[WebAssembly] Prototype i64x2.eq

[tlively]

Summary

As proposed in https://github.com/WebAssembly/simd/pull/381. Since it is still
in the prototyping phase, it is only accessible via a target builtin function
and a target intrinsic.

Depends on D90504.

clang/include/clang/Basic/BuiltinsWebAssembly.def

 TARGET_BUILTIN(__builtin_wasm_load16_lane, "V8ss*V8sIi", "n", "simd128")
 TARGET_BUILTIN(__builtin_wasm_load32_lane, "V4ii*V4iIi", "n", "simd128")
 TARGET_BUILTIN(__builtin_wasm_load64_lane, "V2LLiLLi*V2LLiIi", "n", "simd128")
 TARGET_BUILTIN(__builtin_wasm_store8_lane, "vSc*V16ScIi", "n", "simd128")
 TARGET_BUILTIN(__builtin_wasm_store16_lane, "vs*V8sIi", "n", "simd128")
 TARGET_BUILTIN(__builtin_wasm_store32_lane, "vi*V4iIi", "n", "simd128")
 TARGET_BUILTIN(__builtin_wasm_store64_lane, "vLLi*V2LLiIi", "n", "simd128")
 
+TARGET_BUILTIN(__builtin_wasm_eq_i64x2, "V2LLiV2LLiV2LLi", "nc", "simd128")
+
 #undef BUILTIN
 #undef TARGET_BUILTIN

clang/lib/CodeGen/CGBuiltin.cpp

case WebAssembly::BI__builtin_wasm_dot_s_i32x4_i16x8: {
     Function *Callee = CGM.getIntrinsic(Intrinsic::wasm_dot);
     return Builder.CreateCall(Callee, {LHS, RHS});
   }
   case WebAssembly::BI__builtin_wasm_popcnt_i8x16: {
     Value *Vec = EmitScalarExpr(E->getArg(0));
     Function *Callee = CGM.getIntrinsic(Intrinsic::wasm_popcnt);
     return Builder.CreateCall(Callee, {Vec});
   }
+  case WebAssembly::BI__builtin_wasm_eq_i64x2: {
+    Value *LHS = EmitScalarExpr(E->getArg(0));
+    Value *RHS = EmitScalarExpr(E->getArg(1));
+    Function *Callee = CGM.getIntrinsic(Intrinsic::wasm_eq);
+    return Builder.CreateCall(Callee, {LHS, RHS});
+  }
   case WebAssembly::BI__builtin_wasm_any_true_i8x16:
   case WebAssembly::BI__builtin_wasm_any_true_i16x8:
   case WebAssembly::BI__builtin_wasm_any_true_i32x4:
   case WebAssembly::BI__builtin_wasm_any_true_i64x2:
   case WebAssembly::BI__builtin_wasm_all_true_i8x16:
   case WebAssembly::BI__builtin_wasm_all_true_i16x8:
   case WebAssembly::BI__builtin_wasm_all_true_i32x4:
   case WebAssembly::BI__builtin_wasm_all_true_i64x2: {

clang/test/CodeGen/builtins-wasm.c

 }
 
 i8x16 popcnt(i8x16 x) {
   return __builtin_wasm_popcnt_i8x16(x);
   // WEBASSEMBLY: call <16 x i8> @llvm.wasm.popcnt(<16 x i8> %x)
   // WEBASSEMBLY-NEXT: ret
 }
 
+i64x2 eq_i64x2(i64x2 x, i64x2 y) {
+  return __builtin_wasm_eq_i64x2(x, y);
+  // WEBASSEMBLY: call <2 x i64> @llvm.wasm.eq(<2 x i64> %x, <2 x i64> %y)
+  // WEBASSEMBLY-NEXT: ret
+}
+
 int any_true_i8x16(i8x16 x) {
   return __builtin_wasm_any_true_i8x16(x);
   // WEBASSEMBLY: call i32 @llvm.wasm.anytrue.v16i8(<16 x i8> %x)
   // WEBASSEMBLY: ret
 }
 
 int any_true_i16x8(i16x8 x) {
   return __builtin_wasm_any_true_i16x8(x);

llvm/include/llvm/IR/IntrinsicsWebAssembly.td

Intrinsic<[llvm_anyvector_ty],
             [LLVMSubdivide2VectorType<0>, LLVMSubdivide2VectorType<0>],
             [IntrNoMem, IntrSpeculatable]>;
 
 def int_wasm_signselect :
   Intrinsic<[llvm_anyvector_ty],
             [LLVMMatchType<0>, LLVMMatchType<0>, LLVMMatchType<0>],
             [IntrNoMem, IntrSpeculatable]>;
 
