[TensorV2] Multiplication support #2419
Conversation
djeong20
requested review from
myungjoo,
jijoongmoon,
again4you,
jaeyun-jung,
leemgs,
wooksong,
helloahn,
kparichay,
gichan-jang,
anyj0527,
zhoonit and
a team
as code owners
|
📝 TAOS-CI Version: 1.5.20200925. Thank you for submitting PR #2419. Please a submit 1commit/1PR (one commit per one PR) policy to get comments quickly from reviewers. Your PR must pass all verificiation processes of cibot before starting a review process from reviewers. If you are new member to join this project, please read manuals in documentation folder and wiki page. In order to monitor a progress status of your PR in more detail, visit http://ci.nnstreamer.ai/. |
djeong20
force-pushed
the
impl/tensor_v2/multiply
branch
from
d5aa74e
to
4d130ff
Compare
djeong20
changed the title
| float *out_buf) { | ||
| if (e.strides[3] == 1 && output.getStrides()[3] == 1 && strides[3] == 1 && | ||
| beta == 0.0) { | ||
| std::transform(buf, buf + e.buffer_size, m_buf, out_buf, |
There was a problem hiding this comment.
Even though we use this std::transform, we haven't tested it with other libs or implementations in apply_broadcast. Not in this PR, but we have to evaluate it.
There was a problem hiding this comment.
gotcha. I'll add some testing to verify.
| *out_buf = *buf * *m_buf + beta * *out_buf; | ||
| buf += strides[3]; | ||
| m_buf += e.strides[3]; | ||
| out_buf += output.getStrides()[3]; |
There was a problem hiding this comment.
If it is not continuous, we still can apply the multi-threading with something like omp. There might be some uncertainty about apply_broadcast. It might be better to apply multi-threading in the apply_broadcast function. Not this PR, but we can also evaluate it.
There was a problem hiding this comment.
agree. We can launch a thread using a function pointer or function objects in multithreading support.
djeong20
force-pushed
the
impl/tensor_v2/multiply
branch
from
4d130ff
to
3fa1497
Compare
djeong20
requested review from
lhs8928,
songgot,
jihochu and
DonghakPark
as code owners
djeong20
requested review from
SeoHyungjun,
baek2sm,
skykongkong8 and
EunjuYang
as code owners
This PR adds support for performing the multiplication operation on two tensors. **Changes proposed in this PR:** - TensorV2 includes member functions to perform tensor multiplication. - FloatTensor and HalfTensor take TensorV2 as input/output to perform multiplication. **Self-evaluation:** 1. Build test: [X]Passed [ ]Failed [ ]Skipped 2. Run test: [X]Passed [ ]Failed [ ]Skipped Signed-off-by: Donghyeon Jeong <[email protected]>
djeong20
force-pushed
the
impl/tensor_v2/multiply
branch
from
3fa1497
to
140d04f
Compare
This PR adds support for performing the multiplication operation on two tensors.
Changes proposed in this PR:
Self-evaluation: