2009-09-09 08:09:15 +08:00
|
|
|
; RUN: llc < %s -march=arm -mattr=+neon | FileCheck %s
|
2009-07-26 08:39:34 +08:00
|
|
|
|
2010-06-17 23:18:27 +08:00
|
|
|
define <8 x i8> @test_vrev64D8(<8 x i8>* %A) nounwind {
|
2013-07-14 04:38:47 +08:00
|
|
|
;CHECK-LABEL: test_vrev64D8:
|
2009-07-26 08:39:34 +08:00
|
|
|
;CHECK: vrev64.8
|
|
|
|
%tmp1 = load <8 x i8>* %A
|
|
|
|
%tmp2 = shufflevector <8 x i8> %tmp1, <8 x i8> undef, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
|
|
|
|
ret <8 x i8> %tmp2
|
|
|
|
}
|
|
|
|
|
2010-06-17 23:18:27 +08:00
|
|
|
define <4 x i16> @test_vrev64D16(<4 x i16>* %A) nounwind {
|
2013-07-14 04:38:47 +08:00
|
|
|
;CHECK-LABEL: test_vrev64D16:
|
2009-07-26 08:39:34 +08:00
|
|
|
;CHECK: vrev64.16
|
|
|
|
%tmp1 = load <4 x i16>* %A
|
|
|
|
%tmp2 = shufflevector <4 x i16> %tmp1, <4 x i16> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
|
|
|
|
ret <4 x i16> %tmp2
|
|
|
|
}
|
|
|
|
|
2010-06-17 23:18:27 +08:00
|
|
|
define <2 x i32> @test_vrev64D32(<2 x i32>* %A) nounwind {
|
2013-07-14 04:38:47 +08:00
|
|
|
;CHECK-LABEL: test_vrev64D32:
|
2009-07-26 08:39:34 +08:00
|
|
|
;CHECK: vrev64.32
|
|
|
|
%tmp1 = load <2 x i32>* %A
|
|
|
|
%tmp2 = shufflevector <2 x i32> %tmp1, <2 x i32> undef, <2 x i32> <i32 1, i32 0>
|
|
|
|
ret <2 x i32> %tmp2
|
|
|
|
}
|
|
|
|
|
2010-06-17 23:18:27 +08:00
|
|
|
define <2 x float> @test_vrev64Df(<2 x float>* %A) nounwind {
|
2013-07-14 04:38:47 +08:00
|
|
|
;CHECK-LABEL: test_vrev64Df:
|
2009-07-26 08:39:34 +08:00
|
|
|
;CHECK: vrev64.32
|
|
|
|
%tmp1 = load <2 x float>* %A
|
|
|
|
%tmp2 = shufflevector <2 x float> %tmp1, <2 x float> undef, <2 x i32> <i32 1, i32 0>
|
|
|
|
ret <2 x float> %tmp2
|
|
|
|
}
|
|
|
|
|
2010-06-17 23:18:27 +08:00
|
|
|
define <16 x i8> @test_vrev64Q8(<16 x i8>* %A) nounwind {
|
2013-07-14 04:38:47 +08:00
|
|
|
;CHECK-LABEL: test_vrev64Q8:
|
2009-07-26 08:39:34 +08:00
|
|
|
;CHECK: vrev64.8
|
|
|
|
%tmp1 = load <16 x i8>* %A
|
|
|
|
%tmp2 = shufflevector <16 x i8> %tmp1, <16 x i8> undef, <16 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8>
|
|
|
|
ret <16 x i8> %tmp2
|
|
|
|
}
|
|
|
|
|
2010-06-17 23:18:27 +08:00
|
|
|
define <8 x i16> @test_vrev64Q16(<8 x i16>* %A) nounwind {
|
2013-07-14 04:38:47 +08:00
|
|
|
;CHECK-LABEL: test_vrev64Q16:
|
2009-07-26 08:39:34 +08:00
|
|
|
;CHECK: vrev64.16
|
|
|
|
%tmp1 = load <8 x i16>* %A
|
|
|
|
%tmp2 = shufflevector <8 x i16> %tmp1, <8 x i16> undef, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4>
|
|
|
|
ret <8 x i16> %tmp2
|
|
|
|
}
|
|
|
|
|
2010-06-17 23:18:27 +08:00
|
|
|
define <4 x i32> @test_vrev64Q32(<4 x i32>* %A) nounwind {
|
2013-07-14 04:38:47 +08:00
|
|
|
;CHECK-LABEL: test_vrev64Q32:
|
2009-07-26 08:39:34 +08:00
|
|
|
;CHECK: vrev64.32
|
|
|
|
%tmp1 = load <4 x i32>* %A
|
|
|
|
%tmp2 = shufflevector <4 x i32> %tmp1, <4 x i32> undef, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
|
|
|
|
ret <4 x i32> %tmp2
|
|
|
|
}
|
|
|
|
|
2010-06-17 23:18:27 +08:00
|
|
|
define <4 x float> @test_vrev64Qf(<4 x float>* %A) nounwind {
|
2013-07-14 04:38:47 +08:00
|
|
|
;CHECK-LABEL: test_vrev64Qf:
|
