| Copyright © 2007-2010 ARM. All rights reserved. | ARM DUI 0348C |
| Non-Confidential | ID101213 |
 PDF version | |
| Home > Compiler-specific Features > Pragmas > #pragma unroll_completely |
| |||
| Home > Compiler-specific Features > Pragmas > #pragma unroll_completely | |||
This pragma instructs the compiler to completely unroll a loop. It has an effect only if the compiler can determine the number of iterations the loop has.
Both vectorized and non vectorized loops can be unrolled using #pragma unroll_completely.
That is, #pragma unroll_completely applies to
both --no_vectorize and --vectorize.
When compiling at -O3 -Otime,
the compiler automatically unrolls loops where it is beneficial
to do so. You can use this pragma to request that the compiler completely unroll
a loop that has not automatically been unrolled completely.
Use this #pragma only when you have evidence,
for example from --diag_warning=optimizations,
that the compiler is not unrolling loops optimally by itself.
#pragma unroll_completely can only be used
immediately before a for loop, a while loop,
or a do ... while loop.
Using #pragma unroll_completely on an outer
loop can prevent vectorization. On the other hand, using #pragma
unroll_completely on an inner loop might help in some
cases.
Optimizing loops in the Compiler User Guide.
| Copyright © 2007-2010 ARM. All rights reserved. | ARM DUI 0348C |
| Non-Confidential | ID101213 |
| PDF version | |
| Home > Compiler-specific Features > Pragmas > #pragma unroll_completely |