tree 22cb583b22f6b0d2ddc5677d1951f96a2e1fbe00
parent 442956c85c66028600bcfb83065c0d5b77165675
author Krzysztof Drewniak <Krzysztof.Drewniak@amd.com> 1734116799 -0600
committer GitHub <noreply@github.com> 1734116799 -0600
gpgsig -----BEGIN PGP SIGNATURE-----
 
 wsFcBAABCAAQBQJnXIW/CRC1aQ7uu5UhlAAA5GAQAApe8EdVDxCeBW/n/kZXmFEL
 smv1TC8DdIg5LVtFarvnTWxPwknlMkfGA0yKHXwUPl1dFImtX6aLAVKqfiEQcocL
 GS5CrkmO2udFJAfFsDMt3WOWhA5ZtkKiEefaK21xZx0Pl/0lLcJcRaIJJnc4oRoV
 unyIecDlephVNkAWoQpOeG6uLCyh9kAjc7Z0QhOX4JiY85sQadt5U6ZmDtrbPlpf
 8RpIRzLd7RPhsDXPIQBt20Ick3KY5CRYSx2znsoSEftaHNg3KRh79df+SvRMOAjI
 ob7JpTU9c9Yif9b/I8a5qacT/scXcMixJaZsMpVW6jWdGatkfNuFQ/9x6IWDJE1C
 frrU7M32gSc7fzlRlhShw84vV9WBnJFVUCuRUIZM61r5qTfRMA2RrL94EjLdhvm3
 tngfin2NYfIyWFO7N24+jyDlFDTqaOjll+KKgBs3Ja6ek9UMqR/3j308a/UN7Cuc
 odolrFwrraNdbvGRr32rylQwRDuts7YDeSEzXodexFhve2olNLXz+gw12ZD4GtIZ
 ORHltGD04nkoF0I3iIgniM2D8L6L80PKEzz7NZUNIujiwU5sLAHw+Ae+9Bxgr3K5
 m7Etv/ewFhu8+keHn+S3apWZvBJHwyAYRD7ypMUgh63AvdJzxc1iejFcK77Ynkyj
 KpwQBPLMPdT8HQK63glC
 =g8m/
 -----END PGP SIGNATURE-----
 

Reapply "[Codegen][GPU] Add range information to GPU dispatch IDs" (#19361) (#19372)

This reverts commit cb5be1dbd3560f692578c137eadbb413b41e44c7.

Compaled to the previous revision, this one works around a correctness
bug in dataflow analysis that's being fixed by removing the analysis
after SCF->CF.

---

First, this patch implements InferIntRangeInterface for
hal.interface.workgroup.{size,id,count} using a local upper_bound
attribute.

Then, it adds a -iree-codegen-gpu-propagate-dispatch-size-bounds pass
that adds these upper_bounds identifiers to the interface.workgroup
operations and to gpu.thread_id based on static information available
late in the codegen pipeline.

Then, it uses -optimize-int-arithmetic to optimize indexing after
-lower-affine, getting rid of a bunch of "if the input's negative" logic
that isn't actually needed in many of our kernels.

It also ensures that these upper_bound values propagate to LLVM.