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

Extension methods benchmarked. Slower alternatives replaced.

Browse Source
This commit is contained in:
Marek Lemańczyk committed 2025-09-23 22:01:09 +02:00
1 parent 9becb8df67
commit 6e99ee39e3
40 files changed
+930 -1026
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

PerfectNumbers.Core/Gpu/GpuKernelPool.cs
+10 -11
View File
@@ -1,6 +1,5 @@
using System.Collections.Concurrent;
using System.Runtime.CompilerServices;
using System.Threading;
using ILGPU;
using ILGPU.Runtime;
using static PerfectNumbers.Core.Gpu.GpuContextPool;
@@ -200,8 +199,8 @@ public ref struct GpuKernelLease(IDisposable limiter, GpuContextLease gpu, Kerne
ArrayView1D<uint, Stride1D.Dense> smallCycles)
{
ulong idx = (ulong)index.X;
ulong idxMod3 = idx.Mod3();
ulong idxMod5 = idx.Mod5();
ulong idxMod3 = idx % 3UL;
ulong idxMod5 = idx % 5UL;
// residue automaton
ulong step10 = (exponent.Mod10() << 1).Mod10();
ulong r10 = q0m10 + (step10 * idx).Mod10();
@@ -217,7 +216,7 @@ public ref struct GpuKernelLease(IDisposable limiter, GpuContextLease gpu, Kerne
}
else
{
ulong step3 = (exponent.Mod3() << 1).Mod3();
ulong step3 = ((exponent % 3UL) << 1) % 3UL;
ulong r3 = q0m3 + (step3 * idxMod3); r3 -= (r3 >= 3UL) ? 3UL : 0UL;
if (r3 == 0UL)
{
@@ -225,7 +224,7 @@ public ref struct GpuKernelLease(IDisposable limiter, GpuContextLease gpu, Kerne
}
else
{
ulong step5Loc = (exponent.Mod5() << 1).Mod5();
ulong step5Loc = ((exponent % 5UL) << 1) % 5UL;
ulong r5 = q0m5 + (step5Loc * idxMod5); if (r5 >= 5UL) r5 -= 5UL;
if (r5 == 0UL)
{
@@ -360,8 +359,8 @@ public ref struct GpuKernelLease(IDisposable limiter, GpuContextLease gpu, Kerne
ArrayView1D<ulong, Stride1D.Dense> smallPrimesPow2LastSeven)
{
ulong idx = (ulong)index.X;
ulong idxMod3 = idx.Mod3();
ulong idxMod5 = idx.Mod5();
ulong idxMod3 = idx % 3UL;
ulong idxMod5 = idx % 5UL;
ulong r10 = ra.Q0M10 + (ra.Step10 * idx).Mod10(); r10 -= (r10 >= 10UL) ? 10UL : 0UL;
bool shouldCheck = r10 != 5UL;
if (shouldCheck)
@@ -493,8 +492,8 @@ public ref struct GpuKernelLease(IDisposable limiter, GpuContextLease gpu, Kerne
ResidueAutomatonArgs ra, ArrayView<int> found, ArrayView1D<uint, Stride1D.Dense> smallCycles)
{
ulong idx = (ulong)index.X;
ulong idxMod3 = idx.Mod3();
ulong idxMod5 = idx.Mod5();
ulong idxMod3 = idx % 3UL;
ulong idxMod5 = idx % 5UL;
ulong r10 = ra.Q0M10 + (ra.Step10 * idx).Mod10(); r10 -= (r10 >= 10UL) ? 10UL : 0UL;
bool shouldCheck = r10 != 5UL;
if (shouldCheck)
@@ -579,8 +578,8 @@ public ref struct GpuKernelLease(IDisposable limiter, GpuContextLease gpu, Kerne
ResidueAutomatonArgs ra, ArrayView<int> found, ArrayView1D<uint, Stride1D.Dense> smallCycles)
{
ulong idx = (ulong)index.X;
ulong idxMod3 = idx.Mod3();
ulong idxMod5 = idx.Mod5();
ulong idxMod3 = idx % 3UL;
ulong idxMod5 = idx % 5UL;
ulong r10 = ra.Q0M10 + (ra.Step10 * idx).Mod10(); r10 -= (r10 >= 10UL) ? 10UL : 0UL;
bool shouldCheck = r10 != 5UL;
if (shouldCheck)
PerfectNumbers.Core/Gpu/MersenneNumberIncrementalGpuTester.cs
+86 -90
View File
@@ -1,6 +1,5 @@
using System.Buffers;
using System.Runtime.InteropServices;
using ILGPU;
using ILGPU.Runtime;
namespace PerfectNumbers.Core.Gpu;
@@ -10,98 +9,95 @@ public class MersenneNumberIncrementalGpuTester(GpuKernelType kernelType, bool u
private readonly GpuKernelType _kernelType = kernelType;
private readonly bool _useGpuOrder = useGpuOrder;
public void Scan(ulong exponent, UInt128 twoP, bool lastIsSeven, UInt128 maxK, ref bool isPrime)
{
