caio/clang-p2996
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
ec056f54589d937ae3f74d795b94de886cbb7ec7
clang-p2996/llvm/test/CodeGen/ARM/vzip.ll
Matt Arsenault 58a88001f3 PeepholeOpt: Fix looking for def of current copy to coalesce (#125533) 
This fixes the handling of subregister extract copies. This
will allow AMDGPU to remove its implementation of
shouldRewriteCopySrc, which exists as a 10 year old workaround
to this bug. peephole-opt-fold-reg-sequence-subreg.mir will
show the expected improvement once the custom implementation
is removed.

The copy coalescing processing here is overly abstracted
from what's actually happening. Previously when visiting
coalescable copy-like instructions, we would parse the
sources one at a time and then pass the def of the root
instruction into findNextSource. This means that the
first thing the new ValueTracker constructed would do
is getVRegDef to find the instruction we are currently
processing. This adds an unnecessary step, placing
a useless entry in the RewriteMap, and required skipping
the no-op case where getNewSource would return the original
source operand. This was a problem since in the case
of a subregister extract, shouldRewriteCopySource would always
say that it is useful to rewrite and the use-def chain walk
would abort, returning the original operand. Move the process
to start looking at the source operand to begin with.

This does not fix the confused handling in the uncoalescable
copy case which is proving to be more difficult. Some currently
handled cases have multiple defs from a single source, and other
handled cases have 0 input operands. It would be simpler if
this was implemented with isCopyLikeInstr, rather than guessing
at the operand structure as it does now.

There are some improvements and some regressions. The
regressions appear to be downstream issues for the most part. One
of the uglier regressions is in PPC, where a sequence of insert_subrgs
is used to build registers. I opened #125502 to use reg_sequence instead,
which may help.

The worst regression is an absurd SPARC testcase using a <251 x fp128>,
which uses a very long chain of insert_subregs.

We need improved subregister handling locally in PeepholeOptimizer,
and other pasess like MachineCSE to fix some of the other regressions.
We should handle subregister composes and folding more indexes
into insert_subreg and reg_sequence.
2025-02-05 23:29:02 +07:00

384 lines
15 KiB
LLVM
Raw Blame History

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=arm-eabi -mattr=+neon %s -o - | FileCheck %s
define <8 x i8> @vzipi8(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: vzipi8:
; CHECK: @ %bb.0:
; CHECK-NEXT: vldr d16, [r1]
; CHECK-NEXT: vldr d17, [r0]
; CHECK-NEXT: vzip.8 d17, d16
; CHECK-NEXT: vadd.i8 d16, d17, d16
; CHECK-NEXT: vmov r0, r1, d16
; CHECK-NEXT: mov pc, lr
%tmp1 = load <8 x i8>, ptr %A
%tmp2 = load <8 x i8>, ptr %B
%tmp3 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11>
%tmp4 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
%tmp5 = add <8 x i8> %tmp3, %tmp4
ret <8 x i8> %tmp5
}
define <16 x i8> @vzipi8_Qres(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: vzipi8_Qres:
; CHECK: @ %bb.0:
; CHECK-NEXT: vldr d16, [r1]
; CHECK-NEXT: vldr d17, [r0]
; CHECK-NEXT: vzip.8 d17, d16
; CHECK-NEXT: vmov r0, r1, d17
; CHECK-NEXT: vmov r2, r3, d16
; CHECK-NEXT: mov pc, lr
%tmp1 = load <8 x i8>, ptr %A
%tmp2 = load <8 x i8>, ptr %B
%tmp3 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <16 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11, i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
ret <16 x i8> %tmp3
}
define <4 x i16> @vzipi16(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: vzipi16:
; CHECK: @ %bb.0:
; CHECK-NEXT: vldr d16, [r1]
; CHECK-NEXT: vldr d17, [r0]
; CHECK-NEXT: vzip.16 d17, d16
; CHECK-NEXT: vadd.i16 d16, d17, d16
; CHECK-NEXT: vmov r0, r1, d16
; CHECK-NEXT: mov pc, lr
%tmp1 = load <4 x i16>, ptr %A
%tmp2 = load <4 x i16>, ptr %B
%tmp3 = shufflevector <4 x i16> %tmp1, <4 x i16> %tmp2, <4 x i32> <i32 0, i32 4, i32 1, i32 5>
%tmp4 = shufflevector <4 x i16> %tmp1, <4 x i16> %tmp2, <4 x i32> <i32 2, i32 6, i32 3, i32 7>
%tmp5 = add <4 x i16> %tmp3, %tmp4
ret <4 x i16> %tmp5
}
define <8 x i16> @vzipi16_Qres(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: vzipi16_Qres:
; CHECK: @ %bb.0:
; CHECK-NEXT: vldr d16, [r1]
; CHECK-NEXT: vldr d17, [r0]
; CHECK-NEXT: vzip.16 d17, d16
; CHECK-NEXT: vmov r0, r1, d17
; CHECK-NEXT: vmov r2, r3, d16
; CHECK-NEXT: mov pc, lr
%tmp1 = load <4 x i16>, ptr %A
%tmp2 = load <4 x i16>, ptr %B
%tmp3 = shufflevector <4 x i16> %tmp1, <4 x i16> %tmp2, <8 x i32> <i32 0, i32 4, i32 1, i32 5, i32 2, i32 6, i32 3, i32 7>
ret <8 x i16> %tmp3
}
; VZIP.32 is equivalent to VTRN.32 for 64-bit vectors.
