HCha/Stockfish
1
0
Fork 0
mirror of https://github.com/HChaZZY/Stockfish.git synced 2025-12-24 19:16:49 +08:00
Code Issues Packages Projects Releases Wiki Activity
5,665 Commits 5 Branches 58 Tags
fafb9557a874befe5cb1bcf8d7ab00f5d02ec3dc
Commit Graph

5665 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Tomasz Sobczyk
fafb9557a8 Get train loss from update_parameters. 2020-12-02 08:56:20 +09:00
Tomasz Sobczyk
4eb0e77a2a Store references instead of copying the results of intermediate autograd computations. 2020-12-02 08:56:20 +09:00
Tomasz Sobczyk
6cd0b03098 Add some comments regarding the current state of autograd loss computation. 2020-12-02 08:56:20 +09:00
Tomasz Sobczyk
99cb869db3 Reintroduce use_wdl. 2020-12-02 08:56:20 +09:00
Tomasz Sobczyk
cf6bc7ecaf Cleanup around get_loss 2020-12-02 08:56:20 +09:00
Tomasz Sobczyk
256c4b55ec Properly apply gradient norm clipping after it's scaled in the update_parameters. 2020-12-02 08:56:20 +09:00
Tomasz Sobczyk
de675e3503 Reintroduce optional scaling of the teacher signal. 2020-12-02 08:56:20 +09:00
Tomasz Sobczyk
01ae7b1e2c Simplify passing constants that may vary between calls. 2020-12-02 08:56:20 +09:00
Tomasz Sobczyk
cbd973fdaa Detect constant expressions in autograd and return 0 grad early. 2020-12-02 08:56:20 +09:00
Tomasz Sobczyk
e975889132 Move cross_entropy calculation to a separate function. 2020-12-02 08:56:20 +09:00
Tomasz Sobczyk
891abf5511 Make the autograd loss expression chain thread_local. 2020-12-02 08:56:20 +09:00
Tomasz Sobczyk
8adf00ae6e Identify a single evalation chain by ID in autograd to prevent cache reuse for subsequent evaluations of the same expression tree. 2020-12-02 08:56:20 +09:00
Tomasz Sobczyk
cb812c742c Add [[nodiscard]] attributes to autograd functions. 2020-12-02 08:56:20 +09:00
Tomasz Sobczyk
26f19e1429 Make automatic differentiation node types constexpr. 2020-12-02 08:56:20 +09:00
Tomasz Sobczyk
aec6017195 When forming an autograd expression only copy parts that are rvalue references, store references to lvalues. 2020-12-02 08:56:20 +09:00
Tomasz Sobczyk
a5c20bee5b Apply gradient clipping. 2020-12-02 08:56:20 +09:00
Tomasz Sobczyk
d103867558 Add memoization to the autograd expression evaluator. 2020-12-02 08:56:20 +09:00
Tomasz Sobczyk
aa55692b97 Cross entropy loss. 2020-12-02 08:56:20 +09:00
Tomasz Sobczyk
539bd2d1c8 Replace the old loss/grad calculation completely. 2020-12-02 08:56:20 +09:00
Tomasz Sobczyk
b71d1e8620 Pass the new loss function to update_parameters 2020-12-02 08:56:20 +09:00
Tomasz Sobczyk
5a58eb803a Loss func with autograd 2020-12-02 08:56:20 +09:00
Tomasz Sobczyk
541fb8177a More utility in autograd. 2020-12-02 08:56:20 +09:00
Tomasz Sobczyk
6ce0245787 Basic autograd 2020-12-02 08:56:20 +09:00
Tomasz Sobczyk
1322a9a5fd Prevent false sharing of num_calls counter in the shared input trainer. Fix current_operation not being local to the executing thread. 2020-11-30 08:54:53 +09:00
Tomasz Sobczyk
2aa7f5290e Fix comparison of integers with different signedness. 2020-11-30 08:54:53 +09:00
Tomasz Sobczyk
a97b65eaef Fix compilation error with USE_BLAS 2020-11-30 08:54:53 +09:00
Tomasz Sobczyk
622e0b14c2 Remove superfluous example shuffling. Shuffling now only happens on reading. 2020-11-30 08:54:53 +09:00
Tomasz Sobczyk
34510dd08a Remove used examples asyncronously. 2020-11-30 08:54:53 +09:00
Tomasz Sobczyk
0bee8fef64 Don't unnecessarily copy the batch part. 2020-11-30 08:54:53 +09:00
Tomasz Sobczyk
e954b14196 Prefetch weights for feature transformer backprop to shared cache. 2020-11-30 08:54:53 +09:00
Tomasz Sobczyk
8009973381 Special case for alpha=1 in saxpy, slight performance increase. 2020-11-30 08:54:53 +09:00
Tomasz Sobczyk
49b2dcb1f3 Preallocate memory for unique_features. Keep the training_features temporary buffer as a thread_local so we reuse the storage. 2020-11-30 08:54:53 +09:00
Tomasz Sobczyk
1c8495b54b Remove handwritten saxpy because compilers optimize the second look anyway. 2020-11-30 08:54:53 +09:00
Tomasz Sobczyk
15c528ca7b Prepare feature transformer learner. 2020-11-30 08:54:53 +09:00
Tomasz Sobczyk
a3c78691a2 Prepare input slice trainer. 2020-11-30 08:54:53 +09:00
Tomasz Sobczyk
401fc0fbab Prepare clipped relu trainer. 2020-11-30 08:54:53 +09:00
Tomasz Sobczyk
774b023641 Add chunked for each with workers. 2020-11-30 08:54:53 +09:00
Tomasz Sobczyk
cc11375f6d Skeleton for new evaluate learner 2020-11-30 08:54:53 +09:00
Tomasz Sobczyk
0d4b803b08 Prepare trainer affine transform. 2020-11-30 08:54:53 +09:00
Tomasz Sobczyk
4ea8572b6d Add single threaded sgemm. 2020-11-30 08:54:53 +09:00
nodchip
ef4fdb40f9 Merge pull request #254 from noobpwnftw/merge 
Merge
 2020-11-28 09:03:38 +09:00
noobpwnftw
0b2ae6cb64 Merge remote-tracking branch 'remotes/official/master' into merge 2020-11-28 06:47:04 +08:00
Tomasz Sobczyk
92b14a5ba2 Add docs for transform. 2020-11-27 09:16:22 +09:00
Tomasz Sobczyk
89294e2e4f Add transform command. Add transform nudged_static subcommand. 2020-11-27 09:16:22 +09:00
Vizvezdenec
190dd26b9f use classical for certain endgames. 
STC https://tests.stockfishchess.org/tests/view/5fbc64c067cbf42301d6b1d6
LLR: 2.97 (-2.94,2.94) {-0.25,1.25}
Total: 53360 W: 5223 L: 5024 D: 43113
Ptnml(0-2): 184, 3877, 18390, 4014, 215

