[NVPTX] Implement isTruncateFree and isZExtFree for i32/i64 Optimizations

llvm/lib/Target/NVPTX/NVPTXISelLowering.cpp

@@ -3340,6 +3340,29 @@ bool NVPTXTargetLowering::splitValueIntoRegisterParts(
   return false;
 }
 
+bool llvm::NVPTXTargetLowering::isTruncateFree(EVT FromVT, EVT ToVT) const {
+
+  if (!FromVT.isSimple() || !ToVT.isSimple()) {
+    return false;
+  }
+
+  return (FromVT.getSimpleVT() == MVT::i64 && ToVT.getSimpleVT() == MVT::i32);
+}
+
+bool llvm::NVPTXTargetLowering::isZExtFree(EVT FromVT, EVT ToVT) const {
+  if (!FromVT.isSimple() || !ToVT.isSimple()) {
+    return false;
+  }
+  return (FromVT.getSimpleVT() == MVT::i32 && ToVT.getSimpleVT() == MVT::i64);
+}
+
+bool llvm::NVPTXTargetLowering::isZExtFree(Type *SrcTy, Type *DstTy) const {
+  if (!SrcTy->isIntegerTy() || !DstTy->isIntegerTy())
+    return false;
+  return SrcTy->getPrimitiveSizeInBits() == 32 &&
+         DstTy->getPrimitiveSizeInBits() == 64;
+}
+
 // This creates target external symbol for a function parameter.
 // Name of the symbol is composed from its index and the function name.
 // Negative index corresponds to special parameter (unsized array) used for

llvm/lib/Target/NVPTX/NVPTXISelLowering.h

@@ -616,6 +616,10 @@ class NVPTXTargetLowering : public TargetLowering {
     return true;
   }
 
+  bool isTruncateFree(EVT FromVT, EVT ToVT) const override;
+  bool isZExtFree(EVT FromVT, EVT ToVT) const override;
+  bool isZExtFree(Type *SrcTy, Type *DstTy) const override;
+
 private:
   const NVPTXSubtarget &STI; // cache the subtarget here
   SDValue getParamSymbol(SelectionDAG &DAG, int idx, EVT) const;

llvm/test/CodeGen/NVPTX/truncate_zext.ll

@@ -0,0 +1,17 @@
+; RUN: llc -march=nvptx64 < %s | FileCheck %s
+
+; Test for truncation from i64 to i32
+define i32 @test_trunc_i64_to_i32(i64 %val) {
+  ; CHECK-LABEL: test_trunc_i64_to_i32
+  ; CHECK: trunc
+  %trunc = trunc i64 %val to i32
+  ret i32 %trunc
+}
+
+; Test for zero-extension from i32 to i64
+define i64 @test_zext_i32_to_i64(i32 %val) {
+  ; CHECK-LABEL: test_zext_i32_to_i64
+  ; CHECK: zext
+  %zext = zext i32 %val to i64
+  ret i64 %zext
+}