ret <2 x i64> %v
; CHECK-LABEL: @test26
+
+; Make sure we use only two stores (one for each operand).
+; CHECK: stxvd2x 35,
+; CHECK: stxvd2x 34,
+; CHECK-NOT: stxvd2x
+
; FIXME: The code quality here is not good; just make sure we do something for now.
; CHECK: add
; CHECK: add
; CHECK: blr
}
+define <4 x float> @test32(<4 x float>* %a) {
+ %v = load <4 x float>* %a, align 16
+ ret <4 x float> %v
+
+; CHECK-LABEL: @test32
+; CHECK: lxvw4x 34, 0, 3
+; CHECK: blr
+}
+
+define void @test33(<4 x float>* %a, <4 x float> %b) {
+ store <4 x float> %b, <4 x float>* %a, align 16
+ ret void
+
+; CHECK-LABEL: @test33
+; CHECK: stxvw4x 34, 0, 3
+; CHECK: blr
+}
+
+define <4 x float> @test32u(<4 x float>* %a) {
+ %v = load <4 x float>* %a, align 8
+ ret <4 x float> %v
+
+; CHECK-LABEL: @test32u
+; CHECK-DAG: lvsl
+; CHECK-DAG: lvx
+; CHECK-DAG: lvx
+; CHECK: vperm 2,
+; CHECK: blr
+}
+
+define void @test33u(<4 x float>* %a, <4 x float> %b) {
+ store <4 x float> %b, <4 x float>* %a, align 8
+ ret void
+
+; CHECK-LABEL: @test33u
+; CHECK: stxvw4x 34, 0, 3
+; CHECK: blr
+}
+
+define <4 x i32> @test34(<4 x i32>* %a) {
+ %v = load <4 x i32>* %a, align 16
+ ret <4 x i32> %v
+
+; CHECK-LABEL: @test34
+; CHECK: lxvw4x 34, 0, 3
+; CHECK: blr
+}
+
+define void @test35(<4 x i32>* %a, <4 x i32> %b) {
+ store <4 x i32> %b, <4 x i32>* %a, align 16
+ ret void
+
+; CHECK-LABEL: @test35
+; CHECK: stxvw4x 34, 0, 3
+; CHECK: blr
+}
+
define <2 x double> @test40(<2 x i64> %a) {
%v = uitofp <2 x i64> %a to <2 x double>
ret <2 x double> %v
ret <2 x double> %v
; CHECK-LABEL: @test54
-; CHECK: xxpermdi 34, 34, 35, 1
+; CHECK: xxpermdi 34, 34, 35, 2
; CHECK: blr
}
; CHECK: blr
}
+define double @test63(<2 x double> %a) {
+ %v = extractelement <2 x double> %a, i32 0
+ ret double %v
+
+; CHECK-LABEL: @test63
+; CHECK: xxlor 1, 34, 34
+; CHECK: blr
+}
+
+define double @test64(<2 x double> %a) {
+ %v = extractelement <2 x double> %a, i32 1
+ ret double %v
+
+; CHECK-LABEL: @test64
+; CHECK: xxpermdi 1, 34, 34, 2
+; CHECK: blr
+}
+
+define <2 x i1> @test65(<2 x i64> %a, <2 x i64> %b) {
+ %w = icmp eq <2 x i64> %a, %b
+ ret <2 x i1> %w
+
+; CHECK-LABEL: @test65
+; CHECK: vcmpequw 2, 2, 3
+; CHECK: blr
+}
+
+define <2 x i1> @test66(<2 x i64> %a, <2 x i64> %b) {
+ %w = icmp ne <2 x i64> %a, %b
+ ret <2 x i1> %w
+
+; CHECK-LABEL: @test66
+; CHECK: vcmpequw {{[0-9]+}}, 2, 3
+; CHECK: xxlnor 34, {{[0-9]+}}, {{[0-9]+}}
+; CHECK: blr
+}
+
+define <2 x i1> @test67(<2 x i64> %a, <2 x i64> %b) {
+ %w = icmp ult <2 x i64> %a, %b
+ ret <2 x i1> %w
+
+; CHECK-LABEL: @test67
+; This should scalarize, and the current code quality is not good.
