Nigel
/
mindspore
forked from mindspore-Ecosystem/mindspore
0
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
38,204 Commits 24 Branches 0 Tags 3.9 GiB
Commit Graph

56 Commits

Author SHA1 Message Date
zhousiyi d9aa48bc64 Dont liftfv before grad in higher order grad if closure is kept as bprop of Partial primitive is not supported 2021-12-28 07:54:22 +00:00
zhangzhaoju 722086435d 1. fix:unexpected eiminate of tile 
2. fix:delay memory allocat in NewTensorFilledWithData
 2021-12-06 14:49:48 +08:00
lianliguang 0dc5d7f4f9 modify some eroor log and remove some useless code 2021-11-29 10:23:03 +08:00
He Wei 41dcac9c49 Replace std::unordered_map/set with robin-hood-hashing 
Robin-hood-hashing (https://github.com/martinus/robin-hood-hashing)
is considered faster then std::unordered_map/set,
so we use it to improve mindspore performance.

1. robin_hood head file in `third_party/robin_hood/include`;
2. In `utils/hash_map.h` and `utils/hash_set.h`, we define:
 - mindspore::HashMap as an alias of robin_hood::unordered_map;
 - mindspore::HashSet as an alias of robin_hood::unordered_set;
3. Replace:
 - `#include <unordered_map>` --> `#include "utils/hash_map.h"`;
 - `#include <unordered_set>` --> `#include "utils/hash_set.h"`;
 - `std::unordered_map` --> `mindspore::HashMap`;
 - `std::unordered_set` --> `mindspore::HashSet`;
 - `map.insert(std::pair(key, value))` --> `map.emplace(key, value)`;
 - `[] (const std::pair<K, V> &p) {..} ` --> `[] (const auto &p) {..} `;
4. Fix issues found by switch to robin_hood:
 - AnfNodeConfig hash and equal;
 - Fix a bug in `Slice::operator==()`;
 - Fix a bug in `CNode::HasPrimalAttr()`;
 - Fix map.erase() usage bugs: `map.erase(iter++)` --> `iter = map.erase(iter)`;
 - Fix some iterator invalidated problem;
5. Some std::unordered_map/set can not replace by robin_hood:
 - As parameter of functions that exposed to python by pybind11;
 - Use bad hash that cause robin_hood::map over_flow, such as AbstractBasePtrListHasher;
6. Update cpp unit tests;
7. Add build option '-F' to enable robin_hood, default on.
 2021-11-24 10:47:40 +08:00
zhang__sss 0dd68aa7eb grad 2021-11-11 23:18:35 +08:00
zhang__sss 8bae4d9d50 grad 2021-11-08 14:12:58 +08:00
huanghui ba66c0d491 add security isolate for save_graphs 2021-09-14 10:24:12 +08:00
zhousiyi a5b4e7bbf8 lift fv before grad except weight, then convert 
switch(cond, partial(g1, xs), partial(g2, ys))(Zs)
 to
 switch(cond, g1, g2)(Xs, Ys, Zs)

 switch_layer(index, make_tuple(partial(g1, xs), partial(g2, ys)))(Zs)
 to
 switch_layer(index, make_tuple(g1, g2))(Xs, Ys, Zs)

put Zs at last when unifyparameter as it may have u-monad or io-monad

use joined args other than broadened one as some extra parameter which is not a parameter of while_header can be add to while_body

inline fprop_switch forcely

reorder the parameter if one of the parameter is Monad when incorporate call

incorporate switch tuple_getitem if item 0 of tuple is EnvInstance or
item 1 of tuple is bprop function

addn with shape() and shape(1)

remove context_ from FuncGraphEvaluator to make it re-entry able to resolve evaluator stuck issue because of re-entry of the same FuncGraphEvaluator
 2021-07-03 00:03:37 +08:00
l00591931 0424b2d8d6 Fix warning in master 2021-06-04 17:40:01 +08:00
lvliang 116781041a fix ut compile failed 2021-05-19 19:59:10 +08:00
zhousiyi 4ff19b7082 add API to build bprop funcgraph which can be used for higher grad 2021-05-19 19:59:06 +08:00
lvliang c759effa94 fix_compile_ut_failed 2021-05-19 19:59:06 +08:00
zhousiyi 1843740e0d 1. set abstract for node. 2. Adjust the position of sens parameter from last to position just after Inputs. 3. Set debug name for Parameter 2021-05-19 19:58:51 +08:00
zhousiyi b40816e66a add support for stop_gradient primitive. And defer BackPropagation to End API 2021-05-19 19:58:49 +08:00
zhousiyi 0d6a5ccfe4 grad op for pynative 2021-05-19 19:58:46 +08:00
huangbingjian 134d5dfe4b separate irpass EnvGetItemEliminater and ItemTupleOrListEliminator 2021-04-02 17:38:40 +08:00
chenfei fc335daa30 get all j node and then expand them 2021-03-12 20:06:43 +08:00
yujianfeng f0b7c3dd4d Add a switch to control grad for scalar 2021-02-27 18:12:37 +08:00
yujianfeng 41189781f3 support scalar input for cell 2021-02-25 09:56:15 +08:00
buxue 6ccc4379b4 do not broaden scalar 2021-02-03 11:30:25 +08:00
zhouyuanshen d1e6878011 remove dot 2021-02-01 09:39:27 +08:00
buxue 2530943a7f optimize list getitem in bprop 2020-12-15 15:00:49 +08:00
yujianfeng 3176d377e6 Remove redundant phi nodes 2020-11-16 09:36:55 +08:00
Yi Huaijie d7faa77b5e support int64 shape 2020-11-05 21:15:49 +08:00
Hoai Linh Tran 46f07efc31 Fix AdjustAllReduceMulAdd pass 
Revive tests in lib_test