+// TODO: Remove this intrinsic and the associated builtin if i64x2.eq gets
+// merged to the proposal.
+def int_wasm_eq :
+  Intrinsic<[llvm_v2i64_ty],
+            [llvm_v2i64_ty, llvm_v2i64_ty],
+            [IntrNoMem, IntrSpeculatable]>;
+
 //===----------------------------------------------------------------------===//
 // Thread-local storage intrinsics
 //===----------------------------------------------------------------------===//
 
 def int_wasm_tls_size :
   Intrinsic<[llvm_anyint_ty],
             [],
             [IntrNoMem, IntrSpeculatable]>;

llvm/lib/Target/WebAssembly/WebAssemblyInstrSIMD.td

 def : Pat<(v4i32 (nodes[0] (v4f32 V128:$lhs), (v4f32 V128:$rhs))),
           (v4i32 (nodes[1] (v4f32 V128:$lhs), (v4f32 V128:$rhs)))>;
 
 foreach nodes = [[seteq, EQ_v2f64], [setne, NE_v2f64], [setlt, LT_v2f64],
                  [setgt, GT_v2f64], [setle, LE_v2f64], [setge, GE_v2f64]] in
 def : Pat<(v2i64 (nodes[0] (v2f64 V128:$lhs), (v2f64 V128:$rhs))),
           (v2i64 (nodes[1] (v2f64 V128:$lhs), (v2f64 V128:$rhs)))>;
 
+// Prototype i64x2.eq
+defm EQ_v2i64 :
+  SIMD_I<(outs V128:$dst), (ins V128:$lhs, V128:$rhs), (outs), (ins),
+         [(set (v2i64 V128:$dst),
+           (int_wasm_eq (v2i64 V128:$lhs), (v2i64 V128:$rhs))
+         )],
+         "i64x2.eq\t$dst, $lhs, $rhs", "i64x2.eq", 192>;
+
 
 //===----------------------------------------------------------------------===//
 // Bitwise operations
 //===----------------------------------------------------------------------===//
 
 multiclass SIMDBinary<ValueType vec_t, string vec, SDNode node, string name,
                       bits<32> simdop> {
   defm _#vec_t : SIMD_I<(outs V128:$dst), (ins V128:$lhs, V128:$rhs),

llvm/test/CodeGen/WebAssembly/simd-intrinsics.ll

 define <4 x i32> @trunc_sat_u_v4i32(<4 x float> %x) {
   %a = call <4 x i32> @llvm.wasm.trunc.saturate.unsigned.v4i32.v4f32(<4 x float> %x)
   ret <4 x i32> %a
 }
 
 ; ==============================================================================
 ; 2 x i64
 ; ==============================================================================
+; CHECK-LABEL: eq_v2i64:
+; SIMD128-NEXT: .functype eq_v2i64 (v128, v128) -> (v128){{$}}
+; SIMD128-NEXT: i64x2.eq $push[[R:[0-9]+]]=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop[[R]]{{$}}
+declare <2 x i64> @llvm.wasm.eq(<2 x i64>, <2 x i64>)
+define <2 x i64> @eq_v2i64(<2 x i64> %x, <2 x i64> %y) {
+  %a = call <2 x i64> @llvm.wasm.eq(<2 x i64> %x, <2 x i64> %y)
+  ret <2 x i64> %a
+}
+
 ; CHECK-LABEL: widen_low_s_v2i64:
 ; SIMD128-NEXT: .functype widen_low_s_v2i64 (v128) -> (v128){{$}}
 ; SIMD128-NEXT: i64x2.widen_low_i32x4_s $push[[R:[0-9]+]]=, $0{{$}}
 ; SIMD128-NEXT: return $pop[[R]]{{$}}
 declare <2 x i64> @llvm.wasm.widen.low.signed(<4 x i32>)
 define <2 x i64> @widen_low_s_v2i64(<4 x i32> %x) {
   %a = call <2 x i64> @llvm.wasm.widen.low.signed(<4 x i32> %x)
   ret <2 x i64> %a

llvm/test/MC/WebAssembly/simd-encodings.s

main:
     i32x4.max_s
 
     # CHECK: i32x4.max_u # encoding: [0xfd,0xb9,0x01]
     i32x4.max_u
 
     # CHECK: i32x4.dot_i16x8_s # encoding: [0xfd,0xba,0x01]
     i32x4.dot_i16x8_s
 
+    # CHECK: i64x2.eq # encoding: [0xfd,0xc0,0x01]
+    i64x2.eq
+
     # CHECK: i64x2.neg # encoding: [0xfd,0xc1,0x01]
     i64x2.neg
 
     # CHECK: i64x2.any_true # encoding: [0xfd,0xc2,0x01]
     i64x2.any_true
 
     # CHECK: i64x2.all_true # encoding: [0xfd,0xc3,0x01]
     i64x2.all_true