Cleanup

EvenPerfectBitScanner.Benchmarks/GpuModularArithmeticBenchmarks.cs

@@ -1,4 +1,3 @@
-using System;
 using System.Runtime.CompilerServices;
 using BenchmarkDotNet.Attributes;
 using BenchmarkDotNet.Jobs;

EvenPerfectBitScanner.Benchmarks/MersenneDivisorCycleLengthGpuBenchmarks.cs

@@ -1,6 +1,5 @@
 using System.Runtime.CompilerServices;
 using BenchmarkDotNet.Attributes;
-using PerfectNumbers.Core;
 using BenchmarkDotNet.Jobs;
 
 namespace EvenPerfectBitScanner.Benchmarks;

EvenPerfectBitScanner.Benchmarks/Mod10Benchmarks.cs

@@ -1,5 +1,3 @@
-using System;
-using System.Collections.Generic;
 using System.Runtime.CompilerServices;
 using BenchmarkDotNet.Attributes;
 using BenchmarkDotNet.Jobs;

EvenPerfectBitScanner.Benchmarks/Mod10_8_5_3Benchmarks.cs

@@ -1,5 +1,3 @@
-using System;
-using System.Collections.Generic;
 using System.Runtime.CompilerServices;
 using BenchmarkDotNet.Attributes;
 using PerfectNumbers.Core;

EvenPerfectBitScanner.Benchmarks/Mod11Benchmarks.cs

@@ -1,5 +1,3 @@
-using System;
-using System.Collections.Generic;
 using System.Runtime.CompilerServices;
 using BenchmarkDotNet.Attributes;
 using BenchmarkDotNet.Jobs;

EvenPerfectBitScanner.Benchmarks/Mod128Benchmarks.cs

@@ -1,5 +1,3 @@
-using System;
-using System.Collections.Generic;
 using System.Runtime.CompilerServices;
 using BenchmarkDotNet.Attributes;
 using BenchmarkDotNet.Jobs;

EvenPerfectBitScanner.Benchmarks/Mod3Benchmarks.cs

@@ -1,5 +1,3 @@
-using System;
-using System.Collections.Generic;
 using System.Runtime.CompilerServices;
 using BenchmarkDotNet.Attributes;
 using BenchmarkDotNet.Jobs;

EvenPerfectBitScanner.Benchmarks/Mod5Benchmarks.cs

@@ -1,5 +1,3 @@
-using System;
-using System.Collections.Generic;
 using System.Runtime.CompilerServices;
 using BenchmarkDotNet.Attributes;
 using BenchmarkDotNet.Jobs;

EvenPerfectBitScanner.Benchmarks/Mod6Benchmarks.cs

@@ -1,5 +1,3 @@
-using System;
-using System.Collections.Generic;
 using System.Runtime.CompilerServices;
 using BenchmarkDotNet.Attributes;
 using BenchmarkDotNet.Jobs;

EvenPerfectBitScanner.Benchmarks/Mod7Benchmarks.cs

@@ -1,5 +1,3 @@
-using System;
-using System.Collections.Generic;
 using System.Runtime.CompilerServices;
 using BenchmarkDotNet.Attributes;
 using BenchmarkDotNet.Jobs;

EvenPerfectBitScanner.Benchmarks/Mod8Benchmarks.cs

@@ -1,5 +1,3 @@
-using System;
-using System.Collections.Generic;
 using System.Runtime.CompilerServices;
 using BenchmarkDotNet.Attributes;
 using BenchmarkDotNet.Jobs;

EvenPerfectBitScanner.Benchmarks/ModBenchmarkCase.cs

@@ -1,5 +1,3 @@
-using System;
-
 namespace EvenPerfectBitScanner.Benchmarks;
 
 public enum ModNumericType

EvenPerfectBitScanner.Benchmarks/MontgomeryMultiplyBenchmarks.cs

@@ -1,4 +1,3 @@
-using System;
 using BenchmarkDotNet.Attributes;
 using BenchmarkDotNet.Jobs;
 

EvenPerfectBitScanner.Benchmarks/MulMod64Benchmarks.Gpu.cs

@@ -1,12 +1,8 @@
-using System;
-using System.Collections.Generic;
-using System.Linq;
 using System.Runtime.CompilerServices;
 using BenchmarkDotNet.Attributes;
 using BenchmarkDotNet.Jobs;
 using ILGPU;
 using ILGPU.Runtime;
-using PerfectNumbers.Core;
 using PerfectNumbers.Core.Gpu;
 
 namespace EvenPerfectBitScanner.Benchmarks;

EvenPerfectBitScanner.Benchmarks/Pow2ModBenchmarks.cs

@@ -1,4 +1,3 @@
-using System;
 using System.Buffers.Binary;
 using BenchmarkDotNet.Attributes;
 using BenchmarkDotNet.Jobs;

EvenPerfectBitScanner.Benchmarks/Pow2MontgomeryModWindowedBenchmarkData.cs

@@ -1,4 +1,3 @@
-using System;
 using PerfectNumbers.Core;
 
 namespace EvenPerfectBitScanner.Benchmarks;

EvenPerfectBitScanner.Benchmarks/Pow2MontgomeryModWindowedKeepMontgomeryGpuBenchmarks.cs

@@ -1,4 +1,3 @@
-using System;
 using BenchmarkDotNet.Attributes;
 using BenchmarkDotNet.Jobs;
 using PerfectNumbers.Core;

