tree 3ab51453b7569c78f8e5374b7066793ca8f51693
parent 2605fa104257bea0a95310a662dbec1bc9b450f3
author Lei Zhang <antiagainst@gmail.com> 1704820177 -0500
committer GitHub <noreply@github.com> 1704820177 -0800
gpgsig -----BEGIN PGP SIGNATURE-----
 
 wsBcBAABCAAQBQJlnX3RCRBK7hj4Ov3rIwAAUZMIAGyyC1tqsQsG/5CtXfgmGt0n
 vbjIvC2eF4uZCjMnjMk0kxKRvt6yqWvOTmQHYk0WSOL+YBkDKZyH6tC9becNJQT/
 veeSpWR23ChnVcOamnIaJNe4Zb25tTmi+8mD9PY0qlDMhVm4rnKi6/4/dMD44BY5
 L6CD4eiqBNxMucI745FXaEkn5RgeH4dr0Xr10nR56EMf0AS9IgVXMSN5nqYCTvca
 ebsmYnr8AcJOenlzhPF1FY15X8blQ/pNXm6CZlEMurGuQoJ6NJw3y0EpN1GYxBbD
 zYi+UBO0+DTBc7E3VYv0WXAbDv8bsiSZdIvb8LOuY05YFj/C0iRXFndEm8U9NlA=
 =NvSu
 -----END PGP SIGNATURE-----
 

Reland "[spirv][vulkan] Enable device query generation and execution" (#16075)

This commit relands https://github.com/openxla/iree/pull/15977
with the following changes:

* Disable the test requiring 16bit uniform buffer access on Adreno.
  Moto Edge X30 supports VK_KHR_16bit_storage for only storage
  buffers, but not uniform buffers, see
  https://vulkan.gpuinfo.org/displayreport.php?id=14481#features_extensions
  We request both bits.
* Avoid requesting dot product to be accelerated. As long as the
  `shaderIntegerDotProduct` bit is true, we can use all the integer
  dot product instructions in SPIR-V. Whether it's accelerated or not
  does not matter for the purpose of deciding whether the SPIR-V blob
  is runnable.