Visible to Intel only — GUID: GUID-1DF7D7A8-39C9-40A0-98DA-744F3336F25B
Visible to Intel only — GUID: GUID-1DF7D7A8-39C9-40A0-98DA-744F3336F25B
simd, Qsimd
Enables or disables compiler interpretation of SIMD directives.This feature is only available for ifort.
Syntax
Linux: |
-simd -no-simd |
macOS: |
-simd -no-simd |
Windows: |
/Qsimd /Qsimd- |
Arguments
None
Default
-simd |
SIMD directives are enabled. |
Description
This option enables or disables compiler interpretation of SIMD directives.
To disable interpretation of SIMD directives, specify -no-simd (Linux* and macOS) or /Qsimd- (Windows*). Note that the compiler may still vectorize loops based on its own heuristics (leading to generation of SIMD instructions) even when -no-simd (or /Qsimd-) is specified.
To disable all compiler vectorization, use the "-no-vec -no-simd" (Linux* and macOS) or "/Qvec- /Qsimd-" (Windows*) compiler options. The option -no-vec (and /Qvec-) disables all auto-vectorization, including vectorization of array notation statements. The option -no-simd (and /Qsimd-) disables vectorization of loops that have SIMD directives.
If you specify option -mia32 (Linux*) or option /arch:IA32 (Windows*), SIMD directives are disabled by default and vector instructions cannot be used. Therefore, you cannot explicitly enable SIMD directives by specifying option [Q]simd.
IDE Equivalent
Alternate Options
None