Hari-MathWorks

Hi @igorsafo , I can still see the performance drop with --trivial-strides=true for v2.6. `% ./benchdnn --rnn --mode=P --alg=VANILLA_LSTM --trivial-strides=true l1t1000mb16_sic100_slc3_dhc100_dic100 ` Below are the verbose outputs for v2.6 and...

Hi, I have analyzed further using the verbose logs. Please find the summary of the primitives created using the verbose logs from this [link](https://mathworks-my.sharepoint.com/:i:/p/hnalla/ERbGwgVh_01GtIPk4GY-O3ABBjSTu98mce8t4YWNH4KzqA?e=gEXbxG). For v1.4, we always choose blocked...

Hi, +Adding another observation. I did the benchmarking on the **avx2** machine with OneDNN version 2.6. I found that on the **avx2** machine, v2.6 convolution chooses the optimal output format...

Hi @igorsafo and @vpirogov, Thanks for your response. I'm not hard-coding memory format in the destination memory for any operation primitive. I always use `any`. But, I will conditionally insert...

Hi @igorsafo , Thanks for your response. 1. Regarding additional reorders: We can store the convolution output memory format and we can reuse it. But, the problem is that we...

Hi @igorsafo , @vpirogov , +Adding another observation. I'm facing this regression problem for RNN networks too. I have created a separate issue(https://github.com/oneapi-src/oneDNN/issues/1415) for RNN.

Hi @SURUTHI1605 , @imrickysu , @JithinPillai I have seen failures while using event handlers to benchmark AIE kernels for the [01-aie_lenet_tutorial](https://github.com/Xilinx/Vitis-Tutorials/tree/2022.2/AI_Engine_Development/Design_Tutorials/01-aie_lenet_tutorial). I tried event handles as below around the xrtGraphRun(..)....

Hi, I tried to follow [13-aie-performance-analysis](https://github.com/Xilinx/Vitis-Tutorials/tree/2022.2/AI_Engine_Development/Feature_Tutorials/13-aie-performance-analysis), It was using event handlers to profile the **graphObj.run()**. But, In my case, I'm trying to to use profiling code in the [01-aie_lenet_tutorial](https://github.com/Xilinx/Vitis-Tutorials/tree/2022.2/AI_Engine_Development/Design_Tutorials/01-aie_lenet_tutorial) where...

Below are version and commands details: Vitis Version: 2022.2 [01-aie_lenet_tutorial](https://github.com/Xilinx/Vitis-Tutorials/tree/2022.2/AI_Engine_Development/Design_Tutorials/01-aie_lenet_tutorial) build steps used: make kernels TARGET=hw EN_TRACE=1 make graph TARGET=hw EN_TRACE=1 make xsa TARGET=hw EN_TRACE=1 make application TARGET=hw EN_TRACE=1 make...

Output of "which vitis": `/home/hnalla/Desktop/XilinxVersalAI/installDir/Vitis/2022.2/bin/vitis` Output of `platforminfo --list | grep -m 1 -A 9 vck190_base`