mirror of
https://codeberg.org/ziglang/zig.git
synced 2025-12-06 13:54:21 +00:00
fc59a04061
- approach by Hacker's Delight with wrapping subtraction - performance expected to be similar to addo - tests with all relevant combinations of min,max with -1,0,+1 and all combinations of sequences +-1,2,4..,max
38 lines
1.3 KiB
Zig
38 lines
1.3 KiB
Zig
const builtin = @import("builtin");
|
|
|
|
// addo - add overflow
|
|
// * return a+%b.
|
|
// * return if a+b overflows => 1 else => 0
|
|
// - addoXi4_generic as default
|
|
|
|
inline fn addoXi4_generic(comptime ST: type, a: ST, b: ST, overflow: *c_int) ST {
|
|
@setRuntimeSafety(builtin.is_test);
|
|
overflow.* = 0;
|
|
var sum: ST = a +% b;
|
|
// Hackers Delight: section Overflow Detection, subsection Signed Add/Subtract
|
|
// Let sum = a +% b == a + b + carry == wraparound addition.
|
|
// Overflow in a+b+carry occurs, iff a and b have opposite signs
|
|
// and the sign of a+b+carry is the same as a (or equivalently b).
|
|
// Slower routine: res = ~(a ^ b) & ((sum ^ a)
|
|
// Faster routine: res = (sum ^ a) & (sum ^ b)
|
|
// Overflow occured, iff (res < 0)
|
|
if (((sum ^ a) & (sum ^ b)) < 0)
|
|
overflow.* = 1;
|
|
return sum;
|
|
}
|
|
|
|
pub fn __addosi4(a: i32, b: i32, overflow: *c_int) callconv(.C) i32 {
|
|
return addoXi4_generic(i32, a, b, overflow);
|
|
}
|
|
pub fn __addodi4(a: i64, b: i64, overflow: *c_int) callconv(.C) i64 {
|
|
return addoXi4_generic(i64, a, b, overflow);
|
|
}
|
|
pub fn __addoti4(a: i128, b: i128, overflow: *c_int) callconv(.C) i128 {
|
|
return addoXi4_generic(i128, a, b, overflow);
|
|
}
|
|
|
|
test {
|
|
_ = @import("addosi4_test.zig");
|
|
_ = @import("addodi4_test.zig");
|
|
_ = @import("addoti4_test.zig");
|
|
}
|