Pablo Marquez Tello

Hi @alvoron In order to help I'll need more details. Could you please share more information about the workload configuration that caused the problem on macOS? If you build ACL...

Hi @alvoron Thanks, we managed to reproduce and we are working to fix the problem.

Hi @alvoron This is the patch fixing the problem https://review.mlplatform.org/c/ml/ComputeLibrary/+/11290 The fix will be included in 24.05 Hope this helps

Hi @alvoron I've just tried the shapes and data you shared with tensorflow and I get the same results as ACL `3.75 5.5` for axis `0` ``` >>> x =...

Hi @alvoron I managed to reproduce this, however the range of input values in your test `[-2000.f,3000.f]` is not supported for `float16_t` in the operator `NEMeanStdDevNormalizationLayer`. We just test for...

Hi @alvoron Thank you for sharing the details. The following patch fixes the problem: https://review.mlplatform.org/c/ml/ComputeLibrary/+/11311 This fix will be included in 24.04 Hope this helps.

Hi @Nitesh8998 For further details about how sve works please refer to the [SVE Optimization Guide](https://developer.arm.com/documentation/102699/latest/) and [ARM Architecture Reference Manual Supplement - The Scalable Vector Extension (SVE)](https://developer.arm.com/documentation/ddi0584/latest/)

Hi @sdavejones Could you please let us know what's in the folder `Data path : /root/assets_alexnet` ? If you don't specify the folder to the model's correct weights the example...

Hi @alvoron Thanks for reporting this. Would you please let us know how many inferences/iterations you are running?

Hi @alvoron I ran ACL's benchmark_graph_mobilenet_v2 on a device with M2 but I could not see a significant performance degradation. See below the execution including the patch that you mentioned...