97 lines
3.6 KiB
C#
97 lines
3.6 KiB
C#
using System.Buffers;
|
|
using System.Runtime.InteropServices;
|
|
using ILGPU.Runtime;
|
|
|
|
namespace PerfectNumbers.Core.Gpu;
|
|
|
|
public class MersenneNumberResidueGpuTester(bool useGpuOrder)
|
|
{
|
|
private readonly bool _useGpuOrder = useGpuOrder;
|
|
// TODO: Integrate MersenneDivisorCycles.Shared to consult cycle lengths for small q (<= 4M) and fast-reject
|
|
// candidates without launching heavy kernels. Consider a device-visible constant buffer per-accelerator
|
|
// via GpuKernelPool to avoid host round-trips.
|
|
|
|
// GPU residue variant: check 2^p % q == 1 for q = 2*p*k + 1.
|
|
public void Scan(ulong exponent, UInt128 twoP, bool lastIsSeven, UInt128 maxK, ref bool isPrime)
|
|
{
|
|
var gpuLease = GpuKernelPool.GetKernel(_useGpuOrder);
|
|
var accelerator = gpuLease.Accelerator;
|
|
var stream = gpuLease.Stream;
|
|
// Ensure device has small cycles and primes tables for in-kernel lookup
|
|
var smallCyclesView = GpuKernelPool.EnsureSmallCyclesOnDevice(accelerator);
|
|
ResiduePrimeViews primeViews = GpuKernelPool.EnsureSmallPrimesOnDevice(accelerator);
|
|
int batchSize = GpuConstants.ScanBatchSize;
|
|
UInt128 kStart = 1UL;
|
|
byte last = lastIsSeven ? (byte)1 : (byte)0;
|
|
var kernel = gpuLease.Pow2ModKernel;
|
|
ulong step10 = ((exponent % 10UL) << 1) % 10UL;
|
|
ulong step8 = ((exponent & 7UL) << 1) & 7UL;
|
|
ulong step3 = ((exponent % 3UL) << 1) % 3UL;
|
|
ulong step5 = ((exponent % 5UL) << 1) % 5UL;
|
|
GpuUInt128 twoPGpu = (GpuUInt128)twoP;
|
|
|
|
var orderBuffer = accelerator.Allocate1D<ulong>(batchSize);
|
|
// Device memory returned by Allocate1D is not guaranteed to be zeroed.
|
|
// Ensure the buffer starts with a known state so that lanes skipped by the
|
|
// kernel (for example due to early rejections) do not leave stale garbage
|
|
// values that would be interpreted as composite witnesses when copied back
|
|
// to the host. This mirrors the explicit zeroing performed by other GPU
|
|
// testers such as the order kernels.
|
|
orderBuffer.MemSetToZero();
|
|
ulong[] orderArray = ArrayPool<ulong>.Shared.Rent(batchSize);
|
|
UInt128 remaining;
|
|
int currentSize;
|
|
int i;
|
|
UInt128 batchSize128 = (UInt128)batchSize, q;
|
|
Span<ulong> orders = orderArray.AsSpan(0, batchSize);
|
|
try
|
|
{
|
|
while (kStart < maxK && Volatile.Read(ref isPrime))
|
|
{
|
|
remaining = maxK - kStart;
|
|
if (remaining > batchSize128)
|
|
{
|
|
currentSize = batchSize;
|
|
}
|
|
else
|
|
{
|
|
currentSize = (int)remaining;
|
|
orders = orderArray.AsSpan(0, currentSize);
|
|
}
|
|
|
|
q = twoP * kStart + UInt128.One;
|
|
q.Mod10_8_5_3(out ulong q0m10, out ulong q0m8, out ulong q0m5, out ulong q0m3);
|
|
var ra = new ResidueAutomatonArgs(q0m10, step10, q0m8, step8, q0m3, step3, q0m5, step5);
|
|
|
|
kernel(stream, currentSize, exponent, twoPGpu, (GpuUInt128)kStart, last, 0UL,
|
|
ra, orderBuffer.View, smallCyclesView, primeViews.LastOne, primeViews.LastSeven, primeViews.LastOnePow2, primeViews.LastSevenPow2); // kernel(currentSize, exponent, twoPGpu, (GpuUInt128)kStart, last, 0UL,
|
|
// ra, orderBuffer.View, smallCyclesView, primeViews.LastOne, primeViews.LastSeven, primeViews.LastOnePow2, primeViews.LastSevenPow2);
|
|
|
|
accelerator.Synchronize();
|
|
orderBuffer.View.CopyToCPU(ref MemoryMarshal.GetReference(orders), currentSize);
|
|
if (!Volatile.Read(ref isPrime))
|
|
{
|
|
break;
|
|
}
|
|
|
|
for (i = 0; i < currentSize; i++)
|
|
{
|
|
if (orders[i] != 0UL)
|
|
{
|
|
Volatile.Write(ref isPrime, false);
|
|
break;
|
|
}
|
|
}
|
|
|
|
kStart += batchSize128;
|
|
}
|
|
}
|
|
finally
|
|
{
|
|
ArrayPool<ulong>.Shared.Return(orderArray);
|
|
orderBuffer.Dispose();
|
|
gpuLease.Dispose();
|
|
}
|
|
}
|
|
}
|