AMDGPU: Don't unroll for private with dynamic allocas

[arsenm]

Summary

This won't be elimnated, so this will just bloat code
if/when these are ever used/supported.

[rampitec]

LGTM.

[arsenm]

r294030

lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp

for (const BasicBlock *BB : L->getBlocks()) {
     for (const Instruction &I : *BB) {
       const GetElementPtrInst *GEP = dyn_cast<GetElementPtrInst>(&I);
       if (!GEP || GEP->getAddressSpace() != AMDGPUAS::PRIVATE_ADDRESS)
         continue;
 
       const Value *Ptr = GEP->getPointerOperand();
       const AllocaInst *Alloca =
           dyn_cast<AllocaInst>(GetUnderlyingObject(Ptr, DL));
-      if (Alloca) {
+      if (Alloca && Alloca->isStaticAlloca()) {
         Type *Ty = Alloca->getAllocatedType();
         unsigned AllocaSize = Ty->isSized() ? DL.getTypeAllocSize(Ty) : 0;
         if (AllocaSize > MaxAlloca)
           continue;
 
         // Check if GEP depends on a value defined by this loop itself.
         bool HasLoopDef = false;
         for (const Value *Op : GEP->operands()) {

test/Transforms/LoopUnroll/AMDGPU/unroll-for-private.ll

for.body:                                         ; preds = %for.body, %entry
   %rem = srem i32 %add, 64
   %arrayidx3 = getelementptr inbounds [256 x i32], [256 x i32]* %arr, i32 0, i32 %rem
   store i32 %tmp16, i32* %arrayidx3, align 4
   %inc = add nuw nsw i32 %i.015, 1
   %exitcond = icmp eq i32 %inc, 100
   br i1 %exitcond, label %for.cond.cleanup, label %for.body
 }
 
+; Check we do not enforce unroll if alloca is dynamic
+; CHECK-LABEL: @dynamic_size_alloca(
+; CHECK: alloca i32, i32 %n
+; CHECK:       for.body:
+; CHECK:       icmp eq i32 %{{.*}}, 100
+; CHECK:       br
+
+define void @dynamic_size_alloca(i32 addrspace(1)* nocapture %a, i32 %n, i32 %x) {
+entry:
+  %arr = alloca i32, i32 %n, align 4
+  %tmp1 = tail call i32 @llvm.amdgcn.workitem.id.x() #1
+  br label %for.body
+
+for.cond.cleanup:                                 ; preds = %for.body
+  %arrayidx5 = getelementptr inbounds i32, i32* %arr, i32 %x
+  %tmp15 = load i32, i32* %arrayidx5, align 4
+  %arrayidx7 = getelementptr inbounds i32, i32 addrspace(1)* %a, i32 %tmp1
+  store i32 %tmp15, i32 addrspace(1)* %arrayidx7, align 4
+  ret void
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.015 = phi i32 [ 0, %entry ], [ %inc, %for.body ]
+  %idxprom = sext i32 %i.015 to i64
+  %arrayidx = getelementptr inbounds i32, i32 addrspace(1)* %a, i64 %idxprom
+  %tmp16 = load i32, i32 addrspace(1)* %arrayidx, align 4
+  %add = add nsw i32 %i.015, %tmp1
+  %rem = srem i32 %add, 64
+  %arrayidx3 = getelementptr inbounds i32, i32* %arr, i32 %rem
+  store i32 %tmp16, i32* %arrayidx3, align 4
+  %inc = add nuw nsw i32 %i.015, 1
+  %exitcond = icmp eq i32 %inc, 100
+  br i1 %exitcond, label %for.cond.cleanup, label %for.body
+}
+
 declare i8 addrspace(2)* @llvm.amdgcn.dispatch.ptr() #1
 
 declare i32 @llvm.amdgcn.workitem.id.x() #1
 
 declare i32 @llvm.amdgcn.workgroup.id.x() #1
 
 declare i8 addrspace(2)* @llvm.amdgcn.implicitarg.ptr() #1
 
 attributes #1 = { nounwind readnone }