 mlemanczyk
|
070e2a14fd
|
MontgomeryDivisorData converted to a pooled class to limit GC pressure. MontgomeryDivisorDataGpu added for GPU operations. PrimeOrderCalculator kernels precompiled during warmup.
|
2025-11-24 15:14:31 +01:00 |
|
|
mlemanczyk
|
07efd5d2a1
|
Accelerator locks removed
|
2025-11-23 14:59:29 +01:00 |
|
|
mlemanczyk
|
6d1ff1372e
|
Factoring switched to PrimeTester.IsPrime for the best performance. PrimeOrderCalculator.PartialFactor switched to GPU factorization. Every so often it will send work to GPU instead of CPU. BatchedResources renamed to MersenneNumberDivisorByDivisorAccelerator for consistency and moved to its own file. It now uses array instead of dictionary for lookup free performance.
|
2025-11-23 00:07:03 +01:00 |
|
|
mlemanczyk
|
9939c5d562
|
Divisor will now be saved to CSV file
|
2025-11-19 22:14:28 +01:00 |
|
|
mlemanczyk
|
5cac51479e
|
GPU memory allocations protected with lock to prevent shared memory access issues. GPU usage limited for the best performance.
|
2025-11-19 16:49:01 +01:00 |
|
|
mlemanczyk
|
801b1be3e3
|
Cleanup
|
2025-11-18 04:22:39 +01:00 |
|
|
mlemanczyk
|
342eff2726
|
GpuKernelPool.GetOrAddKernels removed in --mersenne=bydivisor mode. PartialFactorResult.WithAdditionalPrime will now modify the current instance instead of creating new copy for better performance. SmallPrimeFactorViews renamed to SmallPrimeFactorGpuTables for consistency with other static tables.
|
2025-11-17 23:33:59 +01:00 |
|
|
mlemanczyk
|
f630bfb598
|
HeuristicCombinedPrimeTesterAccelerator integrated with PrimeOrderCalculatorAccelerator.
|
2025-11-17 17:38:23 +01:00 |
|
|
mlemanczyk
|
183b147135
|
Heuristic tables split into 2 groups
|
2025-11-17 16:04:27 +01:00 |
|
|
mlemanczyk
|
0540411cad
|
Accelerator index added for dictionary-less use-cases
|
2025-11-15 02:21:45 +01:00 |
|
|
mlemanczyk
|
0d2a88c45f
|
GpuPrimeWorkLimiter.Acquire() / .Release() removed to save time on the hot-path with billions of calls. We'll rely on AcceleratorStreamPool limits and synchronization.
|
2025-11-13 17:52:13 +01:00 |
|
|
mlemanczyk
|
d0b1639a5d
|
GPU stabilization improvements to prevent calculation crashes
|
2025-11-09 21:52:16 +01:00 |
|
|
mlemanczyk
|
8e779c5c9e
|
GpuKernelLease removed
|
2025-11-07 15:36:45 +01:00 |
|
|
mlemanczyk
|
0410fd2c91
|
PooledContext removal - continuation. GpuKernelLease prepared for removal.
|
2025-11-07 14:13:11 +01:00 |
|
|
mlemanczyk
|
f4e365194d
|
GpuContextPool removed, because we share context and accelerator between threads, using streams to separate.
|
2025-11-07 12:52:20 +01:00 |
|
|
mlemanczyk
|
119690086a
|
ConcurrentDictionary removed. Kernel made dependent on the shared GPU context.
|
2025-11-07 10:16:33 +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 |
|
|
mlemanczyk
|
07be671726
|
Various small optimizations
|
2025-11-02 11:24:18 +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 |
|
|
mlemanczyk
|
22f20bfe98
|
Various small optimizations
|
2025-11-01 03:42:36 +01:00 |
|
|
Marek Lemańczyk
|
5536dc4865
|
Fix GPU by-divisor hang for small primes
|
2025-10-29 19:21:41 +01:00 |
|
|
mlemanczyk
|
4c79c4087e
|
Various optimizations
|
2025-10-29 14:00:38 +01:00 |
|
|
Marek Lemańczyk
|
6dd5cea79f
|
Remove temporary by-divisor review documents
|
2025-10-28 02:01:28 +01:00 |
|
|
Marek Lemańczyk
|
94a4ed8328
|
Hoist prime order thresholds in CPU heuristics
|
2025-10-27 21:24:43 +01:00 |
|
|
Marek Lemańczyk
|
3758524450
|
Extract divisor validator and rename legacy CPU prime helper
|
2025-10-26 18:59:07 +01:00 |
|
|
Marek Lemańczyk
|
c01abbd03a
|
Restore legacy by-divisor scans for Mersenne testers
|
2025-10-26 16:04:09 +01:00 |
|
|
Marek Lemańczyk
|
43c7bafd5d
|
Restore CPU PrimeTester usage and rename fallback helpers
|
2025-10-26 15:19:49 +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
|
32f9f25e9b
|
Share GPU by-divisor batch resources across accelerators
|
2025-10-25 05:03:16 +02:00 |
|
|
Marek Lemańczyk
|
3735a1cf0f
|
Gate GPU by-divisor scans to a single accelerator
|
2025-10-25 05:00:54 +02:00 |
|
|
Marek Lemańczyk
|
6b1c2d0665
|
Reuse GPU by-divisor buffers to curb host allocations
|
2025-10-25 03:45:46 +02:00 |
|
|
Marek Lemańczyk
|
4e9d57df4b
|
Unify GPU divisor kernels with stepper path
|
2025-10-24 20:50:52 +02:00 |
|
|
Marek Lemańczyk
|
868c7a4fd2
|
Tighten GPU divisor heuristics and stepper usage
|
2025-10-24 20:50:46 +02:00 |
|
|
Marek Lemańczyk
|
bbe0c02069
|
Use bit masks for divisor heuristics
|
2025-10-24 19:50:27 +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
|
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
|
fbd6235316
|
Handle zero-cycle GPU divisor sessions with heuristics
|
2025-10-24 06:40:33 +02:00 |
|
|
Marek Lemańczyk
|
cf9d143ca2
|
Remove GPU by-divisor snapshot dependency
|
2025-10-24 05:05:21 +02:00 |
|
|
Marek Lemańczyk
|
8637ee8875
|
Restore GPU divisor heuristics to match cycle cache
|
2025-10-24 05:05:16 +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 |
|
|
Marek Lemańczyk
|
f672ff520c
|
Avoid redundant compaction buffer clearing on GPU
|
2025-10-23 01:16:58 +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 |
|