mindspore-ci-bot
8634675e2d
!14499 [GraphKernel]split UMonad in inputs of op
...
From: @wenfangpei
Reviewed-by: @dayschan,@ckey_dou,@gaoxiong1
Signed-off-by: @gaoxiong1
4 years ago
wenfangpei
0085a273e7
split UMonad in inputs of op
4 years ago
lingyunli63
8b3823b22c
optimizeMatmul
4 years ago
mindspore-ci-bot
69526df01e
!14314 [GraphKernel] unify graph kernel pass add_atomic_clean on Ascend and GPU back-end
...
From: @looop5
Reviewed-by: @gaoxiong1,@gaoxiong1,@dylangeng
Signed-off-by: @dylangeng
4 years ago
mindspore-ci-bot
ddf75da542
!14085 [GraphKernel] add some expander ops
...
From: @chenlei_autodiff
Reviewed-by:
Signed-off-by:
4 years ago
looop5
76d322464d
unify graph kernel pass add_atomic_clean on Ascend and GPU back-end
...
refactor CanActivateAtomicAdd
use smart pointer
4 years ago
chenlei_autodiff
f4289d40f3
add graph kernel expander ops.
4 years ago
mindspore-ci-bot
7149e8c2c9
!14045 [Graph Kernel] add compare test case
...
From: @zengzitao
Reviewed-by: @gaoxiong1
Signed-off-by:
4 years ago
zengzitao
72c6dad4ba
add compare_test case in gpu ci and update akg submodule
4 years ago
lingyunli63
4b966ed40d
support matmul on D
4 years ago
mindspore-ci-bot
5b95409022
!13512 add some expander ops
...
From: @zengzitao
Reviewed-by:
Signed-off-by:
4 years ago
wenfangpei
043a558ae2
expander lamb_apply_optimizer_assign
4 years ago
zengzitao
d0a656f3cd
add some expander ops
4 years ago
zengzitao
ef3507e973
fix exec order bug about monad
4 years ago
He Wei
7d9a783993
[auto-monad] Support side-effects by auto-monad
...
The basic idea is: exploits data dependency to control the execution order
of side-effect operations, and keep the semantics of ANF unchanged.
The ControlDepend primitive is removed and there are two primitives added:
1. UpdateState:
```
a = Assign(para, value)
```
became:
```
a = Assign(para, value, u)
u = UpdateState(u, a)
```
2. Load:
```
x = Add(para, value)
```
became:
```
p = Load(para, u)
x = Add(p, value)
u = UpdateState(u, p)
```
4 years ago
jinyaohui
30a27b2adb
modify Gelu、FastGelu to GeLU and FastGeLU
4 years ago
mindspore-ci-bot
e897eb4c41
!11915 Change TensorAdd to Add, merge from r1.1 to master
...
From: @liangzhibo
Reviewed-by: @ginfung,@zh_qh
Signed-off-by: @zh_qh
4 years ago
l00591931
9ec100d069
Change TensorAdd to Add, from r1.1 to master
4 years ago
looop5
0161209e40
update submoudle akg, close graph kernel ascend ci testcases
4 years ago
looop5
8bbe723603
add Tile infer shape function
4 years ago
mindspore-ci-bot
5f2c84f3cb
!9867 Add graph kernel testcases
...
From: @looop5
Reviewed-by: @ckey_dou,@gaoxiong1
Signed-off-by: @gaoxiong1
4 years ago
looop5
4d8205cd93
Delete unused interface in graph_kernels.py
4 years ago
looop5
56fa56b173
add graph kernel testcases
4 years ago
tronzhang
2190da9946
support atomic clean and change package for akg.
4 years ago
zengzitao
3ef0e9f053
substitute dropout by cudnnuniformreal and dropout
4 years ago
zengzitao
266bfa50bf
expand logsoftmax and logsoftmax_grad, delete softmax's cast and fix layernorm op
4 years ago
looop5
f5f66abd06
Add testcases in Ascend back-end for graph kernel
4 years ago
zengzitao
326540cbbd
expand layernorm_grad op
4 years ago
zengzitao
28f1db74dd
expand maximum_grad minimum_grad dropout_grad op
4 years ago
zengzitao
db27783d54
expand tanh_grad and reduce_mean, fix bug and add test_case in ci
4 years ago
zengzitao
53043ae18f
support expand fused_adam and fused_adam_weight_decay op
4 years ago
dayschan
0f8f1cdda7
Eliminate redundant parameters while expanding basic ops.
...
add testcase for Gelu/GeluGrad
4 years ago
mindspore-ci-bot
8d39a8a4b2
!7529 complex arithmetic_simplify
...
Merge pull request !7529 from zhuxiaochen/1020_allsimplify_1.0
4 years ago
zhu_xiaochen
c739f14038
simplify transpose matmul reduce
4 years ago
lingyunli63
a500a57c72
add GraphkernelCSE
4 years ago
Geng_Fei
1455372cf1
add new pass in graph kernel: arithmetic_simplify
4 years ago
dayschan
37a48f6aac
GraphKernel supports GPU
...
1. Update akg submodule
2. Refactor akg_kernel_build, akg_ascend_kernel_build, akg_gpu_kernel_build
3. Add akg_kernel_json_decoder to support converting kernel_json to AnfNode.
4. Add GraphKernel Cost Model. (mindspore/_extends/graph_kernel)
5. Add some GraphKernel passes to GpuSession, move these passes to backend/optimizer/graph_kernel.
6. Add global id for ir files.
7. Fix bug in ConstInputToAttr.
4 years ago
duxiutao
793737ab62
add primitive operator to test_lamb
5 years ago
duxiutao
1e43c609e0
Add test case and fix two bugs
...
1. add case to guard precision
2. fix a shape bug
3. fix a funcGraph bug
5 years ago