mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-30 23:42:52 +01:00
6239dc42c6
llvm-svn: 111226
125 lines
4.8 KiB
LLVM
125 lines
4.8 KiB
LLVM
; RUN: llc < %s -march=arm -mattr=+neon | FileCheck %s
|
|
|
|
define <8 x i8> @vtrni8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
|
|
;CHECK: vtrni8:
|
|
;CHECK: vtrn.8
|
|
;CHECK-NEXT: vadd.i8
|
|
%tmp1 = load <8 x i8>* %A
|
|
%tmp2 = load <8 x i8>* %B
|
|
%tmp3 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
|
|
%tmp4 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 1, i32 9, i32 3, i32 11, i32 5, i32 13, i32 7, i32 15>
|
|
%tmp5 = add <8 x i8> %tmp3, %tmp4
|
|
ret <8 x i8> %tmp5
|
|
}
|
|
|
|
define <4 x i16> @vtrni16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
|
|
;CHECK: vtrni16:
|
|
;CHECK: vtrn.16
|
|
;CHECK-NEXT: vadd.i16
|
|
%tmp1 = load <4 x i16>* %A
|
|
%tmp2 = load <4 x i16>* %B
|
|
%tmp3 = shufflevector <4 x i16> %tmp1, <4 x i16> %tmp2, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
|
|
%tmp4 = shufflevector <4 x i16> %tmp1, <4 x i16> %tmp2, <4 x i32> <i32 1, i32 5, i32 3, i32 7>
|
|
%tmp5 = add <4 x i16> %tmp3, %tmp4
|
|
ret <4 x i16> %tmp5
|
|
}
|
|
|
|
define <2 x i32> @vtrni32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
|
|
;CHECK: vtrni32:
|
|
;CHECK: vtrn.32
|
|
;CHECK-NEXT: vadd.i32
|
|
%tmp1 = load <2 x i32>* %A
|
|
%tmp2 = load <2 x i32>* %B
|
|
%tmp3 = shufflevector <2 x i32> %tmp1, <2 x i32> %tmp2, <2 x i32> <i32 0, i32 2>
|
|
%tmp4 = shufflevector <2 x i32> %tmp1, <2 x i32> %tmp2, <2 x i32> <i32 1, i32 3>
|
|
%tmp5 = add <2 x i32> %tmp3, %tmp4
|
|
ret <2 x i32> %tmp5
|
|
}
|
|
|
|
define <2 x float> @vtrnf(<2 x float>* %A, <2 x float>* %B) nounwind {
|
|
;CHECK: vtrnf:
|
|
;CHECK: vtrn.32
|
|
;CHECK-NEXT: vadd.f32
|
|
%tmp1 = load <2 x float>* %A
|
|
%tmp2 = load <2 x float>* %B
|
|
%tmp3 = shufflevector <2 x float> %tmp1, <2 x float> %tmp2, <2 x i32> <i32 0, i32 2>
|
|
%tmp4 = shufflevector <2 x float> %tmp1, <2 x float> %tmp2, <2 x i32> <i32 1, i32 3>
|
|
%tmp5 = fadd <2 x float> %tmp3, %tmp4
|
|
ret <2 x float> %tmp5
|
|
}
|
|
|
|
define <16 x i8> @vtrnQi8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
|
|
;CHECK: vtrnQi8:
|
|
;CHECK: vtrn.8
|
|
;CHECK-NEXT: vadd.i8
|
|
%tmp1 = load <16 x i8>* %A
|
|
%tmp2 = load <16 x i8>* %B
|
|
%tmp3 = shufflevector <16 x i8> %tmp1, <16 x i8> %tmp2, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
|
|
%tmp4 = shufflevector <16 x i8> %tmp1, <16 x i8> %tmp2, <16 x i32> <i32 1, i32 17, i32 3, i32 19, i32 5, i32 21, i32 7, i32 23, i32 9, i32 25, i32 11, i32 27, i32 13, i32 29, i32 15, i32 31>
|
|
%tmp5 = add <16 x i8> %tmp3, %tmp4
|
|
ret <16 x i8> %tmp5
|
|
}
|
|
|
|
