[x86] Fix an embarressing bug in the INSERTPS formation code. The mask

[oota-llvm.git] / lib / Target / R600 / SIMachineFunctionInfo.cpp

diff --git a/lib/Target/R600/SIMachineFunctionInfo.cpp b/lib/Target/R600/SIMachineFunctionInfo.cpp
index 7e59b4274968f9ad77778fba823ca1f93e288786..b97820383121cfad9fc9d711723530c20066b85d 100644 (file)
--- a/lib/Target/R600/SIMachineFunctionInfo.cpp
+++ b/lib/Target/R600/SIMachineFunctionInfo.cpp
@@ -10,11 +10,69 @@
 
 
 #include "SIMachineFunctionInfo.h"
+#include "SIInstrInfo.h"
+#include "SIRegisterInfo.h"
+#include "llvm/CodeGen/MachineFrameInfo.h"
+#include "llvm/CodeGen/MachineRegisterInfo.h"
+#include "llvm/IR/Function.h"
+#include "llvm/IR/LLVMContext.h"
+
+#define MAX_LANES 64
 
 using namespace llvm;
 
+
+// Pin the vtable to this file.
+void SIMachineFunctionInfo::anchor() {}
+
 SIMachineFunctionInfo::SIMachineFunctionInfo(const MachineFunction &MF)
-  : MachineFunctionInfo(),
-    SPIPSInputAddr(0),
-    ShaderType(0)
-  { }
+  : AMDGPUMachineFunction(MF),
+    PSInputAddr(0),
+    NumUserSGPRs(0) { }
+
+/// \brief Returns a register that is not used at any point in the function.
+///        If all registers are used, then this function will return
+//         AMDGPU::NoRegister.
+static unsigned findUnusedVGPR(const MachineRegisterInfo &MRI) {
+
+  const TargetRegisterClass *RC = &AMDGPU::VGPR_32RegClass;
+
+  for (TargetRegisterClass::iterator I = RC->begin(), E = RC->end();
+       I != E; ++I) {
+    if (!MRI.isPhysRegUsed(*I))
+      return *I;
+  }
+  return AMDGPU::NoRegister;
+}
+
+SIMachineFunctionInfo::SpilledReg SIMachineFunctionInfo::getSpilledReg(
+                                                       MachineFunction *MF,
+                                                       unsigned FrameIndex,
+                                                       unsigned SubIdx) {
+  const MachineFrameInfo *FrameInfo = MF->getFrameInfo();
+  MachineRegisterInfo &MRI = MF->getRegInfo();
+  int64_t Offset = FrameInfo->getObjectOffset(FrameIndex);
+  Offset += SubIdx * 4;
+
+  unsigned LaneVGPRIdx = Offset / (64 * 4);
+  unsigned Lane = (Offset / 4) % 64;
+
+  struct SpilledReg Spill;
+
+  if (!LaneVGPRs.count(LaneVGPRIdx)) {
+    unsigned LaneVGPR = findUnusedVGPR(MRI);
+    LaneVGPRs[LaneVGPRIdx] = LaneVGPR;
+    MRI.setPhysRegUsed(LaneVGPR);
+
+    // Add this register as live-in to all blocks to avoid machine verifer
+    // complaining about use of an undefined physical register.
+    for (MachineFunction::iterator BI = MF->begin(), BE = MF->end();
+         BI != BE; ++BI) {
+      BI->addLiveIn(LaneVGPR);
+    }
+  }
+
+  Spill.VGPR = LaneVGPRs[LaneVGPRIdx];
+  Spill.Lane = Lane;
+  return Spill;
+}