https://llvm.org/bugs/show_bug.cgi?id=28413
Bug ID: 28413
Summary: [mc][gfx8] V_CMP_I/U32 -- fail to accept floating
inline constants.
Product: libraries
Version: trunk
Hardware: PC
OS: Windows NT
Status: NEW
Severity: normal
Priority: P
Component: Backend: AMDGPU
Assignee: sam.kol...@amd.com
Reporter: artem.tama...@amd.com
CC: llvm-bugs@lists.llvm.org, nikolay.haus...@amd.com,
valery.pykh...@gmail.com
Classification: Unclassified
Created attachment 16684
--> https://llvm.org/bugs/attachment.cgi?id=16684&action=edit
20160704-weekly-regressions.zip
192 regressions found during weekly testing.
Example of failing instruction:
> v_cmp_le_i32_e64 s[0:1], 0.5, s0
Most likely, this issue is very similar to
https://github.com/RadeonOpenCompute/LLVM-AMDGPU-Assembler-Extra/issues/13
The regression point is
> r274340 | ad58f8c | [AMDGPU] Assembler: support SDWA for VOPC instructions
Lit tests attached.
--
You are receiving this mail because:
You are on the CC list for the bug.
_______________________________________________
llvm-bugs mailing list
llvm-bugs@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-bugs
