[AArch64] Fixes for ARMv8.2-A FP16 scalar intrinsic

[az]

Summary

A couple of fixes on top of https://reviews.llvm.org/D41792:

• Fixes for freceprical, and fsqrt instructions in the backend.
• The intrinsics that generate builtin calls with i16 data types fails in instruction selection. In a preparation for future fixes in the backend for these, the code generated by the frontend is modified. For example, a builtin that returns i16 is implemented by returning i32 that is truncated to i16. This is done similar to other non-fp16 intrinsics that produces i16 data types.
• Fix frontend code generated for abs.

[SjoerdMeijer]

Thanks for fixing this. Looks very reasonable to me.

Question about the failures: I am now wondering if this means we were and still
are missing tests?

Nit: for future reviews, I think it is better to split patches up if they are commits to
different repos.

[az]

Question about the failures: I am now wondering if this means we were and still are missing tests?

Given that this work is fixing D41792 which is mainly about adding frontend intrinsic support, then there is a test for each intrinsic and I am updating the tests for the intrinsics with code generation changes (they only test the frontend). As we previously discussed it, there is some work to be done in instruction selection in order to generate good IR for some intrinisics and the ones with problems need new tests. In this patch, I am fixing few simple ones that fall into that category (see AArch64InstrInfo.td) and I agree that I should have separated this patch into clang and llvm patches instead of just one. I am adding tests for those in this revision.

[SjoerdMeijer]

Thanks

[az]

Committed as r324940 and r324912

clang/lib/CodeGen/CGBuiltin.cpp

static const NeonIntrinsicInfo AArch64SISDIntrinsicMap[] = {
   NEONMAP1(vsrid_n_s64, aarch64_neon_vsri, Vectorize1ArgType),
   NEONMAP1(vsrid_n_u64, aarch64_neon_vsri, Vectorize1ArgType),
   NEONMAP1(vuqaddb_s8, aarch64_neon_suqadd, Vectorize1ArgType | Use64BitVectors),
   NEONMAP1(vuqaddd_s64, aarch64_neon_suqadd, Add1ArgType),
   NEONMAP1(vuqaddh_s16, aarch64_neon_suqadd, Vectorize1ArgType | Use64BitVectors),
   NEONMAP1(vuqadds_s32, aarch64_neon_suqadd, Add1ArgType),
   // FP16 scalar intrinisics go here.
   NEONMAP1(vabdh_f16, aarch64_sisd_fabd, Add1ArgType),
-  NEONMAP1(vabsh_f16, aarch64_neon_abs, Add1ArgType),
-  NEONMAP1(vcageh_f16, aarch64_neon_facge, AddRetType | Add1ArgType),
-  NEONMAP1(vcagth_f16, aarch64_neon_facgt, AddRetType | Add1ArgType),
-  NEONMAP1(vcaleh_f16, aarch64_neon_facge, AddRetType | Add1ArgType),
-  NEONMAP1(vcalth_f16, aarch64_neon_facgt, AddRetType | Add1ArgType),
-  NEONMAP1(vcvtah_s16_f16, aarch64_neon_fcvtas, AddRetType | Add1ArgType),
   NEONMAP1(vcvtah_s32_f16, aarch64_neon_fcvtas, AddRetType | Add1ArgType),
   NEONMAP1(vcvtah_s64_f16, aarch64_neon_fcvtas, AddRetType | Add1ArgType),
-  NEONMAP1(vcvtah_u16_f16, aarch64_neon_fcvtau, AddRetType | Add1ArgType),
