Constant *C0 = dyn_cast<Constant>(Op0);
Constant *C1 = dyn_cast<Constant>(Op1);
ConstantInt *CI00 =
- C0 ? dyn_cast<ConstantInt>(C0->getAggregateElement((unsigned)0))
+ C0 ? dyn_cast_or_null<ConstantInt>(C0->getAggregateElement((unsigned)0))
: nullptr;
ConstantInt *CI10 =
- C1 ? dyn_cast<ConstantInt>(C1->getAggregateElement((unsigned)0))
+ C1 ? dyn_cast_or_null<ConstantInt>(C1->getAggregateElement((unsigned)0))
: nullptr;
// Constant Fold - insert bottom Length bits starting at the Index'th bit.
// See if we're dealing with constant values.
Constant *C1 = dyn_cast<Constant>(Op1);
ConstantInt *CI11 =
- C1 ? dyn_cast<ConstantInt>(C1->getAggregateElement((unsigned)1))
+ C1 ? dyn_cast_or_null<ConstantInt>(C1->getAggregateElement((unsigned)1))
: nullptr;
// Attempt to simplify to a constant, shuffle vector or INSERTQI call.
ret <2 x i64> %1
}
+define <2 x i64> @test_insertq_call_constexpr(<2 x i64> %x) {
+; CHECK-LABEL: @test_insertq_call_constexpr(
+; CHECK-NEXT: [[TMP1:%.*]] = tail call <2 x i64> @llvm.x86.sse4a.insertq(<2 x i64> %x, <2 x i64> bitcast (<16 x i8> trunc (<16 x i16> bitcast (<4 x i64> <i64 0, i64 undef, i64 2, i64 undef> to <16 x i16>) to <16 x i8>) to <2 x i64>))
+; CHECK-NEXT: ret <2 x i64> [[TMP1]]
+;
+ %1 = tail call <2 x i64> @llvm.x86.sse4a.insertq(<2 x i64> %x, <2 x i64> bitcast (<16 x i8> trunc (<16 x i16> bitcast (<4 x i64> <i64 0, i64 undef, i64 2, i64 undef> to <16 x i16>) to <16 x i8>) to <2 x i64>))
+ ret <2 x i64> %1
+}
+
;
; INSERTQI
;
ret <2 x i64> %1
}
+define <2 x i64> @test_insertqi_call_constexpr(<2 x i64> %x) {
+; CHECK-LABEL: @test_insertqi_call_constexpr(
+; CHECK-NEXT: [[TMP1:%.*]] = tail call <2 x i64> @llvm.x86.sse4a.insertqi(<2 x i64> %x, <2 x i64> bitcast (<16 x i8> trunc (<16 x i16> bitcast (<4 x i64> <i64 0, i64 undef, i64 2, i64 undef> to <16 x i16>) to <16 x i8>) to <2 x i64>), i8 48, i8 3)
+; CHECK-NEXT: ret <2 x i64> [[TMP1]]
+;
+ %1 = tail call <2 x i64> @llvm.x86.sse4a.insertqi(<2 x i64> %x, <2 x i64> bitcast (<16 x i8> trunc (<16 x i16> bitcast (<4 x i64> <i64 0, i64 undef, i64 2, i64 undef> to <16 x i16>) to <16 x i8>) to <2 x i64>), i8 48, i8 3)
+ ret <2 x i64> %1
+}
+
; The result of this insert is the second arg, since the top 64 bits of
; the result are undefined, and we copy the bottom 64 bits from the
; second arg