[NVPTX] Add lowering of i128 params.

The patch adds support of i128 params lowering. The changes are quite trivial to
support i128 as a "special case" of integer type. With this patch, we lower i128
params the same way as aggregates of size 16 bytes: .param .b8 _ [16].

Currently, NVPTX can't deal with the 128 bit integers:
* in some cases because of failed assertions like
  ValVTs.size() == OutVals.size() && "Bad return value decomposition"
* in other cases emitting PTX with .i128 or .u128 types (which are not valid [1])
  [1] http://docs.nvidia.com/cuda/parallel-thread-execution/index.html#fundamental-types

Differential Revision: https://reviews.llvm.org/D34555
Patch by: Denys Zariaiev (denys.zariaiev@gmail.com)

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@308675 91177308-0d34-0410-b5e6-96231b3b80d8

3 files changed, 32 insertions, 11 deletions

diff --git a/lib/Target/NVPTX/NVPTXAsmPrinter.cpp b/lib/Target/NVPTX/NVPTXAsmPrinter.cpp
index 0139646fc3f..82634cf0298 100644
--- a/lib/Target/NVPTX/NVPTXAsmPrinter.cpp
+++ b/lib/Target/NVPTX/NVPTXAsmPrinter.cpp
@@ -400,7 +400,7 @@ void NVPTXAsmPrinter::printReturnValStr(const Function *F, raw_ostream &O) {
   O << " (";
 
   if (isABI) {
-    if (Ty->isFloatingPointTy() || Ty->isIntegerTy()) {
+    if (Ty->isFloatingPointTy() || (Ty->isIntegerTy() && !Ty->isIntegerTy(128))) {
       unsigned size = 0;
       if (auto *ITy = dyn_cast<IntegerType>(Ty)) {
         size = ITy->getBitWidth();
@@ -418,7 +418,7 @@ void NVPTXAsmPrinter::printReturnValStr(const Function *F, raw_ostream &O) {
     } else if (isa<PointerType>(Ty)) {
       O << ".param .b" << TLI->getPointerTy(DL).getSizeInBits()
         << " func_retval0";
-    } else if (Ty->isAggregateType() || Ty->isVectorTy()) {
+    } else if (Ty->isAggregateType() || Ty->isVectorTy() || Ty->isIntegerTy(128)) {
       unsigned totalsz = DL.getTypeAllocSize(Ty);
       unsigned retAlignment = 0;
       if (!getAlign(*F, 0, retAlignment))
@@ -1425,6 +1425,14 @@ void NVPTXAsmPrinter::emitPTXGlobalVariable(const GlobalVariable *GVar,
   else
     O << " .align " << GVar->getAlignment();
 
+  // Special case for i128
+  if (ETy->isIntegerTy(128)) {
+    O << " .b8 ";
+    getSymbol(GVar)->print(O, MAI);
+    O << "[16]";
+    return;
+  }
+
   if (ETy->isFloatingPointTy() || ETy->isIntegerTy() || ETy->isPointerTy()) {
     O << " .";
     O << getPTXFundamentalTypeStr(ETy);
@@ -1551,7 +1559,7 @@ void NVPTXAsmPrinter::emitFunctionParamList(const Function *F, raw_ostream &O) {
     }
 
     if (!PAL.hasParamAttribute(paramIndex, Attribute::ByVal)) {
-      if (Ty->isAggregateType() || Ty->isVectorTy()) {
+      if (Ty->isAggregateType() || Ty->isVectorTy() || Ty->isIntegerTy(128)) {
         // Just print .param .align <a> .b8 .param[size];
         // <a> = PAL.getparamalignment
         // size = typeallocsize of element type
diff --git a/lib/Target/NVPTX/NVPTXISelLowering.cpp b/lib/Target/NVPTX/NVPTXISelLowering.cpp
index 9070b628f12..d939fe5c09b 100644
--- a/lib/Target/NVPTX/NVPTXISelLowering.cpp
+++ b/lib/Target/NVPTX/NVPTXISelLowering.cpp
@@ -168,6 +168,19 @@ static void ComputePTXValueVTs(const TargetLowering &TLI, const DataLayout &DL,
   SmallVector<EVT, 16> TempVTs;
   SmallVector<uint64_t, 16> TempOffsets;
 
