int8 optimizations #1973
Merged
int8 optimizations #1973
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
This was
linked to
issues
Jul 18, 2023
Codecov Report
@@ Coverage Diff @@
## develop #1973 +/- ##
===========================================
+ Coverage 91.37% 91.40% +0.03%
===========================================
Files 422 422
Lines 15652 15645 -7
===========================================
- Hits 14302 14301 -1
+ Misses 1350 1344 -6
|
This build is OK for merge ✅ |
🔴torchvision-inceptionv3_1: FAILED: MIGraphX is not within tolerance - check verbose output🔴cadene-dpn92_1: FAILED: MIGraphX is not within tolerance - check verbose output🔴slim-inceptionv4_1: FAILED: MIGraphX is not within tolerance - check verbose output |
umangyadav
approved these changes
Jul 24, 2023
pfultz2
reviewed
Jul 26, 2023
test/rewrite_quantization_test.cpp
Outdated
| @@ -70,6 +74,8 @@ TEST_CASE(quantizelinear) | |||
| EXPECT(eval(p1) == eval(p2)); | |||
| EXPECT(any_of(*p1.get_main_module(), &is_quantizelinear)); | |||
| EXPECT(none_of(*p2.get_main_module(), &is_quantizelinear)); | |||
| // ensure clip literals created in quantized program are scalar | |||
| EXPECT(any_of(*p2.get_main_module(), &is_scalar)); | |||
There was a problem hiding this comment.
This should probably check the inputs to clip are scalars.
There was a problem hiding this comment.
updated test, please take a look
…MIGraphX into qdot_clip_opts
pfultz2
reviewed
Aug 8, 2023
| @@ -37,6 +37,17 @@ | |||
|
|
|||
| bool is_quantizelinear(migraphx::instruction& ins) { return ins.name() == "quantizelinear"; } | |||
| bool is_dequantizelinear(migraphx::instruction& ins) { return ins.name() == "dequantizelinear"; } | |||
| bool is_clip_scalar(migraphx::instruction& ins) | |||
There was a problem hiding this comment.
should all of them be changed to const?
There was a problem hiding this comment.
Ah yea they should probably all be const.
pfultz2
approved these changes
Aug 8, 2023
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.
rewrite_quantization.cpp, literals generated for clip operator are now scalarssimplify_algebra.cpp, updated matcher to check for quant_dot operators