2014-04-04 00:01:44 +08:00
|
|
|
; RUN: llc -mtriple=arm-eabi -mattr=+neon %s -o - | FileCheck %s
|
2009-08-22 04:54:19 +08:00
|
|
|
|
|
|
|
define <8 x i8> @vuzpi8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
|
2015-06-19 10:15:34 +08:00
|
|
|
; CHECK-LABEL: vuzpi8:
|
|
|
|
; CHECK: @ BB#0:
|
|
|
|
; CHECK-NEXT: vldr d16, [r1]
|
|
|
|
; CHECK-NEXT: vldr d17, [r0]
|
|
|
|
; CHECK-NEXT: vuzp.8 d17, d16
|
|
|
|
; CHECK-NEXT: vadd.i8 d16, d17, d16
|
|
|
|
; CHECK-NEXT: vmov r0, r1, d16
|
|
|
|
; CHECK-NEXT: mov pc, lr
|
2015-02-28 05:17:42 +08:00
|
|
|
%tmp1 = load <8 x i8>, <8 x i8>* %A
|
|
|
|
%tmp2 = load <8 x i8>, <8 x i8>* %B
|
2009-08-22 04:54:19 +08:00
|
|
|
%tmp3 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
|
|
|
|
%tmp4 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
|
|
|
|
%tmp5 = add <8 x i8> %tmp3, %tmp4
|
|
|
|
ret <8 x i8> %tmp5
|
|
|
|
}
|
|
|
|
|
2015-06-19 10:15:34 +08:00
|
|
|
define <16 x i8> @vuzpi8_Qres(<8 x i8>* %A, <8 x i8>* %B) nounwind {
|
|
|
|
; CHECK-LABEL: vuzpi8_Qres:
|
|
|
|
; CHECK: @ BB#0:
|
2015-09-24 16:36:14 +08:00
|
|
|
; CHECK-NEXT: vldr [[LDR1:d[0-9]+]], [r1]
|
|
|
|
; CHECK-NEXT: vldr [[LDR0:d[0-9]+]], [r0]
|
|
|
|
; CHECK-NEXT: vuzp.8 [[LDR0]], [[LDR1]]
|
|
|
|
; CHECK-NEXT: vmov r0, r1, [[LDR0]]
|
|
|
|
; CHECK-NEXT: vmov r2, r3, [[LDR1]]
|
2015-06-19 10:15:34 +08:00
|
|
|
; CHECK-NEXT: mov pc, lr
|
|
|
|
%tmp1 = load <8 x i8>, <8 x i8>* %A
|
|
|
|
%tmp2 = load <8 x i8>, <8 x i8>* %B
|
|
|
|
%tmp3 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <16 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
|
|
|
|
ret <16 x i8> %tmp3
|
|
|
|
}
|
|
|
|
|
2009-08-22 04:54:19 +08:00
|
|
|
define <4 x i16> @vuzpi16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
|
2015-06-19 10:15:34 +08:00
|
|
|
; CHECK-LABEL: vuzpi16:
|
|
|
|
; CHECK: @ BB#0:
|
|
|
|
; CHECK-NEXT: vldr d16, [r1]
|
|
|
|
; CHECK-NEXT: vldr d17, [r0]
|
|
|
|
; CHECK-NEXT: vuzp.16 d17, d16
|
|
|
|
; CHECK-NEXT: vadd.i16 d16, d17, d16
|
|
|
|
; CHECK-NEXT: vmov r0, r1, d16
|
|
|
|
; CHECK-NEXT: mov pc, lr
|
2015-02-28 05:17:42 +08:00
|
|
|
%tmp1 = load <4 x i16>, <4 x i16>* %A
|
|
|
|
%tmp2 = load <4 x i16>, <4 x i16>* %B
|
2009-08-22 04:54:19 +08:00
|
|
|
%tmp3 = shufflevector <4 x i16> %tmp1, <4 x i16> %tmp2, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
|
|
|
|
%tmp4 = shufflevector <4 x i16> %tmp1, <4 x i16> %tmp2, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
