Index: lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
===================================================================
--- lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
+++ lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
@@ -29,15 +29,27 @@
 
 #define DEBUG_TYPE "AMDGPUtti"
 
+static cl::opt<unsigned> UnrollThreshold(
+  "amdgpu-unroll-threshold",
+  cl::desc("Unroll threshold for AMDGPU"),
+  cl::init(300), cl::Hidden); // Twice the default.
+
+static cl::opt<unsigned> UnrollThresholdPrivate(
+  "amdgpu-unroll-threshold-private",
+  cl::desc("Unroll threshold for AMDGPU if private memory used in a loop"),
+  cl::init(800), cl::Hidden);
+
 
 void AMDGPUTTIImpl::getUnrollingPreferences(Loop *L,
                                             TTI::UnrollingPreferences &UP) {
-  UP.Threshold = 300; // Twice the default.
+  UP.Threshold = UnrollThreshold;
   UP.MaxCount = UINT_MAX;
   UP.Partial = true;
 
   // TODO: Do we want runtime unrolling?
 
+  // Maximum alloca size than can fit registers. Reserve 16 registers.
+  const unsigned MaxAlloca = (getNumberOfRegisters(false) - 16) * 4;
   for (const BasicBlock *BB : L->getBlocks()) {
     const DataLayout &DL = BB->getModule()->getDataLayout();
     for (const Instruction &I : *BB) {
@@ -49,6 +61,13 @@
       const AllocaInst *Alloca =
           dyn_cast<AllocaInst>(GetUnderlyingObject(Ptr, DL));
       if (Alloca) {
+        if (L->hasLoopInvariantOperands(GEP))
+          continue;
+        Type *Ty = Alloca->getAllocatedType();
+        unsigned AllocaSize = Ty->isSized() ? DL.getTypeAllocSize(Ty) : 0;
+        if (AllocaSize > MaxAlloca)
+          continue;
+
         // We want to do whatever we can to limit the number of alloca
         // instructions that make it through to the code generator.  allocas
         // require us to use indirect addressing, which is slow and prone to
@@ -59,7 +78,8 @@
         //
         // Don't use the maximum allowed value here as it will make some
         // programs way too big.
-        UP.Threshold = 800;
+        UP.Threshold = UnrollThresholdPrivate;
+        return;
       }
     }
   }
@@ -70,8 +90,10 @@
     return 0;
 
   // Number of VGPRs on SI.
-  if (ST->getGeneration() >= AMDGPUSubtarget::SOUTHERN_ISLANDS)
+  if (ST->getGeneration() >= AMDGPUSubtarget::VOLCANIC_ISLANDS)
     return 256;
+  else if (ST->getGeneration() >= AMDGPUSubtarget::SOUTHERN_ISLANDS)
+    return 128;
 
   return 4 * 128; // XXX - 4 channels. Should these count as vector instead?
 }