows), -m (Linux and macOS), or [Q]x.

Tip

This tip is only for the Intel® C++ (icc) Classic Compiler. To allow comparisons between vectorized and non-vectorized code, disable vectorization using the -no-vec (Linux or macOS) or /Qvec- (Windows) option; enable vectorization using the O2 option.

To learn if a loop was vectorized or not, enable generation of the optimization report using the options qopt-report=1 qopt-report-phase=vec (Linux and macOS) or Qopt-report:1 Qopt-report-phase:vec (Windows) options. These options generate a separate report in an *.optrpt file that includes optimization messages. In Microsoft Visual Studio, the program source is annotated with the report's messages, or you can read the resulting .optrpt file using a text editor. A message appears for every loop that is vectorized, for example:

icl /Qopt-report:1 /Qopt-report-phase:vec  Multiply.c 
Multiply.c(92): (col. 5) remark: LOOP WAS VECTORIZED.

The source line number (92 in the above example) refers to either the beginning or the end of the loop.

To get details about the type of loop transformations and optimizations that took place, use the [Q]opt-report-phase option by itself or along with the [Q]opt-report option.

To get information on if the loop was vectorized using the Microsoft Visual Studio IDE, select Project > Properties > C/C++ > Diagnostics > Optimization Diagnostic Level as Level 1 (/Qopt-report:1) and Optimization Diagnostic Phase as Loop Nest Optimization (/Qopt-report-phase:loop). To get a diagnostic message for every loop that was not vectorized, with a brief explanation of why the loop was not vectorized, select /Qopt-report-phase:vec.

Linux

To evaluate performance enhancement, run vec_samples:

  1. Source an environment script such as compilervars.sh or the compilervars.csh in the <installdir>/bin directory and use the attribute appropriate for the architecture.
  2. Navigate to the <install-dir>\Samples\<locale>\C++\ directory. This application multiplies a vector by a matrix using the following loop:

    for (j = 0;j < size2; j++) { b[i] += a[i][j] * x[j]; }

  3. Build and run the application, first without enabling auto-vectorization. The default O2 optimization enables vectorization, so you need to disable it with a separate option.

    icc -O2 -no-vec  Multiply.c -o NoVectMult 
    ./NoVectMult

  4. Build and run the application, this time with auto-vectorization.

    icx -O2 -qopt-report=3 -vec Multiply.c -o VectMult 
    ./VectMult

Windows

To evaluate performance enhancement, run vec_samples:

  1. Under the Start menu item for your product, select an icon under Compiler and Performance Libraries > Command Prompt with Intel Compiler for Classic Compilers or
  2. Navigate to the <install-dir>\Samples\<locale>\C++\directory. On Windows, unzip the sample project vec_samples.zip to a writable directory. This small application multiplies a vector by a matrix using the following loop:

    for (j = 0;j < size2; j++) { b[i] += a[i][j] * x[j]; }

  3. Build and run the application, first without enabling auto-vectorization. The default O2 optimization enables vectorization, so you need to disable it with a separate option.

    icl /O2 /Qvec- Multiply.c /FeNoVectMult 
    NoVectMult

  4. Build and run the application, this time with auto-vectorization.

    icl /O2 /Qopt-report:3 /Qvec Multiply.c /FeVectMult 
    VectMult

When you compare the timing of the two runs, you may see that the vectorized version runs faster. The time for the non-vectorized version is only slightly faster than would be obtained by compiling with the O1 option.

Obstacles to Vectorization

The following issues do not always prevent vectorization, but frequently cause the compiler to decide that vectorization would not be worthwhile.

Help the Compiler Vectorize

Sometimes the compiler has insufficient information to decide to vectorize a loop. There are several ways to provide additional information to the compiler:

See Also