LTC https://tests.stockfishchess.org/tests/view/5fbc97f267cbf42301d6b1ee
LLR: 2.96 (-2.94,2.94) {0.25,1.25}
Total: 126472 W: 5111 L: 4766 D: 116595
Ptnml(0-2): 50, 4032, 54749, 4333, 72

closes https://github.com/official-stockfish/Stockfish/pull/3240

bench: 3820648
 2020-11-26 08:20:06 +01:00
MaximMolchanov
7615e3485e Calculate sum from first elements 
in affine transform for AVX512/AVX2/SSSE3

The idea is to initialize sum with the first element instead of zero.
Reduce one add_epi32 and one set_zero SIMD instructions for each output dimension.

sum = 0; for i = 1 to n sum += a[i] ->
sum = a[1]; for i = 2 to n sum += a[i]

STC:
LLR: 2.95 (-2.94,2.94) {-0.25,1.25}
Total: 69048 W: 7024 L: 6799 D: 55225
Ptnml(0-2): 260, 5175, 23458, 5342, 289
https://tests.stockfishchess.org/tests/view/5faf2cf467cbf42301d6aa06

closes https://github.com/official-stockfish/Stockfish/pull/3227

No functional change.
 2020-11-25 21:10:13 +01:00
Unai Corzo
9fb6383ed8 Assorted search and eval parameter tune 
Search and eval parameter tune.

STC https://tests.stockfishchess.org/tests/view/5fba850a67cbf42301d6b07d
LLR: 2.94 (-2.94,2.94) {-0.25,1.25}
Total: 24312 W: 2388 L: 2228 D: 19696
Ptnml(0-2): 85, 1800, 8241, 1930, 100

LTC https://tests.stockfishchess.org/tests/view/5fbad5ea67cbf42301d6b0fa
LLR: 2.95 (-2.94,2.94) {0.25,1.25}
Total: 88376 W: 3619 L: 3351 D: 81406
Ptnml(0-2): 56, 2977, 37849, 3255, 51

closes https://github.com/official-stockfish/Stockfish/pull/3232

bench: 3600361
 2020-11-25 21:05:08 +01:00
Stéphane Nicolet
027626db1e Small cleanups 13 
No functional change
 2020-11-23 22:20:32 +01:00
nodchip
c12848d5ac Merge pull request #249 from noobpwnftw/merge 
Merge
 2020-11-23 19:55:23 +09:00
Tomasz Sobczyk
45e3335ee8 Add missing docs. 2020-11-23 19:22:11 +09:00