[llvm-bugs] [Bug 30808] New: [mc][gfx8] s_load_dword to support offsets up to 20 bits width

[via llvm-bugs]

https://llvm.org/bugs/show_bug.cgi?id=30808

            Bug ID: 30808
           Summary: [mc][gfx8] s_load_dword to support offsets up to 20
                    bits width
           Product: libraries
           Version: trunk
          Hardware: PC
                OS: Windows NT
            Status: NEW
          Severity: normal
          Priority: P
         Component: Backend: AMDGPU
          Assignee: unassignedbugs at nondot.org
          Reporter: artem.tamazov at amd.com
                CC: andrey.kasaurov at gmail.com, artem.tamazov at amd.com,
                    i.am.perminov at gmail.com, llvm-bugs at lists.llvm.org,
                    nikolay.haustov at amd.com, sam.kolton at amd.com,
                    valery.pykhtin at gmail.com
    Classification: Unclassified

Example of failing instruction:
> s_load_dword s[0], s[0:1], 256

With 255 assembles OK. GCN3 doc says that there are 20-bits in the instruction
for immediate unsigned byte offset. The bug if gfx8-specific.

Tested with r285055 (git# 797783e).

None lit tests available on hand.

-- 
You are receiving this mail because:
You are on the CC list for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-bugs/attachments/20161027/bc9ef3e2/attachment.html>