diff options
Diffstat (limited to 'contrib/compiler-rt/lib/arm/umodsi3.S')
-rw-r--r-- | contrib/compiler-rt/lib/arm/umodsi3.S | 58 |
1 files changed, 58 insertions, 0 deletions
diff --git a/contrib/compiler-rt/lib/arm/umodsi3.S b/contrib/compiler-rt/lib/arm/umodsi3.S new file mode 100644 index 000000000000..3a2ab2b87751 --- /dev/null +++ b/contrib/compiler-rt/lib/arm/umodsi3.S @@ -0,0 +1,58 @@ +/*===-- 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 |