[DAGCombine] Do not remove masking argument to FP16_TO_FP for some targets

As of commit 284f2bffc9, the DAG Combiner gets rid of the masking of the
input to this node if the mask only keeps the bottom 16 bits. This is because
the underlying library function does not use the high order bits. However, on
PowerPC's ELFv2 ABI, it is the caller that is responsible for clearing the bits
from the register. Therefore, the library implementation of __gnu_h2f_ieee will
return an incorrect result if the bits aren't cleared.

This combine is desired for ARM (and possibly other targets) so this patch adds
a query to Target Lowering to check if this zeroing needs to be kept.

Fixes: https://bugs.llvm.org/show_bug.cgi?id=49092

Differential revision: https://reviews.llvm.org/D96283

llvm/include/llvm/CodeGen/TargetLowering.h

@@ -2789,6 +2789,10 @@ public:
     return false;
   }
 
+  /// Does this target require the clearing of high-order bits in a register
+  /// passed to the fp16 to fp conversion library function.
+  virtual bool shouldKeepZExtForFP16Conv() const { return false; }
+
   //===--------------------------------------------------------------------===//
   // Runtime Library hooks
   //

llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp

@@ -21182,7 +21182,7 @@ SDValue DAGCombiner::visitFP16_TO_FP(SDNode *N) {
   SDValue N0 = N->getOperand(0);
 
   // fold fp16_to_fp(op & 0xffff) -> fp16_to_fp(op)
-  if (N0->getOpcode() == ISD::AND) {
+  if (!TLI.shouldKeepZExtForFP16Conv() && N0->getOpcode() == ISD::AND) {
     ConstantSDNode *AndConst = getAsNonOpaqueConstant(N0.getOperand(1));
     if (AndConst && AndConst->getAPIntValue() == 0xffff) {
       return DAG.getNode(ISD::FP16_TO_FP, SDLoc(N), N->getValueType(0),

llvm/lib/Target/PowerPC/PPCISelLowering.h

@@ -987,6 +987,9 @@ namespace llvm {
     shouldExpandBuildVectorWithShuffles(EVT VT,
                                         unsigned DefinedValues) const override;
 
+    // Keep the zero-extensions for arguments to libcalls.
+    bool shouldKeepZExtForFP16Conv() const override { return true; }
+
     /// createFastISel - This method returns a target-specific FastISel object,
     /// or null if the target does not support "fast" instruction selection.
     FastISel *createFastISel(FunctionLoweringInfo &FuncInfo,

llvm/test/CodeGen/PowerPC/handle-f16-storage-type.ll

@@ -1156,6 +1156,7 @@ define float @test_sitofp_fadd_i32(i32 %a, half* %b) #0 {
 ; P8-NEXT:    xscvsxdsp f1, f0
 ; P8-NEXT:    bl __gnu_f2h_ieee
 ; P8-NEXT:    nop
+; P8-NEXT:    clrldi r3, r3, 48
 ; P8-NEXT:    bl __gnu_h2f_ieee
 ; P8-NEXT:    nop
 ; P8-NEXT:    xsaddsp f1, f31, f1
@@ -1175,6 +1176,7 @@ define float @test_sitofp_fadd_i32(i32 %a, half* %b) #0 {
 ; CHECK-NEXT:    xscvhpdp f0, f0
 ; CHECK-NEXT:    xscvdphp f1, f1
 ; CHECK-NEXT:    mffprwz r3, f1
+; CHECK-NEXT:    clrlwi r3, r3, 16
 ; CHECK-NEXT:    mtfprwz f1, r3
 ; CHECK-NEXT:    xscvhpdp f1, f1
 ; CHECK-NEXT:    xsaddsp f1, f0, f1
@@ -1225,6 +1227,7 @@ define half @PR40273(half) #0 {
 ; P8-NEXT:    stdu r1, -32(r1)
 ; P8-NEXT:    bl __gnu_f2h_ieee
 ; P8-NEXT:    nop
+; P8-NEXT:    clrldi r3, r3, 48
 ; P8-NEXT:    bl __gnu_h2f_ieee
 ; P8-NEXT:    nop
 ; P8-NEXT:    xxlxor f0, f0, f0
@@ -1245,6 +1248,7 @@ define half @PR40273(half) #0 {
 ; CHECK-NEXT:    xscvdphp f0, f1
 ; CHECK-NEXT:    xxlxor f1, f1, f1
 ; CHECK-NEXT:    mffprwz r3, f0
+; CHECK-NEXT:    clrlwi r3, r3, 16
 ; CHECK-NEXT:    mtfprwz f0, r3
 ; CHECK-NEXT:    xscvhpdp f0, f0
 ; CHECK-NEXT:    fcmpu cr0, f0, f1