EvenPerfectBitScanner.Tests/ProgramTests.cs

@@ -3,13 +3,9 @@ using Xunit;
 using System.Reflection;
 using PerfectNumbers.Core;
 using PerfectNumbers.Core.Gpu;
-
-using EvenPerfectBitScanner;
 using EvenPerfectBitScanner.Candidates;
 using EvenPerfectBitScanner.Candidates.Transforms;
 using System.Numerics;
-using System.Threading;
-using System.Threading.Tasks;
 
 namespace EvenPerfectBitScanner.Tests;
 

EvenPerfectBitScanner.Tests/ResultsFileNameTests.cs

@@ -1,6 +1,3 @@
-using System.Collections.Generic;
-using System.IO;
-using System.Numerics;
 using FluentAssertions;
 using PerfectNumbers.Core;
 using PerfectNumbers.Core.Gpu;

EvenPerfectBitScanner/CalculationResultHandler.cs

@@ -1,8 +1,6 @@
 using System.Buffers.Text;
-using System.IO;
 using System.Runtime.CompilerServices;
 using System.Text;
-using System.Threading;
 using PerfectNumbers.Core;
 
 namespace EvenPerfectBitScanner;

EvenPerfectBitScanner/Candidates/CalculationTestTime.cs

@@ -1,5 +1,4 @@
 using System.Globalization;
-using System.IO;
 
 namespace EvenPerfectBitScanner.Candidates;
 

EvenPerfectBitScanner/Candidates/CandidatesCalculator.cs

@@ -1,5 +1,4 @@
 using System.Runtime.CompilerServices;
-using System.Threading;
 using Open.Numeric.Primes;
 using PerfectNumbers.Core;
 using EvenPerfectBitScanner.Candidates.Transforms;

EvenPerfectBitScanner/Candidates/Transforms/CandidateAddPrimesTransform.cs

@@ -1,6 +1,4 @@
 using System.Runtime.CompilerServices;
-using System.Threading;
-using EvenPerfectBitScanner.Candidates;
 using Open.Numeric.Primes;
 
 namespace EvenPerfectBitScanner.Candidates.Transforms;

EvenPerfectBitScanner/Candidates/Transforms/CandidateAddTransform.cs

@@ -1,6 +1,4 @@
 using System.Runtime.CompilerServices;
-using System.Threading;
-using EvenPerfectBitScanner.Candidates;
 
 namespace EvenPerfectBitScanner.Candidates.Transforms;
 

EvenPerfectBitScanner/Candidates/Transforms/CandidateBitTransform.cs

@@ -1,5 +1,4 @@
 using System.Runtime.CompilerServices;
-using System.Threading;
 
 namespace EvenPerfectBitScanner.Candidates.Transforms;
 

EvenPerfectBitScanner/CliArguments.cs

@@ -1,6 +1,4 @@
-using System;
 using System.Globalization;
-using System.Numerics;
 using PerfectNumbers.Core;
 using PerfectNumbers.Core.Gpu;
 

EvenPerfectBitScanner/IO/CalculationResultsFile.cs

@@ -1,7 +1,6 @@
 using Open.Collections;
 using PerfectNumbers.Core;
 using PerfectNumbers.Core.Gpu;
-using EvenPerfectBitScanner;
 
 namespace EvenPerfectBitScanner.IO;
 

EvenPerfectBitScanner/Utf8CliParser.cs

@@ -1,4 +1,3 @@
-using System;
 using System.Buffers;
 using System.Buffers.Text;
 using System.Text;

PerfectNumbers.Core.Tests/Gpu/GpuContextPoolTests.cs

@@ -1,7 +1,3 @@
-using FluentAssertions;
-using ILGPU;
-using ILGPU.Runtime;
-using PerfectNumbers.Core.Gpu;
 using Xunit;
 
 namespace PerfectNumbers.Core.Tests.Gpu;

PerfectNumbers.Core.Tests/Gpu/GpuKernelCompilationTests.cs

@@ -1,5 +1,4 @@
 using System.Reflection;
-using FluentAssertions;
 using ILGPU;
 using ILGPU.Runtime;
 using PerfectNumbers.Core.Gpu;

PerfectNumbers.Core.Tests/Gpu/PrimeTesterGpuTests.cs

@@ -1,5 +1,4 @@
 using FluentAssertions;
-using PerfectNumbers.Core.Gpu;
 using Xunit;
 
 namespace PerfectNumbers.Core.Tests.Gpu;

PerfectNumbers.Core.Tests/Gpu/ULongExtensionsGpuTests.cs

@@ -1,5 +1,4 @@
 using FluentAssertions;
-using PerfectNumbers.Core;
 using Xunit;
 
 namespace PerfectNumbers.Core.Tests.Gpu;

PerfectNumbers.Core.Tests/HeuristicCombinedPrimeTesterTests.cs

@@ -1,7 +1,3 @@
-using System;
-using System.Numerics;
-using System.Collections.Generic;
-using PerfectNumbers.Core;
 using FluentAssertions;
 using Xunit;
 

PerfectNumbers.Core.Tests/MersenneNumberIncrementalCpuTesterTests.cs

@@ -1,5 +1,4 @@
 using FluentAssertions;
-using PerfectNumbers.Core;
 using PerfectNumbers.Core.Cpu;
 using Xunit;
 using UInt128 = System.UInt128;

PerfectNumbers.Core.Tests/MersenneNumberIncrementalGpuTesterTests.cs

@@ -1,5 +1,4 @@
 using FluentAssertions;
-using PerfectNumbers.Core;
 using PerfectNumbers.Core.Gpu;
 using Xunit;
 using UInt128 = System.UInt128;

