tree 30925f848fe55ec04f240157761e6a2bd11fd776
parent 212f2456fcde822fad37bfa4e69ced1a51a4c19d
author Lucas Ramirez <11032120+lucas-rami@users.noreply.github.com> 1746098543 +0200
committer GitHub <noreply@github.com> 1746098543 +0200
gpgsig -----BEGIN PGP SIGNATURE-----
 
 wsFcBAABCAAQBQJoE1lvCRC1aQ7uu5UhlAAAKD0QABaEd2Wp1cGO9zWiv+mSNdyL
 AMxAb4SW+v5b8a+UGP8Xqlgu5QTTu/qRTF3EiptxBr4vHyxuU59CrwMffMR8Td7A
 qk2GQB2o93bjBYgBB4DpGEWENoIORj4BGyaiTmdzDq+7GdrvBX8pGeRDHel9bh6q
 lkk0yBwMT78hJIdzo9pE/hnQtrmQgBBOy28nr1f+BdTcrxsjgeCel2iYYcnPfRrh
 6MvwJRzI1ksDEerrCPVqoQ+FWLZaq1XgwL44B3KHgIk0+E4XS7LgmxOrFoQCoJbA
 qPf0Dsocf7Kl2c9dvBcXsconx3w5/oVdgvm+aU/eZUjtISYipudc/0OdpO8so3mw
 HWM/eBemu3kiwlLl6izF+L8b43tyvYgPq/6+QxKt87zp1PERtJHRQ6sHvUBocgRy
 zExMrJ5diPfPlxzny9O5gyhHPDRACpsOoJ6mPta6R2KVeZ3xgMhmJYzpseRbtE8Z
 WL3vvS24qh6husEKSJR87lUHxSkH4JYj287wfs5UnLOXiKNg6gVQwNIzcWG0A6mR
 yYMuD2KPRT/57iGYs3ebn1ZDdIPrCIwbqBv6TW3KIEDPxeM5v9V4MigdlhCHupKm
 Ludrj6XO7DOu1r6lIWXdTC/XcK2m/dhi4BGXe141TkCxUByn9IhNsbRgaWd0k/OZ
 VgsjFSwvN7/REzQKJ+7K
 =3IF2
 -----END PGP SIGNATURE-----
 

[AMDGPU] Max. WG size-induced occupancy limits max. waves/EU (#137807)

The default maximum waves/EU returned by the family of
`AMDGPUSubtarget::getWavesPerEU` is currently the maximum number of
waves/EU supported by the subtarget (only a valid occupancy range in
"amdgpu-waves-per-eu" may lower that maximum). This ignores maximum
achievable occupancy imposed by flat workgroup size and LDS usage,
resulting in situations where `AMDGPUSubtarget::getWavesPerEU` produces
a maximum higher than the one from
`AMDGPUSubtarget::getOccupancyWithWorkGroupSizes`.

This limits the waves/EU range's maximum to the maximum achievable
occupancy derived from flat workgroup sizes and LDS usage. This only has
an impact on functions which restrict flat workgroup size with
"amdgpu-flat-work-group-size", since the default range of flat workgroup
sizes achieves the maximum number of waves/EU supported by the
subtarget.

Improvements to the handling of "amdgpu-waves-per-eu" are left for a
follow up PR (e.g., I think the attribute should be able to lower the
full range of waves/EU produced by these methods).