llvm/test/CodeGen/PowerPC/pr48519.ll

@@ -22,6 +22,7 @@ define void @julia__typed_vcat_20() #0 {
 ; CHECK-NEXT:    xscvsxdsp f1, f0
 ; CHECK-NEXT:    bl __gnu_f2h_ieee
 ; CHECK-NEXT:    nop
+; CHECK-NEXT:    clrldi r3, r3, 48
 ; CHECK-NEXT:    bl __gnu_h2f_ieee
 ; CHECK-NEXT:    nop
 ; CHECK-NEXT:    addi r30, r30, -1
@@ -46,6 +47,7 @@ define void @julia__typed_vcat_20() #0 {
 ; CHECK-P9-NEXT:    xscvsxdsp f0, f0
 ; CHECK-P9-NEXT:    xscvdphp f0, f0
 ; CHECK-P9-NEXT:    mffprwz r3, f0
+; CHECK-P9-NEXT:    clrlwi r3, r3, 16
 ; CHECK-P9-NEXT:    mtfprwz f0, r3
 ; CHECK-P9-NEXT:    li r3, 0
 ; CHECK-P9-NEXT:    xscvhpdp f0, f0

llvm/test/CodeGen/PowerPC/pr49092.ll

@@ -0,0 +1,39 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mcpu=pwr8 -ppc-asm-full-reg-names -ppc-vsr-nums-as-vr \
+; RUN:   -mtriple=powerpc64le-unknown-unknown < %s | FileCheck %s
+; RUN: llc -mcpu=pwr9 -ppc-asm-full-reg-names -ppc-vsr-nums-as-vr \
+; RUN:   -mtriple=powerpc64le-unknown-unknown < %s | FileCheck %s \
+; RUN:   -check-prefix=CHECK-P9
+
+define dso_local half @test2(i64 %a, i64 %b) local_unnamed_addr #0 {
+; CHECK-LABEL: test2:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    mflr r0
+; CHECK-NEXT:    std r0, 16(r1)
+; CHECK-NEXT:    stdu r1, -32(r1)
+; CHECK-NEXT:    add r3, r4, r3
+; CHECK-NEXT:    addi r3, r3, 11
+; CHECK-NEXT:    clrlwi r3, r3, 16
+; CHECK-NEXT:    bl __gnu_h2f_ieee
+; CHECK-NEXT:    nop
+; CHECK-NEXT:    addi r1, r1, 32
+; CHECK-NEXT:    ld r0, 16(r1)
+; CHECK-NEXT:    mtlr r0
+; CHECK-NEXT:    blr
+;
+; CHECK-P9-LABEL: test2:
+; CHECK-P9:       # %bb.0: # %entry
+; CHECK-P9-NEXT:    add r3, r4, r3
+; CHECK-P9-NEXT:    addi r3, r3, 11
+; CHECK-P9-NEXT:    clrlwi r3, r3, 16
+; CHECK-P9-NEXT:    mtfprwz f0, r3
+; CHECK-P9-NEXT:    xscvhpdp f1, f0
+; CHECK-P9-NEXT:    blr
+entry:
+  %add = add i64 %b, %a
+  %0 = trunc i64 %add to i16
+  %conv = add i16 %0, 11
+  %call = bitcast i16 %conv to half
+  ret half %call
+}
+attributes #0 = { nounwind }