   NEONMAP1(vcvtah_u32_f16, aarch64_neon_fcvtau, AddRetType | Add1ArgType),
   NEONMAP1(vcvtah_u64_f16, aarch64_neon_fcvtau, AddRetType | Add1ArgType),
-  NEONMAP1(vcvth_n_f16_s16, aarch64_neon_vcvtfxs2fp, AddRetType | Add1ArgType),
   NEONMAP1(vcvth_n_f16_s32, aarch64_neon_vcvtfxs2fp, AddRetType | Add1ArgType),
   NEONMAP1(vcvth_n_f16_s64, aarch64_neon_vcvtfxs2fp, AddRetType | Add1ArgType),
-  NEONMAP1(vcvth_n_f16_u16, aarch64_neon_vcvtfxu2fp, AddRetType | Add1ArgType),
   NEONMAP1(vcvth_n_f16_u32, aarch64_neon_vcvtfxu2fp, AddRetType | Add1ArgType),
   NEONMAP1(vcvth_n_f16_u64, aarch64_neon_vcvtfxu2fp, AddRetType | Add1ArgType),
-  NEONMAP1(vcvth_n_s16_f16, aarch64_neon_vcvtfp2fxs, AddRetType | Add1ArgType),
   NEONMAP1(vcvth_n_s32_f16, aarch64_neon_vcvtfp2fxs, AddRetType | Add1ArgType),
   NEONMAP1(vcvth_n_s64_f16, aarch64_neon_vcvtfp2fxs, AddRetType | Add1ArgType),
-  NEONMAP1(vcvth_n_u16_f16, aarch64_neon_vcvtfp2fxu, AddRetType | Add1ArgType),
   NEONMAP1(vcvth_n_u32_f16, aarch64_neon_vcvtfp2fxu, AddRetType | Add1ArgType),
   NEONMAP1(vcvth_n_u64_f16, aarch64_neon_vcvtfp2fxu, AddRetType | Add1ArgType),
-  NEONMAP1(vcvtmh_s16_f16, aarch64_neon_fcvtms, AddRetType | Add1ArgType),
   NEONMAP1(vcvtmh_s32_f16, aarch64_neon_fcvtms, AddRetType | Add1ArgType),
   NEONMAP1(vcvtmh_s64_f16, aarch64_neon_fcvtms, AddRetType | Add1ArgType),
-  NEONMAP1(vcvtmh_u16_f16, aarch64_neon_fcvtmu, AddRetType | Add1ArgType),
   NEONMAP1(vcvtmh_u32_f16, aarch64_neon_fcvtmu, AddRetType | Add1ArgType),
   NEONMAP1(vcvtmh_u64_f16, aarch64_neon_fcvtmu, AddRetType | Add1ArgType),
-  NEONMAP1(vcvtnh_s16_f16, aarch64_neon_fcvtns, AddRetType | Add1ArgType),
   NEONMAP1(vcvtnh_s32_f16, aarch64_neon_fcvtns, AddRetType | Add1ArgType),
   NEONMAP1(vcvtnh_s64_f16, aarch64_neon_fcvtns, AddRetType | Add1ArgType),
-  NEONMAP1(vcvtnh_u16_f16, aarch64_neon_fcvtnu, AddRetType | Add1ArgType),
   NEONMAP1(vcvtnh_u32_f16, aarch64_neon_fcvtnu, AddRetType | Add1ArgType),
   NEONMAP1(vcvtnh_u64_f16, aarch64_neon_fcvtnu, AddRetType | Add1ArgType),
-  NEONMAP1(vcvtph_s16_f16, aarch64_neon_fcvtps, AddRetType | Add1ArgType),
   NEONMAP1(vcvtph_s32_f16, aarch64_neon_fcvtps, AddRetType | Add1ArgType),
   NEONMAP1(vcvtph_s64_f16, aarch64_neon_fcvtps, AddRetType | Add1ArgType),
-  NEONMAP1(vcvtph_u16_f16, aarch64_neon_fcvtpu, AddRetType | Add1ArgType),
   NEONMAP1(vcvtph_u32_f16, aarch64_neon_fcvtpu, AddRetType | Add1ArgType),
   NEONMAP1(vcvtph_u64_f16, aarch64_neon_fcvtpu, AddRetType | Add1ArgType),
   NEONMAP1(vmulxh_f16, aarch64_neon_fmulx, Add1ArgType),
   NEONMAP1(vrecpeh_f16, aarch64_neon_frecpe, Add1ArgType),
   NEONMAP1(vrecpxh_f16, aarch64_neon_frecpx, Add1ArgType),
   NEONMAP1(vrsqrteh_f16, aarch64_neon_frsqrte, Add1ArgType),
   NEONMAP1(vrsqrtsh_f16, aarch64_neon_frsqrts, Add1ArgType),
 };
if (Arg->isIntegerConstantExpr(Result, getContext()))
     Type = NeonTypeFlags(Result.getZExtValue());
 