PerfectNumbers.Core.Tests/MersenneNumberOrderCpuTesterTests.cs

@@ -1,5 +1,4 @@
 using FluentAssertions;
-using PerfectNumbers.Core;
 using PerfectNumbers.Core.Cpu;
 using Xunit;
 using UInt128 = System.UInt128;

PerfectNumbers.Core.Tests/MersenneNumberOrderGpuTesterTests.cs

@@ -1,6 +1,5 @@
 using System.Reflection;
 using FluentAssertions;
-using PerfectNumbers.Core;
 using PerfectNumbers.Core.Gpu;
 using Xunit;
 using UInt128 = System.UInt128;

PerfectNumbers.Core.Tests/MersenneNumberResidueCpuTesterTests.cs

@@ -1,5 +1,4 @@
 using FluentAssertions;
-using PerfectNumbers.Core;
 using PerfectNumbers.Core.Cpu;
 using Xunit;
 using UInt128 = System.UInt128;

PerfectNumbers.Core.Tests/MersenneNumberResidueGpuTesterTests.cs

@@ -1,5 +1,4 @@
 using FluentAssertions;
-using PerfectNumbers.Core;
 using PerfectNumbers.Core.Gpu;
 using Xunit;
 using UInt128 = System.UInt128;

PerfectNumbers.Core/Cpu/MersenneNumberDivisorByDivisorCpuTester.cs

@@ -1,6 +1,4 @@
-using System.Collections.Generic;
 using System.Runtime.CompilerServices;
-using PerfectNumbers.Core;
 using PerfectNumbers.Core.Gpu;
 using PerfectNumbers.Core.Gpu.Accelerators;
 

PerfectNumbers.Core/DivisorCycleCache.cs

@@ -1,10 +1,5 @@
-using System.Buffers;
-using System.Collections.Concurrent;
-using System.Collections.Generic;
 using System.Runtime.CompilerServices;
-using System.Runtime.InteropServices;
 using ILGPU;
-using ILGPU.Algorithms;
 using ILGPU.Runtime;
 using PerfectNumbers.Core.Gpu;
 using PerfectNumbers.Core.Gpu.Accelerators;

PerfectNumbers.Core/DivisorGenerator.cs

@@ -1,5 +1,3 @@
-using System;
-using System.Collections.Generic;
 using System.Runtime.CompilerServices;
 
 namespace PerfectNumbers.Core;

PerfectNumbers.Core/Gpu/Accelerators/PrimeOrderCalculatorAccelerator.cs

@@ -97,14 +97,14 @@ public sealed class PrimeOrderCalculatorAccelerator
 
 	#region Static Tables
 
-	public readonly MemoryBuffer1D<uint, Stride1D.Dense> DevicePrimesLastOne;
+	public readonly ArrayView1D<uint, Stride1D.Dense> DevicePrimesLastOne;
-	public readonly MemoryBuffer1D<uint, Stride1D.Dense> DevicePrimesLastSeven;
+	public readonly ArrayView1D<uint, Stride1D.Dense> DevicePrimesLastSeven;
-	public readonly MemoryBuffer1D<uint, Stride1D.Dense> DevicePrimesLastThree;
+	public readonly ArrayView1D<uint, Stride1D.Dense> DevicePrimesLastThree;
-	public readonly MemoryBuffer1D<uint, Stride1D.Dense> DevicePrimesLastNine;
+	public readonly ArrayView1D<uint, Stride1D.Dense> DevicePrimesLastNine;
-	public readonly MemoryBuffer1D<ulong, Stride1D.Dense> DevicePrimesPow2LastOne;
+	public readonly ArrayView1D<ulong, Stride1D.Dense> DevicePrimesPow2LastOne;
-	public readonly MemoryBuffer1D<ulong, Stride1D.Dense> DevicePrimesPow2LastSeven;
+	public readonly ArrayView1D<ulong, Stride1D.Dense> DevicePrimesPow2LastSeven;
-	public readonly MemoryBuffer1D<ulong, Stride1D.Dense> DevicePrimesPow2LastThree;
+	public readonly ArrayView1D<ulong, Stride1D.Dense> DevicePrimesPow2LastThree;
-	public readonly MemoryBuffer1D<ulong, Stride1D.Dense> DevicePrimesPow2LastNine;
+	public readonly ArrayView1D<ulong, Stride1D.Dense> DevicePrimesPow2LastNine;
 
 	#endregion
 
@@ -112,8 +112,8 @@ public sealed class PrimeOrderCalculatorAccelerator
 	public readonly MemoryBuffer1D<ulong, Stride1D.Dense> SpecialMaxResult;
 
 	public readonly HeuristicCombinedGpuViews DivisorTables;
-	public readonly MemoryBuffer1D<uint, Stride1D.Dense> SmallPrimeFactorPrimes;
+	public readonly ArrayView1D<uint, Stride1D.Dense> SmallPrimeFactorPrimes;
-	public readonly MemoryBuffer1D<ulong, Stride1D.Dense> SmallPrimeFactorSquares;
+	public readonly ArrayView1D<ulong, Stride1D.Dense> SmallPrimeFactorSquares;
 
 	public readonly Kernel CheckFactorsKernel;
 	public readonly Kernel ConvertToStandardKernel;
@@ -127,68 +127,70 @@ public sealed class PrimeOrderCalculatorAccelerator
 	public readonly Kernel SpecialMaxKernel;
 
