查看 Julia 的源代码：
julia/base/math.jl:
^(x::Float64, y::Integer) =
box(Float64, powi_llvm(unbox(Float64,x), unbox(Int32,Int32(y))))
^(x::Float32, y::Integer) =
box(Float32, powi_llvm(unbox(Float32,x), unbox(Int32,Int32(y))))
julia/base/fastmath.jl:
pow_fast{T<:FloatTypes}(x::T, y::Integer) = pow_fast(x, Int32(y))
pow_fast{T<:FloatTypes}(x::T, y::Int32) =
box(T, Base.powi_llvm(unbox(T,x), unbox(Int32,y)))
我们可以看到 Julia 使用了 powi_llvm
检查llvm's source code：
define double @powi(double %F, i32 %power) {
; CHECK: powi:
; CHECK: bl __powidf2
%result = call double @llvm.powi.f64(double %F, i32 %power)
ret double %result
}
现在，__powidf2 是这里有趣的功能：
COMPILER_RT_ABI double
__powidf2(double a, si_int b)
{
const int recip = b < 0;
double r = 1;
while (1)
{
if (b & 1)
r *= a;
b /= 2;
if (b == 0)
break;
a *= a;
}
return recip ? 1/r : r;
}
示例 1：给定 a = 2； b = 7：
- r = 1
- iteration 1: r = 1 * 2 = 2; b = (int)(7/2) = 3; a = 2 * 2 = 4
- iteration 2: r = 2 * 4 = 8; b = (int)(3/2) = 1; a = 4 * 4 = 16
- iteration 3: r = 8 * 16 = 128;
示例 2：给定 a = 2； b = 8：
- r = 1
- iteration 1: r = 1; b = (int)(8/2) = 4; a = 2 * 2 = 4
- iteration 2: r = 1; b = (int)(4/2) = 2; a = 4 * 4 = 16
- iteration 3: r = 1; b = (int)(2/2) = 1; a = 16 * 16 = 256
- iteration 4: r = 1 * 256 = 256; b = (int)(1/2) = 0;
整数幂总是以序列乘法的形式实现。这就是为什么 N^3 比 N^2 慢的原因。
jl_powi_llvm（在 fastmath.jl 中调用。“jl_”由宏扩展连接）另一方面，将指数转换为浮点并调用 pow()。 C源代码：
JL_DLLEXPORT jl_value_t *jl_powi_llvm(jl_value_t *a, jl_value_t *b)
{
jl_value_t *ty = jl_typeof(a);
if (!jl_is_bitstype(ty))
jl_error("powi_llvm: a is not a bitstype");
if (!jl_is_bitstype(jl_typeof(b)) || jl_datatype_size(jl_typeof(b)) != 4)
jl_error("powi_llvm: b is not a 32-bit bitstype");
jl_value_t *newv = newstruct((jl_datatype_t*)ty);
void *pa = jl_data_ptr(a), *pr = jl_data_ptr(newv);
int sz = jl_datatype_size(ty);
switch (sz) {
/* choose the right size c-type operation */
case 4:
*(float*)pr = powf(*(float*)pa, (float)jl_unbox_int32(b));
break;
case 8:
*(double*)pr = pow(*(double*)pa, (double)jl_unbox_int32(b));
break;
default:
jl_error("powi_llvm: runtime floating point intrinsics are not implemented for bit sizes other than 32 and 64");
}
return newv;
}