2009-07-26 08:39:34 +08:00
|
|
|
;CHECK: vrev64.32
|
|
|
|
%tmp1 = load <4 x float>* %A
|
|
|
|
%tmp2 = shufflevector <4 x float> %tmp1, <4 x float> undef, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
|
|
|
|
ret <4 x float> %tmp2
|
|
|
|
}
|
|
|
|
|
2010-06-17 23:18:27 +08:00
|
|
|
define <8 x i8> @test_vrev32D8(<8 x i8>* %A) nounwind {
|
2013-07-14 04:38:47 +08:00
|
|
|
;CHECK-LABEL: test_vrev32D8:
|
2009-07-26 08:39:34 +08:00
|
|
|
;CHECK: vrev32.8
|
|
|
|
%tmp1 = load <8 x i8>* %A
|
|
|
|
%tmp2 = shufflevector <8 x i8> %tmp1, <8 x i8> undef, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4>
|
|
|
|
ret <8 x i8> %tmp2
|
|
|
|
}
|
|
|
|
|
2010-06-17 23:18:27 +08:00
|
|
|
define <4 x i16> @test_vrev32D16(<4 x i16>* %A) nounwind {
|
2013-07-14 04:38:47 +08:00
|
|
|
;CHECK-LABEL: test_vrev32D16:
|
2009-07-26 08:39:34 +08:00
|
|
|
;CHECK: vrev32.16
|
|
|
|
%tmp1 = load <4 x i16>* %A
|
|
|
|
%tmp2 = shufflevector <4 x i16> %tmp1, <4 x i16> undef, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
|
|
|
|
ret <4 x i16> %tmp2
|
|
|
|
}
|
|
|
|
|
2010-06-17 23:18:27 +08:00
|
|
|
define <16 x i8> @test_vrev32Q8(<16 x i8>* %A) nounwind {
|
2013-07-14 04:38:47 +08:00
|
|
|
;CHECK-LABEL: test_vrev32Q8:
|
2009-07-26 08:39:34 +08:00
|
|
|
;CHECK: vrev32.8
|
|
|
|
%tmp1 = load <16 x i8>* %A
|
|
|
|
%tmp2 = shufflevector <16 x i8> %tmp1, <16 x i8> undef, <16 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4, i32 11, i32 10, i32 9, i32 8, i32 15, i32 14, i32 13, i32 12>
|
|
|
|
ret <16 x i8> %tmp2
|
|
|
|
}
|
|
|
|
|
2010-06-17 23:18:27 +08:00
|
|
|
define <8 x i16> @test_vrev32Q16(<8 x i16>* %A) nounwind {
|
2013-07-14 04:38:47 +08:00
|
|
|
;CHECK-LABEL: test_vrev32Q16:
|
2009-07-26 08:39:34 +08:00
|
|
|
;CHECK: vrev32.16
|
|
|
|
%tmp1 = load <8 x i16>* %A
|
|
|
|
%tmp2 = shufflevector <8 x i16> %tmp1, <8 x i16> undef, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6>
|
|
|
|
ret <8 x i16> %tmp2
|
|
|
|
}
|
|
|
|
|
2010-06-17 23:18:27 +08:00
|
|
|
define <8 x i8> @test_vrev16D8(<8 x i8>* %A) nounwind {
|
2013-07-14 04:38:47 +08:00
|
|
|
;CHECK-LABEL: test_vrev16D8:
|
2009-07-26 08:39:34 +08:00
|
|
|
;CHECK: vrev16.8
|
|
|
|
%tmp1 = load <8 x i8>* %A
|
|
|
|
%tmp2 = shufflevector <8 x i8> %tmp1, <8 x i8> undef, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6>
|
|
|
|
ret <8 x i8> %tmp2
|
|
|
|
}
|
|
|
|
|
2010-06-17 23:18:27 +08:00
|
|
|
define <16 x i8> @test_vrev16Q8(<16 x i8>* %A) nounwind {
|
2013-07-14 04:38:47 +08:00
|
|
|
;CHECK-LABEL: test_vrev16Q8:
|
2009-07-26 08:39:34 +08:00
|
|
|
;CHECK: vrev16.8
|
|
|
|
%tmp1 = load <16 x i8>* %A
|
|
|
|
%tmp2 = shufflevector <16 x i8> %tmp1, <16 x i8> undef, <16 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6, i32 9, i32 8, i32 11, i32 10, i32 13, i32 12, i32 15, i32 14>
|
|
|
|
ret <16 x i8> %tmp2
|
|
|
|
}
|
2010-08-17 13:54:34 +08:00
|
|
|
|
|
|
|
; Undef shuffle indices should not prevent matching to VREV:
|
|
|
|
|
|
|
|
define <8 x i8> @test_vrev64D8_undef(<8 x i8>* %A) nounwind {
|
2013-07-14 04:38:47 +08:00
|
|
|
;CHECK-LABEL: test_vrev64D8_undef:
|
2010-08-17 13:54:34 +08:00
|
|
|