Code cleaning
 2020-09-19 01:07:01 -04:00
fary86 fcbb3e0edc Refactor ms_context implementation 2020-08-30 22:51:40 +08:00
zhousiyi c25e37e7bf make backend/optimizer pybind free 2020-08-28 08:56:58 +00:00
panyifeng 34e50e5d6e fix cell bprop 2020-08-07 10:57:01 +08:00
kingfo 28dabf0332 fix grad flag update issue in pynative 2020-08-06 15:12:31 +08:00
liubuyu a499d4e47c decoupling core and debug 2020-07-31 10:39:31 +08:00
liubuyu f4bc0bc9fe move the dependency of utils to core 2020-07-27 10:28:46 +08:00
He Wei 60d168adec Decouple ir from optimizer 2020-07-21 14:48:26 +08:00
mindspore-ci-bot db80643ee2 !3177 Update Arithmetic Simplify to use Pattern Matcher (2) 
Merge pull request !3177 from Giancarlo/pm_arithmetic_simplify
 2020-07-20 10:02:06 +08:00
Giancarlo Colmenares cfbfaddfe1 Updated arithmetic simplify to use Pattern Matcher 2020-07-17 10:05:09 -04:00
panyifeng 5a10383cc3 add coo_tensor 2020-07-17 18:53:03 +08:00
liubuyu 43c79eb853 mindspore path adjust 2020-07-14 18:07:28 +08:00
BowenK af36bd7698 Revert PR 2923 2020-07-14 10:01:08 +08:00
Giancarlo Colmenares 7f759c2a4c Updated arithmetic simplify to use Pattern Matcher 2020-07-08 16:01:04 -04:00
panyifeng d6635bbbe2 Add IndexedSlices 2020-06-30 17:38:24 +08:00
Giancarlo Colmenares aabec55c79 Removing TransformFuncType 2020-06-24 13:48:57 -04:00
zhousiyi b2ec296f99 add opt pass for tuple_getitem with constant input 2020-06-23 07:41:21 +00:00
gong chen a6dfa281ea Init GraphKernel. 
- It provides a unified style to express graph and kernel for user.
- It provides a unified IR to represent graph and kernel for developer.
- It breaks the boundary between graph and kernel.
- It provides more opportunities to do compile optimization.
 2020-06-20 22:31:54 +08:00
BowenK 8f29e7242f add pass to eliminate depend value 2020-06-19 14:52:52 +08:00
Kang 2974b906d3 Optimization for opt 2020-06-17 16:04:54 +08:00
mindspore-ci-bot 9e1dea1ff9 !1928 delete redundant reshape op 
Merge pull request !1928 from yoonlee666/deletereshape
 2020-06-10 20:11:22 +08:00
yoonlee666 881af56ec3 optimize redundant reshape op 2020-06-10 18:21:00 +08:00
zhaoting b16a552d41 Revert "Revert "add pattern AdjustAllReduceMulAdduse the old opadd test case for bugtemp fix try"" 
This reverts commit 705c71a257.
 2020-06-09 20:56:36 +08:00
huangdongrun beacc26077 * add isconstant primitive 
* add infer_value for common math ops
* convert constant bool tensor to bool value

* do not infer value when encounter 0 as division

for while condition, do not unrool if condition is a tensor
 2020-06-04 21:51:44 +08:00
gengdongjie 705c71a257 Revert "add pattern AdjustAllReduceMulAdduse the old opadd test case for bugtemp fix try" 
This reverts commit 3db8cfa54f.
 2020-05-28 15:21:15 +08:00
Zhang Qinghua f31564ce98 Remove the useless collectors in manager. 2020-05-25 09:56:28 +08:00