 	public void EnsureCapacity(int factorsCount, int primeTesterCapacity)
-	{
-		if (factorsCount > Pow2ModEntriesToTestOnDevice.Length)
 	{
 		Accelerator accelerator = Accelerator;
-			Pow2ModEntriesToTestOnDevice.Dispose();
+		MemoryBuffer1D<KeyValuePair<ulong, int>, Stride1D.Dense> pow2ModEntriesToTestOnDevice = Pow2ModEntriesToTestOnDevice;
+		if (pow2ModEntriesToTestOnDevice.Length < factorsCount)
+		{
+			pow2ModEntriesToTestOnDevice.Dispose();
 			Pow2ModEntriesToTestOnDevice = accelerator.Allocate1D<KeyValuePair<ulong, int>>(factorsCount);
 		}
 
-		if (primeTesterCapacity > Input.Length)
+		MemoryBuffer1D<ulong, Stride1D.Dense> input = Input;
+		if (input.Length < primeTesterCapacity)
 		{
-			Input.Dispose();
+			input.Dispose();
-			Input = Accelerator.Allocate1D<ulong>(primeTesterCapacity);			
+			Input = accelerator.Allocate1D<ulong>(primeTesterCapacity);			
 		}
 
-		if (primeTesterCapacity > OutputByte.Length)
+		MemoryBuffer1D<byte, Stride1D.Dense> outputByte = OutputByte;
+		if (outputByte.Length < primeTesterCapacity)
 		{
-			OutputByte.Dispose();
+			outputByte.Dispose();
-			OutputByte = Accelerator.Allocate1D<byte>(primeTesterCapacity);
+			OutputByte = accelerator.Allocate1D<byte>(primeTesterCapacity);
 		}
 
-		if (primeTesterCapacity > OutputInt.Length)
+		MemoryBuffer1D<int, Stride1D.Dense> outputInt = OutputInt;
+		if (outputInt.Length < primeTesterCapacity)
 		{
-			OutputInt.Dispose();
+			outputInt.Dispose();
-			OutputInt = Accelerator.Allocate1D<int>(primeTesterCapacity);
+			OutputInt = accelerator.Allocate1D<int>(primeTesterCapacity);
 		}
 	}
 
 	public void EnsureSmallPrimeFactorSlotsCapacity(int newSize)
 	{
 		// Console.WriteLine($"Resizing GPU scratch buffer from pool ({buffer.SmallPrimeFactorPrimeSlots.Length} / {smallPrimeFactorSlotCount}), ({buffer.SpecialMaxFactors.Length}/{specialMaxFactorCapacity})");
-		if (OutputUlong.Length < newSize)
-		{
-			OutputUlong.Dispose();
-
 		var accelerator = Accelerator;
+		MemoryBuffer1D<ulong, Stride1D.Dense> outputUlong = OutputUlong;
+		if (outputUlong.Length < newSize)
+		{
+			outputUlong.Dispose();
 			OutputUlong = accelerator.Allocate1D<ulong>(newSize);
 		}
 
-		if (OutputInt.Length < newSize)
+		MemoryBuffer1D<int, Stride1D.Dense> outputInt = OutputInt;
+		if (outputInt.Length < newSize)
 		{
-			OutputInt.Dispose();
+			outputInt.Dispose();
-			
-			var accelerator = Accelerator;
 			OutputInt = accelerator.Allocate1D<int>(newSize);
 		}
 	}
 
 	public void EnsureSpecialMaxFactorsCapacity(int newSize)
 	{
-		if (Input.Length < newSize)
-		{
-			Input.Dispose();
-
 		var accelerator = Accelerator;
+		MemoryBuffer1D<ulong, Stride1D.Dense> input = Input;
+		if (input.Length < newSize)
+		{
+			input.Dispose();
 			Input = accelerator.Allocate1D<ulong>(newSize);
 		}
 
-		if (OutputUlong.Length < newSize)
+		MemoryBuffer1D<ulong, Stride1D.Dense> outputUlong = OutputUlong;
+		if (outputUlong.Length < newSize)
 		{
-			OutputUlong.Dispose();
+			outputUlong.Dispose();
-
-			var accelerator = Accelerator;
 			OutputUlong = accelerator.Allocate1D<ulong>(newSize);
 		}
 	}
@@ -209,55 +211,51 @@ public sealed class PrimeOrderCalculatorAccelerator
 
 		LastDigitGpuTables lastDigitSharedTables = LastDigitGpuTables.GetStaticTables(acceleratorIndex);
 
-		DevicePrimesLastOne = lastDigitSharedTables.DevicePrimesLastOne;
+		DevicePrimesLastOne = lastDigitSharedTables.DevicePrimesLastOne.View;
-		DevicePrimesLastSeven = lastDigitSharedTables.DevicePrimesLastSeven;
+		DevicePrimesLastSeven = lastDigitSharedTables.DevicePrimesLastSeven.View;
-		DevicePrimesLastThree = lastDigitSharedTables.DevicePrimesLastThree;
+		DevicePrimesLastThree = lastDigitSharedTables.DevicePrimesLastThree.View;
-		DevicePrimesLastNine = lastDigitSharedTables.DevicePrimesLastNine;
+		DevicePrimesLastNine = lastDigitSharedTables.DevicePrimesLastNine.View;
-		DevicePrimesPow2LastOne = lastDigitSharedTables.DevicePrimesPow2LastOne;
+		DevicePrimesPow2LastOne = lastDigitSharedTables.DevicePrimesPow2LastOne.View;
-		DevicePrimesPow2LastSeven = lastDigitSharedTables.DevicePrimesPow2LastSeven;
+		DevicePrimesPow2LastSeven = lastDigitSharedTables.DevicePrimesPow2LastSeven.View;
-		DevicePrimesPow2LastThree = lastDigitSharedTables.DevicePrimesPow2LastThree;
+		DevicePrimesPow2LastThree = lastDigitSharedTables.DevicePrimesPow2LastThree.View;
-		DevicePrimesPow2LastNine = lastDigitSharedTables.DevicePrimesPow2LastNine;
+		DevicePrimesPow2LastNine = lastDigitSharedTables.DevicePrimesPow2LastNine.View;
 