   bool usgn = Type.isUnsigned();
   bool quad = Type.isQuad();
 
   // Handle non-overloaded intrinsics first.
   switch (BuiltinID) {
   default: break;
+  case NEON::BI__builtin_neon_vabsh_f16:
+    Ops.push_back(EmitScalarExpr(E->getArg(0)));
+    return EmitNeonCall(CGM.getIntrinsic(Intrinsic::fabs, HalfTy), Ops, "vabs");
   case NEON::BI__builtin_neon_vldrq_p128: {
     llvm::Type *Int128Ty = llvm::Type::getIntNTy(getLLVMContext(), 128);
     llvm::Type *Int128PTy = llvm::PointerType::get(Int128Ty, 0);
     Value *Ptr = Builder.CreateBitCast(EmitScalarExpr(E->getArg(0)), Int128PTy);
     return Builder.CreateAlignedLoad(Int128Ty, Ptr,
                                      CharUnits::fromQuantity(16));
   }
   case NEON::BI__builtin_neon_vstrq_p128: {
case NEON::BI__builtin_neon_vcvth_u64_f16:
     // FALL THROUGH
   case NEON::BI__builtin_neon_vcvth_s64_f16: {
     Ops.push_back(EmitScalarExpr(E->getArg(0)));
     Ops[0] = Builder.CreateBitCast(Ops[0], HalfTy);
     if (usgn)
       return Builder.CreateFPToUI(Ops[0], Int64Ty);
     return Builder.CreateFPToSI(Ops[0], Int64Ty);
   }
+  case NEON::BI__builtin_neon_vcvtah_u16_f16:
+  case NEON::BI__builtin_neon_vcvtmh_u16_f16:
+  case NEON::BI__builtin_neon_vcvtnh_u16_f16:
+  case NEON::BI__builtin_neon_vcvtph_u16_f16:
+  case NEON::BI__builtin_neon_vcvtah_s16_f16:
+  case NEON::BI__builtin_neon_vcvtmh_s16_f16:
+  case NEON::BI__builtin_neon_vcvtnh_s16_f16:
+  case NEON::BI__builtin_neon_vcvtph_s16_f16: {
+    unsigned Int;
+    llvm::Type* InTy = Int32Ty;
+    llvm::Type* FTy  = HalfTy;
+    llvm::Type *Tys[2] = {InTy, FTy};
+    Ops.push_back(EmitScalarExpr(E->getArg(0)));
+    switch (BuiltinID) {
+    default: llvm_unreachable("missing builtin ID in switch!");
+    case NEON::BI__builtin_neon_vcvtah_u16_f16:
+      Int = Intrinsic::aarch64_neon_fcvtau; break;
+    case NEON::BI__builtin_neon_vcvtmh_u16_f16:
+      Int = Intrinsic::aarch64_neon_fcvtmu; break;
+    case NEON::BI__builtin_neon_vcvtnh_u16_f16:
+      Int = Intrinsic::aarch64_neon_fcvtnu; break;
+    case NEON::BI__builtin_neon_vcvtph_u16_f16:
+      Int = Intrinsic::aarch64_neon_fcvtpu; break;
+    case NEON::BI__builtin_neon_vcvtah_s16_f16:
+      Int = Intrinsic::aarch64_neon_fcvtas; break;
+    case NEON::BI__builtin_neon_vcvtmh_s16_f16:
+      Int = Intrinsic::aarch64_neon_fcvtms; break;
+    case NEON::BI__builtin_neon_vcvtnh_s16_f16:
+      Int = Intrinsic::aarch64_neon_fcvtns; break;
+    case NEON::BI__builtin_neon_vcvtph_s16_f16:
+      Int = Intrinsic::aarch64_neon_fcvtps; break;
+    }
+    Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "fcvt");
+    return Builder.CreateTrunc(Ops[0], Int16Ty);
+  }
+  case NEON::BI__builtin_neon_vcaleh_f16:
+  case NEON::BI__builtin_neon_vcalth_f16:
+  case NEON::BI__builtin_neon_vcageh_f16:
+  case NEON::BI__builtin_neon_vcagth_f16: {
+    unsigned Int;
+    llvm::Type* InTy = Int32Ty;
+    llvm::Type* FTy  = HalfTy;
+    llvm::Type *Tys[2] = {InTy, FTy};
+    Ops.push_back(EmitScalarExpr(E->getArg(1)));
+    switch (BuiltinID) {
+    default: llvm_unreachable("missing builtin ID in switch!");
+    case NEON::BI__builtin_neon_vcageh_f16:
+      Int = Intrinsic::aarch64_neon_facge; break;
+    case NEON::BI__builtin_neon_vcagth_f16:
+      Int = Intrinsic::aarch64_neon_facgt; break;
+    case NEON::BI__builtin_neon_vcaleh_f16:
+      Int = Intrinsic::aarch64_neon_facge; std::swap(Ops[0], Ops[1]); break;
+    case NEON::BI__builtin_neon_vcalth_f16:
+      Int = Intrinsic::aarch64_neon_facgt; std::swap(Ops[0], Ops[1]); break;
+    }
+    Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "facg");
+    return Builder.CreateTrunc(Ops[0], Int16Ty);
+  }
+  case NEON::BI__builtin_neon_vcvth_n_s16_f16:
+  case NEON::BI__builtin_neon_vcvth_n_u16_f16: {
+    unsigned Int;
+    llvm::Type* InTy = Int32Ty;
+    llvm::Type* FTy  = HalfTy;
+    llvm::Type *Tys[2] = {InTy, FTy};
+    Ops.push_back(EmitScalarExpr(E->getArg(1)));
+    switch (BuiltinID) {
+    default: llvm_unreachable("missing builtin ID in switch!");
+    case NEON::BI__builtin_neon_vcvth_n_s16_f16:
+      Int = Intrinsic::aarch64_neon_vcvtfp2fxs; break;
+    case NEON::BI__builtin_neon_vcvth_n_u16_f16:
+      Int = Intrinsic::aarch64_neon_vcvtfp2fxu; break;
+    }
+    Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "fcvth_n");
+    return Builder.CreateTrunc(Ops[0], Int16Ty);
+  }
+  case NEON::BI__builtin_neon_vcvth_n_f16_s16:
+  case NEON::BI__builtin_neon_vcvth_n_f16_u16: {
+    unsigned Int;
+    llvm::Type* FTy  = HalfTy;
+    llvm::Type* InTy = Int32Ty;
+    llvm::Type *Tys[2] = {FTy, InTy};
+    Ops.push_back(EmitScalarExpr(E->getArg(1)));
+    switch (BuiltinID) {
+    default: llvm_unreachable("missing builtin ID in switch!");
+    case NEON::BI__builtin_neon_vcvth_n_f16_s16:
+      Int = Intrinsic::aarch64_neon_vcvtfxs2fp;
+      Ops[0] = Builder.CreateSExt(Ops[0], InTy, "sext");
+      break;
+    case NEON::BI__builtin_neon_vcvth_n_f16_u16:
+      Int = Intrinsic::aarch64_neon_vcvtfxu2fp;
+      Ops[0] = Builder.CreateZExt(Ops[0], InTy);
+      break;
+    }
+    return EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "fcvth_n");
+  }
   case NEON::BI__builtin_neon_vpaddd_s64: {
     llvm::Type *Ty = llvm::VectorType::get(Int64Ty, 2);
     Value *Vec = EmitScalarExpr(E->getArg(0));
     // The vector is v2f64, so make sure it's bitcast to that.
     Vec = Builder.CreateBitCast(Vec, Ty, "v2i64");
     llvm::Value *Idx0 = llvm::ConstantInt::get(SizeTy, 0);
     llvm::Value *Idx1 = llvm::ConstantInt::get(SizeTy, 1);
     Value *Op0 = Builder.CreateExtractElement(Vec, Idx0, "lane0");

