http://d.puremagic.com/issues/show_bug.cgi?id=9917
Summary: Excessive overhead for small-size vector ops
Product: D
Version: D2
Platform: All
OS/Version: All
Status: NEW
Severity: enhancement
Priority: P2
Component: DMD
AssignedTo: [email protected]
ReportedBy: [email protected]
--- Comment #0 from [email protected] 2013-04-10 19:38:48 PDT ---
I suggest to inline with normal code the vector ops among arrays that are
statically known to be quite short.
The following two benchmarks compute the number of Pythagorean triples and show
the performance difference between using a sum among ulong[2] and doing the
same with a struct that defined opOpAssign("+").
Runtime first version about 5.8 seconds, runtime second version about 0.7
seconds.
// First version - - - - - - - - - -
import std.stdio;
ulong[2] tri(in ulong lim, in ulong a=3, in ulong b=4, in ulong c=5) pure {
immutable l = a + b + c;
if (l > lim)
return [0, 0];
ulong[2] r = [1, lim / l];
r[] += tri(lim, a - 2*b + 2*c, 2*a - b + 2*c, 2*a - 2*b + 3*c)[];
r[] += tri(lim, a + 2*b + 2*c, 2*a + b + 2*c, 2*a + 2*b + 3*c)[];
r[] += tri(lim, -a + 2*b + 2*c, -2*a + b + 2*c, -2*a + 2*b + 3*c)[];
return r;
}
void main() {
tri(10 ^^ 8).writeln;
}
//- - - - - - - - - - - - - - -
// Second version - - - - - - - - - -
import std.stdio;
struct Pair {
ulong x, y;
void opOpAssign(string op="+")(in Pair p2) pure nothrow {
x += p2.x;
y += p2.y;
}
}
Pair tri(in ulong lim, in ulong a=3, in ulong b=4, in ulong c=5) pure {
immutable l = a + b + c;
if (l > lim)
return Pair();
auto r = Pair(1, lim / l);
r += tri(lim, a - 2*b + 2*c, 2*a - b + 2*c, 2*a - 2*b + 3*c);
r += tri(lim, a + 2*b + 2*c, 2*a + b + 2*c, 2*a + 2*b + 3*c);
r += tri(lim, -a + 2*b + 2*c, -2*a + b + 2*c, -2*a + 2*b + 3*c);
return r;
}
void main() {
tri(10 ^^ 8).writeln;
}
//- - - - - - - - - - - - - - -
--
Configure issuemail: http://d.puremagic.com/issues/userprefs.cgi?tab=email
------- You are receiving this mail because: -------
