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

Clarify cycle stepper reset inlining

Browse Source
This commit is contained in:
Marek Lemańczyk committed 2025-10-02 13:30:56 +02:00
1 parent 8b467c27f3
commit b8aa845c5c
53 files changed
+1736 -1131
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

PerfectNumbers.Core/Gpu/MersenneNumberOrderGpuTester.cs
+11 -7
View File
@@ -23,11 +23,12 @@ public class MersenneNumberOrderGpuTester(GpuKernelType kernelType, bool useGpuO
GpuKernelType.Pow2Mod => gpuLease.Pow2ModOrderKernel,
_ => gpuLease.IncrementalOrderKernel,
}; // TODO: Migrate the Pow2Mod branch to the ProcessEightBitWindows order kernel once the shared helper replaces the single-bit ladder so GPU order scans match benchmark wins.
// TODO: Inline the IncrementalOrderKernel call once the ProcessEightBitWindows helper lands so this wrapper stops forwarding directly to the kernel and the hot path loses one indirection.
var foundBuffer = accelerator.Allocate1D<int>(1);
exponent.Mod10_8_5_3Steps(out ulong step10, out ulong step8, out ulong step5, out ulong step3);
try
{
var foundBuffer = accelerator.Allocate1D<int>(1); // TODO: Replace this allocation with the pooled device buffer from GpuOrderKernelBenchmarks so repeated scans reuse the pinned staging memory instead of allocating per run.
exponent.Mod10_8_5_3Steps(out ulong step10, out ulong step8, out ulong step5, out ulong step3);
try
{
UInt128 remaining;
int currentSize;
int found = 0;
@@ -37,9 +38,12 @@ public class MersenneNumberOrderGpuTester(GpuKernelType kernelType, bool useGpuO
currentSize = remaining > (UInt128)batchSize ? batchSize : (int)remaining;
foundBuffer.MemSetToZero();
// Precompute residue automaton bases for this batch
UInt128 q0 = twoP * kStart + 1UL;
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);
UInt128 q0 = twoP * kStart + 1UL;
// TODO: Replace these modulo recomputations with the divisor-cycle stepping deltas captured in
// MersenneDivisorCycleLengthGpuBenchmarks so each batch advances via cached residues from the
// single snapshot block instead of recalculating mod 10/8/5/3 in every iteration.
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);
// Ensure device has small cycles table for early rejections in order kernels