[Relay][QNN] Support for non scalar zero points in qnn.conv2d #8620
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
jwfromm
requested review from
anijain2305,
areusch,
comaniac,
jroesch,
junrushao,
merrymercy,
tqchen,
yzhliu,
zhiics and
ZihengJiang
as code owners
|
@anijain2305 @mbrookhart what do you guys think of this change? |
mehrdadh
pushed a commit
to mehrdadh/tvm
that referenced
this pull request
Aug 11, 2021
…#8620) * conv2d working, fixing conv2d_depthwise * Depthwise conv2d working. * Make convinteger work on cuda. * Simplify code and add tests. * Formatting. * Fixed fallback broadcasting. * Fix fallback broadcasting. * Formatting. * Fix lint * Merge with new test parameterization.
ylc
pushed a commit
to ylc/tvm
that referenced
this pull request
Sep 29, 2021
…#8620) * conv2d working, fixing conv2d_depthwise * Depthwise conv2d working. * Make convinteger work on cuda. * Simplify code and add tests. * Formatting. * Fixed fallback broadcasting. * Fix fallback broadcasting. * Formatting. * Fix lint * Merge with new test parameterization.
ylc
pushed a commit
to ylc/tvm
that referenced
this pull request
Jan 13, 2022
…#8620) * conv2d working, fixing conv2d_depthwise * Depthwise conv2d working. * Make convinteger work on cuda. * Simplify code and add tests. * Formatting. * Fixed fallback broadcasting. * Fix fallback broadcasting. * Formatting. * Fix lint * Merge with new test parameterization.
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Outdated suggestions cannot be applied.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.
This PR adds support for non-scalar zero point values in qnn conv2d operators and also allows the kernel zero points to be channel-wise. This is a needed change to support ONNX's
ConvIntegernodes which typically treat zero points as expressions and are often generated using OnnxRuntimes quantization feature, that produces channel wise zero points. Although the rest of the qnn framework doesn't yet support non constant zero points, this is a good start that improves our onnx coverage considerably.I also found that although qnn supported lowering uint8 convolution and dense to cuda, the dp4a instruction actually only supports int8 datatypes, an error exposed by the onnx frontend tests. I added some legalization logic to convert uint8 to int8 when the target is cuda.