def VLD1LNq16Pseudo : VLD1QLNPseudo<v8i16, extloadi16>;
def VLD1LNq32Pseudo : VLD1QLNPseudo<v4i32, load>;
+def : Pat<(vector_insert (v2f32 DPR:$src),
+ (f32 (load addrmode6:$addr)), imm:$lane),
+ (VLD1LNd32 addrmode6:$addr, DPR:$src, imm:$lane)>;
+def : Pat<(vector_insert (v4f32 QPR:$src),
+ (f32 (load addrmode6:$addr)), imm:$lane),
+ (VLD1LNq32Pseudo addrmode6:$addr, QPR:$src, imm:$lane)>;
+
let mayLoad = 1, neverHasSideEffects = 1, hasExtraDefRegAllocReq = 1 in {
// ...with address register writeback:
def VLD1DUPq16Pseudo : VLD1QDUPPseudo<v8i16, extloadi16>;
def VLD1DUPq32Pseudo : VLD1QDUPPseudo<v4i32, load>;
+def : Pat<(v2f32 (NEONvdup (f32 (load addrmode6dup:$addr)))),
+ (VLD1DUPd32 addrmode6:$addr)>;
+def : Pat<(v4f32 (NEONvdup (f32 (load addrmode6dup:$addr)))),
+ (VLD1DUPq32Pseudo addrmode6:$addr)>;
+
let mayLoad = 1, neverHasSideEffects = 1, hasExtraDefRegAllocReq = 1 in {
class VLD1QDUP<bits<4> op7_4, string Dt>
def VST1LNq16Pseudo : VST1QLNPseudo<v8i16, truncstorei16, NEONvgetlaneu>;
def VST1LNq32Pseudo : VST1QLNPseudo<v4i32, store, extractelt>;
+def : Pat<(store (extractelt (v2f32 DPR:$src), imm:$lane), addrmode6:$addr),
+ (VST1LNd32 addrmode6:$addr, DPR:$src, imm:$lane)>;
+def : Pat<(store (extractelt (v4f32 QPR:$src), imm:$lane), addrmode6:$addr),
+ (VST1LNq32Pseudo addrmode6:$addr, QPR:$src, imm:$lane)>;
+
let mayStore = 1, neverHasSideEffects = 1, hasExtraSrcRegAllocReq = 1 in {
// ...with address register writeback:
ret <4 x float> %tmp2
}
-define <2 x float> @v_shuffledupfloat2(float* %A) nounwind {
-;CHECK: v_shuffledupfloat2:
-;CHECK: vdup.32
- %tmp0 = load float* %A
- %tmp1 = insertelement <2 x float> undef, float %tmp0, i32 0
- %tmp2 = shufflevector <2 x float> %tmp1, <2 x float> undef, <2 x i32> zeroinitializer
- ret <2 x float> %tmp2
-}
-
-define <4 x float> @v_shuffledupQfloat2(float* %A) nounwind {
-;CHECK: v_shuffledupQfloat2:
-;CHECK: vdup.32
- %tmp0 = load float* %A
- %tmp1 = insertelement <4 x float> undef, float %tmp0, i32 0
- %tmp2 = shufflevector <4 x float> %tmp1, <4 x float> undef, <4 x i32> zeroinitializer
- ret <4 x float> %tmp2
-}
-
define <8 x i8> @vduplane8(<8 x i8>* %A) nounwind {
;CHECK: vduplane8:
;CHECK: vdup.8
ret <2 x i32> %tmp3
}
+define <2 x float> @vld1dupf(float* %A) nounwind {
+;CHECK: vld1dupf:
+;CHECK: vld1.32 {d16[]}, [r0]
+ %tmp0 = load float* %A
+ %tmp1 = insertelement <2 x float> undef, float %tmp0, i32 0
+ %tmp2 = shufflevector <2 x float> %tmp1, <2 x float> undef, <2 x i32> zeroinitializer
+ ret <2 x float> %tmp2
+}
+
define <16 x i8> @vld1dupQi8(i8* %A) nounwind {
;CHECK: vld1dupQi8:
;Check the (default) alignment value.
ret <16 x i8> %tmp3
}
+define <4 x float> @vld1dupQf(float* %A) nounwind {
+;CHECK: vld1dupQf:
+;CHECK: vld1.32 {d16[], d17[]}, [r0]
+ %tmp0 = load float* %A
+ %tmp1 = insertelement <4 x float> undef, float %tmp0, i32 0
+ %tmp2 = shufflevector <4 x float> %tmp1, <4 x float> undef, <4 x i32> zeroinitializer
+ ret <4 x float> %tmp2
+}
+
%struct.__neon_int8x8x2_t = type { <8 x i8>, <8 x i8> }
%struct.__neon_int4x16x2_t = type { <4 x i16>, <4 x i16> }
%struct.__neon_int2x32x2_t = type { <2 x i32>, <2 x i32> }
ret <2 x i32> %tmp3
}
+define <2 x float> @vld1lanef(float* %A, <2 x float>* %B) nounwind {
+;CHECK: vld1lanef:
+;CHECK: vld1.32 {d16[1]}, [r0]
+ %tmp1 = load <2 x float>* %B
+ %tmp2 = load float* %A, align 4
+ %tmp3 = insertelement <2 x float> %tmp1, float %tmp2, i32 1
+ ret <2 x float> %tmp3
+}
+
define <16 x i8> @vld1laneQi8(i8* %A, <16 x i8>* %B) nounwind {
;CHECK: vld1laneQi8:
;CHECK: vld1.8 {d17[1]}, [r0]
ret <4 x i32> %tmp3
}
+define <4 x float> @vld1laneQf(float* %A, <4 x float>* %B) nounwind {
+;CHECK: vld1laneQf:
+;CHECK: vld1.32 {d16[0]}, [r0]
+ %tmp1 = load <4 x float>* %B
+ %tmp2 = load float* %A
+ %tmp3 = insertelement <4 x float> %tmp1, float %tmp2, i32 0
+ ret <4 x float> %tmp3
+}
+
%struct.__neon_int8x8x2_t = type { <8 x i8>, <8 x i8> }
%struct.__neon_int16x4x2_t = type { <4 x i16>, <4 x i16> }
%struct.__neon_int32x2x2_t = type { <2 x i32>, <2 x i32> }
ret void
}
+define void @vst1lanef(float* %A, <2 x float>* %B) nounwind {
+;CHECK: vst1lanef:
+;CHECK: vst1.32 {d16[1]}, [r0]
+ %tmp1 = load <2 x float>* %B
+ %tmp2 = extractelement <2 x float> %tmp1, i32 1
+ store float %tmp2, float* %A
+ ret void
+}
+
define void @vst1laneQi8(i8* %A, <16 x i8>* %B) nounwind {
;CHECK: vst1laneQi8:
;CHECK: vst1.8 {d17[1]}, [r0]
ret void
}
+define void @vst1laneQf(float* %A, <4 x float>* %B) nounwind {
+;CHECK: vst1laneQf:
+;CHECK: vst1.32 {d17[1]}, [r0]
+ %tmp1 = load <4 x float>* %B
+ %tmp2 = extractelement <4 x float> %tmp1, i32 3
+ store float %tmp2, float* %A
+ ret void
+}
+
define void @vst2lanei8(i8* %A, <8 x i8>* %B) nounwind {
;CHECK: vst2lanei8:
;Check the alignment value. Max for this instruction is 16 bits: