Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

MNN推理的内存/cpu使用率 #2870

Open
jamesdod opened this issue May 16, 2024 · 1 comment
Open

MNN推理的内存/cpu使用率 #2870

jamesdod opened this issue May 16, 2024 · 1 comment

Comments

@jamesdod
Copy link

平台(如果交叉编译请再附上交叉编译目标平台):

linux,x86_64

Github版本:

2.8.2

编译方式:

cmake ..
make

设置:

  1. 推理代码完全一样,只有forward_type不一样,一个为MNN_FORWARD_CPU,一个为MNN_FORWARD_OPENCL
  2. 通过cat /proc/pid/status来查看物理内存,CPU内存
  3. 通过top命令查看cpu使用率

现象:

  1. CPU版本内存为50M,GPU版本内存为150M。这仅是CPU内存,为什么GPU版本的CPU内存使用比CPU版本还高呢
  2. CPU版本的cpu使用率为80%,GPU版本的cpu使用率为60%。为什么GPU版本的cpu使用率还这么高呢,应该只有传入和传出数据,计算量很低吧
@jxt1234
Copy link
Collaborator

jxt1234 commented May 16, 2024

  1. 用 MNNV2Basic.out 测试一下
  2. 相关模型提交一下吧

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants