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

Various optimizations and cleanups. "in" removed from GpuUInt128 to avoid defensive copies from IL.

Browse Source
This commit is contained in:
mlemanczyk committed 2025-10-10 09:26:25 +02:00
1 parent 70eca5126b
commit ca0cadc8a3
18 files changed
+565 -395
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

PerfectNumbers.Core/ExponentRemainderStepper.cs
+16 -27
View File
@@ -1,31 +1,20 @@
namespace PerfectNumbers.Core;
internal struct ExponentRemainderStepper
internal struct ExponentRemainderStepper(in MontgomeryDivisorData divisor)
{
private readonly MontgomeryDivisorData _divisor;
private readonly ulong _modulus;
private readonly ulong _nPrime;
private readonly ulong _montgomeryOne;
private ulong _previousExponent;
private ulong _currentMontgomery;
private bool _hasState;
private readonly MontgomeryDivisorData _divisor = divisor;
private readonly ulong _modulus = divisor.Modulus;
private readonly ulong _nPrime = divisor.NPrime;
private readonly ulong _montgomeryOne = divisor.MontgomeryOne;
private ulong _previousExponent = 0UL;
private ulong _currentMontgomery = divisor.MontgomeryOne;
private bool _hasState = false;
public ExponentRemainderStepper(in MontgomeryDivisorData divisor)
{
_divisor = divisor;
_modulus = divisor.Modulus;
_nPrime = divisor.NPrime;
_montgomeryOne = divisor.MontgomeryOne;
_previousExponent = 0UL;
_currentMontgomery = divisor.MontgomeryOne;
_hasState = false;
}
public readonly bool IsValidModulus => _modulus > 1UL && (_modulus & 1UL) != 0UL;
public bool IsValidModulus => _modulus > 1UL && (_modulus & 1UL) != 0UL;
public readonly bool HasState => _hasState;
public bool HasState => _hasState;
public ulong PreviousExponent => _previousExponent;
public readonly ulong PreviousExponent => _previousExponent;
public void Reset()
{
@@ -47,7 +36,7 @@ internal struct ExponentRemainderStepper
// TODO: Route these state resets through the ProcessEightBitWindows helper once the scalar
// Pow2MontgomeryMod implementation adopts it so delta stepping inherits the benchmarked
// 2× gains for large exponents.
_currentMontgomery = exponent.Pow2MontgomeryModWindowed(_divisor, keepMontgomery: true);
_currentMontgomery = exponent.Pow2MontgomeryModWindowedCpu(_divisor, keepMontgomery: true);
_previousExponent = exponent;
_hasState = true;
return ReduceCurrent();
@@ -59,7 +48,7 @@ internal struct ExponentRemainderStepper
// cached Montgomery residue ladder highlighted in MersenneDivisorCycleLengthGpuBenchmarks.
// TODO: Replace this per-delta powmod with the upcoming windowed ladder so incremental
// updates stop paying the single-bit cost highlighted in GpuPow2ModBenchmarks.
ulong multiplier = delta.Pow2MontgomeryModWindowed(_divisor, keepMontgomery: true);
ulong multiplier = delta.Pow2MontgomeryModWindowedCpu(_divisor, keepMontgomery: true);
_currentMontgomery = _currentMontgomery.MontgomeryMultiply(multiplier, _modulus, _nPrime);
_previousExponent = exponent;
return ReduceCurrent();
@@ -77,7 +66,7 @@ internal struct ExponentRemainderStepper
{
// TODO: Switch this reload to the shared windowed pow2 helper once available so CPU
// residue checks align with the optimized ProcessEightBitWindows timings.
_currentMontgomery = exponent.Pow2MontgomeryModWindowed(_divisor, keepMontgomery: true);
_currentMontgomery = exponent.Pow2MontgomeryModWindowedCpu(_divisor, keepMontgomery: true);
_previousExponent = exponent;
_hasState = true;
return _currentMontgomery == _montgomeryOne;
@@ -88,7 +77,7 @@ internal struct ExponentRemainderStepper
// lookups so this branch also avoids recomputing powmods when the snapshot lacks the divisor.
// TODO: Use the windowed delta pow2 helper here as well to avoid the single-bit ladder that
// currently lags behind the benchmarked implementation for huge divisor cycles.
ulong multiplier = delta.Pow2MontgomeryModWindowed(_divisor, keepMontgomery: true);
ulong multiplier = delta.Pow2MontgomeryModWindowedCpu(_divisor, keepMontgomery: true);
_currentMontgomery = _currentMontgomery.MontgomeryMultiply(multiplier, _modulus, _nPrime);
_previousExponent = exponent;
return _currentMontgomery == _montgomeryOne;
@@ -123,7 +112,7 @@ internal struct ExponentRemainderStepper
{
// TODO: Replace this fallback path with the upcoming ProcessEightBitWindows helper so
// fresh Montgomery states also benefit from the faster pow2 ladder measured on CPUs.
_currentMontgomery = exponent.Pow2MontgomeryModWindowed(_divisor, keepMontgomery: true);
_currentMontgomery = exponent.Pow2MontgomeryModWindowedCpu(_divisor, keepMontgomery: true);
_previousExponent = exponent;
_hasState = true;
isUnity = _currentMontgomery == _montgomeryOne;