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

104 Commits

Author SHA1 Message Date
i-robot e4438f3028
!28310 dynamic_kernel_mod 
Merge pull request !28310 from TuDouNi/dynamic_shape_stage1
 2022-01-04 12:48:53 +00:00
ttudu 9373679c04 dynamic_kernel_mod 2022-01-04 14:13:19 +08:00
caifubi 49328ae86d Modify Hccl Error Log 2021-12-31 17:24:54 +08:00
yuximiao 393d3621a3 fix no paralle stratege if start profiler in the process of trainging 2021-12-13 10:44:07 +08:00
l00591931 62e474aaf1 Enable mindir for layout 2021-12-02 17:50:43 +08:00
i-robot 4252b24335 !26792 malloc ts memory for label 
Merge pull request !26792 from zhoufeng/change-label-memory-type
 2021-11-27 01:09:03 +00:00
zhoufeng 881179fa10 malloc ts memory for label 
Signed-off-by: zhoufeng <zhoufeng54@huawei.com>
 2021-11-26 09:17:02 +08:00
i-robot 3d0f9d8aae !26683 Enable compile cache feature to load hyper parameter data from python 
Merge pull request !26683 from LiangZhibo/mindir
 2021-11-25 03:25:27 +00:00
i-robot cfc6ea32ff !24714 replace rtmemcpyxx to acl memcpy 
Merge pull request !24714 from jjfeing/br_replace_rtmemcpyxx_with_acl_api
 2021-11-24 07:47:43 +00:00
l00591931 21df240f23 Enable mindir to load initialize weight from python 2021-11-24 11:33:43 +08:00
jjfeing 05485d991c replace api with acl api 2021-11-23 09:06:28 +08:00
i-robot ce00ee1ad1 !25367 use acl api to control profiling 
Merge pull request !25367 from yanghaitao/yht_condation_start_profiler
 2021-11-18 12:36:14 +00:00
i-robot 9d6248194e !26310 MindSpore support load custom aicpu kernels. 
Merge pull request !26310 from linqingke/aicpu
 2021-11-18 08:09:26 +00:00
yanghaitao1 c94aa6b872 use profiler acl api instead 2021-11-17 09:33:31 -05:00
linqingke bef2923acf MindSpore support load custom aicpu ops. 2021-11-17 14:58:50 +08:00
yao_yf 501b978d16 find data parallel common group in auto parallel 2021-11-13 10:23:45 +08:00
ougongchang 9229f1c1ff profiler support to collect parallel strategy info 
If SetNodeOutputType functions forcibly splits into multiple functions, the readability decreases, so it blocks lizard scans
 2021-11-11 20:11:42 +08:00
baihuawei e59d07899b fix reset8p pynative performance 2021-11-03 09:13:19 +08:00
LaiYongqiang dc7988f4bd log improvement 2021-10-27 12:36:47 +08:00
i-robot cb307e24cf !25153 refactor device loop control 
Merge pull request !25153 from laiyongqiang/adjust_kernel_refactory
 2021-10-23 07:42:49 +00:00
LaiYongqiang 9bfb2d99fa refactor device loop control 2021-10-22 20:42:38 +08:00
lby 6872e67131 split compile ang gen kernel mod 2021-10-22 10:13:50 +08:00
i-robot e920a1c07e !24593 Continue execution when saving and loading mindir failed 
Merge pull request !24593 from YuJianfeng/master
 2021-10-12 01:51:12 +00:00
yujianfeng d384db6c01 Continue execution when saving and loading mindir failed 2021-10-11 19:05:25 +08:00
lby 3e9fd763c3 delete old build process 2021-10-09 11:16:09 +08:00
caifubi f092e623e0 Compile isolation for Profiling and Dump 2021-09-09 16:46:43 +08:00
i-robot 2c692bf7de !22450 insert the overflow check operators according to the "gradients" scope name. 
Merge pull request !22450 from guoqi/overflow-check-master
 2021-08-31 13:37:09 +00:00
guoqi 8fccec4c20 insert overflow check operaters according to the 'gradients' scope 2021-08-31 16:44:02 +08:00
gaojing fa02606348 step train modified 2021-08-29 23:04:55 -04:00
baihuawei a9694a9230 ascend add nontask sink mode 2021-08-25 14:45:58 +08:00
ms_yan 36a8886ca2 Revert "[feat] [assistant] [I3T96T] add new Dataset operator CMUARCTICDataset" 
This reverts commit b077aa1cab.

