[llvm] r272337 - AMDGPU: Remove incorrect assertion

[Matt Arsenault via llvm-commits]

Author: arsenm
Date: Thu Jun  9 18:19:08 2016
New Revision: 272337

URL: http://llvm.org/viewvc/llvm-project?rev=272337&view=rev
Log:
AMDGPU: Remove incorrect assertion

I'm still not sure under what circumstances the offset here is non-0,
but private memory is not limited to 27-bits.

Modified:
    llvm/trunk/lib/Target/AMDGPU/SIRegisterInfo.cpp

Modified: llvm/trunk/lib/Target/AMDGPU/SIRegisterInfo.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/AMDGPU/SIRegisterInfo.cpp?rev=272337&r1=272336&r2=272337&view=diff
==============================================================================
--- llvm/trunk/lib/Target/AMDGPU/SIRegisterInfo.cpp (original)
+++ llvm/trunk/lib/Target/AMDGPU/SIRegisterInfo.cpp Thu Jun  9 18:19:08 2016
@@ -277,10 +277,6 @@ void SIRegisterInfo::materializeFrameBas
   const AMDGPUSubtarget &Subtarget = MF->getSubtarget<AMDGPUSubtarget>();
   const TargetInstrInfo *TII = Subtarget.getInstrInfo();
 
-  assert(isUInt<27>(Offset) &&
-         "Private offset should never exceed maximum private size");
-
-
   if (Offset == 0) {
     BuildMI(*MBB, Ins, DL, TII->get(AMDGPU::V_MOV_B32_e32), BaseReg)
       .addFrameIndex(FrameIdx);