forked from OSchip/llvm-project
59 lines
1.8 KiB
ArmAsm
59 lines
1.8 KiB
ArmAsm
/*===-- umodsi3.S - 32-bit unsigned integer modulus -----------------------===//
|
|
*
|
|
* The LLVM Compiler Infrastructure
|
|
*
|
|
* This file is dual licensed under the MIT and the University of Illinois Open
|
|
* Source Licenses. See LICENSE.TXT for details.
|
|
*
|
|
*===----------------------------------------------------------------------===//
|
|
*
|
|
* This file implements the __umodsi3 (32-bit unsigned integer modulus)
|
|
* function for the ARM architecture. A naive digit-by-digit computation is
|
|
* employed for simplicity.
|
|
*
|
|
*===----------------------------------------------------------------------===*/
|
|
|
|
#include "../assembly.h"
|
|
|
|
#define a r0
|
|
#define b r1
|
|
#define r r2
|
|
#define i r3
|
|
|
|
.syntax unified
|
|
.align 3
|
|
DEFINE_COMPILERRT_FUNCTION(__umodsi3)
|
|
// We use a simple digit by digit algorithm; before we get into the actual
|
|
// divide loop, we must calculate the left-shift amount necessary to align
|
|
// the MSB of the divisor with that of the dividend.
|
|
clz r2, a
|
|
tst b, b // detect b == 0
|
|
clz r3, b
|
|
bxeq lr // return a if b == 0
|
|
subs i, r3, r2
|
|
bxlt lr // return a if MSB(a) < MSB(b)
|
|
|
|
LOCAL_LABEL(mainLoop):
|
|
// This loop basically implements the following:
|
|
//
|
|
// do {
|
|
// if (a >= b << i) {
|
|
// a -= b << i;
|
|
// if (a == 0) break;
|
|
// }
|
|
// } while (--i)
|
|
//
|
|
// Note that this does not perform the final iteration (i == 0); by doing it
|
|
// this way, we can merge the two branches which is a substantial win for
|
|
// such a tight loop on current ARM architectures.
|
|
subs r, a, b, lsl i
|
|
movhs a, r
|
|
subsne i, i, #1
|
|
bhi LOCAL_LABEL(mainLoop)
|
|
|
|
// Do the final test subtraction and update of remainder (i == 0), as it is
|
|
// not performed in the main loop.
|
|
subs r, a, b
|
|
movhs a, r
|
|
bx lr
|