+  // Special case for i128 - decompose to (i64, i64)
+  if (Ty->isIntegerTy(128)) {
+    ValueVTs.push_back(EVT(MVT::i64));
+    ValueVTs.push_back(EVT(MVT::i64));
+
+    if (Offsets) {
+      Offsets->push_back(StartingOffset + 0);
+      Offsets->push_back(StartingOffset + 8);
+    }
+
+    return;
+  }
+
   ComputeValueVTs(TLI, DL, Ty, TempVTs, &TempOffsets, StartingOffset);
   for (unsigned i = 0, e = TempVTs.size(); i != e; ++i) {
     EVT VT = TempVTs[i];
@@ -1262,7 +1275,7 @@ std::string NVPTXTargetLowering::getPrototype(
     O << "()";
   } else {
     O << "(";
-    if (retTy->isFloatingPointTy() || retTy->isIntegerTy()) {
+    if (retTy->isFloatingPointTy() || (retTy->isIntegerTy() && !retTy->isIntegerTy(128))) {
       unsigned size = 0;
       if (auto *ITy = dyn_cast<IntegerType>(retTy)) {
         size = ITy->getBitWidth();
@@ -1280,7 +1293,7 @@ std::string NVPTXTargetLowering::getPrototype(
       O << ".param .b" << size << " _";
     } else if (isa<PointerType>(retTy)) {
       O << ".param .b" << PtrVT.getSizeInBits() << " _";
-    } else if (retTy->isAggregateType() || retTy->isVectorTy()) {
+    } else if (retTy->isAggregateType() || retTy->isVectorTy() || retTy->isIntegerTy(128)) {
       auto &DL = CS->getCalledFunction()->getParent()->getDataLayout();
       O << ".param .align " << retAlignment << " .b8 _["
         << DL.getTypeAllocSize(retTy) << "]";
@@ -1302,7 +1315,7 @@ std::string NVPTXTargetLowering::getPrototype(
     first = false;
 
     if (!Outs[OIdx].Flags.isByVal()) {
-      if (Ty->isAggregateType() || Ty->isVectorTy()) {
+      if (Ty->isAggregateType() || Ty->isVectorTy() || Ty->isIntegerTy(128)) {
         unsigned align = 0;
         const CallInst *CallI = cast<CallInst>(CS->getInstruction());
         // +1 because index 0 is reserved for return type alignment
@@ -1458,7 +1471,7 @@ SDValue NVPTXTargetLowering::LowerCall(TargetLowering::CallLoweringInfo &CLI,
       unsigned AllocSize = DL.getTypeAllocSize(Ty);
       SDVTList DeclareParamVTs = DAG.getVTList(MVT::Other, MVT::Glue);
       bool NeedAlign; // Does argument declaration specify alignment?
-      if (Ty->isAggregateType() || Ty->isVectorTy()) {
+      if (Ty->isAggregateType() || Ty->isVectorTy() || Ty->isIntegerTy(128)) {
         // declare .param .align <align> .b8 .param<n>[<size>];
         SDValue DeclareParamOps[] = {
             Chain, DAG.getConstant(ArgAlign, dl, MVT::i32),
@@ -1634,8 +1647,8 @@ SDValue NVPTXTargetLowering::LowerCall(TargetLowering::CallLoweringInfo &CLI,
     // these three types to match the logic in
     // NVPTXAsmPrinter::printReturnValStr and NVPTXTargetLowering::getPrototype.
     // Plus, this behavior is consistent with nvcc's.
-    if (RetTy->isFloatingPointTy() || RetTy->isIntegerTy() ||
-        RetTy->isPointerTy()) {
+    if (RetTy->isFloatingPointTy() || RetTy->isPointerTy() ||
+        (RetTy->isIntegerTy() && !RetTy->isIntegerTy(128))) {
       // Scalar needs to be at least 32bit wide
       if (resultsz < 32)
         resultsz = 32;
@@ -2366,7 +2379,7 @@ SDValue NVPTXTargetLowering::LowerFormalArguments(
 
     if (theArgs[i]->use_empty()) {
       // argument is dead
-      if (Ty->isAggregateType()) {
+      if (Ty->isAggregateType() || Ty->isIntegerTy(128)) {
         SmallVector<EVT, 16> vtparts;
 
         ComputePTXValueVTs(*this, DAG.getDataLayout(), Ty, vtparts);
diff --git a/lib/Target/NVPTX/NVPTXTargetMachine.cpp b/lib/Target/NVPTX/NVPTXTargetMachine.cpp
index 2b6ba8c85d4..ac21563ee9a 100644
--- a/lib/Target/NVPTX/NVPTXTargetMachine.cpp
+++ b/lib/Target/NVPTX/NVPTXTargetMachine.cpp
@@ -81,7 +81,7 @@ static std::string computeDataLayout(bool is64Bit) {
   if (!is64Bit)
     Ret += "-p:32:32";
 
-  Ret += "-i64:64-v16:16-v32:32-n16:32:64";
+  Ret += "-i64:64-i128:128-v16:16-v32:32-n16:32:64";
 
   return Ret;
 }