 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 |
|
|
Marek Lemańczyk
|
4d9158e8f3
|
Make GPU mask compaction branchless with shared staging
|
2025-10-22 22:01:39 +02:00 |
|
|
Marek Lemańczyk
|
586eb8d303
|
Document hot-path guards in GPU mask compaction helpers
|
2025-10-22 18:48:03 +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 |
|