@FrozenGene Thank you for your reply. I refer to this tutorial for my experiments: https://zhuanlan.zhihu.com/p/75203171, and this tutorial seems to be written by you. I tried [1024, 1024] * [1024, 1024], [2048, 2048] * [2048, 2048], [256, 256] * [256, 256], [128, 128] * [128, 128], etc, and tvm does not exceed strassen algorithm at all. I think tvm should be able to get better performance and beyond strassen algorithm, but I don’t know what to do. Do you have any ideas? Thanks a lot
@jcf94 Can you briefly describe the results of your experiments？ Thanks a lot