|
|
|
|
%tmp5 = add <4 x i16> %tmp3, %tmp4
|
|
|
|
ret <4 x i16> %tmp5
|
|
|
|
}
|
|
|
|
|
2015-06-19 10:15:34 +08:00
|
|
|
define <8 x i16> @vuzpi16_Qres(<4 x i16>* %A, <4 x i16>* %B) nounwind {
|
|
|
|
; CHECK-LABEL: vuzpi16_Qres:
|
|
|
|
; CHECK: @ BB#0:
|
2015-09-24 16:36:14 +08:00
|
|
|
; CHECK-NEXT: vldr [[LDR1:d[0-9]+]], [r1]
|
|
|
|
; CHECK-NEXT: vldr [[LDR0:d[0-9]+]], [r0]
|
|
|
|
; CHECK-NEXT: vuzp.16 [[LDR0]], [[LDR1]]
|
|
|
|
; CHECK-NEXT: vmov r0, r1, [[LDR0]]
|
|
|
|
; CHECK-NEXT: vmov r2, r3, [[LDR1]]
|
2015-06-19 10:15:34 +08:00
|
|
|
; CHECK-NEXT: mov pc, lr
|
|
|
|
%tmp1 = load <4 x i16>, <4 x i16>* %A
|
|
|
|
%tmp2 = load <4 x i16>, <4 x i16>* %B
|
|
|
|
%tmp3 = shufflevector <4 x i16> %tmp1, <4 x i16> %tmp2, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 1, i32 3, i32 5, i32 7>
|
|
|
|
ret <8 x i16> %tmp3
|
|
|
|
}
|
|
|
|
|
2009-08-22 04:54:19 +08:00
|
|
|
; VUZP.32 is equivalent to VTRN.32 for 64-bit vectors.
|
|
|
|
|
|
|
|
define <16 x i8> @vuzpQi8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
|
2015-06-19 10:15:34 +08:00
|
|
|
; CHECK-LABEL: vuzpQi8:
|
|
|
|
; CHECK: @ BB#0:
|
|
|
|
; CHECK-NEXT: vld1.64 {d16, d17}, [r1]
|
|
|
|
; CHECK-NEXT: vld1.64 {d18, d19}, [r0]
|
|
|
|
; CHECK-NEXT: vuzp.8 q9, q8
|
|
|
|
; CHECK-NEXT: vadd.i8 q8, q9, q8
|
|
|
|
; CHECK-NEXT: vmov r0, r1, d16
|
|
|
|
; CHECK-NEXT: vmov r2, r3, d17
|
|
|
|
; CHECK-NEXT: mov pc, lr
|
2015-02-28 05:17:42 +08:00
|
|
|
%tmp1 = load <16 x i8>, <16 x i8>* %A
|
|
|
|
%tmp2 = load <16 x i8>, <16 x i8>* %B
|
2009-08-22 04:54:19 +08:00
|
|
|
%tmp3 = shufflevector <16 x i8> %tmp1, <16 x i8> %tmp2, <16 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 16, i32 18, i32 20, i32 22, i32 24, i32 26, i32 28, i32 30>
|
|
|
|
%tmp4 = shufflevector <16 x i8> %tmp1, <16 x i8> %tmp2, <16 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15, i32 17, i32 19, i32 21, i32 23, i32 25, i32 27, i32 29, i32 31>
|
|
|
|
%tmp5 = add <16 x i8> %tmp3, %tmp4
|
|
|
|
ret <16 x i8> %tmp5
|
|
|
|
}
|
|
|
|
|
2015-06-19 10:15:34 +08:00
|
|
|
define <32 x i8> @vuzpQi8_QQres(<16 x i8>* %A, <16 x i8>* %B) nounwind {
|
|
|
|
; CHECK-LABEL: vuzpQi8_QQres:
|
|
|
|
; CHECK: @ BB#0:
|
|
|
|
; CHECK-NEXT: vld1.64 {d16, d17}, [r2]
|
|
|
|
; CHECK-NEXT: vld1.64 {d18, d19}, [r1]
|
|
|
|
; CHECK-NEXT: vuzp.8 q9, q8
|
|
|
|
; CHECK-NEXT: vst1.8 {d18, d19}, [r0:128]!