var gpuLease = GpuKernelPool.GetKernel(_useGpuOrder);
var execution = gpuLease.EnterExecutionScope();
var accelerator = gpuLease.Accelerator;
var stream = gpuLease.Stream;
int batchSize = GpuConstants.ScanBatchSize; // large batch improves GPU occupancy
UInt128 kStart = 1UL;
ulong divMul = (ulong)((((UInt128)1 << 64) - UInt128.One) / exponent) + 1UL;
byte last = lastIsSeven ? (byte)1 : (byte)0; // ILGPU kernels do not support bool parameters
public void Scan(ulong exponent, UInt128 twoP, bool lastIsSeven, UInt128 maxK, ref bool isPrime)
{
var gpuLease = GpuKernelPool.GetKernel(_useGpuOrder);
var execution = gpuLease.EnterExecutionScope();
var accelerator = gpuLease.Accelerator;
var stream = gpuLease.Stream;
int batchSize = GpuConstants.ScanBatchSize; // large batch improves GPU occupancy
UInt128 kStart = 1UL;
ulong divMul = (ulong)((((UInt128)1 << 64) - UInt128.One) / exponent) + 1UL;
byte last = lastIsSeven ? (byte)1 : (byte)0; // ILGPU kernels do not support bool parameters
var pow2Kernel = gpuLease.Pow2ModKernel;
var incKernel = gpuLease.IncrementalKernel;
ulong step10 = (exponent.Mod10() << 1).Mod10();
ulong step8 = ((exponent & 7UL) << 1) & 7UL;
ulong step3 = (exponent.Mod3() << 1).Mod3();
ulong step5 = (exponent.Mod5() << 1).Mod5();
GpuUInt128 twoPGpu = (GpuUInt128)twoP;
var smallCyclesView = GpuKernelPool.EnsureSmallCyclesOnDevice(accelerator);
ResiduePrimeViews primeViews = default;
if (_kernelType == GpuKernelType.Pow2Mod)
{
primeViews = GpuKernelPool.EnsureSmallPrimesOnDevice(accelerator);
}
var pow2Kernel = gpuLease.Pow2ModKernel;
var incKernel = gpuLease.IncrementalKernel;
exponent.Mod10_8_5_3Steps(out ulong step10, out ulong step8, out ulong step5, out ulong step3);
GpuUInt128 twoPGpu = (GpuUInt128)twoP;
var smallCyclesView = GpuKernelPool.EnsureSmallCyclesOnDevice(accelerator);
ResiduePrimeViews primeViews = default;
if (_kernelType == GpuKernelType.Pow2Mod)
{
primeViews = GpuKernelPool.EnsureSmallPrimesOnDevice(accelerator);
}
var orderBuffer = accelerator.Allocate1D<ulong>(batchSize);
// Avoid giant stack allocations that can trigger StackOverflow when batchSize is large.
// Rent a reusable array from the shared pool instead.
ulong[] orderArray = ArrayPool<ulong>.Shared.Rent(batchSize);
UInt128 remaining;
int currentSize;
int i;
UInt128 q = UInt128.Zero;
try
{
while (kStart <= maxK && Volatile.Read(ref isPrime))
{
remaining = maxK - kStart + UInt128.One;
currentSize = remaining > (UInt128)batchSize ? batchSize : (int)remaining;
Span<ulong> orders = orderArray.AsSpan(0, currentSize);
// Precompute residue automaton bases for this batch
UInt128 q0 = twoP * kStart + UInt128.One;
if (_kernelType == GpuKernelType.Pow2Mod)
{
q0.Mod10_8_5_3(out ulong q0m10, out ulong q0m8, out ulong q0m5, out ulong q0m3);
var kernelArgs = new ResidueAutomatonArgs(q0m10, step10, q0m8, step8, q0m3, step3, q0m5, step5);
pow2Kernel(stream, currentSize, exponent, twoPGpu, (GpuUInt128)kStart, last, divMul,
kernelArgs, orderBuffer.View, smallCyclesView, primeViews.LastOne, primeViews.LastSeven,
primeViews.LastOnePow2, primeViews.LastSevenPow2);
}
else
{
q0.Mod10_8_5_3(out ulong q0m10, out ulong q0m8, out ulong q0m5, out ulong q0m3);
incKernel(stream, currentSize, exponent, twoPGpu, (GpuUInt128)kStart, last, divMul,
q0m10, q0m8, q0m3, q0m5, orderBuffer.View, smallCyclesView);
}
var orderBuffer = accelerator.Allocate1D<ulong>(batchSize);
// Avoid giant stack allocations that can trigger StackOverflow when batchSize is large.