define <16 x i8> @vzipQi8(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: vzipQi8:
; CHECK: @ %bb.0:
; CHECK-NEXT: vld1.64 {d16, d17}, [r1]
; CHECK-NEXT: vld1.64 {d18, d19}, [r0]
; CHECK-NEXT: vzip.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
%tmp1 = load <16 x i8>, ptr %A
%tmp2 = load <16 x i8>, ptr %B
%tmp3 = shufflevector <16 x i8> %tmp1, <16 x i8> %tmp2, <16 x i32> <i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23>
%tmp4 = shufflevector <16 x i8> %tmp1, <16 x i8> %tmp2, <16 x i32> <i32 8, i32 24, i32 9, i32 25, i32 10, i32 26, i32 11, i32 27, i32 12, i32 28, i32 13, i32 29, i32 14, i32 30, i32 15, i32 31>
%tmp5 = add <16 x i8> %tmp3, %tmp4
ret <16 x i8> %tmp5
}
define <32 x i8> @vzipQi8_QQres(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: vzipQi8_QQres:
; CHECK: @ %bb.0:
; CHECK-NEXT: vld1.64 {d16, d17}, [r2]
; CHECK-NEXT: vld1.64 {d18, d19}, [r1]
; CHECK-NEXT: vzip.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>, ptr %A
%tmp2 = load <16 x i8>, ptr %B
%tmp3 = shufflevector <16 x i8> %tmp1, <16 x i8> %tmp2, <32 x i32> <i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23, i32 8, i32 24, i32 9, i32 25, i32 10, i32 26, i32 11, i32 27, i32 12, i32 28, i32 13, i32 29, i32 14, i32 30, i32 15, i32 31>
ret <32 x i8> %tmp3
}
define <8 x i16> @vzipQi16(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: vzipQi16:
; CHECK: @ %bb.0:
; CHECK-NEXT: vld1.64 {d16, d17}, [r1]
; CHECK-NEXT: vld1.64 {d18, d19}, [r0]
; CHECK-NEXT: vzip.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
%tmp1 = load <8 x i16>, ptr %A
%tmp2 = load <8 x i16>, ptr %B
%tmp3 = shufflevector <8 x i16> %tmp1, <8 x i16> %tmp2, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11>
%tmp4 = shufflevector <8 x i16> %tmp1, <8 x i16> %tmp2, <8 x i32> <i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
%tmp5 = add <8 x i16> %tmp3, %tmp4
ret <8 x i16> %tmp5
}
define <16 x i16> @vzipQi16_QQres(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: vzipQi16_QQres:
; CHECK: @ %bb.0:
; CHECK-NEXT: vld1.64 {d16, d17}, [r2]
; CHECK-NEXT: vld1.64 {d18, d19}, [r1]
; CHECK-NEXT: vzip.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>, ptr %A
%tmp2 = load <8 x i16>, ptr %B
%tmp3 = shufflevector <8 x i16> %tmp1, <8 x i16> %tmp2, <16 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11, i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
ret <16 x i16> %tmp3
}
define <4 x i32> @vzipQi32(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: vzipQi32:
; CHECK: @ %bb.0:
; CHECK-NEXT: vld1.64 {d16, d17}, [r1]
; CHECK-NEXT: vld1.64 {d18, d19}, [r0]
; CHECK-NEXT: vzip.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
