 mlemanczyk
|
5bc65464d0
|
Initial PollardRho implementation for GPU. Added pool for accelerator streams shared across the threads. GPU processing performance and stabilization improvements. GpuUInt128.BinaryGcd switched to the version which outperformed other in benchmarks.
|
2025-11-12 21:18:30 +01:00 |
|
|
mlemanczyk
|
cf5f78c2ef
|
PrimeTesterByLastDigitAccelerator integrated into Pow2MontgomeryGpuCalculator for better performance.
|
2025-11-11 13:36:21 +01:00 |
|
|
mlemanczyk
|
0de9871529
|
Functionality and classes separated. Kernel initialization made dependent on a flag. Cleanup.
|
2025-11-10 18:35:50 +01:00 |
|
|
mlemanczyk
|
fa89958736
|
Stabilization improvements. Stream will be released when releasing GPU lease to prevent application crashes.
|
2025-11-10 14:30:30 +01:00 |
|
|
mlemanczyk
|
d0b1639a5d
|
GPU stabilization improvements to prevent calculation crashes
|
2025-11-09 21:52:16 +01:00 |
|
|
mlemanczyk
|
de2a78b27b
|
Streams added to all kernels and GPU operations to separate threads from each other.
|
2025-11-06 18:53:55 +01:00 |
|
|
mlemanczyk
|
64d615c402
|
Various optimizations to separate non-static data between threads and resolve read/write access issue.
|
2025-11-04 20:45:56 +01:00 |
|
|
Marek Lemańczyk
|
4c4d4243fb
|
Merge remote-tracking branch 'github/codex/optimize-evenperfectbitscanner-for-static-arrays-khd9w8' into work
# Conflicts:
# PerfectNumbers.Core/Gpu/GpuContextPool.cs
# PerfectNumbers.Core/Gpu/GpuKernelLease.cs
# PerfectNumbers.Core/Gpu/GpuKernelPool.cs
# PerfectNumbers.Core/Gpu/GpuStaticTableInitializer.cs
# PerfectNumbers.Core/Gpu/Kernels/PrimeOrderSpecialMaxKernels.cs
# PerfectNumbers.Core/PrimeOrderCalculator.Cpu.cs
# PerfectNumbers.Core/PrimeOrderCalculator.Gpu.cs
# PerfectNumbers.Core/PrimeTester.cs
|
2025-11-03 23:59:12 +01:00 |
|
|
Marek Lemańczyk
|
76dfe108a9
|
Address feedback on GPU pooling and heuristic factoring
|
2025-11-02 11:22:49 +01:00 |
|
|
Marek Lemańczyk
|
ab6a416de2
|
Warm GPU resources before thread startup
|
2025-11-02 11:22:28 +01:00 |
|
|
mlemanczyk
|
2281d9535e
|
Revert "Merge pull request #251 from mlemanczyk/codex/refactor-prime-checking-on-gpu-n5t2pm"
This reverts commit 936ce239db, reversing
changes made to e14b77e504.
|
2025-11-02 11:22:14 +01:00 |
|
|
Marek Lemańczyk
|
469c8057d3
|
Flatten heuristic trial division bounds checks
|
2025-10-31 22:45:59 +01:00 |
|
|
Marek Lemańczyk
|
8c662c5c85
|
Address feedback on GPU pooling and heuristic factoring
|
2025-10-31 21:47:42 +01:00 |
|
|
Marek Lemańczyk
|
6864b316d5
|
Warm GPU resources before thread startup
|
2025-10-31 16:56:25 +01:00 |
|
|
mlemanczyk
|
e14b77e504
|
Batch size made dynamic - dependent on the value
|
2025-10-30 02:43:15 +01:00 |
|
|
Marek Lemańczyk
|
f9504a6a19
|
Use atomic flag writes in heuristic trial division
|
2025-10-29 20:40:40 +01:00 |
|
|
Marek Lemańczyk
|
08499fdda1
|
Refine GPU prime tester leasing
|
2025-10-29 17:39:38 +01:00 |
|
|
Marek Lemańczyk
|
b0158a844a
|
Use divisor squares to bound heuristic combined trial division
|
2025-10-29 15:13:54 +01:00 |
|
|
Marek Lemańczyk
|
1792349bad
|
Make GPU sieve results authoritative
|
2025-10-28 20:14:22 +01:00 |
|
|
Marek Lemańczyk
|
c53966e481
|
Enable residue-aware GPU sieve in PrimeTester
|
2025-10-28 18:39:18 +01:00 |
|
|
Marek Lemańczyk
|
94a4ed8328
|
Hoist prime order thresholds in CPU heuristics
|
2025-10-27 21:24:43 +01:00 |
|
|
Marek Lemańczyk
|
9a0e328995
|
Reintroduce MulHigh CPU helper and tighten GPU sieve loop
