[GitHub] [incubator-tvm] roastduck commented on pull request #5382: [TE] Fix MakeLoopNest for warp memory

2020-05-07 Thread GitBox
roastduck commented on pull request #5382: URL: https://github.com/apache/incubator-tvm/pull/5382#issuecomment-625574365 @yongfeng-nv Fixed. This is an automated message from the Apache Git Service. To respond to the

[GitHub] [incubator-tvm] roastduck commented on pull request #5382: [TE] Fix MakeLoopNest for warp memory

2020-05-06 Thread GitBox
roastduck commented on pull request #5382: URL: https://github.com/apache/incubator-tvm/pull/5382#issuecomment-625044388 @yongfeng-nv Thanks. Your improved test helps a lot. I call `tvm.driver.build_module.form_irmodule` directly, in order not to run the transformation passes in

[GitHub] [incubator-tvm] roastduck commented on pull request #5382: [TE] Fix MakeLoopNest for warp memory

2020-05-02 Thread GitBox
roastduck commented on pull request #5382: URL: https://github.com/apache/incubator-tvm/pull/5382#issuecomment-623041791 It will be great if someone can make a review. This is an automated message from the Apache Git

[GitHub] [incubator-tvm] roastduck commented on pull request #5382: [TE] Fix MakeLoopNest for warp memory

2020-04-28 Thread GitBox
roastduck commented on pull request #5382: URL: https://github.com/apache/incubator-tvm/pull/5382#issuecomment-620456420 @wpan11nv Could you explain how subgroups in OpenCL works? Up to now, we always assumed `threadIdx.x` equals to warp in the `lower_warp_memory` pass. Does it mean there

[GitHub] [incubator-tvm] roastduck commented on pull request #5382: [TE] Fix MakeLoopNest for warp memory

2020-04-24 Thread GitBox
roastduck commented on pull request #5382: URL: https://github.com/apache/incubator-tvm/pull/5382#issuecomment-619291622 Do you mean requiring the users to tag the iter_var or we do it in InferBound? If the former, maybe we can merge this PR first and then start an RFC for the API change.