llvm-project/compiler-rt/lib/arm/umodsi3.S

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