+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-linux-gnu -mcpu=corei7 | FileCheck %s
define <2 x i64> @test20(<2 x i64> %a, <2 x i64> %b) {
; CHECK-LABEL: test20:
; CHECK: # BB#0:
-; CHECK-NEXT: orps %xmm1, %xmm0
+; CHECK-NEXT: por %xmm1, %xmm0
; CHECK-NEXT: movq {{.*#+}} xmm0 = xmm0[0],zero
; CHECK-NEXT: retq
%shuf1 = shufflevector <2 x i64> %a, <2 x i64> zeroinitializer, <2 x i32><i32 0, i32 2>
ret <2 x i64> %or
}
+
+; Verify that the dag-combiner keeps the correct domain for float/double vectors
+; bitcast to use the mask-or blend combine.
+
+define <2 x double> @test22(<2 x double> %a0, <2 x double> %a1) {
+; CHECK-LABEL: test22:
+; CHECK: # BB#0:
+; CHECK-NEXT: blendpd {{.*#+}} xmm0 = xmm1[0],xmm0[1]
+; CHECK-NEXT: retq
+ %bc1 = bitcast <2 x double> %a0 to <2 x i64>
+ %bc2 = bitcast <2 x double> %a1 to <2 x i64>
+ %and1 = and <2 x i64> %bc1, <i64 0, i64 -1>
+ %and2 = and <2 x i64> %bc2, <i64 -1, i64 0>
+ %or = or <2 x i64> %and1, %and2
+ %bc3 = bitcast <2 x i64> %or to <2 x double>
+ ret <2 x double> %bc3
+}
+
+
+define <4 x float> @test23(<4 x float> %a0, <4 x float> %a1) {
+; CHECK-LABEL: test23:
+; CHECK: # BB#0:
+; CHECK-NEXT: blendps {{.*#+}} xmm0 = xmm1[0],xmm0[1,2],xmm1[3]
+; CHECK-NEXT: retq
+ %bc1 = bitcast <4 x float> %a0 to <4 x i32>
+ %bc2 = bitcast <4 x float> %a1 to <4 x i32>
+ %and1 = and <4 x i32> %bc1, <i32 0, i32 -1, i32 -1, i32 0>
+ %and2 = and <4 x i32> %bc2, <i32 -1, i32 0, i32 0, i32 -1>
+ %or = or <4 x i32> %and1, %and2
+ %bc3 = bitcast <4 x i32> %or to <4 x float>
+ ret <4 x float> %bc3
+}
+
+
+define <4 x float> @test24(<4 x float> %a0, <4 x float> %a1) {
+; CHECK-LABEL: test24:
+; CHECK: # BB#0:
+; CHECK-NEXT: blendpd {{.*#+}} xmm0 = xmm1[0],xmm0[1]
+; CHECK-NEXT: retq
+ %bc1 = bitcast <4 x float> %a0 to <2 x i64>
+ %bc2 = bitcast <4 x float> %a1 to <2 x i64>
+ %and1 = and <2 x i64> %bc1, <i64 0, i64 -1>
+ %and2 = and <2 x i64> %bc2, <i64 -1, i64 0>
+ %or = or <2 x i64> %and1, %and2
+ %bc3 = bitcast <2 x i64> %or to <4 x float>
+ ret <4 x float> %bc3
+}
+
+
+define <4 x float> @test25(<4 x float> %a0) {
+; CHECK-LABEL: test25:
+; CHECK: # BB#0:
+; CHECK-NEXT: blendps {{.*#+}} xmm0 = mem[0],xmm0[1,2],mem[3]
+; CHECK-NEXT: retq
+ %bc1 = bitcast <4 x float> %a0 to <4 x i32>
+ %bc2 = bitcast <4 x float> <float 1.0, float 1.0, float 1.0, float 1.0> to <4 x i32>
+ %and1 = and <4 x i32> %bc1, <i32 0, i32 -1, i32 -1, i32 0>
+ %and2 = and <4 x i32> %bc2, <i32 -1, i32 0, i32 0, i32 -1>
+ %or = or <4 x i32> %and1, %and2
+ %bc3 = bitcast <4 x i32> %or to <4 x float>
+ ret <4 x float> %bc3
+}
+
+
; Verify that the DAGCombiner doesn't crash in the attempt to check if a shuffle
; with illegal type has a legal mask. Method 'isShuffleMaskLegal' only knows how to
; handle legal vector value types.