|
|
|
|
; CHECK-NEXT: vst1.64 {d16, d17}, [r0:128]
|
|
|
|
; CHECK-NEXT: mov pc, lr
|
|
|
|
%tmp1 = load <16 x i8>, <16 x i8>* %A
|
|
|
|
%tmp2 = load <16 x i8>, <16 x i8>* %B
|
|
|
|
%tmp3 = shufflevector <16 x i8> %tmp1, <16 x i8> %tmp2, <32 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 16, i32 18, i32 20, i32 22, i32 24, i32 26, i32 28, i32 30, i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15, i32 17, i32 19, i32 21, i32 23, i32 25, i32 27, i32 29, i32 31>
|
|
|
|
ret <32 x i8> %tmp3
|
|
|
|
}
|
|
|
|
|
2009-08-22 04:54:19 +08:00
|
|
|
define <8 x i16> @vuzpQi16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
|
2015-06-19 10:15:34 +08:00
|
|
|
; CHECK-LABEL: vuzpQi16:
|
|
|
|
; CHECK: @ BB#0:
|
|
|
|
; CHECK-NEXT: vld1.64 {d16, d17}, [r1]
|
|
|
|
; CHECK-NEXT: vld1.64 {d18, d19}, [r0]
|
|
|
|
; CHECK-NEXT: vuzp.16 q9, q8
|
|
|
|
; CHECK-NEXT: vadd.i16 q8, q9, q8
|
|
|
|
; CHECK-NEXT: vmov r0, r1, d16
|
|
|
|
; CHECK-NEXT: vmov r2, r3, d17
|
|
|
|
; CHECK-NEXT: mov pc, lr
|
2015-02-28 05:17:42 +08:00
|
|
|
%tmp1 = load <8 x i16>, <8 x i16>* %A
|
|
|
|
%tmp2 = load <8 x i16>, <8 x i16>* %B
|
2009-08-22 04:54:19 +08:00
|
|
|
%tmp3 = shufflevector <8 x i16> %tmp1, <8 x i16> %tmp2, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
|
|
|
|
%tmp4 = shufflevector <8 x i16> %tmp1, <8 x i16> %tmp2, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
|
|
|
|
%tmp5 = add <8 x i16> %tmp3, %tmp4
|
|
|
|
ret <8 x i16> %tmp5
|
|
|
|
}
|
|
|
|
|
2015-06-19 10:15:34 +08:00
|
|
|
define <16 x i16> @vuzpQi16_QQres(<8 x i16>* %A, <8 x i16>* %B) nounwind {
|
|
|
|
; CHECK-LABEL: vuzpQi16_QQres:
|
|
|
|
; CHECK: @ BB#0:
|
|
|
|
; CHECK-NEXT: vld1.64 {d16, d17}, [r2]
|
|
|
|
; CHECK-NEXT: vld1.64 {d18, d19}, [r1]
|
|
|
|
; CHECK-NEXT: vuzp.16 q9, q8
|
|
|
|
; CHECK-NEXT: vst1.16 {d18, d19}, [r0:128]!
|
|
|
|
; CHECK-NEXT: vst1.64 {d16, d17}, [r0:128]
|
|
|
|
; CHECK-NEXT: mov pc, lr
|
|
|
|
%tmp1 = load <8 x i16>, <8 x i16>* %A
|
|
|
|
%tmp2 = load <8 x i16>, <8 x i16>* %B
|
|
|
|
%tmp3 = shufflevector <8 x i16> %tmp1, <8 x i16> %tmp2, <16 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
|
|
|
|
ret <16 x i16> %tmp3
|
|
|
|
}
|
|
|
|
|
2009-08-22 04:54:19 +08:00
|
|
|
define <4 x i32> @vuzpQi32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
|
2015-06-19 10:15:34 +08:00
|
|
|
; CHECK-LABEL: vuzpQi32:
|
|
|
|
; CHECK: @ BB#0:
|
|
|
|
; CHECK-NEXT: vld1.64 {d16, d17}, [r1]
|
|
|
|
; CHECK-NEXT: vld1.64 {d18, d19}, [r0]
|
|
|
|
; CHECK-NEXT: vuzp.32 q9, q8
|
|
|
|
; CHECK-NEXT: vadd.i32 q8, q9, q8
|
|
|
|
; CHECK-NEXT: vmov r0, r1, d16
|
|
|
|
; CHECK-NEXT: vmov r2, r3, d17
