 Marek Lemańczyk
|
645969309c
|
Reuse Pollard rho reciprocals for fast Montgomery stepping
|
2025-10-10 13:44:23 +02:00 |
|
|
Marek Lemańczyk
|
2b0d7278db
|
Replace Pollard-Rho random sources with deterministic generator
|
2025-10-10 10:41:47 +02:00 |
|
|
Marek Lemańczyk
|
4ed9db7d0b
|
Optimize Pollard Rho random sampling
|
2025-10-10 10:31:14 +02:00 |
|
|
mlemanczyk
|
99a7ec5b70
|
Tiny cleanup
|
2025-10-10 10:23:45 +02:00 |
|
|
mlemanczyk
|
ca0cadc8a3
|
Various optimizations and cleanups. "in" removed from GpuUInt128 to avoid defensive copies from IL.
|
2025-10-10 09:26:25 +02:00 |
|
|
Marek Lemańczyk
|
7aaccb5feb
|
Stop using IDisposable on prime order scopes
|
2025-10-10 02:57:54 +02:00 |
|
|
mlemanczyk
|
e7ac18ea0b
|
struct performance improvements
|
2025-10-10 01:19:53 +02:00 |
|
|
mlemanczyk
|
ef5a77cedd
|
IDisposable removed for better performance
|
2025-10-10 01:09:12 +02:00 |
|
|
Marek Lemańczyk
|
58c546cd87
|
Merge pull request #140 from mlemanczyk/codex/optimize-partialfactor-in-evenperfectbitscanner
Reduce garbage collector pressure in CPU partial factoring
|
2025-10-10 00:08:21 +02:00 |
|
|
Marek Lemańczyk
|
8054f9fe59
|
Reduce CPU partial factor allocations
|
2025-10-10 00:07:39 +02:00 |
|
|
mlemanczyk
|
b2ab47e0ee
|
Recording of failed heuristic cases turned off to speed up calculations
|
2025-10-09 23:57:10 +02:00 |
|
|
Marek Lemańczyk
|
f196f1fb96
|
Assume heuristic order when divisors are unresolved
|
2025-10-09 23:13:37 +02:00 |
|
|
mlemanczyk
|
a1a9c5f033
|
Comleted TODO removed
|
2025-10-09 23:05:48 +02:00 |
|
|
Marek Lemańczyk
|
9e0c90a281
|
Log heuristic fallback primes
|
2025-10-09 22:49:20 +02:00 |
|
|
Marek Lemańczyk
|
ebfdc7d8b8
|
Assign contiguous by-divisor ranges per worker
|
2025-10-09 22:09:05 +02:00 |
|
|
Marek Lemańczyk
|
ce8c3a660a
|
Extend bit skipping to UInt128 strides
|
2025-10-09 21:18:18 +02:00 |
|
|
Marek Lemańczyk
|
e1d4bbf12d
|
Optimize filtering strategy for previous Mersenne results
|
2025-10-09 05:28:59 +02:00 |
|
|
Marek Lemańczyk
|
668e161554
|
Fix divisor scan session compilation issues
|
2025-10-09 04:46:01 +02:00 |
|
|
Marek Lemańczyk
|
6bd8945565
|
Use analytic delta updates in CPU divisor sessions
|
2025-10-09 04:31:03 +02:00 |
|
|
mlemanczyk
|
99c9ddf73d
|
Merge branch 'pollardrhoplus2' of https://github.com/mlemanczyk/even-perfect-numbers-scanner into pollardrhoplus2
|
2025-10-09 03:57:18 +02:00 |
|
|
mlemanczyk
|
32de7ebc75
|
DebugLog disabled for profiling
|
2025-10-09 03:56:49 +02:00 |
|
|
Marek Lemańczyk
|
a19cbd245d
|
Prune completed CPU status TODO entry
|
2025-10-09 03:52:11 +02:00 |
|
|
mlemanczyk
|
64c08f9b49
|
We'll resolve the check when divisor cycle equals p. Tiny cleanup
|
2025-10-09 00:18:48 +02:00 |
|
|
Marek Lemańczyk
|
adac9ff5f9
|
Compact by-divisor candidate filtering
|
2025-10-08 23:34:35 +02:00 |
|
|
Marek Lemańczyk
|
9a81f5f685
|
Enable parallel by-divisor scanning threads
|
2025-10-08 22:45:53 +02:00 |
|
|
Marek Lemańczyk
|
85a98eb009
|
Reduce GPU remainder transfers for divisor filtering
|
2025-10-08 22:28:36 +02:00 |
|
|
Marek Lemańczyk
|
c45b3951c3
|
Align CPU by-divisor scan with cached divisor filters
|
2025-10-08 20:15:26 +02:00 |
|
|
mlemanczyk
|
6dc26336c6
|
Remainder check adjusted to PrimesGenerator.
