diff options
Diffstat (limited to 'sysdeps/sparc/sparc32/umul.S')
| -rw-r--r-- | sysdeps/sparc/sparc32/umul.S | 26 |
1 files changed, 14 insertions, 12 deletions
diff --git a/sysdeps/sparc/sparc32/umul.S b/sysdeps/sparc/sparc32/umul.S index 7a26c295cb..096554a2bc 100644 --- a/sysdeps/sparc/sparc32/umul.S +++ b/sysdeps/sparc/sparc32/umul.S @@ -14,13 +14,14 @@ * bnz overflow (or tnz) */ -#include "DEFS.h" -FUNC(.umul) +#include <sysdep.h> + +ENTRY(.umul) or %o0, %o1, %o4 - mov %o0, %y ! multiplier -> Y - andncc %o4, 0xfff, %g0 ! test bits 12..31 of *both* args - be Lmul_shortway ! if zero, can do it the short way - andcc %g0, %g0, %o4 ! zero the partial product and clear N and V + mov %o0, %y ! multiplier -> Y + andncc %o4, 0xfff, %g0 ! test bits 12..31 of *both* args + be LOC(mul_shortway) ! if zero, can do it the short way + andcc %g0, %g0, %o4 ! zero the partial product; clear N & V /* * Long multiply. 32 steps, followed by a final shift step. @@ -59,7 +60,6 @@ FUNC(.umul) mulscc %o4, %o1, %o4 ! 32 mulscc %o4, %g0, %o4 ! final shift - /* * Normally, with the shift-and-add approach, if both numbers are * positive you get the correct result. With 32-bit two's-complement @@ -97,20 +97,20 @@ FUNC(.umul) #if 0 tst %o1 bl,a 1f ! if %o1 < 0 (high order bit = 1), - add %o4, %o0, %o4 ! %o4 += %o0 (add y to upper half) + add %o4, %o0, %o4 ! %o4 += %o0 (add y to upper half) 1: rd %y, %o0 ! get lower half of product retl - addcc %o4, %g0, %o1 ! put upper half in place and set Z for %o1==0 + addcc %o4, %g0, %o1 ! put upper half in place and set Z for %o1==0 #else /* Faster code from tege@sics.se. */ sra %o1, 31, %o2 ! make mask from sign bit and %o0, %o2, %o2 ! %o2 = 0 or %o0, depending on sign of %o1 rd %y, %o0 ! get lower half of product retl - addcc %o4, %o2, %o1 ! add compensation and put upper half in place + addcc %o4, %o2, %o1 ! add compensation and put upper half in place #endif -Lmul_shortway: +LOC(mul_shortway): /* * Short multiply. 12 steps, followed by a final shift step. * The resulting bits are off by 12 and (32-12) = 20 bit positions, @@ -150,4 +150,6 @@ Lmul_shortway: srl %o5, 20, %o5 ! shift low bits right 20 or %o5, %o0, %o0 retl - addcc %g0, %g0, %o1 ! %o1 = zero, and set Z + addcc %g0, %g0, %o1 ! %o1 = zero, and set Z + +END(.umul) |