|
|
|
|
; CHECK-NEXT: mov pc, lr
|
2015-02-28 05:17:42 +08:00
|
|
|
%tmp1 = load <4 x i32>, <4 x i32>* %A
|
|
|
|
%tmp2 = load <4 x i32>, <4 x i32>* %B
|
2009-08-22 04:54:19 +08:00
|
|
|
%tmp3 = shufflevector <4 x i32> %tmp1, <4 x i32> %tmp2, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
|
|
|
|
%tmp4 = shufflevector <4 x i32> %tmp1, <4 x i32> %tmp2, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
|
|
|
|
%tmp5 = add <4 x i32> %tmp3, %tmp4
|
|
|
|
ret <4 x i32> %tmp5
|
|
|
|
}
|
|
|
|
|
2015-06-19 10:15:34 +08:00
|
|
|
define <8 x i32> @vuzpQi32_QQres(<4 x i32>* %A, <4 x i32>* %B) nounwind {
|
|
|
|
; CHECK-LABEL: vuzpQi32_QQres:
|
|
|
|
; CHECK: @ BB#0:
|
|
|
|
; CHECK-NEXT: vld1.64 {d16, d17}, [r2]
|
|
|
|
; CHECK-NEXT: vld1.64 {d18, d19}, [r1]
|
|
|
|
; CHECK-NEXT: vuzp.32 q9, q8
|
|
|
|
; CHECK-NEXT: vst1.32 {d18, d19}, [r0:128]!
|
|
|
|
; CHECK-NEXT: vst1.64 {d16, d17}, [r0:128]
|
|
|
|
; CHECK-NEXT: mov pc, lr
|
|
|
|
%tmp1 = load <4 x i32>, <4 x i32>* %A
|
|
|
|
%tmp2 = load <4 x i32>, <4 x i32>* %B
|
|
|
|
%tmp3 = shufflevector <4 x i32> %tmp1, <4 x i32> %tmp2, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 1, i32 3, i32 5, i32 7>
|
|
|
|
ret <8 x i32> %tmp3
|
|
|
|
}
|
|
|
|
|
2009-08-22 04:54:19 +08:00
|
|
|
define <4 x float> @vuzpQf(<4 x float>* %A, <4 x float>* %B) nounwind {
|
2015-06-19 10:15:34 +08:00
|
|
|
; CHECK-LABEL: vuzpQf:
|
|
|
|
; CHECK: @ BB#0:
|
|
|
|
; CHECK-NEXT: vld1.64 {d16, d17}, [r1]
|
|
|
|
; CHECK-NEXT: vld1.64 {d18, d19}, [r0]
|
|
|
|
; CHECK-NEXT: vuzp.32 q9, q8
|
|
|
|
; CHECK-NEXT: vadd.f32 q8, q9, q8
|
|
|
|
; CHECK-NEXT: vmov r0, r1, d16
|
|
|
|
; CHECK-NEXT: vmov r2, r3, d17
|
|
|
|
; CHECK-NEXT: mov pc, lr
|
2015-02-28 05:17:42 +08:00
|
|
|
%tmp1 = load <4 x float>, <4 x float>* %A
|
|
|
|
%tmp2 = load <4 x float>, <4 x float>* %B
|
2009-08-22 04:54:19 +08:00
|
|
|
%tmp3 = shufflevector <4 x float> %tmp1, <4 x float> %tmp2, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
|
|
|
|
%tmp4 = shufflevector <4 x float> %tmp1, <4 x float> %tmp2, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
|
2010-05-04 06:36:46 +08:00
|
|
|
%tmp5 = fadd <4 x float> %tmp3, %tmp4
|
2009-08-22 04:54:19 +08:00
|
|
|
ret <4 x float> %tmp5
|
|
|
|
}
|
2010-08-17 13:54:34 +08:00
|
|
|
|
2015-06-19 10:15:34 +08:00
|
|
|
define <8 x float> @vuzpQf_QQres(<4 x float>* %A, <4 x float>* %B) nounwind {
|
|
|
|
; CHECK-LABEL: vuzpQf_QQres:
|
|
|
|
; CHECK: @ BB#0:
|
|
|
|
; CHECK-NEXT: vld1.64 {d16, d17}, [r2]
|
|
|
|
; CHECK-NEXT: vld1.64 {d18, d19}, [r1]
|
|
|
|
; CHECK-NEXT: vuzp.32 q9, q8
|
|
|
|
; CHECK-NEXT: vst1.32 {d18, d19}, [r0:128]!
