[llvm-bugs] [Bug 44584] New: [AMDGPU][MC][GFX908] 'glc' is not supported for buffer_atomic_add_f32 and buffer_atomic_pk_add_f16

[via llvm-bugs]

https://bugs.llvm.org/show_bug.cgi?id=44584

            Bug ID: 44584
           Summary: [AMDGPU][MC][GFX908] 'glc' is not supported for
                    buffer_atomic_add_f32 and buffer_atomic_pk_add_f16
           Product: libraries
           Version: trunk
          Hardware: PC
                OS: Windows NT
            Status: NEW
          Severity: enhancement
          Priority: P
         Component: Backend: AMDGPU
          Assignee: unassignedbugs at nondot.org
          Reporter: dpreobrazhensky at luxoft.com
                CC: llvm-bugs at lists.llvm.org

'glc' is not currently supported for these opcodes:

    buffer_atomic_add       v5, off, s[8:11], s3 offset:4095 glc    // ok
    buffer_atomic_add_f32   v5, off, s[8:11], s3 offset:4095 glc    // fail
    buffer_atomic_add_f32   v5, off, s[8:11], s3 offset:4095        // ok

sp3 assembler seems to support 'glc' modifier:

    buffer_atomic_add_f32   v5, v0, s[8:11], s3 offset:4095 glc     // sp3:ok

-- 
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/20200117/22115ed5/attachment.html>