;CHECK: vrev64.8
|
|
|
|
%tmp1 = load <8 x i8>* %A
|
|
|
|
%tmp2 = shufflevector <8 x i8> %tmp1, <8 x i8> undef, <8 x i32> <i32 7, i32 undef, i32 undef, i32 4, i32 3, i32 2, i32 1, i32 0>
|
|
|
|
ret <8 x i8> %tmp2
|
|
|
|
}
|
|
|
|
|
|
|
|
define <8 x i16> @test_vrev32Q16_undef(<8 x i16>* %A) nounwind {
|
2013-07-14 04:38:47 +08:00
|
|
|
;CHECK-LABEL: test_vrev32Q16_undef:
|
2010-08-17 13:54:34 +08:00
|
|
|
;CHECK: vrev32.16
|
|
|
|
%tmp1 = load <8 x i16>* %A
|
|
|
|
%tmp2 = shufflevector <8 x i16> %tmp1, <8 x i16> undef, <8 x i32> <i32 undef, i32 0, i32 undef, i32 2, i32 5, i32 4, i32 7, i32 undef>
|
|
|
|
ret <8 x i16> %tmp2
|
|
|
|
}
|
SelectionDAG shuffle nodes do not allow operands with different numbers of
elements than the result vector type. So, when an instruction like:
%8 = shufflevector <2 x float> %4, <2 x float> %7, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
is translated to a DAG, each operand is changed to a concat_vectors node that appends 2 undef elements. That is:
shuffle [a,b], [c,d] is changed to:
shuffle [a,b,u,u], [c,d,u,u]
That's probably the right thing for x86 but for NEON, we'd much rather have:
shuffle [a,b,c,d], undef
Teach the DAG combiner how to do that transformation for ARM. Radar 8597007.
llvm-svn: 117482
2010-10-28 04:38:28 +08:00
|
|
|
|
|
|
|
; A vcombine feeding a VREV should not obscure things. Radar 8597007.
|
|
|
|
|
|
|
|
define void @test_with_vcombine(<4 x float>* %v) nounwind {
|
2013-07-14 04:38:47 +08:00
|
|
|
;CHECK-LABEL: test_with_vcombine:
|
SelectionDAG shuffle nodes do not allow operands with different numbers of
elements than the result vector type. So, when an instruction like:
%8 = shufflevector <2 x float> %4, <2 x float> %7, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
is translated to a DAG, each operand is changed to a concat_vectors node that appends 2 undef elements. That is:
shuffle [a,b], [c,d] is changed to:
shuffle [a,b,u,u], [c,d,u,u]
That's probably the right thing for x86 but for NEON, we'd much rather have:
shuffle [a,b,c,d], undef
Teach the DAG combiner how to do that transformation for ARM. Radar 8597007.
llvm-svn: 117482
2010-10-28 04:38:28 +08:00
|
|
|
;CHECK-NOT: vext
|
|
|
|
;CHECK: vrev64.32
|
|
|
|
%tmp1 = load <4 x float>* %v, align 16
|
|
|
|
%tmp2 = bitcast <4 x float> %tmp1 to <2 x double>
|
|
|
|
%tmp3 = extractelement <2 x double> %tmp2, i32 0
|
|
|
|
%tmp4 = bitcast double %tmp3 to <2 x float>
|
|
|
|
%tmp5 = extractelement <2 x double> %tmp2, i32 1
|
|
|
|
%tmp6 = bitcast double %tmp5 to <2 x float>
|
|
|
|
%tmp7 = fadd <2 x float> %tmp6, %tmp6
|
|
|
|
%tmp8 = shufflevector <2 x float> %tmp4, <2 x float> %tmp7, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
|
|
|
|
store <4 x float> %tmp8, <4 x float>* %v, align 16
|
|
|
|
ret void
|
|
|
|
}
|
2011-05-18 04:48:40 +08:00
|
|
|
|
2011-10-18 04:23:23 +08:00
|
|
|
; The type <2 x i16> is legalized to <2 x i32> and need to be trunc-stored
|
When performing a truncating store, it's possible to rearrange the data
in-register, such that we can use a single vector store rather then a
series of scalar stores.