define <8 x i16> @vtrnQi16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
|
|
;CHECK: vtrnQi16:
|
|
;CHECK: vtrn.16
|
|
;CHECK-NEXT: vadd.i16
|
|
%tmp1 = load <8 x i16>* %A
|
|
%tmp2 = load <8 x i16>* %B
|
|
%tmp3 = shufflevector <8 x i16> %tmp1, <8 x i16> %tmp2, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
|
|
%tmp4 = shufflevector <8 x i16> %tmp1, <8 x i16> %tmp2, <8 x i32> <i32 1, i32 9, i32 3, i32 11, i32 5, i32 13, i32 7, i32 15>
|
|
%tmp5 = add <8 x i16> %tmp3, %tmp4
|
|
ret <8 x i16> %tmp5
|
|
}
|
|
|
|
define <4 x i32> @vtrnQi32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
|
|
;CHECK: vtrnQi32:
|
|
;CHECK: vtrn.32
|
|
;CHECK-NEXT: vadd.i32
|
|
%tmp1 = load <4 x i32>* %A
|
|
%tmp2 = load <4 x i32>* %B
|
|
%tmp3 = shufflevector <4 x i32> %tmp1, <4 x i32> %tmp2, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
|
|
%tmp4 = shufflevector <4 x i32> %tmp1, <4 x i32> %tmp2, <4 x i32> <i32 1, i32 5, i32 3, i32 7>
|
|
%tmp5 = add <4 x i32> %tmp3, %tmp4
|
|
ret <4 x i32> %tmp5
|
|
}
|
|
|
|
define <4 x float> @vtrnQf(<4 x float>* %A, <4 x float>* %B) nounwind {
|
|
;CHECK: vtrnQf:
|
|
;CHECK: vtrn.32
|
|
;CHECK-NEXT: vadd.f32
|
|
%tmp1 = load <4 x float>* %A
|
|
%tmp2 = load <4 x float>* %B
|
|
%tmp3 = shufflevector <4 x float> %tmp1, <4 x float> %tmp2, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
|
|
%tmp4 = shufflevector <4 x float> %tmp1, <4 x float> %tmp2, <4 x i32> <i32 1, i32 5, i32 3, i32 7>
|
|
%tmp5 = fadd <4 x float> %tmp3, %tmp4
|
|
ret <4 x float> %tmp5
|
|
}
|
|
|
|
; Undef shuffle indices should not prevent matching to VTRN:
|
|
|
|
define <8 x i8> @vtrni8_undef(<8 x i8>* %A, <8 x i8>* %B) nounwind {
|
|
;CHECK: vtrni8_undef:
|
|
;CHECK: vtrn.8
|
|
;CHECK-NEXT: vadd.i8
|
|
%tmp1 = load <8 x i8>* %A
|
|
%tmp2 = load <8 x i8>* %B
|
|
%tmp3 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 0, i32 undef, i32 2, i32 10, i32 undef, i32 12, i32 6, i32 14>
|
|
%tmp4 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 1, i32 9, i32 3, i32 11, i32 5, i32 undef, i32 undef, i32 15>
|
|
%tmp5 = add <8 x i8> %tmp3, %tmp4
|
|
ret <8 x i8> %tmp5
|
|
}
|
|
|
|
define <8 x i16> @vtrnQi16_undef(<8 x i16>* %A, <8 x i16>* %B) nounwind {
|
|
;CHECK: vtrnQi16_undef:
|
|
;CHECK: vtrn.16
|
|
;CHECK-NEXT: vadd.i16
|
|
%tmp1 = load <8 x i16>* %A
|
|
%tmp2 = load <8 x i16>* %B
|
|
%tmp3 = shufflevector <8 x i16> %tmp1, <8 x i16> %tmp2, <8 x i32> <i32 0, i32 8, i32 undef, i32 undef, i32 4, i32 12, i32 6, i32 14>
|
|
%tmp4 = shufflevector <8 x i16> %tmp1, <8 x i16> %tmp2, <8 x i32> <i32 1, i32 undef, i32 3, i32 11, i32 5, i32 13, i32 undef, i32 undef>
|
|
%tmp5 = add <8 x i16> %tmp3, %tmp4
|
|
ret <8 x i16> %tmp5
|
|
}
|
|
|