|
2025-10-26 23:41:14 +01:00 |
|
|
Marek Lemańczyk
|
e2f68cedf2
|
Short-circuit small prime sieve kernel loops
|
2025-10-26 22:42:27 +01:00 |
|
|
Marek Lemańczyk
|
3d458fc6da
|
Use precomputed small prime squares in GPU sieve
|
2025-10-26 22:28:04 +01:00 |
|
|
Marek Lemańczyk
|
15c229665d
|
Add heuristic prime sieves for cached divisor sequences
|
2025-10-26 03:21:29 +01:00 |
|
|
Marek Lemańczyk
|
2d103a9662
|
Compute initial divisor remainders inside GPU kernel
|
2025-10-25 05:41:05 +02:00 |
|
|
Marek Lemańczyk
|
4e9d57df4b
|
Unify GPU divisor kernels with stepper path
|
2025-10-24 20:50:52 +02:00 |
|
|
Marek Lemańczyk
|
46a2178d65
|
Remove Montgomery data from GPU divisor flow
|
2025-10-24 18:56:28 +02:00 |
|
|
Marek Lemańczyk
|
69acd3dad9
|
Cache GPU divisor partial data on GPU path
|
2025-10-24 18:56:21 +02:00 |
|
|
Marek Lemańczyk
|
cc281ab423
|
Refactor GPU powmod helpers into ULongExtensions
|
2025-10-24 17:26:55 +02:00 |
|
|
Marek Lemańczyk
|
d20362a2fc
|
Switch GPU by-divisor stepper to standard modular arithmetic
|
2025-10-24 09:20:17 +02:00 |
|
|
Marek Lemańczyk
|
1e5a9128cb
|
Split CPU and GPU exponent steppers
|
2025-10-24 08:49:53 +02:00 |
|
|
Marek Lemańczyk
|
035956cdb6
|
Replace GPU by-divisor kernel with standard modular exponentiation
|
2025-10-24 08:49:48 +02:00 |
|
|
Marek Lemańczyk
|
8a258f7536
|
Collapse GPU by-divisor batching to a single launch
|
2025-10-24 01:23:38 +02:00 |
|
|
Marek Lemańczyk
|
1075ab1ea1
|
Fuse GPU hit detection with divisor evaluation
|
2025-10-24 01:23:31 +02:00 |
|
|
Marek Lemańczyk
|
40d3b4b3ac
|
Fuse GPU by-divisor candidate filtering into one kernel
|
2025-10-24 01:23:25 +02:00 |
|
|
Marek Lemańczyk
|
ab1a069e57
|
Optimize GPU divisor heuristics pipeline
|
2025-10-24 00:29:26 +02:00 |
|
|
mlemanczyk
|
0d7df2e45b
|
Unnecessary memory zeroing commented out. TODOs added for the remainders.
|
2025-10-23 19:42:03 +02:00 |
|
|
Marek Lemańczyk
|
f672ff520c
|
Avoid redundant compaction buffer clearing on GPU
|
2025-10-23 01:16:58 +02:00 |
|
|
Marek Lemańczyk
|
dda53581c0
|
Merge pull request #225 from mlemanczyk/codex/analyze-evenperfectbitscanner-for-gpu-optimization
Add GPU candidate generation for divisor scanning
|
2025-10-23 00:52:59 +02:00 |
|
|
Marek Lemańczyk
|
ea01585892
|
Convert divisor session results to hits on the GPU
|
2025-10-23 00:34:17 +02:00 |
|
|
Marek Lemańczyk
|
faab60c2cd
|
Reduce host hit detection overhead
|
2025-10-22 23:51:19 +02:00 |
|
|
Marek Lemańczyk
|
4d9158e8f3
|
Make GPU mask compaction branchless with shared staging
|
2025-10-22 22:01:39 +02:00 |
|
|
Marek Lemańczyk
|
ea0770a84a
|
Clarify stream kernel bounds assumptions
|
2025-10-22 21:41:51 +02:00 |
|
|
Marek Lemańczyk
|
add62df697
|
Compact GPU divisor masks on device
|
2025-10-22 18:47:55 +02:00 |
|
|
Marek Lemańczyk
|
bae39ad95e
|
Capture GPU next start for divisor batches
|
2025-10-22 06:43:05 +02:00 |
|
|
Marek Lemańczyk
|
5b973fb513
|
Document and streamline GPU candidate kernel guards
|
2025-10-22 06:43:00 +02:00 |
|
|
Marek Lemańczyk
|
4d8ea9dccd
|
Use GpuUInt128 in GPU divisor candidate generation
|
2025-10-22 06:05:22 +02:00 |
|
|
Marek Lemańczyk
|
6c3efb90c9
|
Merge pull request #222 from mlemanczyk/codex/refactor-primetester.isprimegpu-for-branch-less-execution
Clarify GPU sieve invariants and trim defensive guards
|
2025-10-22 05:24:57 +02:00 |
|
|
Marek Lemańczyk
|
bfc5712d81
|
Add GPU kernel for divisor candidate generation
|
2025-10-22 05:24:01 +02:00 |
|