For func_4_8 the generated code
vldr d16, LCPI0_0
vmov d17, r0, r1
vadd.i16 d16, d17, d16
vmov.u16 r0, d16[3]
strb r0, [r2, #3]
vmov.u16 r0, d16[2]
strb r0, [r2, #2]
vmov.u16 r0, d16[1]
strb r0, [r2, #1]
vmov.u16 r0, d16[0]
strb r0, [r2]
bx lr
becomes
vldr d16, LCPI0_0
vmov d17, r0, r1
vadd.i16 d16, d17, d16
vuzp.8 d16, d17
vst1.32 {d16[0]}, [r2, :32]
bx lr
I'm not fond of how this combine pessimizes 2012-03-13-DAGCombineBug.ll,
but I couldn't think of a way to judiciously apply this combine.
This
ldrh r0, [r0, #4]
strh r0, [r1]
becomes
vldr d16, [r0]
vmov.u16 r0, d16[2]
vmov.32 d16[0], r0
vuzp.16 d16, d17
vst1.32 {d16[0]}, [r1, :32]
PR11158
rdar://10703339
llvm-svn: 154340
2012-04-10 04:32:02 +08:00
|
|
|
; to <2 x i16> when stored to memory.
|
2011-05-18 04:48:40 +08:00
|
|
|
define void @test_vrev64(<4 x i16>* nocapture %source, <2 x i16>* nocapture %dst) nounwind ssp {
|
2013-07-14 04:38:47 +08:00
|
|
|
; CHECK-LABEL: test_vrev64:
|
When performing a truncating store, it's possible to rearrange the data
in-register, such that we can use a single vector store rather then a
series of scalar stores.
For func_4_8 the generated code
vldr d16, LCPI0_0
vmov d17, r0, r1
vadd.i16 d16, d17, d16
vmov.u16 r0, d16[3]
strb r0, [r2, #3]
vmov.u16 r0, d16[2]
strb r0, [r2, #2]
vmov.u16 r0, d16[1]
strb r0, [r2, #1]
vmov.u16 r0, d16[0]
strb r0, [r2]
bx lr
becomes
vldr d16, LCPI0_0
vmov d17, r0, r1
vadd.i16 d16, d17, d16
vuzp.8 d16, d17
vst1.32 {d16[0]}, [r2, :32]
bx lr
I'm not fond of how this combine pessimizes 2012-03-13-DAGCombineBug.ll,
but I couldn't think of a way to judiciously apply this combine.
This
ldrh r0, [r0, #4]
strh r0, [r1]
becomes
vldr d16, [r0]
vmov.u16 r0, d16[2]
vmov.32 d16[0], r0
vuzp.16 d16, d17
vst1.32 {d16[0]}, [r1, :32]
PR11158
rdar://10703339
llvm-svn: 154340
2012-04-10 04:32:02 +08:00
|
|
|
; CHECK: vst1.32
|
2011-05-18 04:48:40 +08:00
|
|
|
entry:
|
|
|
|
%0 = bitcast <4 x i16>* %source to <8 x i16>*
|
|
|
|
%tmp2 = load <8 x i16>* %0, align 4
|
|
|
|
%tmp3 = extractelement <8 x i16> %tmp2, i32 6
|
|
|
|
%tmp5 = insertelement <2 x i16> undef, i16 %tmp3, i32 0
|
|
|
|
%tmp9 = extractelement <8 x i16> %tmp2, i32 5
|
|
|
|
%tmp11 = insertelement <2 x i16> %tmp5, i16 %tmp9, i32 1
|
|
|
|
store <2 x i16> %tmp11, <2 x i16>* %dst, align 4
|
|
|
|
ret void
|
|
|
|
}
|
2011-05-19 05:44:54 +08:00
|
|
|
|
|
|
|
; Test vrev of float4
|
|
|
|
define void @float_vrev64(float* nocapture %source, <4 x float>* nocapture %dest) nounwind noinline ssp {
|
|
|
|
; CHECK: float_vrev64
|
|
|
|
; CHECK: vext.32
|
|
|
|
; CHECK: vrev64.32
|
|
|
|
entry:
|
|
|
|
%0 = bitcast float* %source to <4 x float>*
|
|
|
|
%tmp2 = load <4 x float>* %0, align 4
|
|
|
|
%tmp5 = shufflevector <4 x float> <float 0.000000e+00, float undef, float undef, float undef>, <4 x float> %tmp2, <4 x i32> <i32 0, i32 7, i32 0, i32 0>
|
|
|
|
%arrayidx8 = getelementptr inbounds <4 x float>* %dest, i32 11
|
|
|
|
store <4 x float> %tmp5, <4 x float>* %arrayidx8, align 4
|
|
|
|
ret void
|
|
|
|
}
|
|
|
|
|