-		var heuristicSharedTables = HeuristicCombinedGpuTables.GetStaticTables(acceleratorIndex);
+		DivisorTables = HeuristicCombinedGpuTables
-
+			.GetStaticTables(acceleratorIndex)
-		DivisorTables = heuristicSharedTables.CreateViews();
+			.CreateViews();
 
 		var smallPrimeFactorTables = SmallPrimeFactorGpuTables.GetStaticTables(acceleratorIndex);
-		SmallPrimeFactorPrimes = smallPrimeFactorTables.Primes;
+		SmallPrimeFactorPrimes = smallPrimeFactorTables.Primes.View;
-		SmallPrimeFactorSquares = smallPrimeFactorTables.Squares;
+		SmallPrimeFactorSquares = smallPrimeFactorTables.Squares.View;
 
-		var checkFactorsKernel = accelerator.LoadStreamKernel<int, ulong, ArrayView1D<KeyValuePair<ulong, int>, Stride1D.Dense>, MontgomeryDivisorData, ArrayView1D<ulong, Stride1D.Dense>>(PrimeOrderGpuHeuristics.CheckFactorsKernel);
+		CheckFactorsKernel = KernelUtil.GetKernel(accelerator.LoadStreamKernel<int, ulong, ArrayView1D<KeyValuePair<ulong, int>, Stride1D.Dense>, MontgomeryDivisorData, ArrayView1D<ulong, Stride1D.Dense>>(PrimeOrderGpuHeuristics.CheckFactorsKernel));
-		CheckFactorsKernel = KernelUtil.GetKernel(checkFactorsKernel);
 
-		var convertKernel = accelerator.LoadAutoGroupedStreamKernel<Index1D, ArrayView1D<ulong, Stride1D.Dense>, MontgomeryDivisorData, ArrayView1D<ulong, Stride1D.Dense>>(Pow2MontgomeryKernels.Pow2MontgomeryKernelConvertToStandard);
+		ConvertToStandardKernel = KernelUtil.GetKernel(accelerator.LoadAutoGroupedStreamKernel<Index1D, ArrayView1D<ulong, Stride1D.Dense>, MontgomeryDivisorData, ArrayView1D<ulong, Stride1D.Dense>>(Pow2MontgomeryKernels.Pow2MontgomeryKernelConvertToStandard));
-		ConvertToStandardKernel = KernelUtil.GetKernel(convertKernel);
 
 		HeuristicCombinedTrialDivisionKernel = KernelUtil.GetKernel(accelerator.LoadAutoGroupedStreamKernel<Index1D, byte, ArrayView<int>, ulong, ulong, HeuristicCombinedGpuViews>(PrimeTesterKernels.HeuristicTrialCombinedDivisionKernel));
 
-		var keepKernel = accelerator.LoadAutoGroupedStreamKernel<Index1D, ArrayView1D<ulong, Stride1D.Dense>, MontgomeryDivisorData, ArrayView1D<ulong, Stride1D.Dense>>(Pow2MontgomeryKernels.Pow2MontgomeryKernelKeepMontgomery);
+		KeepMontgomeryKernel = KernelUtil.GetKernel(accelerator.LoadAutoGroupedStreamKernel<Index1D, ArrayView1D<ulong, Stride1D.Dense>, MontgomeryDivisorData, ArrayView1D<ulong, Stride1D.Dense>>(Pow2MontgomeryKernels.Pow2MontgomeryKernelKeepMontgomery));
-		KeepMontgomeryKernel = KernelUtil.GetKernel(keepKernel);
-
-		SmallPrimeSieveKernel = KernelUtil.GetKernel(accelerator.LoadAutoGroupedStreamKernel<Index1D, ArrayView<ulong>, ArrayView<uint>, ArrayView<uint>, ArrayView<uint>, ArrayView<uint>, ArrayView<ulong>, ArrayView<ulong>, ArrayView<ulong>, ArrayView<ulong>, ArrayView<byte>>(PrimeTesterKernels.SmallPrimeSieveKernel));
 
 		PollardRhoKernel = KernelUtil.GetKernel(accelerator.LoadStreamKernel<ulong, int, ArrayView1D<ulong, Stride1D.Dense>, ArrayView1D<byte, Stride1D.Dense>, ArrayView1D<ulong, Stride1D.Dense>>(Pow2MontgomeryKernels.TryPollardRhoKernel));
 