|
|
|
|
; CHECK-NEXT: vst1.64 {d16, d17}, [r0:128]
|
|
|
|
; CHECK-NEXT: mov pc, lr
|
|
|
|
%tmp1 = load <4 x float>, <4 x float>* %A
|
|
|
|
%tmp2 = load <4 x float>, <4 x float>* %B
|
|
|
|
%tmp3 = shufflevector <4 x float> %tmp1, <4 x float> %tmp2, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 1, i32 3, i32 5, i32 7>
|
|
|
|
ret <8 x float> %tmp3
|
|
|
|
}
|
|
|
|
|
2010-08-17 13:54:34 +08:00
|
|
|
; Undef shuffle indices should not prevent matching to VUZP:
|
|
|
|
|
|
|
|
define <8 x i8> @vuzpi8_undef(<8 x i8>* %A, <8 x i8>* %B) nounwind {
|
2015-06-19 10:15:34 +08:00
|
|
|
; CHECK-LABEL: vuzpi8_undef:
|
|
|
|
; CHECK: @ BB#0:
|
|
|
|
; CHECK-NEXT: vldr d16, [r1]
|
|
|
|
; CHECK-NEXT: vldr d17, [r0]
|
|
|
|
; CHECK-NEXT: vuzp.8 d17, d16
|
|
|
|
; CHECK-NEXT: vadd.i8 d16, d17, d16
|
|
|
|
; CHECK-NEXT: vmov r0, r1, d16
|
|
|
|
; CHECK-NEXT: mov pc, lr
|
2015-02-28 05:17:42 +08:00
|
|
|
%tmp1 = load <8 x i8>, <8 x i8>* %A
|
|
|
|
%tmp2 = load <8 x i8>, <8 x i8>* %B
|
2010-08-17 13:54:34 +08:00
|
|
|
%tmp3 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 0, i32 2, i32 undef, i32 undef, i32 8, i32 10, i32 12, i32 14>
|
|
|
|
%tmp4 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 undef, i32 undef, i32 13, i32 15>
|
|
|
|
%tmp5 = add <8 x i8> %tmp3, %tmp4
|
|
|
|
ret <8 x i8> %tmp5
|
|
|
|
}
|
|
|
|
|
2015-06-19 10:15:34 +08:00
|
|
|
define <16 x i8> @vuzpi8_undef_Qres(<8 x i8>* %A, <8 x i8>* %B) nounwind {
|
|
|
|
; CHECK-LABEL: vuzpi8_undef_Qres:
|
|
|
|
; CHECK: @ BB#0:
|
2015-09-24 16:36:14 +08:00
|
|
|
; CHECK-NEXT: vldr [[LDR1:d[0-9]+]], [r1]
|
|
|
|
; CHECK-NEXT: vldr [[LDR0:d[0-9]+]], [r0]
|
|
|
|
; CHECK-NEXT: vuzp.8 [[LDR0]], [[LDR1]]
|
|
|
|
; CHECK-NEXT: vmov r0, r1, [[LDR0]]
|
|
|
|
; CHECK-NEXT: vmov r2, r3, [[LDR1]]
|
2015-06-19 10:15:34 +08:00
|
|
|
; CHECK-NEXT: mov pc, lr
|
|
|
|
%tmp1 = load <8 x i8>, <8 x i8>* %A
|
|
|
|
%tmp2 = load <8 x i8>, <8 x i8>* %B
|
|
|
|
%tmp3 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <16 x i32> <i32 0, i32 2, i32 undef, i32 undef, i32 8, i32 10, i32 12, i32 14, i32 1, i32 3, i32 5, i32 7, i32 undef, i32 undef, i32 13, i32 15>
|
|
|
|
ret <16 x i8> %tmp3
|
|
|
|
}
|
|
|
|
|
2010-08-17 13:54:34 +08:00
|
|
|
define <8 x i16> @vuzpQi16_undef(<8 x i16>* %A, <8 x i16>* %B) nounwind {
|