Revert "[feat] [assistant] [I3T96X] add new Dataset operator LibriSpeechDataset"

This reverts commit 4e6f7dc97d.

delete pass_registry_test.cc

comment  hiai_nlu_model_multi.pb related  line
 2021-08-23 01:46:38 +08:00
djc b077aa1cab [feat] [assistant] [I3T96T] add new Dataset operator CMUARCTICDataset 2021-08-22 16:26:45 +08:00
djc 4e6f7dc97d [feat] [assistant] [I3T96X] add new Dataset operator LibriSpeechDataset 2021-08-22 13:39:37 +08:00
yanghaitao1 8fc11cb676 adapt delete libms_profiler_fwk.a 2021-08-19 19:33:53 +08:00
caifubi dfe0e94466 Fix PyNative get_rank_id/get_rank_size 2021-08-18 16:39:18 +08:00
i-robot 6afcd815d2 !21362 add pynative profiling codes based on ascend and gpu 
Merge pull request !21362 from lvchangquan/profiling_refactor
 2021-08-13 06:18:31 +00:00
zhoufeng 03a56f2bb0 alltoall exception handle 
Signed-off-by: zhoufeng <zhoufeng54@huawei.com>
 2021-08-11 17:30:49 +08:00
lby a5029f061c ascend kernel build refactory 2021-08-10 23:40:49 +08:00
lvchangquan e8d9803258 add profiling codes based on ascend and gpu in pynative mode 2021-08-10 20:46:51 +08:00
lby e6cdf098db op tiling compute interface replace 2021-08-06 11:26:24 +08:00
baihuawei 41de02a58c ascend support nontask sink 2021-08-03 20:55:43 +08:00
i-robot 69c5021bb5 !20995 pyfunc cpu kernel 
Merge pull request !20995 from chenweifeng/cpu-dynamic-input
 2021-08-03 04:51:20 +00:00
wilfChen d6fffdad6e support dynamic inputs & outputs 2021-08-02 20:05:46 +08:00
yanghaoran 0364650eae Upgrade Ascend packages 28 Jul 21, with testcases removed 2021-07-31 18:55:55 +08:00
dayschan 3ab53dd26d Send compilation attrs to akg 
1. Add a new message type "AKG/ATTR" in AkgKernelBuilder.
   the attrs was sent before the kernel infos.
2. Send "online_tuning" attribute when the flag is not zero,
   but error occurs in the latest akg submodule.
3. Send "repository_path" attribute when the flag is not empty.
4. Add a new value "compute_capability" into kernel info when the processor is GPU.
 2021-07-16 16:52:18 +08:00
dingpeifei 24ff7ab8b4 upgrade_ascend_0705 2021-07-06 11:31:45 +08:00
zhoufeng b9378e36c3 dynamic default memory size for vnpu 
Signed-off-by: zhoufeng <zhoufeng54@huawei.com>
 2021-06-29 19:23:04 +08:00
dingpeifei 63784e49f5 upgrade_ascend_0626_mindspore 2021-06-28 22:03:19 +08:00
i-robot 708e56f659 !17899 Fix compile cache bug for resent50 
Merge pull request !17899 from LiangZhibo/cache
 2021-06-24 13:29:58 +00:00
l00591931 8ae5d7cc84 Fix compile cache for resnet50 2021-06-24 14:36:24 +08:00