mlemanczyk/even-perfect-numbers-scanner
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Benchmark results and TODOs added / updated

Browse Source
This commit is contained in:
Marek Lemańczyk committed 2025-10-02 15:00:30 +02:00
1 parent 507b9c91f4
commit f9e548279c
31 files changed
+581 -364
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

EvenPerfectBitScanner.Benchmarks/Mod10_8_5_3Benchmarks.cs
+41 -31
View File
@@ -9,51 +9,62 @@ public class Mod10_8_5_3Benchmarks
[Params(3UL, 8191UL, 131071UL, 2147483647UL)]
public ulong Value { get; set; }
/// <summary>
/// Fastest
/// </summary>
[Benchmark(Baseline = true)]
/// <summary>
/// Baseline scalar modulo path; held steady between 1.13 ns and 1.14 ns across every value (1.138 ns at 3, 1.143 ns at 8191,
/// 1.134 ns at 131071, 1.141 ns at 2147483647), making it the fastest option overall.
/// </summary>
[Benchmark(Baseline = true)]
public (ulong Mod10, ulong Mod8, ulong Mod3, ulong Mod5) ModuloOperator()
{
ulong value = Value;
return (value % 10UL, value % 8UL, value % 3UL, value % 5UL);
}
/// <summary>
/// Legacy folding helper; useful for cross-checks but stays at 2.83-3.07 ns (2.834 ns at 3, 3.038 ns at 8191, 3.067 ns at
/// 131071, 3.039 ns at 2147483647), roughly 2.5-2.7x slower than the baseline.
/// </summary>
[Benchmark]
public (ulong Mod10, ulong Mod8, ulong Mod3, ulong Mod5) LegacyModulo()
{
ulong mod10, mod8, mod3, mod5;
UInt128 zero = UInt128.Zero;
if (Value == zero)
{
mod3 = 0UL;
mod5 = 0UL;
mod8 = 0UL;
mod10 = 0UL;
return (mod10, mod8, mod3, mod5);
}
ulong mod10;
ulong mod8;
ulong mod3;
ulong mod5;
UInt128 zero = UInt128.Zero;
if (Value == zero)
{
mod3 = 0UL;
mod5 = 0UL;
mod8 = 0UL;
mod10 = 0UL;
return (mod10, mod8, mod3, mod5);
}
UInt128 high = Value >> 64;
ulong result = Value;
mod8 = result & 7UL;
// 2^64 ≡ 1 (mod 3)
ulong modRem = (result % 3UL) + ((ulong)high % 3UL);
mod3 = modRem >= 3UL ? modRem - 3UL : modRem;
// 2^64 ≡ 1 (mod 5)
modRem = (result % 5UL) + ((ulong)high % 5UL);
mod5 = modRem >= 5UL ? modRem - 5UL : modRem;
UInt128 high = Value >> 64;
ulong result = Value;
mod8 = result & 7UL;
while (high != zero)
{
// 2^64 ≡ 6 (mod 10)
result = (result + (ulong)high * 6UL) % 10UL;
high >>= 64;
}
ulong modRem = (result % 3UL) + ((ulong)high % 3UL);
mod3 = modRem >= 3UL ? modRem - 3UL : modRem;
mod10 = result % 10UL;
modRem = (result % 5UL) + ((ulong)high % 5UL);
mod5 = modRem >= 5UL ? modRem - 5UL : modRem;
while (high != zero)
{
result = (result + (ulong)high * 6UL) % 10UL;
high >>= 64;
}
mod10 = result % 10UL;
return (mod10, mod8, mod3, mod5);
}
/// <summary>
/// Method-based optimized helper; clocks in at 1.63 ns for value 3, 1.64 ns at 8191, 1.875 ns at 131071, and 2.164 ns at
/// 2147483647 (1.43-1.90x the baseline) so it trails the raw `%` but remains 1.6x quicker than the legacy fold.
/// </summary>
[Benchmark]
public (ulong Mod10, ulong Mod8, ulong Mod3, ulong Mod5) ModMethodModulo()
{
@@ -61,4 +72,3 @@ public class Mod10_8_5_3Benchmarks
return (mod10, mod8, mod3, mod5);
}
}