clang/test/CodeGen/aarch64-v8.2a-fp16-intrinsics.c

 // RUN: %clang_cc1 -triple arm64-none-linux-gnu -target-feature +fullfp16\
 // RUN: -fallow-half-arguments-and-returns -S -disable-O0-optnone -emit-llvm -o - %s \
 // RUN: | opt -S -mem2reg \
 // RUN: | FileCheck %s
 
 // REQUIRES: aarch64-registered-target
 
 #include <arm_fp16.h>
 
 // CHECK-LABEL: test_vabsh_f16
-// CHECK:  [[ABS:%.*]] =  call half @llvm.aarch64.neon.abs.f16(half %a)
+// CHECK:  [[ABS:%.*]] =  call half @llvm.fabs.f16(half %a)
 // CHECK:  ret half [[ABS]]
 float16_t test_vabsh_f16(float16_t a) {
   return vabsh_f16(a);
 }
 
 // CHECK-LABEL: test_vceqzh_f16
 // CHECK:  [[TMP1:%.*]] = fcmp oeq half %a, 0xH0000
 // CHECK:  [[TMP2:%.*]] = sext i1 [[TMP1]] to i16

 // CHECK-LABEL: test_vcvth_u64_f16
 // CHECK:  [[VCVT:%.*]] = fptoui half %a to i64
 // CHECK:  ret i64 [[VCVT]]
 uint64_t test_vcvth_u64_f16 (float16_t a) {
   return vcvth_u64_f16(a);
 }
 
 // CHECK-LABEL: test_vcvtah_s16_f16
-// CHECK: [[VCVT:%.*]] = call i16 @llvm.aarch64.neon.fcvtas.i16.f16(half %a)
-// CHECK: ret i16 [[VCVT]]
+// CHECK: [[FCVT:%.*]] = call i32 @llvm.aarch64.neon.fcvtas.i32.f16(half %a)
+// CHECK: [[RET:%.*]] = trunc i32 [[FCVT]] to i16
+// CHECK: ret i16 [[RET]]
 int16_t test_vcvtah_s16_f16 (float16_t a) {
   return vcvtah_s16_f16(a);
 }
 
 // CHECK-LABEL: test_vcvtah_s32_f16
 // CHECK: [[VCVT:%.*]] = call i32 @llvm.aarch64.neon.fcvtas.i32.f16(half %a)
 // CHECK: ret i32 [[VCVT]]
 int32_t test_vcvtah_s32_f16 (float16_t a) {
   return vcvtah_s32_f16(a);
 }
 
 // CHECK-LABEL: test_vcvtah_s64_f16
 // CHECK: [[VCVT:%.*]] = call i64 @llvm.aarch64.neon.fcvtas.i64.f16(half %a)
 // CHECK: ret i64 [[VCVT]]
 int64_t test_vcvtah_s64_f16 (float16_t a) {
   return vcvtah_s64_f16(a);
 }
 
 // CHECK-LABEL: test_vcvtah_u16_f16
-// CHECK: [[VCVT:%.*]] = call i16 @llvm.aarch64.neon.fcvtau.i16.f16(half %a)
-// CHECK: ret i16 [[VCVT]]
+// CHECK: [[FCVT:%.*]] = call i32 @llvm.aarch64.neon.fcvtau.i32.f16(half %a)
+// CHECK: [[RET:%.*]] = trunc i32 [[FCVT]] to i16
+// CHECK: ret i16 [[RET]]
 uint16_t test_vcvtah_u16_f16 (float16_t a) {
   return vcvtah_u16_f16(a);
 }
 
 // CHECK-LABEL: test_vcvtah_u32_f16
 // CHECK: [[VCVT:%.*]] = call i32 @llvm.aarch64.neon.fcvtau.i32.f16(half %a)
 // CHECK: ret i32 [[VCVT]]
 uint32_t test_vcvtah_u32_f16 (float16_t a) {
   return vcvtah_u32_f16(a);
 }
 
 // CHECK-LABEL: test_vcvtah_u64_f16
 // CHECK: [[VCVT:%.*]] = call i64 @llvm.aarch64.neon.fcvtau.i64.f16(half %a)
 // CHECK: ret i64 [[VCVT]]
 uint64_t test_vcvtah_u64_f16 (float16_t a) {
   return vcvtah_u64_f16(a);
 }
 
