Clean up resolved windowed pow2 TODOs on CPU paths

This commit is contained in:
Marek Lemańczyk committed 2025-10-20 18:36:51 +02:00
1 parent 798ae455b1
commit 4831fc84d1
5 files changed
-38

No files matched your search

@@ -44,9 +44,6 @@ internal struct ExponentRemainderStepper
if (!_hasState || exponent <= _previousExponent)
{
// 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.Pow2MontgomeryModWindowedCpu(_divisor, keepMontgomery: true);
_previousExponent = exponent;
_hasState = true;
@@ -57,8 +54,6 @@ internal struct ExponentRemainderStepper
// TODO: Once divisor cycle lengths are mandatory, pull the delta multiplier from the
// single-block divisor-cycle snapshot so we can skip the powmod entirely and reuse the
// 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.Pow2MontgomeryModWindowedCpu(_divisor, keepMontgomery: true);
_currentMontgomery = _currentMontgomery.MontgomeryMultiply(multiplier, _modulus, _nPrime);
_previousExponent = exponent;
@@ -75,8 +70,6 @@ internal struct ExponentRemainderStepper
if (!_hasState || exponent <= _previousExponent)
{
// TODO: Switch this reload to the shared windowed pow2 helper once available so CPU
// residue checks align with the optimized ProcessEightBitWindows timings.
_currentMontgomery = exponent.Pow2MontgomeryModWindowedCpu(_divisor, keepMontgomery: true);
_previousExponent = exponent;
_hasState = true;
@@ -86,8 +79,6 @@ internal struct ExponentRemainderStepper
ulong delta = exponent - _previousExponent;
// TODO: Reuse the divisor-cycle derived Montgomery delta once the cache exposes single-cycle
// 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.Pow2MontgomeryModWindowedCpu(_divisor, keepMontgomery: true);
_currentMontgomery = _currentMontgomery.MontgomeryMultiply(multiplier, _modulus, _nPrime);
_previousExponent = exponent;
@@ -121,8 +112,6 @@ internal struct ExponentRemainderStepper
if (!_hasState || exponent <= _previousExponent)
{
// 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.Pow2MontgomeryModWindowedCpu(_divisor, keepMontgomery: true);
_previousExponent = exponent;
_hasState = true;