tree e4c7d78f7db0fa3b7be95e9d49ab46ee55b7a1a2
parent 37cc010b91e0aaeced53d9261c1f4b511f603871
author Jianhui Li <jian.hui.li@intel.com> 1755196027 -0700
committer GitHub <noreply@github.com> 1755196027 -0700
gpgsig -----BEGIN PGP SIGNATURE-----
 
 wsFcBAABCAAQBQJonip7CRC1aQ7uu5UhlAAAcZwQAAbEcwORz9rk32vpWj1Ip7OE
 4ytHXUFMGaW52iU9PP6VX6m5rrXjC/B0xSXL5ko+MCa1Z7FT9C++spHUlfa6cS2x
 UkLdLuDT30nfD2cyAFYP5Hd3BtB84DSs8AOolvmLiP2/Eezq0ZsLFDvM5bYTotrO
 CK1JwyyEKT1O+NBwf0WJ5TscIiUInFHCcbEIWDIZif++UsmIvJkDrZOvdHP+yrwg
 EAT4hciIB8CsdkrrEGLA0won5RgI2QoEl0aD+RANe3Eoxis6ZCGKAuMXMGxR07m1
 dyGibvT2HZiZsoDprVHA73OGoSguXwjxtAub9Ji5LJdrmOHhfR4lpXIYxqOfHhIA
 PvTUOD6SJVv2CKohcpxxdawmNdQwATOxfn0pTtB9q7YqkWNkDl/D7PQgyzt5Klvs
 S1jGAQT34E8F3EUTO0UVrjWyQAE+Tmw795jUrf6q4O5J65PM4TrASIU0QgpDO5qK
 AAaDzpIP92gI+yJRn6yU/1Mj6+fiDrvYO4QZoF0g7BWR9rhLSgf4P3GaRJK40AFt
 jD2qEMW1fJspkOnHremBcO5IALfT9xZY8yolqus2syAkDx2bOktv/fx1ahrzC4OQ
 tAUVHtq+8MM+m+IezimiI3qfAEby+S+LbvBgP6ARD8x/XDuS6RepP9eY+7/vTaRm
 J5VNJ2IK9QrLuedjsRQp
 =yDVa
 -----END PGP SIGNATURE-----
 

[MLIR][XeGPU] Add lowering from transfer_read/transfer_write to load_gather/store_scatter  (#152429)

Lowering transfer_read/transfer_write to load_gather/store_scatter in
case the target uArch doesn't support load_nd/store_nd. The high level
steps:
  1. compute Strides;
  2. compute Offsets;
  3. collapseMemrefTo1D;
  4. create Load gather or store_scatter op