Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[COLLAGE][BYOC][ADRENO] Integrate byoc preprocess in collage and benchmark #17512

Open
wants to merge 1 commit into
base: main
Choose a base branch
from

Conversation

srkreddy1238
Copy link
Contributor

@srkreddy1238 srkreddy1238 commented Nov 11, 2024

Integrate implicit call of BYOC preprocessing module into collage tunning module and enable benchmark script for adreno targets.

Benchmark results:

Networks | OpenCL texture | OpenCLML | Collage
resnet-18-float32 | 10.58 | 7.21 | 7.29
resnet-18-float16 | 7.05 | 4.56 | 4.86
resnet-34-float32 | 16.26 | 12.42 | 13.07
resnet-34-float16 | 11.35 | 7.35 | 7.97
resnet-50-float32 | 19.19 | 20.86 | 18.91
resnet-50-float16 | 13.39 | 12 | 11.09 (8%)
densenet-121-float32 | 25.43 | 17.98 | 13.21 (36%)
densenet-121-float16 | 12.38 | 11.01 | 8.72 (26%)
inception_v3-float32 | 40.41 | 22.3 | 22.64
inception_v3-float16 | 29.91 | 13.69 | 14.52
mobilenet-float32 | 4.09 | 3.68 | 3.19 (15%)
mobilenet-float16 | 2.8 | 2.44 | 2.1 (16%)

Integrate implicit call of BYOC preprocessing module into collage tunning module
and enable benchmark script for adreno targets.

Benchmark results:

**Networks                     | OpenCL texture | OpenCLML  | Collage**
resnet-18-float32        | 0.010584622      | 0.00720695 | 0.007289728
resnet-18-float16        | 0.007052029      | 0.0045642   | 0.004857585
resnet-34-float32        | 0.016259185      | 0.01242092 | 0.013071063
resnet-34-float16        | 0.011350326      | 0.0073473   | 0.00796802
resnet-50-float32        | 0.019188419      | 0.02085548 | 0.018910226
resnet-50-float16        | 0.01338978        | 0.01199576 | 0.011089206
densenet-121-float32 | 0.025430062      | 0.01798478 | 0.013212844
densenet-121-float16 | 0.012384599      | 0.01101491 | 0.008722716
inception_v3-float32   | 0.040408253      | 0.02229727 | 0.022636675
inception_v3-float16   | 0.029910533      | 0.01368941 | 0.014519823
mobilenet-float32       | 0.004093148      | 0.00367917 | 0.003189258
mobilenet-float16       | 0.00280268        | 0.00244494 | 0.002101514

</body>

</html>

Co-authored-by: krishnaraj36 <[email protected]>
@srkreddy1238 srkreddy1238 changed the title Integrate byoc preprocess in collage and benchmark (#26) [COLLAGE][BYOC][ADRENO] Integrate byoc preprocess in collage and benchmark Nov 11, 2024
Copy link
Contributor

@echuraev echuraev left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM. But I'm not very familiar with this part of code, so, I would prefer if someone else takes a look at these changes.

@@ -48,8 +48,7 @@
from tvm.runtime.vm import VirtualMachine
import json


NDK_CROSS_COMPILER = os.getenv("TVM_NDK_CC", "aarch64-linux-android-g++")
from tvm.relay.collage.collage import *
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I would prefer explicitly import modules

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants