Skip to content
体验新版
项目
组织
正在加载...
登录
切换导航
打开侧边栏
OPTHREE
Paddle
提交
d651a911
P
Paddle
项目概览
OPTHREE
/
Paddle
与 Fork 源项目一致
Fork自
PaddlePaddle / Paddle
通知
1
Star
1
Fork
0
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
1
列表
看板
标记
里程碑
合并请求
0
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
P
Paddle
项目概览
项目概览
详情
发布
仓库
仓库
文件
提交
分支
标签
贡献者
分支图
比较
Issue
1
Issue
1
列表
看板
标记
里程碑
合并请求
0
合并请求
0
Pages
分析
分析
仓库分析
DevOps
Wiki
0
Wiki
成员
成员
收起侧边栏
关闭侧边栏
动态
分支图
创建新Issue
提交
Issue看板
体验新版 GitCode,发现更多精彩内容 >>
提交
d651a911
编写于
12月 19, 2018
作者:
T
tensor-tang
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
fix build on win, fix use condition of crf decoding and layer norm and
enhance test precision test=develop
上级
141ebcd4
变更
4
隐藏空白更改
内联
并排
Showing
4 changed file
with
18 addition
and
6 deletion
+18
-6
paddle/fluid/operators/jit/CMakeLists.txt
paddle/fluid/operators/jit/CMakeLists.txt
+3
-1
paddle/fluid/operators/jit/more/intrinsic/crf_decoding.cc
paddle/fluid/operators/jit/more/intrinsic/crf_decoding.cc
+13
-3
paddle/fluid/operators/jit/more/intrinsic/layer_norm.cc
paddle/fluid/operators/jit/more/intrinsic/layer_norm.cc
+1
-1
paddle/fluid/operators/jit/test.cc
paddle/fluid/operators/jit/test.cc
+1
-1
未找到文件。
paddle/fluid/operators/jit/CMakeLists.txt
浏览文件 @
d651a911
...
...
@@ -20,4 +20,6 @@ endif()
cc_library
(
jit_kernel_helper SRCS
${
jit_kernel_cc_srcs
}
DEPS
${
JIT_KERNEL_DEPS
}
)
cc_test
(
jit_kernel_test SRCS test.cc DEPS jit_kernel_helper
)
cc_binary
(
jit_kernel_benchmark SRCS benchmark.cc DEPS jit_kernel_helper
)
if
(
NOT WIN32
)
cc_binary
(
jit_kernel_benchmark SRCS benchmark.cc DEPS jit_kernel_helper
)
endif
()
paddle/fluid/operators/jit/more/intrinsic/crf_decoding.cc
浏览文件 @
d651a911
...
...
@@ -22,11 +22,16 @@ namespace operators {
namespace
jit
{
namespace
more
{
namespace
intrinsic
{
// Note: intrinsic code is not runtime build.
// For example, if you build code on AVX, and run on AVX512 it can only use AVX
void
CRFDecoding
(
const
int
seq_len
,
const
float
*
x
,
const
float
*
w
,
float
*
alpha
,
int
*
track
,
int
tag_num
)
{
const
int
step_size
=
platform
::
MayIUse
(
platform
::
avx512f
)
?
ZMM_FLOAT_BLOCK
:
YMM_FLOAT_BLOCK
;
#ifdef __AVX512F__
const
int
step_size
=
ZMM_FLOAT_BLOCK
;
#else
const
int
step_size
=
YMM_FLOAT_BLOCK
;
#endif
const
int
end
=
tag_num
/
step_size
;
const
int
rest
=
tag_num
%
step_size
;
/* Setup the alpha initial value.*/
...
...
@@ -157,7 +162,12 @@ void CRFDecoding(const int seq_len, const float* x, const float* w,
}
bool
CRFDecodingKernel
::
UseMe
(
const
int
&
d
)
const
{
return
platform
::
MayIUse
(
platform
::
avx
);
#ifdef __AVX512F__
constexpr
int
block
=
ZMM_FLOAT_BLOCK
;
#else
constexpr
int
block
=
YMM_FLOAT_BLOCK
;
#endif
return
platform
::
MayIUse
(
platform
::
avx
)
&&
d
>=
block
;
}
}
// namespace intrinsic
...
...
paddle/fluid/operators/jit/more/intrinsic/layer_norm.cc
浏览文件 @
d651a911
...
...
@@ -154,7 +154,7 @@ void LayerNorm(float* x, float* out, float* mean, float* var,
}
bool
LayerNormKernel
::
UseMe
(
const
int
&
d
)
const
{
return
platform
::
MayIUse
(
platform
::
avx
);
return
platform
::
MayIUse
(
platform
::
avx
)
&&
d
>=
YMM_FLOAT_BLOCK
;
}
}
// namespace intrinsic
...
...
paddle/fluid/operators/jit/test.cc
浏览文件 @
d651a911
...
...
@@ -37,7 +37,7 @@ template <typename T>
void
ExpectEQ
(
const
T
*
target
,
const
T
*
refer
,
int
n
)
{
if
(
std
::
is_floating_point
<
T
>::
value
)
{
for
(
int
i
=
0
;
i
<
n
;
++
i
)
{
EXPECT_NEAR
(
target
[
i
],
refer
[
i
],
1e-
3
);
EXPECT_NEAR
(
target
[
i
],
refer
[
i
],
1e-
5
);
}
}
else
{
for
(
int
i
=
0
;
i
<
n
;
++
i
)
{
...
...
编辑
预览
Markdown
is supported
0%
请重试
或
添加新附件
.
添加附件
取消
You are about to add
0
people
to the discussion. Proceed with caution.
先完成此消息的编辑!
取消
想要评论请
注册
或
登录