-		Pow2ModWideKernel = KernelUtil.GetKernel(
+		Pow2ModWideKernel = KernelUtil.GetKernel(accelerator.LoadAutoGroupedStreamKernel<Index1D, ArrayView1D<GpuUInt128, Stride1D.Dense>, GpuUInt128, ArrayView1D<GpuUInt128, Stride1D.Dense>>(PrimeOrderGpuHeuristics.Pow2ModKernelWide));
-			accelerator.LoadAutoGroupedStreamKernel<Index1D, ArrayView1D<GpuUInt128, Stride1D.Dense>, GpuUInt128, ArrayView1D<GpuUInt128, Stride1D.Dense>>(PrimeOrderGpuHeuristics.Pow2ModKernelWide));
 
 		SharesFactorKernel = KernelUtil.GetKernel(accelerator.LoadAutoGroupedStreamKernel<Index1D, ArrayView<ulong>, ArrayView<byte>>(PrimeTesterKernels.SharesFactorKernel));
 
-		SpecialMaxKernel = KernelUtil.GetKernel(accelerator.LoadAutoGroupedStreamKernel<Index1D, ulong, ArrayView1D<ulong, Stride1D.Dense>, int, MontgomeryDivisorData, ArrayView1D<ulong, Stride1D.Dense>, ArrayView1D<ulong, Stride1D.Dense>>(PrimeOrderGpuHeuristics.EvaluateSpecialMaxCandidatesKernel));
-
 		SmallPrimeFactorKernel = KernelUtil.GetKernel(accelerator.LoadAutoGroupedStreamKernel<Index1D, ulong, uint, ArrayView1D<uint, Stride1D.Dense>, ArrayView1D<ulong, Stride1D.Dense>, int, ArrayView1D<ulong, Stride1D.Dense>, ArrayView1D<int, Stride1D.Dense>, ArrayView1D<int, Stride1D.Dense>, ArrayView1D<ulong, Stride1D.Dense>>(SmallPrimeFactorKernels.SmallPrimeFactorKernelScan));
+
+		SmallPrimeSieveKernel = KernelUtil.GetKernel(accelerator.LoadAutoGroupedStreamKernel<Index1D, ArrayView<ulong>, ArrayView<uint>, ArrayView<uint>, ArrayView<uint>, ArrayView<uint>, ArrayView<ulong>, ArrayView<ulong>, ArrayView<ulong>, ArrayView<ulong>, ArrayView<byte>>(PrimeTesterKernels.SmallPrimeSieveKernel));
+
+		SpecialMaxKernel = KernelUtil.GetKernel(accelerator.LoadAutoGroupedStreamKernel<Index1D, ulong, ArrayView1D<ulong, Stride1D.Dense>, int, MontgomeryDivisorData, ArrayView1D<ulong, Stride1D.Dense>, ArrayView1D<ulong, Stride1D.Dense>>(PrimeOrderGpuHeuristics.EvaluateSpecialMaxCandidatesKernel));
 	}
 
 	public void Dispose()
 	{
 		Input.Dispose();
-		OutputUlong.Dispose();
-		Pow2ModEntriesToTestOnDevice.Dispose();
 		OutputByte.Dispose();
 		OutputInt.Dispose();
+		OutputUlong.Dispose();
+		Pow2ModEntriesToTestOnDevice.Dispose();
 		SmallPrimeFactorCountSlot.Dispose();
 		SpecialMaxResult.Dispose();
 

PerfectNumbers.Core/Gpu/ExponentRemainderStepperGpu.cs

@@ -1,5 +1,4 @@
 using System.Runtime.CompilerServices;
-using PerfectNumbers.Core;
 
 namespace PerfectNumbers.Core.Gpu;
 

PerfectNumbers.Core/Gpu/GpuPrimeWorkLimiter.cs

@@ -1,6 +1,3 @@
-using System;
-using System.Threading;
-
 namespace PerfectNumbers.Core.Gpu;
 
 public static class GpuPrimeWorkLimiter

PerfectNumbers.Core/Gpu/Kernels/DivisorByDivisorKernels.cs

@@ -1,7 +1,4 @@
 using ILGPU;
-using ILGPU.Algorithms;
-using ILGPU.Runtime;
-using PerfectNumbers.Core;
 
 namespace PerfectNumbers.Core.Gpu;
 

PerfectNumbers.Core/Gpu/Kernels/DivisorKernels.cs

@@ -1,6 +1,5 @@
 using ILGPU;
 using ILGPU.Algorithms;
-using ILGPU.Runtime;
 
 namespace PerfectNumbers.Core.Gpu;
 

PerfectNumbers.Core/Gpu/Kernels/IncrementalKernels.cs

@@ -1,5 +1,4 @@
 using ILGPU;
-using ILGPU.Algorithms;
 using ILGPU.Runtime;
 
 namespace PerfectNumbers.Core.Gpu;

PerfectNumbers.Core/Gpu/Kernels/LucasLehmerKernels.cs

@@ -1,7 +1,5 @@
-using System;
 using System.Runtime.CompilerServices;
 using ILGPU;
-using ILGPU.Runtime;
 using UInt128 = System.UInt128;
 
 namespace PerfectNumbers.Core.Gpu;

PerfectNumbers.Core/Gpu/Kernels/NttButterflyKernels.cs

@@ -1,5 +1,4 @@
 using ILGPU;
-using ILGPU.Runtime;
 
 namespace PerfectNumbers.Core.Gpu;
 

PerfectNumbers.Core/Gpu/Kernels/NttPointwiseKernels.cs

@@ -1,5 +1,4 @@
 using ILGPU;
-using ILGPU.Runtime;
 
 namespace PerfectNumbers.Core.Gpu;
 

