-; RUN: llvm-as < %s | llc -mtriple=i686-apple-darwin -mattr=+sse2 -coalescer-commute-instrs | grep movsd | count 4
+; RUN: llc < %s -march=x86-64 | grep paddw | count 2
+; RUN: llc < %s -march=x86-64 | not grep mov
-define i32 @main(i32 %argc, i8** %argv) nounwind {
+; The 2-addr pass should ensure that identical code is produced for these functions
+; no extra copy should be generated.
+
+define <2 x i64> @test1(<2 x i64> %x, <2 x i64> %y) nounwind {
entry:
- br label %bb145.us.i.i
+ %tmp6 = bitcast <2 x i64> %y to <8 x i16> ; <<8 x i16>> [#uses=1]
+ %tmp8 = bitcast <2 x i64> %x to <8 x i16> ; <<8 x i16>> [#uses=1]
+ %tmp9 = add <8 x i16> %tmp8, %tmp6 ; <<8 x i16>> [#uses=1]
+ %tmp10 = bitcast <8 x i16> %tmp9 to <2 x i64> ; <<2 x i64>> [#uses=1]
+ ret <2 x i64> %tmp10
+}
-bb145.us.i.i: ; preds = %bb145.us.i.i, %entry
- %seed.3.reg2mem.0.us.i.i = phi double [ 0.000000e+00, %entry ], [ %tmp9.i.us.i.i, %bb145.us.i.i ] ; <double> [#uses=1]
- %tmp2.i13.us.i.i = mul double %seed.3.reg2mem.0.us.i.i, 1.680700e+04 ; <double> [#uses=1]
- %tmp3.i.us.i.i = add double %tmp2.i13.us.i.i, 1.000000e+00 ; <double> [#uses=1]
- %tmp6.i15.us.i.i = call double @floor( double 0.000000e+00 ) nounwind readnone ; <double> [#uses=1]
- %tmp7.i16.us.i.i = mul double %tmp6.i15.us.i.i, 0xC1DFFFFFFFC00000 ; <double> [#uses=1]
- %tmp9.i.us.i.i = add double %tmp7.i16.us.i.i, %tmp3.i.us.i.i ; <double> [#uses=2]
- %tmp5.i12.us.i.i = mul double %tmp9.i.us.i.i, 2.000000e+00 ; <double> [#uses=1]
- %tmp6.i.us.i.i = fdiv double %tmp5.i12.us.i.i, 0x41DFFFFFFFC00000 ; <double> [#uses=1]
- %tmp8.i.us.i.i = add double %tmp6.i.us.i.i, -1.000000e+00 ; <double> [#uses=1]
- store double %tmp8.i.us.i.i, double* null, align 8
- br label %bb145.us.i.i
+define <2 x i64> @test2(<2 x i64> %x, <2 x i64> %y) nounwind {
+entry:
+ %tmp6 = bitcast <2 x i64> %x to <8 x i16> ; <<8 x i16>> [#uses=1]
+ %tmp8 = bitcast <2 x i64> %y to <8 x i16> ; <<8 x i16>> [#uses=1]
+ %tmp9 = add <8 x i16> %tmp8, %tmp6 ; <<8 x i16>> [#uses=1]
+ %tmp10 = bitcast <8 x i16> %tmp9 to <2 x i64> ; <<2 x i64>> [#uses=1]
+ ret <2 x i64> %tmp10
+}
+
+
+; The coalescer should commute the add to avoid a copy.
+define <4 x float> @test3(<4 x float> %V) {
+entry:
+ %tmp8 = shufflevector <4 x float> %V, <4 x float> undef,
+ <4 x i32> < i32 3, i32 2, i32 1, i32 0 >
+ %add = fadd <4 x float> %tmp8, %V
+ ret <4 x float> %add
}
-declare double @floor(double) nounwind readnone