[QNN] Refactor fixed point multiplication in requantize #4073
Conversation
This file contains hidden or 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
anijain2305
approved these changes
Oct 7, 2019
vinx13
force-pushed
the
feature/qnn_refactor
branch
from
8455eba to
4b4912f
Compare
|
Another comment - Currently, QNN includes headers (code) from Relay. I tried to make it as uni-directional as possible. However, this will create bi-directional code inclusion (which might be ok). Therefore, it is worth thinking if we should put FixedPointMultiply in some header in Relay, which QNN can now read from. |
|
LGTM. Or we can just add a util.h header to put the declarations. |
|
@zhiics Can you approve? Or shall we move FixedPointMul to relay/quantize/util.cc ? |
zhiics
approved these changes
Oct 8, 2019
anijain2305
pushed a commit
to anijain2305/tvm
that referenced
this pull request
Oct 17, 2019
wweic
pushed a commit
to neo-ai/tvm
that referenced
this pull request
Oct 18, 2019
petrex
pushed a commit
to petrex/tvm
that referenced
this pull request
Oct 29, 2019
* master: (21 commits) [Fix][VM] Fix VM invoke with set_params (apache#4079) [QNN] Refactor fixed point multiplication in requantize (apache#4073) Fix match case in Python-side expr functor (apache#4037) Hide symbols from dependent libraries if HIDE_PRIVATE_SYMBOLS is ON. (apache#4041) Add gradient for log-softmax (apache#4069) [DOC] Fix typos in tutorials (apache#4066) dicrease the complexity of CalcDep from exponential to linear (apache#4053) [Relay][AlterOp] Minor refactor. (apache#4064) [Relay][AlterOp] Improving support for broadcast layout alteration. (apache#4040) Add parses support for zeros_like tflite operator (apache#4042) [Bugfix][TF] reset graph after getting tag of savedmodel (apache#4055) [Relay][VM] Add more passes to VMCompiler (apache#4058) [Relay][VM] Add autotvm context when compile (apache#4062) [Bugfix] Fix target host for vm compiler (apache#4057) [Relay][Training] Add gradient for Crossentropy (apache#3925) [llvm] switch to use Align for llvm trunk (apache#4051) [Relay][TopHub] Add switch to disable TopHub download (apache#4015) [Relay][Op] Add instance norm op (apache#4004) [QNN][Relay] Calling Dialect passes from inside Relay Build API. (apache#3971) [RELAY/PASS] Fix the extent for the post_stmt in the loop partition (apache#3734) ...
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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.
This PR extracts fixed point multiplication in
qnn.requantizeintoutil.ccso that it can be used in other places likerelay::quantize::QuantizeRealizePlease review @anijain2305 @zhiics