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

Make GPU mask compaction branchless with shared staging

Browse Source
This commit is contained in:
Marek Lemańczyk committed 2025-10-22 22:01:39 +02:00
1 parent ea0770a84a
commit 4d9158e8f3
2 files changed
+38 -19
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

PerfectNumbers.Core/Gpu/MersenneNumberDivisorByDivisorGpuTester.cs
+2 -1
View File
@@ -588,7 +588,8 @@ public sealed class MersenneNumberDivisorByDivisorGpuTester : IMersenneNumberDiv
// return 0;
// }
SharedMemoryConfig sharedMemoryConfig = SharedMemoryConfig.RequestDynamic<int>(count);
countView.MemSetToZero();
SharedMemoryConfig sharedMemoryConfig = SharedMemoryConfig.RequestDynamic<int>(count * 3);
Index1D gridDim = new Index1D(1);
Index1D groupDim = new Index1D(count);
KernelConfig kernelConfig = new KernelConfig(gridDim, groupDim, sharedMemoryConfig);