 // CHECK-LABEL: test_vcvtmh_s16_f16
-// CHECK: [[VCVT:%.*]] = call i16 @llvm.aarch64.neon.fcvtms.i16.f16(half %a)
-// CHECK: ret i16 [[VCVT]]
+// CHECK: [[FCVT:%.*]] = call i32 @llvm.aarch64.neon.fcvtms.i32.f16(half %a)
+// CHECK: [[RET:%.*]] = trunc i32 [[FCVT]] to i16
+// CHECK: ret i16 [[RET]]
 int16_t test_vcvtmh_s16_f16 (float16_t a) {
   return vcvtmh_s16_f16(a);
 }
 
 // CHECK-LABEL: test_vcvtmh_s32_f16
 // CHECK: [[VCVT:%.*]] = call i32 @llvm.aarch64.neon.fcvtms.i32.f16(half %a)
 // CHECK: ret i32 [[VCVT]]
 int32_t test_vcvtmh_s32_f16 (float16_t a) {
   return vcvtmh_s32_f16(a);
 }
 
 // CHECK-LABEL: test_vcvtmh_s64_f16
 // CHECK: [[VCVT:%.*]] = call i64 @llvm.aarch64.neon.fcvtms.i64.f16(half %a)
 // CHECK: ret i64 [[VCVT]]
 int64_t test_vcvtmh_s64_f16 (float16_t a) {
   return vcvtmh_s64_f16(a);
 }
 
 // CHECK-LABEL: test_vcvtmh_u16_f16
-// CHECK: [[VCVT:%.*]] = call i16 @llvm.aarch64.neon.fcvtmu.i16.f16(half %a)
-// CHECK: ret i16 [[VCVT]]
+// CHECK: [[FCVT:%.*]] = call i32 @llvm.aarch64.neon.fcvtmu.i32.f16(half %a)
+// CHECK: [[RET:%.*]] = trunc i32 [[FCVT]] to i16
+// CHECK: ret i16 [[RET]]
 uint16_t test_vcvtmh_u16_f16 (float16_t a) {
   return vcvtmh_u16_f16(a);
 }
 
 // CHECK-LABEL: test_vcvtmh_u32_f16
 // CHECK: [[VCVT:%.*]] = call i32 @llvm.aarch64.neon.fcvtmu.i32.f16(half %a)
 // CHECK: ret i32 [[VCVT]]
 uint32_t test_vcvtmh_u32_f16 (float16_t a) {
   return vcvtmh_u32_f16(a);
 }
 
 // CHECK-LABEL: test_vcvtmh_u64_f16
 // CHECK: [[VCVT:%.*]] = call i64 @llvm.aarch64.neon.fcvtmu.i64.f16(half %a)
 // CHECK: ret i64 [[VCVT]]
 uint64_t test_vcvtmh_u64_f16 (float16_t a) {
   return vcvtmh_u64_f16(a);
 }
 
 // CHECK-LABEL: test_vcvtnh_s16_f16
-// CHECK: [[VCVT:%.*]] = call i16 @llvm.aarch64.neon.fcvtns.i16.f16(half %a)
-// CHECK: ret i16 [[VCVT]]
+// CHECK: [[FCVT:%.*]] = call i32 @llvm.aarch64.neon.fcvtns.i32.f16(half %a)
+// CHECK: [[RET:%.*]] = trunc i32 [[FCVT]] to i16
+// CHECK: ret i16 [[RET]]
 int16_t test_vcvtnh_s16_f16 (float16_t a) {
   return vcvtnh_s16_f16(a);
 }
 
 // CHECK-LABEL: test_vcvtnh_s32_f16
 // CHECK: [[VCVT:%.*]] = call i32 @llvm.aarch64.neon.fcvtns.i32.f16(half %a)
 // CHECK: ret i32 [[VCVT]]
 int32_t test_vcvtnh_s32_f16 (float16_t a) {
   return vcvtnh_s32_f16(a);
 }
 
 // CHECK-LABEL: test_vcvtnh_s64_f16
 // CHECK: [[VCVT:%.*]] = call i64 @llvm.aarch64.neon.fcvtns.i64.f16(half %a)
 // CHECK: ret i64 [[VCVT]]
 int64_t test_vcvtnh_s64_f16 (float16_t a) {
   return vcvtnh_s64_f16(a);
 }
 
 // CHECK-LABEL: test_vcvtnh_u16_f16
-// CHECK: [[VCVT:%.*]] = call i16 @llvm.aarch64.neon.fcvtnu.i16.f16(half %a)
-// CHECK: ret i16 [[VCVT]]
+// CHECK: [[FCVT:%.*]] = call i32 @llvm.aarch64.neon.fcvtnu.i32.f16(half %a)
+// CHECK: [[RET:%.*]] = trunc i32 [[FCVT]] to i16
+// CHECK: ret i16 [[RET]]
 uint16_t test_vcvtnh_u16_f16 (float16_t a) {
   return vcvtnh_u16_f16(a);
 }
 
 // CHECK-LABEL: test_vcvtnh_u32_f16
 // CHECK: [[VCVT:%.*]] = call i32 @llvm.aarch64.neon.fcvtnu.i32.f16(half %a)
 // CHECK: ret i32 [[VCVT]]
 uint32_t test_vcvtnh_u32_f16 (float16_t a) {
   return vcvtnh_u32_f16(a);
 }
 
