[MULTI] Zero-copy (when backed by the determenistic app-level scheduling) #3286
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
myshevts
force-pushed
the
data_affinity_zero_copy
branch
2 times, most recently
from
3ffa35c to
933d151
Compare
ilya-lavrenov
added
pr: needs tests
myshevts
force-pushed
the
data_affinity_zero_copy
branch
from
4855fa7 to
03f8958
Compare
…ution directly into the loop over devices (avoids pointers and 'else' clause)
…lti-device, via "borrowing" the corresponding device-specific blobs and letting the app to implicitly use these 2) Initial MULTI section in the opt guide (primarily to document a tip on helping the MULTI to keep the zero-copy path)
myshevts
force-pushed
the
data_affinity_zero_copy
branch
from
03f8958 to
ee33a9d
Compare
myshevts
changed the title
myshevts
changed the title
ilya-lavrenov
approved these changes
Nov 30, 2020
evolosen
pushed a commit
to evolosen/openvino
that referenced
this pull request
Dec 3, 2020
…ing) (openvinotoolkit#3286) * Optimized Infer Request Scheduling * Fixed misprint * Brushing the code and comments a bit * further brushing of the ScheduleToWorkerRequest: moving the task execution directly into the loop over devices (avoids pointers and 'else' clause) * 1) zero-copy (assuming determenistic app-level scheduling) for the multi-device, via "borrowing" the corresponding device-specific blobs and letting the app to implicitly use these 2) Initial MULTI section in the opt guide (primarily to document a tip on helping the MULTI to keep the zero-copy path) Co-authored-by: apankratovantonp <[email protected]>
mryzhov
pushed a commit
to mryzhov/openvino
that referenced
this pull request
Dec 11, 2020
…ing) (openvinotoolkit#3286) * Optimized Infer Request Scheduling * Fixed misprint * Brushing the code and comments a bit * further brushing of the ScheduleToWorkerRequest: moving the task execution directly into the loop over devices (avoids pointers and 'else' clause) * 1) zero-copy (assuming determenistic app-level scheduling) for the multi-device, via "borrowing" the corresponding device-specific blobs and letting the app to implicitly use these 2) Initial MULTI section in the opt guide (primarily to document a tip on helping the MULTI to keep the zero-copy path) Co-authored-by: apankratovantonp <[email protected]>
mryzhov
pushed a commit
to mryzhov/openvino
that referenced
this pull request
Dec 16, 2020
…ing) (openvinotoolkit#3286) * Optimized Infer Request Scheduling * Fixed misprint * Brushing the code and comments a bit * further brushing of the ScheduleToWorkerRequest: moving the task execution directly into the loop over devices (avoids pointers and 'else' clause) * 1) zero-copy (assuming determenistic app-level scheduling) for the multi-device, via "borrowing" the corresponding device-specific blobs and letting the app to implicitly use these 2) Initial MULTI section in the opt guide (primarily to document a tip on helping the MULTI to keep the zero-copy path) Co-authored-by: apankratovantonp <[email protected]>
mryzhov
pushed a commit
to mryzhov/openvino
that referenced
this pull request
Jan 14, 2021
…ing) (openvinotoolkit#3286) * Optimized Infer Request Scheduling * Fixed misprint * Brushing the code and comments a bit * further brushing of the ScheduleToWorkerRequest: moving the task execution directly into the loop over devices (avoids pointers and 'else' clause) * 1) zero-copy (assuming determenistic app-level scheduling) for the multi-device, via "borrowing" the corresponding device-specific blobs and letting the app to implicitly use these 2) Initial MULTI section in the opt guide (primarily to document a tip on helping the MULTI to keep the zero-copy path) Co-authored-by: apankratovantonp <[email protected]>
jiwaszki
pushed a commit
to akuporos/openvino
that referenced
this pull request
Jan 15, 2021
…ing) (openvinotoolkit#3286) * Optimized Infer Request Scheduling * Fixed misprint * Brushing the code and comments a bit * further brushing of the ScheduleToWorkerRequest: moving the task execution directly into the loop over devices (avoids pointers and 'else' clause) * 1) zero-copy (assuming determenistic app-level scheduling) for the multi-device, via "borrowing" the corresponding device-specific blobs and letting the app to implicitly use these 2) Initial MULTI section in the opt guide (primarily to document a tip on helping the MULTI to keep the zero-copy path) Co-authored-by: apankratovantonp <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
via "borrowing" the corresponding device-specific blobs and letting the app to implicitly use these