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

PrimeOrderCalculatorAccelerator.Rent is now created outside of the loops and re-used for all calculations.

Browse Source
This commit is contained in:
mlemanczyk committed 2025-11-24 22:51:53 +01:00
1 parent 57a50e2a37
commit b9ca95bf8c
53 files changed
+4639 -4229
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

PerfectNumbers.Core/Cpu/MersenneNumberOrderCpuTester.cs
+35 -33
View File
@@ -1,10 +1,12 @@
using PerfectNumbers.Core.Gpu.Accelerators;
namespace PerfectNumbers.Core.Cpu;
public class MersenneNumberOrderCpuTester(GpuKernelType kernelType)
{
private readonly GpuKernelType _kernelType = kernelType;
public void Scan(ulong exponent, UInt128 twoP, LastDigit lastDigit, UInt128 maxK, ref bool isPrime)
public void Scan(PrimeOrderCalculatorAccelerator gpu, ulong exponent, UInt128 twoP, LastDigit lastDigit, UInt128 maxK, ref bool isPrime)
{
UInt128 k = 1UL;
var auto = new MersenneResidueAutomaton(exponent);
@@ -13,10 +15,10 @@ public class MersenneNumberOrderCpuTester(GpuKernelType kernelType)
while (k <= maxK && Volatile.Read(ref isPrime))
{
qCycle = MersenneDivisorCycles.GetCycle(q);
// TODO: When this lookup misses the snapshot, invoke the configured device to compute the
// single required cycle on demand without persisting it so the CPU order path retains the
// cycle-stepping speedups while honoring the no-extra-cache constraint for large divisors.
qCycle = MersenneDivisorCycles.GetCycle(gpu, q);
// TODO: When this lookup misses the snapshot, invoke the configured device to compute the
// single required cycle on demand without persisting it so the CPU order path retains the
// cycle-stepping speedups while honoring the no-extra-cache constraint for large divisors.
int allowMask2 = lastDigit == LastDigit.Seven ? CpuConstants.LastSevenMask10 : CpuConstants.LastOneMask10;
bool shouldCheck = ((allowMask2 >> (int)auto.Mod10R) & 1) != 0;
if (shouldCheck)
@@ -33,33 +35,33 @@ public class MersenneNumberOrderCpuTester(GpuKernelType kernelType)
}
if (shouldCheck)
{
if (_kernelType == GpuKernelType.Pow2Mod)
{
if (exponent.PowModWithCycle(q, qCycle) == 1UL)
{
Volatile.Write(ref isPrime, false);
break;
}
}
else
{
UInt128 phi = q - 1UL;
if (phi <= ulong.MaxValue)
{
ulong phi64 = (ulong)phi;
if (phi64.PowModWithCycle(q, qCycle) == 1UL)
{
UInt128 halfPow = (phi64 >> 1).PowModWithCycle(q, qCycle) - 1UL;
if (halfPow.BinaryGcd(q) == 1UL)
{
ulong divMul = (ulong)((((UInt128)1 << 64) - 1UL) / exponent) + 1UL;
ulong div = phi64.FastDiv64(exponent, divMul);
UInt128 divPow = div.PowModWithCycle(q, qCycle) - 1UL;
if (divPow.BinaryGcd(q) == 1UL)
{
Volatile.Write(ref isPrime, false);
break;
}
if (_kernelType == GpuKernelType.Pow2Mod)
{
if (exponent.PowModWithCycle(q, qCycle) == 1UL)
{
Volatile.Write(ref isPrime, false);
break;
}
}
else
{
UInt128 phi = q - 1UL;
if (phi <= ulong.MaxValue)
{
ulong phi64 = (ulong)phi;
if (phi64.PowModWithCycle(q, qCycle) == 1UL)
{
UInt128 halfPow = (phi64 >> 1).PowModWithCycle(q, qCycle) - 1UL;
if (halfPow.BinaryGcd(q) == 1UL)
{
ulong divMul = (ulong)((((UInt128)1 << 64) - 1UL) / exponent) + 1UL;
ulong div = phi64.FastDiv64(exponent, divMul);
UInt128 divPow = div.PowModWithCycle(q, qCycle) - 1UL;
if (divPow.BinaryGcd(q) == 1UL)
{
Volatile.Write(ref isPrime, false);
break;
}
}
}
}
@@ -70,7 +72,7 @@ public class MersenneNumberOrderCpuTester(GpuKernelType kernelType)
auto.Next();
q = auto.CurrentQ();
}
return;
}