2015-06-19 10:15:34 +08:00
|
|
|
; CHECK-LABEL: vuzpQi16_undef:
|
|
|
|
; CHECK: @ BB#0:
|
|
|
|
; CHECK-NEXT: vld1.64 {d16, d17}, [r1]
|
|
|
|
; CHECK-NEXT: vld1.64 {d18, d19}, [r0]
|
|
|
|
; CHECK-NEXT: vuzp.16 q9, q8
|
|
|
|
; CHECK-NEXT: vadd.i16 q8, q9, q8
|
|
|
|
; CHECK-NEXT: vmov r0, r1, d16
|
|
|
|
; CHECK-NEXT: vmov r2, r3, d17
|
|
|
|
; CHECK-NEXT: mov pc, lr
|
2015-02-28 05:17:42 +08:00
|
|
|
%tmp1 = load <8 x i16>, <8 x i16>* %A
|
|
|
|
%tmp2 = load <8 x i16>, <8 x i16>* %B
|
2010-08-17 13:54:34 +08:00
|
|
|
%tmp3 = shufflevector <8 x i16> %tmp1, <8 x i16> %tmp2, <8 x i32> <i32 0, i32 undef, i32 4, i32 undef, i32 8, i32 10, i32 12, i32 14>
|
|
|
|
%tmp4 = shufflevector <8 x i16> %tmp1, <8 x i16> %tmp2, <8 x i32> <i32 1, i32 3, i32 5, i32 undef, i32 undef, i32 11, i32 13, i32 15>
|
|
|
|
%tmp5 = add <8 x i16> %tmp3, %tmp4
|
|
|
|
ret <8 x i16> %tmp5
|
|
|
|
}
|
|
|
|
|
2015-06-19 10:15:34 +08:00
|
|
|
define <16 x i16> @vuzpQi16_undef_QQres(<8 x i16>* %A, <8 x i16>* %B) nounwind {
|
|
|
|
; CHECK-LABEL: vuzpQi16_undef_QQres:
|
|
|
|
; CHECK: @ BB#0:
|
|
|
|
; CHECK-NEXT: vld1.64 {d16, d17}, [r2]
|
|
|
|
; CHECK-NEXT: vld1.64 {d18, d19}, [r1]
|
|
|
|
; CHECK-NEXT: vuzp.16 q9, q8
|
|
|
|
; CHECK-NEXT: vst1.16 {d18, d19}, [r0:128]!
|
|
|
|
; CHECK-NEXT: vst1.64 {d16, d17}, [r0:128]
|
|
|
|
; CHECK-NEXT: mov pc, lr
|
|
|
|
%tmp1 = load <8 x i16>, <8 x i16>* %A
|
|
|
|
%tmp2 = load <8 x i16>, <8 x i16>* %B
|
|
|
|
%tmp3 = shufflevector <8 x i16> %tmp1, <8 x i16> %tmp2, <16 x i32> <i32 0, i32 undef, i32 4, i32 undef, i32 8, i32 10, i32 12, i32 14, i32 1, i32 3, i32 5, i32 undef, i32 undef, i32 11, i32 13, i32 15>
|
|
|
|
ret <16 x i16> %tmp3
|
|
|
|
}
|
2015-07-24 17:57:05 +08:00
|
|
|
|
|
|
|
define <8 x i16> @vuzp_lower_shufflemask_undef(<4 x i16>* %A, <4 x i16>* %B) {
|
|
|
|
entry:
|
|
|
|
; CHECK-LABEL: vuzp_lower_shufflemask_undef
|
|
|
|
; CHECK: vuzp
|
|
|
|
%tmp1 = load <4 x i16>, <4 x i16>* %A
|
|
|
|
%tmp2 = load <4 x i16>, <4 x i16>* %B
|
|
|
|
%0 = shufflevector <4 x i16> %tmp1, <4 x i16> %tmp2, <8 x i32> <i32 undef, i32 undef, i32 undef, i32 undef, i32 1, i32 3, i32 5, i32 7>
|
|
|
|
ret <8 x i16> %0
|
|
|
|
}
|
|
|
|
|
|
|
|
define <4 x i32> @vuzp_lower_shufflemask_zeroed(<2 x i32>* %A, <2 x i32>* %B) {
|
|
|
|
entry:
|
|
|
|
; CHECK-LABEL: vuzp_lower_shufflemask_zeroed
