3
我试图以正确的方式优化此代码。我的意思是正确的是...我会想象有一种通用的方法来执行这些优化,以便如果其他人查看代码,他们将能够删除优化。对于可读性代码优化SPARC汇编中的循环
C采样...
int a = 1; // mapped to %l0
int b = 5; // mapped to %l1
int c = 0; // mapped to %l2
int d; // mapped to %l3
while(a < b) {
c += a * b;
++a;
}
d = c * b;
SPARC集版本......
mov %g0, %l2
cmp %l0, %l1
bge END_LOOP
nop
LOOP:
mov %l0, %o0
call .mul
mov %l1, %o1 ! Fill delay slot with second argument
add %l2, %o0, %l2
inc %l0
cmp %l0, %l1
bl LOOP
nop
END_LOOP:
mov %l2, %o0
call .mul ! Fill delay sot with second argument
mov %l1, %o1
mov %o0, %l3
我可以优化第一部分(不知道是否正确),但我不知道如何优化第二部分。
mov %g0, %l2
cmp %l0, %l1
bge,a END_LOOP ! Annul branch to execute if branch is taken
mov %l2, %o0 ! Instruction at target
LOOP:
mov %l0, %o0
call .mul
mov %l1, %o1 ! Fill delay slot with second argument
add %l2, %o0, %l2
inc %l0
cmp %l0, %l1
bl LOOP
nop
mov %l2, %o0 ! Move the instruction to above the target
END_LOOP:
call .mul ! Fill delay sot with second argument
mov %l1, %o1
mov %o0, %l3
任何有关如何执行这些优化的帮助将非常感激。
如果您的目标是SPARC v8或更高版本,则可以使用'SMUL'指令而不是调用'.mul'系统库例程。 – Michael
我可能应该补充一点。这是一个较旧的32位SPARC机器。 – logbaseinfinity