PerfectNumbers.Core/Gpu/Kernels/NttTransformKernels.cs

@@ -1,5 +1,4 @@
 using ILGPU;
-using ILGPU.Runtime;
 
 namespace PerfectNumbers.Core.Gpu;
 

PerfectNumbers.Core/Gpu/Kernels/OrderKernels.cs

@@ -1,5 +1,4 @@
 using ILGPU;
-using ILGPU.Runtime;
 
 namespace PerfectNumbers.Core.Gpu;
 

PerfectNumbers.Core/Gpu/Kernels/Pow2ModKernels.cs

@@ -1,5 +1,4 @@
 using ILGPU;
-using ILGPU.Algorithms;
 using ILGPU.Runtime;
 
 namespace PerfectNumbers.Core.Gpu;

PerfectNumbers.Core/Gpu/MersenneNumberDivisorByDivisorGpuTester.cs

@@ -1,11 +1,7 @@
-using PerfectNumbers.Core.Gpu;
-using System;
 using System.Buffers;
 using System.Collections.Concurrent;
 using System.Runtime.CompilerServices;
 using System.Runtime.InteropServices;
-using System.Threading;
-using PerfectNumbers.Core;
 using ILGPU;
 using ILGPU.Runtime;
 using PerfectNumbers.Core.Gpu.Accelerators;

PerfectNumbers.Core/Gpu/MersenneNumberDivisorGpuTester.cs

@@ -1,6 +1,4 @@
-using System.Collections.Concurrent;
 using ILGPU;
-using ILGPU.Algorithms;
 using ILGPU.Runtime;
 
 namespace PerfectNumbers.Core.Gpu;

PerfectNumbers.Core/Gpu/NttGpuMath.cs

@@ -1,4 +1,3 @@
-using System.Buffers;
 using System.Collections.Concurrent;
 using ILGPU;
 using ILGPU.Runtime;

PerfectNumbers.Core/HeuristicPrimeSieves.cs

@@ -1,5 +1,3 @@
-using System;
-
 namespace PerfectNumbers.Core;
 
 public static class HeuristicPrimeSieves

PerfectNumbers.Core/MersenneDivisorCycles.cs

@@ -1,4 +1,3 @@
-using System.Buffers;
 using System.Buffers.Binary;
 using System.Numerics;
 using System.Runtime.CompilerServices;
@@ -7,7 +6,6 @@ using System.Text;
 using System.Runtime.InteropServices;
 using PerfectNumbers.Core.Gpu;
 using ILGPU;
-using ILGPU.Algorithms;
 using ILGPU.Runtime;
 using PerfectNumbers.Core.Gpu.Accelerators;
 

PerfectNumbers.Core/MersenneNumberDivisorByDivisorTester.cs

@@ -1,10 +1,7 @@
 using System.Buffers;
-using System.Threading;
-using System.Threading.Tasks;
 using System.Globalization;
 using System.Runtime.InteropServices;
 using PerfectNumbers.Core.Gpu.Accelerators;
-using PerfectNumbers.Core.Gpu;
 
 namespace PerfectNumbers.Core;
 

PerfectNumbers.Core/MersennePrimeFactorTester.cs

@@ -2,7 +2,6 @@ using System.Collections.Concurrent;
 using System.Runtime.CompilerServices;
 using System.Numerics;
 using UInt128 = System.UInt128;
-using ILGPU;
 using System.Buffers;
 using PerfectNumbers.Core.Cpu;
 

PerfectNumbers.Core/PerfectNumberConstants.cs

@@ -1,5 +1,3 @@
-using PerfectNumbers.Core.Gpu;
-
 namespace PerfectNumbers.Core;
 
 public static class PerfectNumberConstants

PerfectNumbers.Core/PooledValueStringBuilder.cs

@@ -1,4 +1,3 @@
-using System;
 using System.Globalization;
 using System.Runtime.CompilerServices;
 

PerfectNumbers.Core/PrimeOrderCalculator.Cpu.cs

@@ -3,7 +3,6 @@ using System.Diagnostics;
 using System.Numerics;
 using System.Runtime.CompilerServices;
 using System.Runtime.InteropServices;
-using ILGPU;
 using PerfectNumbers.Core.Cpu;
 using PerfectNumbers.Core.Gpu;
 using PerfectNumbers.Core.Gpu.Accelerators;

PerfectNumbers.Core/PrimeOrderCalculator.Gpu.cs

@@ -1,4 +1,3 @@
-using System.Runtime.InteropServices;
 using ILGPU;
 using ILGPU.Runtime;
 using PerfectNumbers.Core.Gpu;

PerfectNumbers.Core/PrimeTester.cs

@@ -1,9 +1,7 @@
-using System.Buffers;
 using System.Numerics;
 using System.Runtime.CompilerServices;
 using ILGPU;
 using ILGPU.Runtime;
-using PerfectNumbers.Core.Gpu;
 using PerfectNumbers.Core.Gpu.Accelerators;
 
