[llvm] r255906 - AMDGPU: Fix off-by-one in SIRegisterInfo::eliminateFrameIndex

[Nicolai Haehnle via llvm-commits]

Author: nha
Date: Thu Dec 17 10:46:42 2015
New Revision: 255906

URL: http://llvm.org/viewvc/llvm-project?rev=255906&view=rev
Log:
AMDGPU: Fix off-by-one in SIRegisterInfo::eliminateFrameIndex

Summary:
The method insertNOPs expected the number of wait states to be passed as
parameter, while eliminateFrameIndex passed the immediate argument for the
S_NOP, leading to an off-by-one error. Rename the method to make the
meaning of its parameter clearer. The number of 4 / 5 wait states (which
is what the method has always _tried_ to do according to the comment) is
correct according to the hardware docs.

I stumbled upon this while trying to track down the cause of
https://bugs.freedesktop.org/show_bug.cgi?id=93264. While clearly needed,
this patch unfortunately does not fix that bug...

Reviewers: arsenm, tstellarAMD

Subscribers: arsenm, llvm-commits

Differential Revision: http://reviews.llvm.org/D15542

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

Modified: llvm/trunk/lib/Target/AMDGPU/SIInstrInfo.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/AMDGPU/SIInstrInfo.cpp?rev=255906&r1=255905&r2=255906&view=diff
==============================================================================
--- llvm/trunk/lib/Target/AMDGPU/SIInstrInfo.cpp (original)
+++ llvm/trunk/lib/Target/AMDGPU/SIInstrInfo.cpp Thu Dec 17 10:46:42 2015
@@ -742,8 +742,8 @@ unsigned SIInstrInfo::calculateLDSSpillA
   return TmpReg;
 }
 
-void SIInstrInfo::insertNOPs(MachineBasicBlock::iterator MI,
-                             int Count) const {
+void SIInstrInfo::insertWaitStates(MachineBasicBlock::iterator MI,
+                                   int Count) const {
   while (Count > 0) {
     int Arg;
     if (Count >= 8)

Modified: llvm/trunk/lib/Target/AMDGPU/SIInstrInfo.h
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/AMDGPU/SIInstrInfo.h?rev=255906&r1=255905&r2=255906&view=diff
==============================================================================
--- llvm/trunk/lib/Target/AMDGPU/SIInstrInfo.h (original)
+++ llvm/trunk/lib/Target/AMDGPU/SIInstrInfo.h Thu Dec 17 10:46:42 2015
@@ -441,7 +441,7 @@ public:
   void LoadM0(MachineInstr *MoveRel, MachineBasicBlock::iterator I,
               unsigned SavReg, unsigned IndexReg) const;
 
-  void insertNOPs(MachineBasicBlock::iterator MI, int Count) const;
+  void insertWaitStates(MachineBasicBlock::iterator MI, int Count) const;
 
   /// \brief Returns the operand named \p Op.  If \p MI does not have an
   /// operand named \c Op, this function returns nullptr.

Modified: llvm/trunk/lib/Target/AMDGPU/SIRegisterInfo.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/AMDGPU/SIRegisterInfo.cpp?rev=255906&r1=255905&r2=255906&view=diff
==============================================================================
--- llvm/trunk/lib/Target/AMDGPU/SIRegisterInfo.cpp (original)
+++ llvm/trunk/lib/Target/AMDGPU/SIRegisterInfo.cpp Thu Dec 17 10:46:42 2015
@@ -331,16 +331,17 @@ void SIRegisterInfo::eliminateFrameIndex
       // TODO: only do this when it is needed
       switch (MF->getSubtarget<AMDGPUSubtarget>().getGeneration()) {
       case AMDGPUSubtarget::SOUTHERN_ISLANDS:
-        // "VALU writes SGPR" -> "SMRD reads that SGPR" needs "S_NOP 3" on SI
-        TII->insertNOPs(MI, 3);
+        // "VALU writes SGPR" -> "SMRD reads that SGPR" needs 4 wait states
+        // ("S_NOP 3") on SI
+        TII->insertWaitStates(MI, 4);
         break;
       case AMDGPUSubtarget::SEA_ISLANDS:
         break;
       default: // VOLCANIC_ISLANDS and later
-        // "VALU writes SGPR -> VMEM reads that SGPR" needs "S_NOP 4" on VI
-        // and later. This also applies to VALUs which write VCC, but we're
-        // unlikely to see VMEM use VCC.
-        TII->insertNOPs(MI, 4);
+        // "VALU writes SGPR -> VMEM reads that SGPR" needs 5 wait states
+        // ("S_NOP 4") on VI and later. This also applies to VALUs which write
+        // VCC, but we're unlikely to see VMEM use VCC.
+        TII->insertWaitStates(MI, 5);
       }
 
       MI->eraseFromParent();