|
|
|
|
; CHECK-NOT: vtrn
|
|
|
|
; CHECK: vuzp
|
|
|
|
%tmp1 = load <2 x i32>, <2 x i32>* %A
|
|
|
|
%tmp2 = load <2 x i32>, <2 x i32>* %B
|
|
|
|
%0 = shufflevector <2 x i32> %tmp1, <2 x i32> %tmp2, <4 x i32> <i32 0, i32 0, i32 1, i32 3>
|
|
|
|
ret <4 x i32> %0
|
|
|
|
}
|
2015-08-07 19:40:46 +08:00
|
|
|
|
[ARM] Do not use vtrn for vectorshuffle if the order is reversed
The tests in isVTRNMask and isVTRN_v_undef_Mask should also check that the elements of the upper and lower half of the vectorshuffle occur in the correct order when both halves are used. Without this test the code assumes that it is correct to use vector transpose (vtrn) for the masks <1, 1, 0, 0> and <1, 3, 0, 2>, among others, but the transpose actually incorrectly generates shuffles for <0, 0, 1, 1> and <0, 2, 1, 3> in this case.
Patch by Jeroen Ketema!
llvm-svn: 247254
2015-09-10 16:42:28 +08:00
|
|
|
define void @vuzp_rev_shufflemask_vtrn(<2 x i32>* %A, <2 x i32>* %B, <4 x i32>* %C) {
|
|
|
|
entry:
|
|
|
|
; CHECK-LABEL: vuzp_rev_shufflemask_vtrn
|
|
|
|
; CHECK-NOT: vtrn
|
|
|
|
; CHECK: vuzp
|
|
|
|
%tmp1 = load <2 x i32>, <2 x i32>* %A
|
|
|
|
%tmp2 = load <2 x i32>, <2 x i32>* %B
|
|
|
|
%0 = shufflevector <2 x i32> %tmp1, <2 x i32> %tmp2, <4 x i32> <i32 1, i32 3, i32 0, i32 2>
|
|
|
|
store <4 x i32> %0, <4 x i32>* %C
|
|
|
|
ret void
|
|
|
|
}
|
|
|
|
|
2015-08-07 19:40:46 +08:00
|
|
|
define <8 x i8> @vuzp_trunc(<8 x i8> %in0, <8 x i8> %in1, <8 x i32> %cmp0, <8 x i32> %cmp1) {
|
|
|
|
; In order to create the select we need to truncate the vcgt result from a vector of i32 to a vector of i8.
|
|
|
|
; This results in a build_vector with mismatched types. We will generate two vmovn.i32 instructions to
|
|
|
|
; truncate from i32 to i16 and one vuzp to perform the final truncation for i8.
|
|
|
|
; CHECK-LABEL: vuzp_trunc
|
|
|
|
; CHECK: vmovn.i32
|
|
|
|
; CHECK: vmovn.i32
|
|
|
|
; CHECK: vuzp
|
|
|
|
; CHECK: vbsl
|
|
|
|
%c = icmp ult <8 x i32> %cmp0, %cmp1
|
|
|
|
%res = select <8 x i1> %c, <8 x i8> %in0, <8 x i8> %in1
|
|
|
|
ret <8 x i8> %res
|
|
|
|
}
|
|
|
|
|
|
|
|
; Shuffle the result from the compare with a <4 x i8>.
|
|
|
|
; We need to extend the loaded <4 x i8> to <4 x i16>. Otherwise we wouldn't be able
|
|
|
|
; to perform the vuzp and get the vbsl mask.