%tmp1 = load <4 x i32>, ptr %A
%tmp2 = load <4 x i32>, ptr %B
%tmp3 = shufflevector <4 x i32> %tmp1, <4 x i32> %tmp2, <4 x i32> <i32 0, i32 4, i32 1, i32 5>
%tmp4 = shufflevector <4 x i32> %tmp1, <4 x i32> %tmp2, <4 x i32> <i32 2, i32 6, i32 3, i32 7>
%tmp5 = add <4 x i32> %tmp3, %tmp4
ret <4 x i32> %tmp5
}
define <8 x i32> @vzipQi32_QQres(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: vzipQi32_QQres:
; CHECK: @ %bb.0:
; CHECK-NEXT: vld1.64 {d16, d17}, [r2]
; CHECK-NEXT: vld1.64 {d18, d19}, [r1]
; CHECK-NEXT: vzip.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>, ptr %A
%tmp2 = load <4 x i32>, ptr %B
%tmp3 = shufflevector <4 x i32> %tmp1, <4 x i32> %tmp2, <8 x i32> <i32 0, i32 4, i32 1, i32 5, i32 2, i32 6, i32 3, i32 7>
ret <8 x i32> %tmp3
}
define <4 x float> @vzipQf(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: vzipQf:
; CHECK: @ %bb.0:
; CHECK-NEXT: vld1.64 {d16, d17}, [r1]
; CHECK-NEXT: vld1.64 {d18, d19}, [r0]
; CHECK-NEXT: vzip.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
%tmp1 = load <4 x float>, ptr %A
%tmp2 = load <4 x float>, ptr %B
%tmp3 = shufflevector <4 x float> %tmp1, <4 x float> %tmp2, <4 x i32> <i32 0, i32 4, i32 1, i32 5>
%tmp4 = shufflevector <4 x float> %tmp1, <4 x float> %tmp2, <4 x i32> <i32 2, i32 6, i32 3, i32 7>
%tmp5 = fadd <4 x float> %tmp3, %tmp4
ret <4 x float> %tmp5
}
define <8 x float> @vzipQf_QQres(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: vzipQf_QQres:
; CHECK: @ %bb.0:
; CHECK-NEXT: vld1.64 {d16, d17}, [r2]
; CHECK-NEXT: vld1.64 {d18, d19}, [r1]
; CHECK-NEXT: vzip.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>, ptr %A
%tmp2 = load <4 x float>, ptr %B
%tmp3 = shufflevector <4 x float> %tmp1, <4 x float> %tmp2, <8 x i32> <i32 0, i32 4, i32 1, i32 5, i32 2, i32 6, i32 3, i32 7>
ret <8 x float> %tmp3
}
; Undef shuffle indices should not prevent matching to VZIP:
define <8 x i8> @vzipi8_undef(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: vzipi8_undef:
; CHECK: @ %bb.0:
; CHECK-NEXT: vldr d16, [r1]
; CHECK-NEXT: vldr d17, [r0]
; CHECK-NEXT: vzip.8 d17, d16
; CHECK-NEXT: vadd.i8 d16, d17, d16
; CHECK-NEXT: vmov r0, r1, d16
; CHECK-NEXT: mov pc, lr
%tmp1 = load <8 x i8>, ptr %A
%tmp2 = load <8 x i8>, ptr %B
%tmp3 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 0, i32 undef, i32 1, i32 9, i32 undef, i32 10, i32 3, i32 11>
%tmp4 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 4, i32 12, i32 5, i32 13, i32 6, i32 undef, i32 undef, i32 15>
%tmp5 = add <8 x i8> %tmp3, %tmp4
ret <8 x i8> %tmp5
}
define <16 x i8> @vzipi8_undef_Qres(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: vzipi8_undef_Qres:
