blob: e83dd51a8328fc8f5b7ef4baef947330b6d75ab7 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
|
/**
* Not necessarily optimal... but it produces correct results (at least for int)
* If we're lucky, LLVM will recognize the pattern and produce rotate
* instructions:
* http://llvm.1065342.n5.nabble.com/rotate-td47679.html
*
* Eventually, someone should feel free to implement an llvm-specific version
*/
_CLC_OVERLOAD _CLC_DEF GENTYPE rotate(GENTYPE x, GENTYPE n){
//Try to avoid extra work if someone's spinning the value through multiple
//full rotations
n = n % (GENTYPE)GENSIZE;
//Determine if we're doing a right or left shift on each component
//The actual shift algorithm is based on a rotate right
//e.g. a rotate of int by 5 bits becomes rotate right by 26 bits
// and a rotate of int by -4 bits becomes rotate right by 4
GENTYPE amt = (n > (GENTYPE)0 ? (GENTYPE)GENSIZE - n : (GENTYPE)0 - n );
//Calculate the bits that will wrap
GENTYPE mask = ( (GENTYPE)1 << amt ) - (GENTYPE)1;
GENTYPE wrapped_bits = x & mask;
//Shift the input value right and then AND a mask that eliminates
//sign-extension interference
//if the rotate amount is 0, just use ~0 for a mask
GENTYPE se_mask = !amt ? ~((GENTYPE)0) :
( ( (GENTYPE)1 << ((GENTYPE)GENSIZE - amt) ) - (GENTYPE)1 );
GENTYPE unwrapped_bits = x >> amt;
unwrapped_bits &= se_mask;
//Finally shift the input right after moving the wrapped bits into position
return unwrapped_bits | (wrapped_bits << ( (GENTYPE)GENSIZE - amt ) );
}
|