// Rent a reusable array from the shared pool instead.
ulong[] orderArray = ArrayPool<ulong>.Shared.Rent(batchSize);
UInt128 remaining;
int currentSize;
int i;
UInt128 q = UInt128.Zero;
try
{
while (kStart <= maxK && Volatile.Read(ref isPrime))
{
remaining = maxK - kStart + UInt128.One;
currentSize = remaining > (UInt128)batchSize ? batchSize : (int)remaining;
Span<ulong> orders = orderArray.AsSpan(0, currentSize);
// Precompute residue automaton bases for this batch
UInt128 q0 = twoP * kStart + UInt128.One;
if (_kernelType == GpuKernelType.Pow2Mod)
{
q0.Mod10_8_5_3(out ulong q0m10, out ulong q0m8, out ulong q0m5, out ulong q0m3);
var kernelArgs = new ResidueAutomatonArgs(q0m10, step10, q0m8, step8, q0m3, step3, q0m5, step5);
pow2Kernel(stream, currentSize, exponent, twoPGpu, (GpuUInt128)kStart, last, divMul,
kernelArgs, orderBuffer.View, smallCyclesView, primeViews.LastOne, primeViews.LastSeven,
primeViews.LastOnePow2, primeViews.LastSevenPow2);
}
else
{
q0.Mod10_8_5_3(out ulong q0m10, out ulong q0m8, out ulong q0m5, out ulong q0m3);
incKernel(stream, currentSize, exponent, twoPGpu, (GpuUInt128)kStart, last, divMul,
q0m10, q0m8, q0m3, q0m5, orderBuffer.View, smallCyclesView);
}
stream.Synchronize();
orderBuffer.View.CopyToCPU(ref MemoryMarshal.GetReference(orders), currentSize);
if (_kernelType == GpuKernelType.Pow2Mod)
{
for (i = 0; i < currentSize; i++)
{
if (orders[i] != 0UL)
{
Volatile.Write(ref isPrime, false);
break;
}
}
}
else
{
q = twoP * kStart + UInt128.One;
for (i = 0; i < currentSize && Volatile.Read(ref isPrime); i++, q += twoP)
{
if (orders[i] != 0UL && q.IsPrimeCandidate())
{
Volatile.Write(ref isPrime, false);
}
}
}
stream.Synchronize();
orderBuffer.View.CopyToCPU(ref MemoryMarshal.GetReference(orders), currentSize);
if (_kernelType == GpuKernelType.Pow2Mod)
{
for (i = 0; i < currentSize; i++)
{
if (orders[i] != 0UL)
{
Volatile.Write(ref isPrime, false);
break;
}
}
}
else
{
q = twoP * kStart + UInt128.One;
for (i = 0; i < currentSize && Volatile.Read(ref isPrime); i++, q += twoP)
{
if (orders[i] != 0UL && q.IsPrimeCandidate())
{
Volatile.Write(ref isPrime, false);
}
}
}
kStart += (UInt128)currentSize;
}
}
finally
{
ArrayPool<ulong>.Shared.Return(orderArray);
orderBuffer.Dispose();
execution.Dispose();
gpuLease.Dispose();
}
kStart += (UInt128)currentSize;
}
}
finally
{
ArrayPool<ulong>.Shared.Return(orderArray);
orderBuffer.Dispose();
execution.Dispose();
gpuLease.Dispose();
}
}
}
}
PerfectNumbers.Core/Gpu/MersenneNumberLucasLehmerGpuTester.cs
+1 -1
View File
@@ -51,7 +51,7 @@ public class MersenneNumberLucasLehmerGpuTester
// Early rejections aligned with incremental/order sieves, but safe for small p:
// - If 3 | p and p != 3, then 7 | M_p -> composite.
// - If p ≡ 1 (mod 4) and p shares a factor with (p-1), reject fast.
if (exponent.Mod3() == 0UL && exponent != 3UL)
if ((exponent % 3UL) == 0UL && exponent != 3UL)
{
return false;
}
PerfectNumbers.Core/Gpu/MersenneNumberOrderGpuTester.cs
+1 -6
View File
@@ -25,12 +25,7 @@ public class MersenneNumberOrderGpuTester(GpuKernelType kernelType, bool useGpuO
};
var foundBuffer = accelerator.Allocate1D<int>(1);
UInt128 exponent128 = exponent;
exponent128.Mod10_8_5_3(out ulong exponentMod10, out ulong exponentMod8, out ulong exponentMod5, out ulong exponentMod3);
ulong step10 = (exponentMod10 << 1).Mod10();
ulong step8 = (exponentMod8 << 1) & 7UL;
ulong step3 = (exponentMod3 << 1).Mod3();
ulong step5 = (exponentMod5 << 1).Mod5();
exponent.Mod10_8_5_3Steps(out ulong step10, out ulong step8, out ulong step5, out ulong step3);
try
{
UInt128 remaining;
PerfectNumbers.Core/Gpu/MersenneNumberResidueGpuTester.cs
+5 -1
View File
@@ -24,7 +24,11 @@ public class MersenneNumberResidueGpuTester(bool useGpuOrder)
UInt128 kStart = 1UL;
byte last = lastIsSeven ? (byte)1 : (byte)0;
var kernel = gpuLease.Pow2ModKernel;
exponent.Mod10_8_5_3Steps(out ulong step10, out ulong step8, out ulong step5, out ulong step3);
ulong step3 = exponent % 3UL,
step5 = exponent % 5UL,
step8 = exponent % 8UL,
step10 = exponent.Mod10();
GpuUInt128 twoPGpu = (GpuUInt128)twoP;
var orderBuffer = accelerator.Allocate1D<ulong>(batchSize);