tree d4b23e996df324c8f339688a6c88ecf27651ee4a
parent 4ee7d600c9ef024f85c7f6860abdebc1a964f7bc
author Krzysztof Drewniak <Krzysztof.Drewniak@amd.com> 1733184937 -0600
committer GitHub <noreply@github.com> 1733184937 -0600
gpgsig -----BEGIN PGP SIGNATURE-----
 
 wsFcBAABCAAQBQJnTk2pCRC1aQ7uu5UhlAAAKv0QAIbeTBgMju6D5vFHcCHpKW0s
 TaIXCskmx6nR/lKEHMVGNOxr4YXa2w6jdIJMlwv66IvAB6H4CereuCLIZzbu9qMY
 MJauYCDa5MWWvpiYar7MkAyKePPk/ZBCDIUf6/JlzLDExPUIfGbPrQFFlVB8nFBt
 DmHmI7smIFjXA/IXE1OduYR1wWD+LIJMGyxc+Ovn+Us7LXu+XBTAqRmz4o6Et3eu
 wmLjdTA2Zd5Jze/5rzlv79ZACkAIPyLm01JFONM3lckzwzhdChPvuwRNcTSEJMBn
 HQpDKZ5qNfLoxxgvAmmFwjM555KI2H3K19N8xdZCE0HK4d5a4aBjfmZAWHFiiOyf
 vbDzDqCSGYZV5F51hSVW/U/tahB+htceAOJQg6rAwccJGQXmQkOi7VMD7LAJz88x
 6pCuK/2z7+9yYGFebrmbzwg02bZggCx37fOOnwCmdVarAsMeyjKM53777YXQLafB
 rDxHsF8hILjT4fkbS3cJSOp9YQRw9ZdlYJkD+ZwGStc2+S4yuQZ/0Xvfa8hAq/h5
 zMXKJkUlO4YdbV/d9I5gpkuNjEXKr+qBTNSUCa687A6KeOTyadULe86MdSq9R6q9
 93ACbz7Cn01OscTTA/x2A95r6JQCrXZlTarfZXCOsi5eAsrh8Y/pjzO09xruE6vn
 d4p0T9eTwMxOpwfg6qXV
 =4mOQ
 -----END PGP SIGNATURE-----
 

[Codegen][GPU] Add range information to GPU dispatch IDs (#17707)

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.

---------

Signed-off-by: Krzysztof Drewniak <Krzysztof.Drewniak@amd.com>
Co-authored-by: Jakub Kuderski <kubakuderski@gmail.com>