; CHECK: @ %bb.0:
; CHECK-NEXT: vldr d16, [r1]
; CHECK-NEXT: vldr d17, [r0]
; CHECK-NEXT: vzip.8 d17, d16
; CHECK-NEXT: vmov r0, r1, d17
; CHECK-NEXT: vmov r2, r3, d16
; CHECK-NEXT: mov pc, lr
%tmp1 = load <8 x i8>, ptr %A
%tmp2 = load <8 x i8>, ptr %B
%tmp3 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <16 x i32> <i32 0, i32 undef, i32 1, i32 9, i32 undef, i32 10, i32 3, i32 11, i32 4, i32 12, i32 5, i32 13, i32 6, i32 undef, i32 undef, i32 15>
ret <16 x i8> %tmp3
}
define <16 x i8> @vzipQi8_undef(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: vzipQi8_undef:
; CHECK: @ %bb.0:
; CHECK-NEXT: vld1.64 {d16, d17}, [r1]
; CHECK-NEXT: vld1.64 {d18, d19}, [r0]
; CHECK-NEXT: vzip.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
%tmp1 = load <16 x i8>, ptr %A
%tmp2 = load <16 x i8>, ptr %B
%tmp3 = shufflevector <16 x i8> %tmp1, <16 x i8> %tmp2, <16 x i32> <i32 0, i32 16, i32 1, i32 undef, i32 undef, i32 undef, i32 3, i32 19, i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23>
%tmp4 = shufflevector <16 x i8> %tmp1, <16 x i8> %tmp2, <16 x i32> <i32 8, i32 24, i32 9, i32 undef, i32 10, i32 26, i32 11, i32 27, i32 12, i32 28, i32 13, i32 undef, i32 14, i32 30, i32 undef, i32 31>
%tmp5 = add <16 x i8> %tmp3, %tmp4
ret <16 x i8> %tmp5
}
define <32 x i8> @vzipQi8_undef_QQres(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: vzipQi8_undef_QQres:
; CHECK: @ %bb.0:
; CHECK-NEXT: vld1.64 {d16, d17}, [r2]
; CHECK-NEXT: vld1.64 {d18, d19}, [r1]
; CHECK-NEXT: vzip.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>, ptr %A
%tmp2 = load <16 x i8>, ptr %B
%tmp3 = shufflevector <16 x i8> %tmp1, <16 x i8> %tmp2, <32 x i32> <i32 0, i32 16, i32 1, i32 undef, i32 undef, i32 undef, i32 3, i32 19, i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23, i32 8, i32 24, i32 9, i32 undef, i32 10, i32 26, i32 11, i32 27, i32 12, i32 28, i32 13, i32 undef, i32 14, i32 30, i32 undef, i32 31>
ret <32 x i8> %tmp3
}
define <8 x i16> @vzip_lower_shufflemask_undef(ptr %A, ptr %B) {
; CHECK-LABEL: vzip_lower_shufflemask_undef:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vldr d16, [r1]
; CHECK-NEXT: vldr d17, [r0]
; CHECK-NEXT: vzip.16 d17, d16
; CHECK-NEXT: vmov r0, r1, d16
; CHECK-NEXT: vmov r2, r3, d16
; CHECK-NEXT: mov pc, lr
entry:
%tmp1 = load <4 x i16>, ptr %A
%tmp2 = load <4 x i16>, ptr %B
%0 = shufflevector <4 x i16> %tmp1, <4 x i16> %tmp2, <8 x i32> <i32 undef, i32 undef, i32 undef, i32 undef, i32 2, i32 6, i32 3, i32 7>
ret <8 x i16> %0
}
; NOTE: The mask here looks like something that could be done with a vzip,
; but which the current handling of two-result vzip can't do - thus ending up
; as a vtrn.
