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
机器未来
Paddle
提交
4c0c55bb
P
Paddle
项目概览
机器未来
/
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
未验证
提交
4c0c55bb
编写于
3月 17, 2021
作者:
Z
Zhou Wei
提交者:
GitHub
3月 17, 2021
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
support Geforce RTX 30+ GPU (#31529)
上级
cdc5a55a
变更
2
隐藏空白更改
内联
并排
Showing
2 changed file
with
15 addition
and
3 deletion
+15
-3
CMakeLists.txt
CMakeLists.txt
+5
-1
cmake/cuda.cmake
cmake/cuda.cmake
+10
-2
未找到文件。
CMakeLists.txt
浏览文件 @
4c0c55bb
...
...
@@ -95,7 +95,7 @@ if(WIN32)
endif
()
endforeach
(
flag_var
)
endif
()
# NOTE(Avin0323): Less parallel count result in faster compilation.
math
(
EXPR PROCESS_MAX
"
${
CPU_CORES
}
* 2 / 3"
)
# windows build turn off warnings, use parallel compiling.
...
...
@@ -123,6 +123,10 @@ if(WIN32)
set
(
CMAKE_C_FLAGS
"
${
CMAKE_C_FLAGS
}
/wd4068 /wd4129 /wd4244 /wd4267 /wd4297 /wd4530 /wd4577 /wd4819 /wd4838"
)
set
(
CMAKE_CXX_FLAGS
"
${
CMAKE_CXX_FLAGS
}
/wd4068 /wd4129 /wd4244 /wd4267 /wd4297 /wd4530 /wd4577 /wd4819 /wd4838"
)
foreach
(
flag_var CMAKE_SHARED_LINKER_FLAGS CMAKE_STATIC_LINKER_FLAGS CMAKE_EXE_LINKER_FLAGS CMAKE_LINKER_FLAGS
)
string
(
APPEND
${
flag_var
}
"/ignore:4049 /ignore:4217 /ignore:4006 /ignore:4221"
)
endforeach
(
flag_var
)
if
(
WITH_WIN_DUMP_DBG
)
set
(
CMAKE_C_FLAGS
"
${
CMAKE_C_FLAGS
}
/Zi"
)
set
(
CMAKE_CXX_FLAGS
"
${
CMAKE_CXX_FLAGS
}
/Zi"
)
...
...
cmake/cuda.cmake
浏览文件 @
4c0c55bb
...
...
@@ -91,7 +91,7 @@ function(select_nvcc_arch_flags out_variable)
if
(
${
CUDA_ARCH_NAME
}
STREQUAL
"Manual"
)
set
(
CUDA_ARCH_BIN
${
paddle_known_gpu_archs
}
CACHE STRING
"Specify 'real' GPU architectures to build binaries for, BIN(PTX) format is supported"
)
set
(
CUDA_ARCH_PTX
"
50"
CACHE STRING
"Specify 'virtual' PTX architectures to build PTX intermediate code for"
)
set
(
CUDA_ARCH_PTX
"
"
CACHE STRING
"Specify 'virtual' PTX architectures to build PTX intermediate code for"
)
mark_as_advanced
(
CUDA_ARCH_BIN CUDA_ARCH_PTX
)
else
()
unset
(
CUDA_ARCH_BIN CACHE
)
...
...
@@ -175,14 +175,22 @@ elseif (${CMAKE_CUDA_COMPILER_VERSION} LESS 10.0) # CUDA 9.x
set
(
paddle_known_gpu_archs
${
paddle_known_gpu_archs9
}
)
set
(
CMAKE_CUDA_FLAGS
"
${
CMAKE_CUDA_FLAGS
}
-D_MWAITXINTRIN_H_INCLUDED"
)
set
(
CMAKE_CUDA_FLAGS
"
${
CMAKE_CUDA_FLAGS
}
-D__STRICT_ANSI__"
)
set
(
CMAKE_CUDA_FLAGS
"
${
CMAKE_CUDA_FLAGS
}
-Wno-deprecated-gpu-targets"
)
elseif
(
${
CMAKE_CUDA_COMPILER_VERSION
}
LESS 11.0
)
# CUDA 10.x
set
(
paddle_known_gpu_archs
${
paddle_known_gpu_archs10
}
)
set
(
CMAKE_CUDA_FLAGS
"
${
CMAKE_CUDA_FLAGS
}
-D_MWAITXINTRIN_H_INCLUDED"
)
set
(
CMAKE_CUDA_FLAGS
"
${
CMAKE_CUDA_FLAGS
}
-D__STRICT_ANSI__"
)
elseif
(
${
CMAKE_CUDA_COMPILER_VERSION
}
LESS 12.0
)
# CUDA 11.x
set
(
CMAKE_CUDA_FLAGS
"
${
CMAKE_CUDA_FLAGS
}
-Wno-deprecated-gpu-targets"
)
elseif
(
${
CMAKE_CUDA_COMPILER_VERSION
}
LESS 11.2
)
# CUDA 11.0/11.1
set
(
paddle_known_gpu_archs
${
paddle_known_gpu_archs11
}
)
set
(
CMAKE_CUDA_FLAGS
"
${
CMAKE_CUDA_FLAGS
}
-D_MWAITXINTRIN_H_INCLUDED"
)
set
(
CMAKE_CUDA_FLAGS
"
${
CMAKE_CUDA_FLAGS
}
-D__STRICT_ANSI__"
)
set
(
CMAKE_CUDA_FLAGS
"
${
CMAKE_CUDA_FLAGS
}
-Wno-deprecated-gpu-targets"
)
elseif
(
${
CMAKE_CUDA_COMPILER_VERSION
}
LESS 12.0
)
# CUDA 11.2+
set
(
paddle_known_gpu_archs
"
${
paddle_known_gpu_archs11
}
86"
)
set
(
CMAKE_CUDA_FLAGS
"
${
CMAKE_CUDA_FLAGS
}
-D_MWAITXINTRIN_H_INCLUDED"
)
set
(
CMAKE_CUDA_FLAGS
"
${
CMAKE_CUDA_FLAGS
}
-D__STRICT_ANSI__"
)
set
(
CMAKE_CUDA_FLAGS
"
${
CMAKE_CUDA_FLAGS
}
-Wno-deprecated-gpu-targets"
)
endif
()
if
(
NOT
${
CMAKE_CUDA_COMPILER_VERSION
}
LESS 10.0
)
...
...
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