-
Notifications
You must be signed in to change notification settings - Fork 5.5k
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
Modified iou_similarity_op cuda kernel #10224
Conversation
baiyfbupt
commented
Apr 26, 2018
•
edited
edited
Time unit: ms | Event | Total | Min. | Max. | Ave. |
---|---|---|---|---|---|
Before | thread0::iou_similarity | 10 | 6.77757 | 0.64416 | 0.677757 |
Optimized | thread0::iou_similarity | 10 | 0.064512 | 0.085952 | 0.072 |
root seems not to be a GitHub user. You need a GitHub account to be able to sign the CLA. If you have already a GitHub account, please add the email address used for this commit to your account. You have signed the CLA already but the status is still pending? Let us recheck it. |
|
||
inline HOSTDEVICE void operator()(size_t tid) const { | ||
size_t row_id = tid/cols_; | ||
size_t col_id = tid%cols_; |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Please note the code format and install pre-commit
and cpplint.
size_t row_id = tid / cols_;
size_t col_id = tid % cols_;
|
||
platform::ForRange<DeviceContext> for_range( | ||
static_cast<const DeviceContext&>(ctx.device_context()), x_n); | ||
for_range(functor); | ||
static_cast<const DeviceContext&>(ctx.device_context()), x_n*y_n); |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Please note the code format x_n * y_n
.