|
|
|
|
define <8 x i8> @vuzp_trunc_and_shuffle(<8 x i8> %tr0, <8 x i8> %tr1,
|
|
|
|
<4 x i32> %cmp0, <4 x i32> %cmp1, <4 x i8> *%cmp2_ptr) {
|
|
|
|
; CHECK-LABEL: vuzp_trunc_and_shuffle
|
|
|
|
; CHECK: vmovl
|
|
|
|
; CHECK: vuzp
|
|
|
|
; CHECK: vbsl
|
|
|
|
%cmp2_load = load <4 x i8>, <4 x i8> * %cmp2_ptr, align 4
|
|
|
|
%cmp2 = trunc <4 x i8> %cmp2_load to <4 x i1>
|
|
|
|
%c0 = icmp ult <4 x i32> %cmp0, %cmp1
|
|
|
|
%c = shufflevector <4 x i1> %c0, <4 x i1> %cmp2, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
|
|
|
|
%rv = select <8 x i1> %c, <8 x i8> %tr0, <8 x i8> %tr1
|
|
|
|
ret <8 x i8> %rv
|
|
|
|
}
|
|
|
|
|
|
|
|
; Use an undef value for the <4 x i8> that is being shuffled with the compare result.
|
|
|
|
; This produces a build_vector with some of the operands undefs.
|
|
|
|
define <8 x i8> @vuzp_trunc_and_shuffle_undef_right(<8 x i8> %tr0, <8 x i8> %tr1,
|
|
|
|
<4 x i32> %cmp0, <4 x i32> %cmp1, <4 x i8> *%cmp2_ptr) {
|
|
|
|
; CHECK-LABEL: vuzp_trunc_and_shuffle_undef_right
|
|
|
|
; CHECK: vuzp
|
|
|
|
; CHECK: vbsl
|
|
|
|
%cmp2_load = load <4 x i8>, <4 x i8> * %cmp2_ptr, align 4
|
|
|
|
%cmp2 = trunc <4 x i8> %cmp2_load to <4 x i1>
|
|
|
|
%c0 = icmp ult <4 x i32> %cmp0, %cmp1
|
|
|
|
%c = shufflevector <4 x i1> %c0, <4 x i1> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
|
|
|
|
%rv = select <8 x i1> %c, <8 x i8> %tr0, <8 x i8> %tr1
|
|
|
|
ret <8 x i8> %rv
|
|
|
|
}
|
|
|
|
|
|
|
|
define <8 x i8> @vuzp_trunc_and_shuffle_undef_left(<8 x i8> %tr0, <8 x i8> %tr1,
|
|
|
|
<4 x i32> %cmp0, <4 x i32> %cmp1, <4 x i8> *%cmp2_ptr) {
|
|
|
|
; CHECK-LABEL: vuzp_trunc_and_shuffle_undef_left
|
|
|
|
; CHECK: vuzp
|
|
|
|
; CHECK: vbsl
|
|
|
|
%cmp2_load = load <4 x i8>, <4 x i8> * %cmp2_ptr, align 4
|
|
|
|
%cmp2 = trunc <4 x i8> %cmp2_load to <4 x i1>
|
|
|
|
%c0 = icmp ult <4 x i32> %cmp0, %cmp1
|
|
|
|
%c = shufflevector <4 x i1> undef, <4 x i1> %c0, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
|
|
|
|
%rv = select <8 x i1> %c, <8 x i8> %tr0, <8 x i8> %tr1
|
|
|
|
ret <8 x i8> %rv
|
|
|
|
}
|
|
|
|
|
|
|
|
; We're using large data types here, and we have to fill with undef values until we
|
|
|
|
; get some vector size that we can represent.
|
|
|
|
define <10 x i8> @vuzp_wide_type(<10 x i8> %tr0, <10 x i8> %tr1,
|
|
|
|
<5 x i32> %cmp0, <5 x i32> %cmp1, <5 x i8> *%cmp2_ptr) {
|
|
|
|
; CHECK-LABEL: vuzp_wide_type
|
|
|
|
; CHECK: vbsl
|
|
|
|
%cmp2_load = load <5 x i8>, <5 x i8> * %cmp2_ptr, align 4
|
|
|
|
%cmp2 = trunc <5 x i8> %cmp2_load to <5 x i1>
|
|
|
|
%c0 = icmp ult <5 x i32> %cmp0, %cmp1
|
|
|
|
%c = shufflevector <5 x i1> %c0, <5 x i1> %cmp2, <10 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9>
|
|
|
|
%rv = select <10 x i1> %c, <10 x i8> %tr0, <10 x i8> %tr1
|
|
|
|
ret <10 x i8> %rv
|
|
|
|
}
|