tree b70d46cd052ab6e6de71a6e8a4c87efb2b5e1d84
parent 024dd569223d00da55412bff8fffffebd1cb799b
author Md Abdullah Shahneous Bari <98356296+mshahneo@users.noreply.github.com> 1760730080 -0500
committer GitHub <noreply@github.com> 1760730080 -0500
gpgsig -----BEGIN PGP SIGNATURE-----
 
 wsFcBAABCAAQBQJo8pvgCRC1aQ7uu5UhlAAAv1wQAJjlv6DBijoiaysOTIbRkCia
 Ym0GAK6M4SRFnuGlGsmEuLj7GAQLYtZ/FOVnb7PUKM9LKyLL2f3M8QU9XfSznxp3
 CqFReVSECaVU+/M21Nvy6UEW4A7y0r5Bz8YyUk3F3KjekMPFPIYc48H3+omyVrCh
 EALNC5Trvbd+bkI6OtfbqmR7VPxO1okbP3aF2f5pv+hEA/3n8GD90oYOaWdLYP8I
 gi9dwU0f/PbwGgdUzffPkxnjGfHDflAOMsgIVi7KdxqmAVYYrImwpo1xaW0t3o2C
 iHoSeVqNLH70SfeJ53M+gKxM/GJDT9pSeBqahSyU0JPA2SZCvoNgdT/QLhcqgECG
 4t8sG0k8DVrwI/dkpDEpOoPV6JRV+dQCF/uGyiz3B9wfqSED0wLeLqd2C8NIzGcN
 yXgn1HcbBLsQEXz41JW8j2rtHfMP0co+0NHNyuELWiG/maVFHS8mUP5wUP4ErzDU
 dxFfDCFxSXqijW4Uvgh4d5HY/PzSbhQuN8L8bY0RQn3N0nL33nn0u9OUivnfJois
 +p23DOvK3ioftfmHIAohueCxPaXHfNQZCSs03gzX2luZE3z8+Kg+4P/BAtQXJ3eL
 2DdrP18vK5Gou0ViGAb3r5/cE+KmtoR36MYmEUGJ5InbECpktzYmeReQUi79vUzY
 wZ02wf+GwaZzN6yUsBOW
 =lBIU
 -----END PGP SIGNATURE-----
 

[mlir][gpu]Add GPUToXeVM lowering pipeline pass. (#161216)

It's the default GPU to XeVM lowering pipeline. It starts by lowering
GPU code to the specified compilation target (default is fatbin), then
lowers the host code.
If XeGPU ops are used, it expects the MLIR code to have XeGPU ops
already embedded in gpu code.