 // CHECK-LABEL: test_vcvtnh_u64_f16
 // CHECK: [[VCVT:%.*]] = call i64 @llvm.aarch64.neon.fcvtnu.i64.f16(half %a)
 // CHECK: ret i64 [[VCVT]]
 uint64_t test_vcvtnh_u64_f16 (float16_t a) {
   return vcvtnh_u64_f16(a);
 }
 
 // CHECK-LABEL: test_vcvtph_s16_f16
-// CHECK: [[VCVT:%.*]] = call i16 @llvm.aarch64.neon.fcvtps.i16.f16(half %a)
-// CHECK: ret i16 [[VCVT]]
+// CHECK: [[FCVT:%.*]] = call i32 @llvm.aarch64.neon.fcvtps.i32.f16(half %a)
+// CHECK: [[RET:%.*]] = trunc i32 [[FCVT]] to i16
+// CHECK: ret i16 [[RET]]
 int16_t test_vcvtph_s16_f16 (float16_t a) {
   return vcvtph_s16_f16(a);
 }
 
 // CHECK-LABEL: test_vcvtph_s32_f16
 // CHECK: [[VCVT:%.*]] = call i32 @llvm.aarch64.neon.fcvtps.i32.f16(half %a)
 // CHECK: ret i32 [[VCVT]]
 int32_t test_vcvtph_s32_f16 (float16_t a) {
   return vcvtph_s32_f16(a);
 }
 
 // CHECK-LABEL: test_vcvtph_s64_f16
 // CHECK: [[VCVT:%.*]] = call i64 @llvm.aarch64.neon.fcvtps.i64.f16(half %a)
 // CHECK: ret i64 [[VCVT]]
 int64_t test_vcvtph_s64_f16 (float16_t a) {
   return vcvtph_s64_f16(a);
 }
 
 // CHECK-LABEL: test_vcvtph_u16_f16
-// CHECK: [[VCVT:%.*]] = call i16 @llvm.aarch64.neon.fcvtpu.i16.f16(half %a)
-// CHECK: ret i16 [[VCVT]]
+// CHECK: [[FCVT:%.*]] = call i32 @llvm.aarch64.neon.fcvtpu.i32.f16(half %a)
+// CHECK: [[RET:%.*]] = trunc i32 [[FCVT]] to i16
+// CHECK: ret i16 [[RET]]
 uint16_t test_vcvtph_u16_f16 (float16_t a) {
   return vcvtph_u16_f16(a);
 }
 
 // CHECK-LABEL: test_vcvtph_u32_f16
 // CHECK: [[VCVT:%.*]] = call i32 @llvm.aarch64.neon.fcvtpu.i32.f16(half %a)
 // CHECK: ret i32 [[VCVT]]
 uint32_t test_vcvtph_u32_f16 (float16_t a) {

 // CHECK-LABEL: test_vabdh_f16
 // CHECK:  [[ABD:%.*]] = call half @llvm.aarch64.sisd.fabd.f16(half %a, half %b)
 // CHECK:  ret half [[ABD]]
 float16_t test_vabdh_f16(float16_t a, float16_t b) {
   return vabdh_f16(a, b);
 }
 
 // CHECK-LABEL: test_vcageh_f16
-// CHECK:  [[ABS:%.*]] = call i16 @llvm.aarch64.neon.facge.i16.f16(half %a, half %b)
-// CHECK:  ret i16 [[ABS]]
+// CHECK:  [[FACG:%.*]] = call i32 @llvm.aarch64.neon.facge.i32.f16(half %a, half %b)
+// CHECK: [[RET:%.*]] = trunc i32 [[FACG]] to i16
+// CHECK: ret i16 [[RET]]
 uint16_t test_vcageh_f16(float16_t a, float16_t b) {
   return vcageh_f16(a, b);
 }
 
 // CHECK-LABEL: test_vcagth_f16
-// CHECK:  [[ABS:%.*]] = call i16 @llvm.aarch64.neon.facgt.i16.f16(half %a, half %b)
-// CHECK:  ret i16 [[ABS]]
+// CHECK:  [[FACG:%.*]] = call i32 @llvm.aarch64.neon.facgt.i32.f16(half %a, half %b)
+// CHECK: [[RET:%.*]] = trunc i32 [[FACG]] to i16
+// CHECK: ret i16 [[RET]]
 uint16_t test_vcagth_f16(float16_t a, float16_t b) {
   return vcagth_f16(a, b);
 }
 
 // CHECK-LABEL: test_vcaleh_f16
-// CHECK:  [[ABS:%.*]] = call i16 @llvm.aarch64.neon.facge.i16.f16(half %a, half %b)
-// CHECK:  ret i16 [[ABS]]
+// CHECK:  [[FACG:%.*]] = call i32 @llvm.aarch64.neon.facge.i32.f16(half %b, half %a)
+// CHECK: [[RET:%.*]] = trunc i32 [[FACG]] to i16
+// CHECK: ret i16 [[RET]]
 uint16_t test_vcaleh_f16(float16_t a, float16_t b) {
   return vcaleh_f16(a, b);
 }
 