|
2025-10-08 19:56:53 +02:00 |
|
|
Marek Lemańczyk
|
85634da6eb
|
Filter CPU divisor checks by admissible residues
|
2025-10-08 19:23:09 +02:00 |
|
|
Marek Lemańczyk
|
6918bd28ff
|
Make by-divisor GPU kernels reuse read-only operands
|
2025-10-08 18:47:16 +02:00 |
|
|
Marek Lemańczyk
|
cd1debe9d6
|
Various micro- and medium- optimizations
|
2025-10-07 22:14:34 +02:00 |
|
|
Marek Lemańczyk
|
48127845b5
|
GPU errors won't go silently, so that we can analyze and fix them.
|
2025-10-07 21:57:27 +02:00 |
|
|
Marek Lemańczyk
|
31e95e5a8b
|
Merge pull request #120 from mlemanczyk/codex/refactor-cycle-calculation-methods-for-mersenne
Streamline by-divisor cycle equality checks
|
2025-10-05 21:33:10 +02:00 |
|
|
Marek Lemańczyk
|
16181903a1
|
Streamline by-divisor cycle equality checks
|
2025-10-05 21:32:40 +02:00 |
|
|
Marek Lemańczyk
|
bd8686b86b
|
Unused parameter removed
|
2025-10-05 19:14:42 +02:00 |
|
|
Marek Lemańczyk
|
581da24b2f
|
Restore GPU incremental scan logic behind exception
|
2025-10-05 17:39:31 +02:00 |
|
|
Marek Lemańczyk
|
20120f5bc0
|
Fix odd power table updates in GPU heuristics
|
2025-10-05 16:55:27 +02:00 |
|
|
Marek Lemańczyk
|
ce1355c749
|
Compilation errors fixed
|
2025-10-05 13:13:47 +02:00 |
|
|
Marek Lemańczyk
|
6b1ebf01a6
|
Replace inline array in Montgomery table for GPU support
|
2025-10-05 06:42:38 +02:00 |
|
|
Marek Lemańczyk
|
abab307da4
|
Fix GPU-safe Montgomery window exponentiation
|
2025-10-05 06:35:18 +02:00 |
|
|
Marek Lemańczyk
|
26cc574020
|
Treat Pollard Rho success as the GPU primality check
|
2025-10-05 06:26:09 +02:00 |
|
|
Marek Lemańczyk
|
b6b372bc59
|
TODO moved to the code to concentrate on mirroring heuristic cycle algorithm on GPU
|
2025-10-05 02:17:08 +02:00 |
|
|
Marek Lemańczyk
|
0bc97937aa
|
Restore GPU-backed UInt128 pow2 Montgomery helper
|
2025-10-05 02:13:31 +02:00 |
|
|
Marek Lemańczyk
|
72dd69bd53
|
Align GPU pow2 heuristics with Montgomery helper
|
2025-10-04 22:40:27 +02:00 |
|
|
Marek Lemańczyk
|
b2a7190c14
|
Inline GPU capability checks for pow2 heuristics
|
2025-10-04 22:40:23 +02:00 |
|
|
Marek Lemańczyk
|
75586d07b8
|
Relax ulong multiply-shift guards and refresh tests
|
2025-10-04 22:40:18 +02:00 |
|
|
Marek Lemańczyk
|
38df505f4f
|
Implement GPU pow2 heuristics with safe fallbacks
|
2025-10-04 22:40:12 +02:00 |
|
|
Marek Lemańczyk
|
ea08d3f71f
|
Inline GPU overflow tracking helpers
|
2025-10-04 22:40:07 +02:00 |
|
|
Marek Lemańczyk
|
85c6eaece7
|
Persist GPU capability snapshot without volatile
|
2025-10-04 22:40:02 +02:00 |
|
|
Marek Lemańczyk
|
6adac6b7a7
|
Consolidate multiply helpers and guard GPU fallbacks
|
2025-10-04 21:20:29 +02:00 |
|