[PATCH 1/2] R600/SI: Add kill flag when copying scratch offset to a register

Tom Stellard thomas.stellard at amd.com
Thu Jan 8 07:44:55 PST 2015


This allows us to re-use the same register for the scratch offset
when accessing large private arrays.
---
 lib/Target/R600/SIRegisterInfo.cpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/Target/R600/SIRegisterInfo.cpp b/lib/Target/R600/SIRegisterInfo.cpp
index d955c72..0b930855 100644
--- a/lib/Target/R600/SIRegisterInfo.cpp
+++ b/lib/Target/R600/SIRegisterInfo.cpp
@@ -256,7 +256,7 @@ void SIRegisterInfo::eliminateFrameIndex(MachineBasicBlock::iterator MI,
         BuildMI(*MBB, MI, MI->getDebugLoc(),
                 TII->get(AMDGPU::V_MOV_B32_e32), TmpReg)
                 .addImm(Offset);
-        FIOp.ChangeToRegister(TmpReg, false);
+        FIOp.ChangeToRegister(TmpReg, false, false, true);
       }
     }
   }
-- 
1.8.5.5




More information about the llvm-commits mailing list