 // CHECK-LABEL: test_vcalth_f16
-// CHECK:  [[ABS:%.*]] = call i16 @llvm.aarch64.neon.facgt.i16.f16(half %a, half %b)
-// CHECK:  ret i16 [[ABS]]
+// CHECK:  [[FACG:%.*]] = call i32 @llvm.aarch64.neon.facgt.i32.f16(half %b, half %a)
+// CHECK: [[RET:%.*]] = trunc i32 [[FACG]] to i16
+// CHECK: ret i16 [[RET]]
 uint16_t test_vcalth_f16(float16_t a, float16_t b) {
   return vcalth_f16(a, b);
 }
 
 // CHECK-LABEL: test_vceqh_f16
 // CHECK:  [[TMP1:%.*]] = fcmp oeq half %a, %b
 // CHECK:  [[TMP2:%.*]] = sext i1 [[TMP1]] to i16
 // CHECK:  ret i16 [[TMP2]]

 // CHECK:  [[TMP1:%.*]] = fcmp olt half %a, %b
 // CHECK:  [[TMP2:%.*]] = sext i1 [[TMP1]] to i16
 // CHECK:  ret i16 [[TMP2]]
 uint16_t test_vclth_f16(float16_t a, float16_t b) {
   return vclth_f16(a, b);
 }
 
 // CHECK-LABEL: test_vcvth_n_f16_s16
-// CHECK:  [[CVT:%.*]] = call half @llvm.aarch64.neon.vcvtfxs2fp.f16.i16(i16 %a, i32 0)
+// CHECK: [[SEXT:%.*]] = sext i16 %a to i32
+// CHECK:  [[CVT:%.*]] = call half @llvm.aarch64.neon.vcvtfxs2fp.f16.i32(i32 [[SEXT]], i32 0)
 // CHECK:  ret half [[CVT]]
 float16_t test_vcvth_n_f16_s16(int16_t a) {
   return vcvth_n_f16_s16(a, 0);
 }
 
 // CHECK-LABEL: test_vcvth_n_f16_s32
 // CHECK:  [[CVT:%.*]] = call half @llvm.aarch64.neon.vcvtfxs2fp.f16.i32(i32 %a, i32 0)
 // CHECK:  ret half [[CVT]]
 float16_t test_vcvth_n_f16_s32(int32_t a) {
   return vcvth_n_f16_s32(a, 0);
 }
 
 // CHECK-LABEL: test_vcvth_n_f16_s64
 // CHECK:  [[CVT:%.*]] = call half @llvm.aarch64.neon.vcvtfxs2fp.f16.i64(i64 %a, i32 0)
 // CHECK:  ret half [[CVT]]
 float16_t test_vcvth_n_f16_s64(int64_t a) {
   return vcvth_n_f16_s64(a, 0);
 }
 
 // CHECK-LABEL: test_vcvth_n_s16_f16
-// CHECK:  [[CVT:%.*]] = call i16 @llvm.aarch64.neon.vcvtfp2fxs.i16.f16(half %a, i32 0)
-// CHECK:  ret i16 [[CVT]]
+// CHECK:  [[CVT:%.*]] = call i32 @llvm.aarch64.neon.vcvtfp2fxs.i32.f16(half %a, i32 0)
+// CHECK: [[RET:%.*]] = trunc i32 [[CVT]] to i16
+// CHECK: ret i16 [[RET]]
 int16_t test_vcvth_n_s16_f16(float16_t a) {
   return vcvth_n_s16_f16(a, 0);
 }
 
 // CHECK-LABEL: test_vcvth_n_s32_f16
 // CHECK:  [[CVT:%.*]] = call i32 @llvm.aarch64.neon.vcvtfp2fxs.i32.f16(half %a, i32 0)
 // CHECK:  ret i32 [[CVT]]
 int32_t test_vcvth_n_s32_f16(float16_t a) {
   return vcvth_n_s32_f16(a, 0);
 }
 
 // CHECK-LABEL: test_vcvth_n_s64_f16
 // CHECK:  [[CVT:%.*]] = call i64 @llvm.aarch64.neon.vcvtfp2fxs.i64.f16(half %a, i32 0)
 // CHECK:  ret i64 [[CVT]]
 int64_t test_vcvth_n_s64_f16(float16_t a) {
   return vcvth_n_s64_f16(a, 0);
 }
 
 // CHECK-LABEL: test_vcvth_n_f16_u16
-// CHECK:  [[CVT:%.*]] = call half @llvm.aarch64.neon.vcvtfxu2fp.f16.i16(i16 %a, i32 0)
+// CHECK: [[SEXT:%.*]] = zext i16 %a to i32
+// CHECK:  [[CVT:%.*]] = call half @llvm.aarch64.neon.vcvtfxu2fp.f16.i32(i32 [[SEXT]], i32 0)
 // CHECK:  ret half [[CVT]]
 float16_t test_vcvth_n_f16_u16(int16_t a) {
   return vcvth_n_f16_u16(a, 0);
 }
 
 // CHECK-LABEL: test_vcvth_n_f16_u32
 // CHECK:  [[CVT:%.*]] = call half @llvm.aarch64.neon.vcvtfxu2fp.f16.i32(i32 %a, i32 0)
 // CHECK:  ret half [[CVT]]
 float16_t test_vcvth_n_f16_u32(int32_t a) {
   return vcvth_n_f16_u32(a, 0);
 }
 
