| commit | 86d93952ed625036fdfb652cc25c41757862d815 | [log] [tgz] |
|---|---|---|
| author | Artem Tamazov <artem.tamazov@amd.com> | Mon Oct 31 16:07:39 2016 +0000 |
| committer | Artem Tamazov <artem.tamazov@amd.com> | Mon Oct 31 16:07:39 2016 +0000 |
| tree | d5ad8c86fd58ef2e988adeaecaf162b8931fa07a | |
| parent | abc5ce4bbcbdc9219e7a5b9dc6aa771ab0a5c2ef [diff] |
[AMDGPU][MC][gfx8] Support 20-bit immediate offset in SMEM instructions. Fixes Bug 30808. Note that passing subtarget information to predicates seems too complicated, so gfx8-specific def smrd_offset_20 introduced. Old gfx6/7-specific def renamed to smrd_offset_8 for clarity. Lit tests updated. Differential Revision: https://reviews.llvm.org/D26085 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@285590 91177308-0d34-0410-b5e6-96231b3b80d8