[X86][SSE] Vector integer/float conversion memory folding

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

diff --git a/lib/Target/R600/SIMachineFunctionInfo.cpp b/lib/Target/R600/SIMachineFunctionInfo.cpp
index ee0e30755f017ed7f8f773303ef701be76728fe7..d58f31db508638143302f3719a5722fae7ba51b6 100644 (file)
--- a/lib/Target/R600/SIMachineFunctionInfo.cpp
+++ b/lib/Target/R600/SIMachineFunctionInfo.cpp
@@ -10,9 +10,67 @@
 
 
 #include "SIMachineFunctionInfo.h"
+#include "AMDGPUSubtarget.h"
+#include "SIInstrInfo.h"
+#include "llvm/CodeGen/MachineInstrBuilder.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)
   : AMDGPUMachineFunction(MF),
-    PSInputAddr(0) { }
+    TIDReg(AMDGPU::NoRegister),
+    PSInputAddr(0),
+    NumUserSGPRs(0),
+    LDSWaveSpillSize(0) { }
+
+SIMachineFunctionInfo::SpilledReg SIMachineFunctionInfo::getSpilledReg(
+                                                       MachineFunction *MF,
+                                                       unsigned FrameIndex,
+                                                       unsigned SubIdx) {
+  const MachineFrameInfo *FrameInfo = MF->getFrameInfo();
+  const SIRegisterInfo *TRI = static_cast<const SIRegisterInfo*>(
+      MF->getTarget().getSubtarget<AMDGPUSubtarget>().getRegisterInfo());
+  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 = TRI->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;
+}
+
+unsigned SIMachineFunctionInfo::getMaximumWorkGroupSize(
+                                              const MachineFunction &MF) const {
+  const AMDGPUSubtarget &ST = MF.getTarget().getSubtarget<AMDGPUSubtarget>();
+  // FIXME: We should get this information from kernel attributes if it
+  // is available.
+  return getShaderType() == ShaderType::COMPUTE ? 256 : ST.getWavefrontSize();
+}