onnxruntime
Add cuda kernels for GreaterOrEqual, LessOrEqual, Where; modify Clip to avoid memcpy
#7187

Merged

Add cuda kernels for GreaterOrEqual, LessOrEqual, Where; modify Clip to avoid memcpy #7187

ashbhandare merged 8 commits into master from aibhanda/kernels_hft5

ashbhandare requested a review 5 years ago

ashbhandare added core runtime

ytaous commented on 2021-03-31

mrry commented on 2021-03-31

SherlockNoMad dismissed these changes on 2021-04-01

ashbhandare dismissed their stale review via 26cd26ff 5 years ago

ashbhandare force pushed from 31c3ee42 to 26cd26ff 5 years ago

ytaous dismissed these changes on 2021-04-02

SherlockNoMad commented on 2021-04-02

ashbhandare dismissed their stale review via 1e520d2e 5 years ago

ytaous dismissed these changes on 2021-04-05

yuslepukhin commented on 2021-04-05

Where and Clip cuda kernel support

e726cafe

GreaterOrEqual and LessOrEqual cuda kernels

014d37b2

Clip input GPU mem

8906fbbb

review comments

1bb64446

Add CPU kernel as well

db2fd5f3

review comment

3dbde3e2

Add kernel def hash for new op kernels

132514b3

ashbhandare dismissed their stale review via 132514b3 5 years ago

ashbhandare force pushed from 1e520d2e to 132514b3 5 years ago

Fix CI

eca01834

ytaous approved these changes on 2021-04-06

SherlockNoMad approved these changes on 2021-04-06

ashbhandare merged e9ffcfa2 into master 5 years ago

ashbhandare deleted the aibhanda/kernels_hft5 branch 5 years ago

Reviewers

SherlockNoMad

ytaous

yuslepukhin

mrry

Assignees

No one assigned

Labels

core runtime

Milestone

No milestone

onnxruntime Add cuda kernels for GreaterOrEqual, LessOrEqual, Where; modify Clip to avoid memcpy #7187 Merged

Add cuda kernels for GreaterOrEqual, LessOrEqual, Where; modify Clip to avoid memcpy #7187

onnxruntime
Add cuda kernels for GreaterOrEqual, LessOrEqual, Where; modify Clip to avoid memcpy
#7187

Merged