tree ab3deb7e7fa2e95974df8d184b85381b1123dca5
parent f227dc9ca24296cec0878b92d5ad3f853417e264
author Sumanth Gundapaneni <sumanth.gundapaneni@amd.com> 1721752474 -0500
committer GitHub <noreply@github.com> 1721752474 +0400
gpgsig -----BEGIN PGP SIGNATURE-----
 
 wsFcBAABCAAQBQJmn9uaCRC1aQ7uu5UhlAAAAJcQACXwMm3foyrFKt8PmRNkxOV+
 2Oojx4rrx5taUKm+llBPbxb2gNjXlSiLfkNclujdEOuVN+JwhmpmFiMuTJY8fA+V
 NeBGLh1UpXUvUXn73fG1ki9OGRsR/jXVM9Y3epEPQP4W5wvlalW39q5KnHtIrPh1
 mpsu+79w01UUBLYAjrn/KJ8dEn1Bki2Qvn90r6otONMwN2gSkD4tTAxLvs8BLJf+
 FZlOMBA7w+wSow+aOAAhgZTWC9Hq3lCJX/8Ms1VfIMJX7DwQhZF69Ijx48UovgZH
 4h1Q70Khu+QLhFA5teoWie64Zm1pesuNdP+5JvQstItY3+/R8qxje32F97h/qGMe
 VBBVgfN46yerAouuBmMtcohnTtc4ouXVqmj6nPGdyoAqmmEy6Ljbl7KUWptx58As
 oGeMpJOWddfLwUKksSxMVG4bWvHGLbDlFkuW6bu8bwXW6uyFLilkuwhEqsWrmoom
 HdDIzyCmcAffBl8/cOA6idXIIGfRwJte2WJVDdEFtzgKu/GqM4EhyP1homYn1KBm
 QCdqNc8HP3NsyUrrWyzalgy5sJiuvsmzag9rLQ4pdjWaVe9cSgJSb+r1ZK/Tq08B
 /k3rrR90QcwoPwhppQ4GeabrIsGjrGND7WPJP65ocPyTdGJ7wquJ0fHdzoKcfebt
 ul6Dc25toRO/F36yRwH8
 =1bQg
 -----END PGP SIGNATURE-----
 

[AMDGPU] Implement llvm.lround intrinsic lowering. (#98970)

This patch enables the target-independent lowering of llvm.lround via
GlobalISel. For SelectionDAG, the instrinsic is custom lowered for
AMDGPU. In order to support vector floating point input for llvm.lround,
this patch extends the target independent APIs and provide support for
scalarizing. pr98950 is needed to let verifier allow vector floating
point types