[Requantize] Cleanup and Optimize Lowering #5286
Merged
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
anijain2305
commented
Apr 9, 2020
anijain2305
force-pushed
the
arm_int64_mult
branch
from
5f2744e
to
8535134
Compare
yzhliu
approved these changes
Apr 12, 2020
|
Thanks @anijain2305 |
masahi
pushed a commit
to masahi/tvm
that referenced
this pull request
Apr 12, 2020
* Adding Cast back to Int32 in FixedPointMultiply. * Removing extra clip. * Fix space. * Retrigger. * Retrigger.
trevor-m
pushed a commit
to trevor-m/tvm
that referenced
this pull request
Apr 16, 2020
* Adding Cast back to Int32 in FixedPointMultiply. * Removing extra clip. * Fix space. * Retrigger. * Retrigger.
zhiics
pushed a commit
to neo-ai/tvm
that referenced
this pull request
Apr 17, 2020
* Adding Cast back to Int32 in FixedPointMultiply. * Removing extra clip. * Fix space. * Retrigger. * Retrigger.
dpankratz
pushed a commit
to dpankratz/incubator-tvm
that referenced
this pull request
Apr 24, 2020
* Adding Cast back to Int32 in FixedPointMultiply. * Removing extra clip. * Fix space. * Retrigger. * Retrigger.
shoubhik
added a commit
to shoubhik/incubator-tvm
that referenced
this pull request
May 12, 2020
monklof
pushed a commit
to monklof/incubator-tvm
that referenced
this pull request
Jan 22, 2021
…m_data:master to master * commit 'cd0d52daa6942bdafa9363ff6cfa3d25fcd5b8d6': (824 commits) [Intrinsic] Add log1p, ldexp, atan2, hypot, nextafter, copysign (apache#5312) [Rust][CI] Restore Rust CI (apache#5137) Remove PrimExpr from String (apache#5311) [Requantize] Cleanup and Optimize Lowering (apache#5286) [IR][TRANSFORM] Enable CopyOnWrite for passes. (apache#5309) [PYTORCH]Abs, Arange, Softplus ops (apache#5295) [LLVM] Fix generation of LLVM intrinsics (apache#5282) [BYOC] Add example of Composite + Annotate for DNNL fused op (apache#5272) [Frontend][TensorFlow]Improve TensorFlow Static Shape Tensor Array (apache#5243) [RUNTIME] Introduce RValue reference(move) support to TypedPackedFunc (apache#5271) [RELAY][FRONTEND][CAFFE2] add Mul and ConvTranspose operator (apache#5302) [BYOC] Refine AnnotateTarget and MergeCompilerRegion Passes (apache#5277) [CI] Fix the hexagon string (apache#5304) [Arith] linear system and equation solver (apache#5171) [PYTORCH]Repeat, Reciprocal & Reshape Op support (apache#5280) [FRONTEND][TENSORFLOW] Fix gather_nd indices (apache#5279) Update device_annotation.cc (apache#5291) [REFACTOR][IR] Move to runtime::String (apache#5276) [NDArray] Set shape_ in NDArray::FromDLPack (apache#5301) [RUNTIME] Initial implementation of Hexagon runtime support (apache#5252) ...
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 does minor cleanup and optimizes the lowering. Basically, the FixedPointMultiply now takes int32 inputs and gives int32 outputs. Internally it upcast the integers to int64 as before.
I checked the accuracy for all MXNet pre-quantized models, and it is unchanged. Writing down the numbers here for completeness.
Same accuracy before and after this PR (measures on Intel machine)
This PR helps a lot in improving performance on rasp4. Quantized TFLite mobilenet performance improved from 56 ms to 46 ms. This is mainly due to keeping calculations in int64 to as minimum as possible.