define <8 x i16> @vzip_lower_shufflemask_undef_rev(ptr %A, ptr %B) {
; CHECK-LABEL: vzip_lower_shufflemask_undef_rev:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vldr d16, [r1]
; CHECK-NEXT: vldr d17, [r0]
; CHECK-NEXT: vtrn.16 d17, d16
; CHECK-NEXT: vmov r0, r1, d16
; CHECK-NEXT: vmov r2, r3, d17
; CHECK-NEXT: mov pc, lr
entry:
%tmp1 = load <4 x i16>, ptr %A
%tmp2 = load <4 x i16>, ptr %B
%0 = shufflevector <4 x i16> %tmp1, <4 x i16> %tmp2, <8 x i32> <i32 undef, i32 undef, i32 undef, i32 undef, i32 0, i32 4, i32 undef, i32 undef>
ret <8 x i16> %0
}
define <4 x i32> @vzip_lower_shufflemask_zeroed(ptr %A) {
; CHECK-LABEL: vzip_lower_shufflemask_zeroed:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vldr d16, [r0]
; CHECK-NEXT: vdup.32 q9, d16[0]
; CHECK-NEXT: vzip.32 q8, q9
; CHECK-NEXT: vmov r0, r1, d16
; CHECK-NEXT: vmov r2, r3, d17
; CHECK-NEXT: mov pc, lr
entry:
%tmp1 = load <2 x i32>, ptr %A
%0 = shufflevector <2 x i32> %tmp1, <2 x i32> %tmp1, <4 x i32> <i32 0, i32 0, i32 1, i32 0>
ret <4 x i32> %0
}
define <4 x i32> @vzip_lower_shufflemask_vuzp(ptr %A) {
; CHECK-LABEL: vzip_lower_shufflemask_vuzp:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vldr d16, [r0]
; CHECK-NEXT: vdup.32 q9, d16[0]
; CHECK-NEXT: vzip.32 q8, q9
; CHECK-NEXT: vmov r0, r1, d16
; CHECK-NEXT: vmov r2, r3, d17
; CHECK-NEXT: mov pc, lr
entry:
%tmp1 = load <2 x i32>, ptr %A
%0 = shufflevector <2 x i32> %tmp1, <2 x i32> %tmp1, <4 x i32> <i32 0, i32 2, i32 1, i32 0>
ret <4 x i32> %0
}
define void @vzip_undef_rev_shufflemask_vtrn(ptr %A, ptr %B) {
; CHECK-LABEL: vzip_undef_rev_shufflemask_vtrn:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vldr d16, [r0]
; CHECK-NEXT: vorr q9, q8, q8
; CHECK-NEXT: vzip.32 q8, q9
; CHECK-NEXT: vext.32 q8, q8, q8, #2
; CHECK-NEXT: vst1.64 {d16, d17}, [r1]
; CHECK-NEXT: mov pc, lr
entry:
%tmp1 = load <2 x i32>, ptr %A
%0 = shufflevector <2 x i32> %tmp1, <2 x i32> undef, <4 x i32> <i32 1, i32 1, i32 0, i32 0>
store <4 x i32> %0, ptr %B
ret void
}
define void @vzip_vext_factor(ptr %A, ptr %B) {
; CHECK-LABEL: vzip_vext_factor:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vld1.64 {d16, d17}, [r0]
; CHECK-NEXT: vext.16 d18, d16, d17, #1
; CHECK-NEXT: vext.16 d16, d18, d17, #2
; CHECK-NEXT: vext.16 d16, d16, d16, #1
; CHECK-NEXT: vstr d16, [r1]
; CHECK-NEXT: mov pc, lr
entry:
%tmp1 = load <8 x i16>, ptr %A
%0 = shufflevector <8 x i16> %tmp1, <8 x i16> undef, <4 x i32> <i32 4, i32 4, i32 5, i32 3>
store <4 x i16> %0, ptr %B
ret void
}
define <8 x i8> @vdup_zip(ptr nocapture readonly %x, ptr nocapture readonly %y) {
; CHECK-LABEL: vdup_zip:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vld1.8 {d16[]}, [r1]
; CHECK-NEXT: vld1.8 {d17[]}, [r0]
; CHECK-NEXT: vzip.8 d17, d16
; CHECK-NEXT: vmov r0, r1, d17
; CHECK-NEXT: mov pc, lr
entry:
%0 = load i8, ptr %x, align 1
%1 = insertelement <8 x i8> undef, i8 %0, i32 0
%lane = shufflevector <8 x i8> %1, <8 x i8> undef, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 undef, i32 undef, i32 undef, i32 undef>
%2 = load i8, ptr %y, align 1
%3 = insertelement <8 x i8> undef, i8 %2, i32 0
%lane3 = shufflevector <8 x i8> %3, <8 x i8> undef, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 undef, i32 undef, i32 undef, i32 undef>
%vzip.i = shufflevector <8 x i8> %lane, <8 x i8> %lane3, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11>
ret <8 x i8> %vzip.i
}
Reference in New Issue View Git Blame Copy Permalink