Intel-Specific Pragma Reference
The pragmas that are specific to the
Intel® oneAPI
are described below. Click on each pragma name for a more detailed description.
DPC++/C++
CompilerSome
pragmas
are available for both Intel® microprocessors and non-Intel microprocessors, but may perform additional optimizations for Intel® microprocessors than for non-Intel microprocessors.
Pragma
| Description
|
|---|---|
Allocates one or more
variables in the specified section. Controls section attribute specification
for variables. | |
Instructs the compiler
to prefer loop distribution at the location indicated. | |
Specifies inlining of
all calls in a statement. This also describes pragmas forceinline and
noinline. | |
For Intel legacy tasking, specifies a unit of work,
potentially executed by a different thread. | |
For Intel legacy tasking, specifies an environment for the
while loop in which to queue the units of work specified by the enclosed
task pragma. | |
Instructs the compiler
to ignore assumed vector dependencies. | |
Specifies the
iterations for a for loop. | |
Prevents a loop from fusing with adjacent loops. | |
Specifies that a
particular loop should never be vectorized. | |
Controls optimization for one function or all functions
after its first occurrence. | |
Passes certain information about a function to the
optimizer. | |
Extends
#pragma omp simd , allowing vectorization of multiple exit loops.
| |
Enables or disables
optimizations for code after this pragma until another optimize pragma or end
of the translation unit. | |
Resolves dependencies
to facilitate auto-parallelization of the immediately following loop (parallel)
or prevents auto-parallelization of the immediately following loop
(noparallel). | |
Enforces vectorization
of loops. | |
Specifies a block of
code in the SIMD loop or SIMD-enabled function that should be executed
serially, in a logical order of SIMD lanes. | |
Conditionally calls a
procedure offload variant if the specified device is available; otherwise,
executes the procedure on the host.
| |
Tells the compiler to
unroll or not to unroll a counted loop. | |
Enables or disables
loop unrolling and jamming. These pragmas can only be applied to iterative for
loops. | |
Tells the compiler
that the loop should be vectorized according to the argument keywords.
|