v_writelane_b32 is defined so that vdst and vdst_in operand types do not match. This result in incorrect decoding of v_writelane_b32 with dst=v255.
See bug 45193.
Paths
| Differential D80636
[AMDGPU][MC] Corrected v_writelane_b32 to fix a decoding bug ClosedPublic Authored by dp on May 27 2020, 8:25 AM.
Details Summary v_writelane_b32 is defined so that vdst and vdst_in operand types do not match. This result in incorrect decoding of v_writelane_b32 with dst=v255. See bug 45193.
Diff Detail
Event TimelineThis revision is now accepted and ready to land.May 27 2020, 9:52 AM Closed by commit rG45251ef5345b: [AMDGPU][MC] Corrected v_writelane_b32 to fix a decoding bug (authored by dp). · Explain WhyMay 28 2020, 4:51 AM This revision was automatically updated to reflect the committed changes.
Revision Contents
Diff 266819 llvm/lib/Target/AMDGPU/VOP2Instructions.td
llvm/lib/Target/AMDGPU/VOP3Instructions.td
llvm/test/MC/Disassembler/AMDGPU/gfx10_dasm_all.txt
|