 namespace PerfectNumbers.Core;
@@ -110,14 +108,14 @@ public sealed class PrimeTester
 						stream,
 						1,
 						inputView,
-						gpu.DevicePrimesLastOne.View,
+						gpu.DevicePrimesLastOne,
-						gpu.DevicePrimesLastSeven.View,
+						gpu.DevicePrimesLastSeven,
-						gpu.DevicePrimesLastThree.View,
+						gpu.DevicePrimesLastThree,
-						gpu.DevicePrimesLastNine.View,
+						gpu.DevicePrimesLastNine,
-						gpu.DevicePrimesPow2LastOne.View,
+						gpu.DevicePrimesPow2LastOne,
-						gpu.DevicePrimesPow2LastSeven.View,
+						gpu.DevicePrimesPow2LastSeven,
-						gpu.DevicePrimesPow2LastThree.View,
+						gpu.DevicePrimesPow2LastThree,
-						gpu.DevicePrimesPow2LastNine.View,
+						gpu.DevicePrimesPow2LastNine,
 						outputView);
 
 		outputView.CopyToCPU(stream, ref flag, 1);
@@ -150,14 +148,14 @@ public sealed class PrimeTester
 						stream,
 						1,
 						inputView,
-						gpu.DevicePrimesLastOne.View,
+						gpu.DevicePrimesLastOne,
-						gpu.DevicePrimesLastSeven.View,
+						gpu.DevicePrimesLastSeven,
-						gpu.DevicePrimesLastThree.View,
+						gpu.DevicePrimesLastThree,
-						gpu.DevicePrimesLastNine.View,
+						gpu.DevicePrimesLastNine,
-						gpu.DevicePrimesPow2LastOne.View,
+						gpu.DevicePrimesPow2LastOne,
-						gpu.DevicePrimesPow2LastSeven.View,
+						gpu.DevicePrimesPow2LastSeven,
-						gpu.DevicePrimesPow2LastThree.View,
+						gpu.DevicePrimesPow2LastThree,
-						gpu.DevicePrimesPow2LastNine.View,
+						gpu.DevicePrimesPow2LastNine,
 						outputView);
 
 		outputView.CopyToCPU(stream, ref flag, 1);
@@ -198,7 +196,6 @@ public sealed class PrimeTester
 		// GpuPrimeWorkLimiter.Acquire();
 		var gpu = PrimeOrderCalculatorAccelerator.Rent(GpuBatchSize);
 		int acceleratorIndex = gpu.AcceleratorIndex;
-		var accelerator = gpu.Accelerator;
 		var kernel = gpu.SmallPrimeSieveKernel!;
 		int totalLength = values.Length;
 		int batchSize = GpuBatchSize;
@@ -222,14 +219,14 @@ public sealed class PrimeTester
 					stream,
 					count,
 					inputView,
-					gpu.DevicePrimesLastOne.View,
+					gpu.DevicePrimesLastOne,
-					gpu.DevicePrimesLastSeven.View,
+					gpu.DevicePrimesLastSeven,
-					gpu.DevicePrimesLastThree.View,
+					gpu.DevicePrimesLastThree,
-					gpu.DevicePrimesLastNine.View,
+					gpu.DevicePrimesLastNine,
-					gpu.DevicePrimesPow2LastOne.View,
+					gpu.DevicePrimesPow2LastOne,
-					gpu.DevicePrimesPow2LastSeven.View,
+					gpu.DevicePrimesPow2LastSeven,
-					gpu.DevicePrimesPow2LastThree.View,
+					gpu.DevicePrimesPow2LastThree,
-					gpu.DevicePrimesPow2LastNine.View,
+					gpu.DevicePrimesPow2LastNine,
 					outputView);
 
 			var resultSlice = results.Slice(pos, count);

PerfectNumbers.Core/TaskThreadPool.cs

@@ -1,8 +1,4 @@
-using System;
 using System.Collections.Concurrent;
-using System.Collections.Generic;
-using System.Threading;
-using System.Threading.Tasks;
 
 namespace PerfectNumbers.Core;
 

PerfectNumbers.Core/TextFileWriter.cs

@@ -1,4 +1,3 @@
-using System;
 using System.Text;
 
 namespace PerfectNumbers.Core;

PerfectNumbers.Core/ThreadStaticPools.cs

@@ -1,5 +1,4 @@
 using System.Buffers;
-using System.Collections.Generic;
 using System.Runtime.CompilerServices;
 using PerfectNumbers.Core.Cpu;
 using PerfectNumbers.Core.Gpu;

PerfectNumbers.Core/UInt128Extensions.cs

@@ -1,6 +1,5 @@
 using System.Numerics;
 using System.Runtime.CompilerServices;
-using System.Threading;
 using PerfectNumbers.Core.Gpu;
 
 namespace PerfectNumbers.Core;

PerfectNumbers.Core/ULongExtensions.Cpu.cs

@@ -1,4 +1,3 @@
-using System;
 using System.Numerics;
 using System.Runtime.CompilerServices;
 

PerfectNumbers.Core/ULongExtensions.Gpu.cs

@@ -1,8 +1,5 @@
-using System;
-using System.Collections.Concurrent;
 using System.Runtime.CompilerServices;
 using ILGPU.Algorithms;
-using ILGPU.Runtime;
 using PerfectNumbers.Core.Gpu;
 using PerfectNumbers.Core.Gpu.Accelerators;
 

PerfectNumbers.Core/ULongExtensions.cs

@@ -1,6 +1,5 @@
 using System.Numerics;
 using System.Runtime.CompilerServices;
-using ILGPU.Algorithms;
 
 namespace PerfectNumbers.Core;
 

PerfectNumbers.Core/UnboundedTaskScheduler.cs

@@ -1,7 +1,3 @@
-using System;
-using System.Collections.Generic;
-using System.Threading.Tasks;
-
 namespace PerfectNumbers.Core;
 
 public sealed class UnboundedTaskScheduler : TaskScheduler