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
BaiXuePrincess
milvus
提交
a7932b03
milvus
项目概览
BaiXuePrincess
/
milvus
与 Fork 源项目一致
从无法访问的项目Fork
通知
7
Star
4
Fork
0
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
0
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
milvus
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
0
Issue
0
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 >>
未验证
提交
a7932b03
编写于
3月 28, 2020
作者:
C
Cai Yudong
提交者:
GitHub
3月 28, 2020
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
#1781 fix search hang with SQ8H (#1783)
Signed-off-by:
N
yudong.cai
<
yudong.cai@zilliz.com
>
上级
af73dccb
变更
2
隐藏空白更改
内联
并排
Showing
2 changed file
with
5 addition
and
4 deletion
+5
-4
CHANGELOG.md
CHANGELOG.md
+1
-0
core/src/db/engine/ExecutionEngineImpl.cpp
core/src/db/engine/ExecutionEngineImpl.cpp
+4
-4
未找到文件。
CHANGELOG.md
浏览文件 @
a7932b03
...
@@ -21,6 +21,7 @@ Please mark all change in change log and use the issue from GitHub
...
@@ -21,6 +21,7 @@ Please mark all change in change log and use the issue from GitHub
-
\#
1735 Fix search out of memory with ivf_flat
-
\#
1735 Fix search out of memory with ivf_flat
-
\#
1747 Expected error status if search with partition_tag not existed
-
\#
1747 Expected error status if search with partition_tag not existed
-
\#
1756 Fix memory exhausted during searching
-
\#
1756 Fix memory exhausted during searching
-
\#
1781 Fix search hang with SQ8H
## Feature
## Feature
-
\#
1603 BinaryFlat add 2 Metric: Substructure and Superstructure
-
\#
1603 BinaryFlat add 2 Metric: Substructure and Superstructure
...
...
core/src/db/engine/ExecutionEngineImpl.cpp
浏览文件 @
a7932b03
...
@@ -551,11 +551,11 @@ ExecutionEngineImpl::CopyToGpu(uint64_t device_id, bool hybrid) {
...
@@ -551,11 +551,11 @@ ExecutionEngineImpl::CopyToGpu(uint64_t device_id, bool hybrid) {
*/
*/
ENGINE_LOG_DEBUG
<<
"CPU to GPU"
<<
device_id
<<
" start"
;
ENGINE_LOG_DEBUG
<<
"CPU to GPU"
<<
device_id
<<
" start"
;
auto
gpu_cache_mgr
=
cache
::
GpuCacheMgr
::
GetInstance
(
device_id
);
auto
gpu_cache_mgr
=
cache
::
GpuCacheMgr
::
GetInstance
(
device_id
);
gpu_cache_mgr
->
Lock
();
//
gpu_cache_mgr->Lock();
gpu_cache_mgr
->
Reserve
(
index_
->
Size
());
//
gpu_cache_mgr->Reserve(index_->Size());
index_
=
knowhere
::
cloner
::
CopyCpuToGpu
(
index_
,
device_id
,
knowhere
::
Config
());
index_
=
knowhere
::
cloner
::
CopyCpuToGpu
(
index_
,
device_id
,
knowhere
::
Config
());
gpu_cache_mgr
->
InsertItem
(
location_
,
std
::
static_pointer_cast
<
cache
::
DataObj
>
(
index_
));
//
gpu_cache_mgr->InsertItem(location_, std::static_pointer_cast<cache::DataObj>(index_));
gpu_cache_mgr
->
Unlock
();
//
gpu_cache_mgr->Unlock();
ENGINE_LOG_DEBUG
<<
"CPU to GPU"
<<
device_id
<<
" finished"
;
ENGINE_LOG_DEBUG
<<
"CPU to GPU"
<<
device_id
<<
" finished"
;
}
catch
(
std
::
exception
&
e
)
{
}
catch
(
std
::
exception
&
e
)
{
ENGINE_LOG_ERROR
<<
e
.
what
();
ENGINE_LOG_ERROR
<<
e
.
what
();
...
...
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