%c = add i32 %c2, %b
ret i32 %c
}
+
+; WIN64: test_float4
+; WIN64-NOT: vzeroupper
+; WIN64: call
+; WIN64-NOT: vzeroupper
+; WIN64: call
+; WIN64: ret
+
+; X64: test_float4
+; X64-NOT: vzeroupper
+; X64: call
+; X64-NOT: vzeroupper
+; X64: call
+; X64: ret
+
+; X32: test_float4
+; X32: vzeroupper
+; X32: call
+; X32: vzeroupper
+; X32: call
+; X32: ret
+
+declare <4 x float> @func_float4(<4 x float>, <4 x float>, <4 x float>)
+
+define <8 x float> @test_float4(<8 x float> %a, <8 x float> %b, <8 x float> %c) nounwind readnone {
+entry:
+ %0 = shufflevector <8 x float> %a, <8 x float> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+ %1 = shufflevector <8 x float> %b, <8 x float> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+ %2 = shufflevector <8 x float> %c, <8 x float> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+ %call.i = tail call intel_ocl_bicc <4 x float> @func_float4(<4 x float> %0, <4 x float> %1, <4 x float> %2) nounwind
+ %3 = shufflevector <4 x float> %call.i, <4 x float> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>
+ %4 = shufflevector <8 x float> %a, <8 x float> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+ %5 = shufflevector <8 x float> %b, <8 x float> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+ %6 = shufflevector <8 x float> %c, <8 x float> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+ %call.i2 = tail call intel_ocl_bicc <4 x float> @func_float4(<4 x float> %4, <4 x float> %5, <4 x float> %6) nounwind
+ %7 = shufflevector <4 x float> %call.i2, <4 x float> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>
+ %8 = shufflevector <8 x float> %3, <8 x float> %7, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
+ ret <8 x float> %8
+}
+