+; CHECK: stxvd2x
+; CHECK: stxvd2x
+; CHECK: cmpld
+; CHECK: cmpld
+; CHECK: lxvd2x
+; CHECK: blr
+}
+
+define <2 x double> @test68(<2 x i32> %a) {
+ %w = sitofp <2 x i32> %a to <2 x double>
+ ret <2 x double> %w
+
+; CHECK-LABEL: @test68
+; CHECK: xxsldwi [[V1:[0-9]+]], 34, 34, 1
+; CHECK: xvcvsxwdp 34, [[V1]]
+; CHECK: blr
+}
+
+define <2 x double> @test69(<2 x i16> %a) {
+ %w = sitofp <2 x i16> %a to <2 x double>
+ ret <2 x double> %w
+
+; CHECK-LABEL: @test69
+; CHECK: vspltisw [[V1:[0-9]+]], 8
+; CHECK: vadduwm [[V2:[0-9]+]], [[V1]], [[V1]]
+; CHECK: vslw [[V3:[0-9]+]], 2, [[V2]]
+; CHECK: vsraw {{[0-9]+}}, [[V3]], [[V2]]
+; CHECK: xxsldwi [[V4:[0-9]+]], {{[0-9]+}}, {{[0-9]+}}, 1
+; CHECK: xvcvsxwdp 34, [[V4]]
+; CHECK: blr
+}
+
+define <2 x double> @test70(<2 x i8> %a) {
+ %w = sitofp <2 x i8> %a to <2 x double>
+ ret <2 x double> %w
+
+; CHECK-LABEL: @test70
+; CHECK: vspltisw [[V1:[0-9]+]], 12
+; CHECK: vadduwm [[V2:[0-9]+]], [[V1]], [[V1]]
+; CHECK: vslw [[V3:[0-9]+]], 2, [[V2]]
+; CHECK: vsraw {{[0-9]+}}, [[V3]], [[V2]]
+; CHECK: xxsldwi [[V4:[0-9]+]], {{[0-9]+}}, {{[0-9]+}}, 1
+; CHECK: xvcvsxwdp 34, [[V4]]
+; CHECK: blr
+}
+
+define <2 x i32> @test80(i32 %v) {
+ %b1 = insertelement <2 x i32> undef, i32 %v, i32 0
+ %b2 = shufflevector <2 x i32> %b1, <2 x i32> undef, <2 x i32> zeroinitializer
+ %i = add <2 x i32> %b2, <i32 2, i32 3>
+ ret <2 x i32> %i
+
+; CHECK-LABEL: @test80
+; CHECK-DAG: addi [[R1:[0-9]+]], 3, 3
+; CHECK-DAG: addi [[R2:[0-9]+]], 1, -16
+; CHECK-DAG: addi [[R3:[0-9]+]], 3, 2
+; CHECK: std [[R1]], -8(1)
+; CHECK: std [[R3]], -16(1)
+; CHECK: lxvd2x 34, 0, [[R2]]
+; CHECK-NOT: stxvd2x
+; CHECK: blr
+}
+
+define <2 x double> @test81(<4 x float> %b) {
+ %w = bitcast <4 x float> %b to <2 x double>
+ ret <2 x double> %w
+
+; CHECK-LABEL: @test81
+; CHECK: blr
+}
+
+define double @test82(double %a, double %b, double %c, double %d) {
+entry:
+ %m = fcmp oeq double %c, %d
+ %v = select i1 %m, double %a, double %b
+ ret double %v
+
+; CHECK-LABEL: @test82
+; CHECK: xscmpudp [[REG:[0-9]+]], 3, 4
+; CHECK: beqlr [[REG]]
+}
+
projects / oota-llvm.git / blobdiff