 // CHECK-LABEL: test_vcvth_n_f16_u64
 // CHECK:  [[CVT:%.*]] = call half @llvm.aarch64.neon.vcvtfxu2fp.f16.i64(i64 %a, i32 0)
 // CHECK:  ret half [[CVT]]
 float16_t test_vcvth_n_f16_u64(int64_t a) {
   return vcvth_n_f16_u64(a, 0);
 }
 
 // CHECK-LABEL: test_vcvth_n_u16_f16
-// CHECK:  [[CVT:%.*]] = call i16 @llvm.aarch64.neon.vcvtfp2fxu.i16.f16(half %a, i32 0)
-// CHECK:  ret i16 [[CVT]]
+// CHECK:  [[CVT:%.*]] = call i32 @llvm.aarch64.neon.vcvtfp2fxu.i32.f16(half %a, i32 0)
+// CHECK: [[RET:%.*]] = trunc i32 [[CVT]] to i16
+// CHECK: ret i16 [[RET]]
 int16_t test_vcvth_n_u16_f16(float16_t a) {
   return vcvth_n_u16_f16(a, 0);
 }
 
 // CHECK-LABEL: test_vcvth_n_u32_f16
 // CHECK:  [[CVT:%.*]] = call i32 @llvm.aarch64.neon.vcvtfp2fxu.i32.f16(half %a, i32 0)
 // CHECK:  ret i32 [[CVT]]
 int32_t test_vcvth_n_u32_f16(float16_t a) {

llvm/lib/Target/AArch64/AArch64InstrInfo.td

def : Pat<(v1i64 (int_aarch64_neon_fcvtns (v1f64 FPR64:$Rn))),
           (FCVTNSv1i64 FPR64:$Rn)>;
 def : Pat<(v1i64 (int_aarch64_neon_fcvtnu (v1f64 FPR64:$Rn))),
           (FCVTNUv1i64 FPR64:$Rn)>;
 def : Pat<(v1i64 (int_aarch64_neon_fcvtps (v1f64 FPR64:$Rn))),
           (FCVTPSv1i64 FPR64:$Rn)>;
 def : Pat<(v1i64 (int_aarch64_neon_fcvtpu (v1f64 FPR64:$Rn))),
           (FCVTPUv1i64 FPR64:$Rn)>;
 
+def : Pat<(f16 (int_aarch64_neon_frecpe (f16 FPR16:$Rn))),
+          (FRECPEv1f16 FPR16:$Rn)>;
 def : Pat<(f32 (int_aarch64_neon_frecpe (f32 FPR32:$Rn))),
           (FRECPEv1i32 FPR32:$Rn)>;
 def : Pat<(f64 (int_aarch64_neon_frecpe (f64 FPR64:$Rn))),
           (FRECPEv1i64 FPR64:$Rn)>;
 def : Pat<(v1f64 (int_aarch64_neon_frecpe (v1f64 FPR64:$Rn))),
           (FRECPEv1i64 FPR64:$Rn)>;
 
 def : Pat<(f32 (AArch64frecpe (f32 FPR32:$Rn))),
def : Pat<(v2f32 (AArch64frecps (v2f32 V64:$Rn), (v2f32 V64:$Rm))),
           (FRECPSv2f32 V64:$Rn, V64:$Rm)>;
 def : Pat<(v4f32 (AArch64frecps (v4f32 FPR128:$Rn), (v4f32 FPR128:$Rm))),
           (FRECPSv4f32 FPR128:$Rn, FPR128:$Rm)>;
 def : Pat<(f64 (AArch64frecps (f64 FPR64:$Rn), (f64 FPR64:$Rm))),
           (FRECPS64 FPR64:$Rn, FPR64:$Rm)>;
 def : Pat<(v2f64 (AArch64frecps (v2f64 FPR128:$Rn), (v2f64 FPR128:$Rm))),
           (FRECPSv2f64 FPR128:$Rn, FPR128:$Rm)>;
 
+def : Pat<(f16 (int_aarch64_neon_frecpx (f16 FPR16:$Rn))),
+          (FRECPXv1f16 FPR16:$Rn)>;
 def : Pat<(f32 (int_aarch64_neon_frecpx (f32 FPR32:$Rn))),
           (FRECPXv1i32 FPR32:$Rn)>;
 def : Pat<(f64 (int_aarch64_neon_frecpx (f64 FPR64:$Rn))),
           (FRECPXv1i64 FPR64:$Rn)>;
 
+def : Pat<(f16 (int_aarch64_neon_frsqrte (f16 FPR16:$Rn))),
+          (FRSQRTEv1f16 FPR16:$Rn)>;
 def : Pat<(f32 (int_aarch64_neon_frsqrte (f32 FPR32:$Rn))),
           (FRSQRTEv1i32 FPR32:$Rn)>;
 def : Pat<(f64 (int_aarch64_neon_frsqrte (f64 FPR64:$Rn))),
           (FRSQRTEv1i64 FPR64:$Rn)>;
 def : Pat<(v1f64 (int_aarch64_neon_frsqrte (v1f64 FPR64:$Rn))),
           (FRSQRTEv1i64 FPR64:$Rn)>;
 
 def : Pat<(f32 (AArch64frsqrte (f32 FPR32:$Rn))),