You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by GitBox <gi...@apache.org> on 2022/01/18 20:24:05 UTC
[GitHub] [tvm] tkonolige opened a new pull request #9966: [TOPI,x86] Improve performance on int8 conv2d on x86
tkonolige opened a new pull request #9966:
URL: https://github.com/apache/tvm/pull/9966
Appended fused operations in cov2d for int8 were computed in a separate loop from the main conv2d computation:
```
for i in ... parallel
for j in ...
accumulator = 0
for k in ..
vectorized_multiply_add(accumulator, data, kernel)
out = accumulator
for k in ..
out = out + fused subsequent ops
```
This patch moves the fused ops one more loop nesting inwards to get
```
for i in ... parallel
for j in ...
accumulator = 0
for k in ..
vectorized_multiply_add(accumulator, data, kernel)
out = accumulator + fused subsequent ops
```
On quantized mobilenetv2, this results in approximately a 30% speedup.
@masahi @mbrookhart
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [tvm] tkonolige edited a comment on pull request #9966: [TOPI,x86] Improve performance on int8 conv2d on x86
Posted by GitBox <gi...@apache.org>.
tkonolige edited a comment on pull request #9966:
URL: https://github.com/apache/tvm/pull/9966#issuecomment-1015925994
| Model | Before (ms) | After (ms) |
| resnet50 | 5.5282 | 4.7501 |
| inception_v3 | 3.4320 | 3.2994 |
| mobilenetv2 | 1.5239 | 1.1931 |
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [tvm] tkonolige edited a comment on pull request #9966: [TOPI,x86] Improve performance on int8 conv2d on x86
Posted by GitBox <gi...@apache.org>.
tkonolige edited a comment on pull request #9966:
URL: https://github.com/apache/tvm/pull/9966#issuecomment-1015925994
| Model | Before (ms) | After (ms) |
| --- | --- | ---|
| resnet50 | 5.5282 | 4.7501 |
| inception_v3 | 3.4320 | 3.2994 |
| mobilenetv2 | 1.5239 | 1.1931 |
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [tvm] masahi merged pull request #9966: [TOPI,x86] Improve performance on int8 conv2d on x86
Posted by GitBox <gi...@apache.org>.
masahi merged pull request #9966:
URL: https://github.com/apache/tvm/pull/9966
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [tvm] tkonolige commented on pull request #9966: [TOPI,x86] Improve performance on int8 conv2d on x86
Posted by GitBox <gi...@apache.org>.
tkonolige commented on pull request #9966:
URL: https://github.com/apache/tvm/pull/9966#issuecomment-1015925994
Model | Before (ms) | After (ms)
resnet50 | 5.5282 | 4.7501
inception_v3 | 3.4320 | 3.2994
mobilenetv2 | 1.5239 | 1.1931
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org