derek/TheRock
1
0 Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
Files
1a182e2dac58879f215c0fad0f5f78c76dcafe56
TheRock/compiler/amd-llvm/llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-opts-cmpne.ll
T
derek.holloway 7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
Details
CodeQL / Analyze (python) (push) Canceled after 0s
Details
pre-commit / pre-commit (push) Canceled after 0s
Details
Multi-Arch CI / setup (push) Canceled after 0s
Details
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Details
Setup (Multi-Arch) / setup (push) Canceled after 0s
Details
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Details
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
Details
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Details
Multi-Arch CI / CI Summary (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Details
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Details
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
Details
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

484 lines
31 KiB
LLVM
Raw Blame History

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
; RUN: opt -S -passes=instcombine < %s | FileCheck %s
target triple = "aarch64-unknown-linux-gnu"
; DUPQ b8
define <vscale x 16 x i1> @dupq_b_0() #0 {
; CHECK-LABEL: define <vscale x 16 x i1> @dupq_b_0(
; CHECK-SAME: ) #[[ATTR0:[0-9]+]] {
; CHECK-NEXT: ret <vscale x 16 x i1> zeroinitializer
;
%1 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
%2 = tail call <vscale x 16 x i8> @llvm.vector.insert.nxv16i8.v16i8(<vscale x 16 x i8> poison,
<16 x i8> <i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0>, i64 0)
%3 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.dupq.lane.nxv16i8(<vscale x 16 x i8> %2 , i64 0)
%4 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 0)
%5 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.cmpne.wide.nxv16i8(<vscale x 16 x i1> %1, <vscale x 16 x i8> %3, <vscale x 2 x i64> %4)
ret <vscale x 16 x i1> %5
}
define <vscale x 16 x i1> @dupq_b_d() #0 {
; CHECK-LABEL: define <vscale x 16 x i1> @dupq_b_d(
; CHECK-SAME: ) #[[ATTR0]] {
; CHECK-NEXT: [[TMP2:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> splat (i1 true))
; CHECK-NEXT: ret <vscale x 16 x i1> [[TMP2]]
;
%1 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
%2 = tail call <vscale x 16 x i8> @llvm.vector.insert.nxv16i8.v16i8(<vscale x 16 x i8> poison,
<16 x i8> <i8 1, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 1, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0>, i64 0)
%3 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.dupq.lane.nxv16i8(<vscale x 16 x i8> %2 , i64 0)
%4 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 0)
%5 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.cmpne.wide.nxv16i8(<vscale x 16 x i1> %1, <vscale x 16 x i8> %3, <vscale x 2 x i64> %4)
ret <vscale x 16 x i1> %5
}
define <vscale x 16 x i1> @dupq_b_w() #0 {
; CHECK-LABEL: define <vscale x 16 x i1> @dupq_b_w(
; CHECK-SAME: ) #[[ATTR0]] {
; CHECK-NEXT: [[TMP2:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> splat (i1 true))
; CHECK-NEXT: ret <vscale x 16 x i1> [[TMP2]]
;
%1 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
%2 = tail call <vscale x 16 x i8> @llvm.vector.insert.nxv16i8.v16i8(<vscale x 16 x i8> poison,
<16 x i8> <i8 1, i8 0, i8 0, i8 0, i8 1, i8 0, i8 0, i8 0, i8 1, i8 0, i8 0, i8 0, i8 1, i8 0, i8 0, i8 0>, i64 0)
%3 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.dupq.lane.nxv16i8(<vscale x 16 x i8> %2 , i64 0)
%4 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 0)
%5 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.cmpne.wide.nxv16i8(<vscale x 16 x i1> %1, <vscale x 16 x i8> %3, <vscale x 2 x i64> %4)
ret <vscale x 16 x i1> %5
}
define <vscale x 16 x i1> @dupq_b_h() #0 {
; CHECK-LABEL: define <vscale x 16 x i1> @dupq_b_h(
; CHECK-SAME: ) #[[ATTR0]] {
; CHECK-NEXT: [[TMP2:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> splat (i1 true))
; CHECK-NEXT: ret <vscale x 16 x i1> [[TMP2]]
;
%1 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
%2 = tail call <vscale x 16 x i8> @llvm.vector.insert.nxv16i8.v16i8(<vscale x 16 x i8> poison,
<16 x i8> <i8 1, i8 0, i8 1, i8 0, i8 1, i8 0, i8 1, i8 0, i8 1, i8 0, i8 1, i8 0, i8 1, i8 0, i8 1, i8 0>, i64 0)
%3 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.dupq.lane.nxv16i8(<vscale x 16 x i8> %2 , i64 0)
%4 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 0)
%5 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.cmpne.wide.nxv16i8(<vscale x 16 x i1> %1, <vscale x 16 x i8> %3, <vscale x 2 x i64> %4)
ret <vscale x 16 x i1> %5
}
define <vscale x 16 x i1> @dupq_b_b() #0 {
; CHECK-LABEL: define <vscale x 16 x i1> @dupq_b_b(
; CHECK-SAME: ) #[[ATTR0]] {
; CHECK-NEXT: ret <vscale x 16 x i1> splat (i1 true)
;
%1 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
%2 = tail call <vscale x 16 x i8> @llvm.vector.insert.nxv16i8.v16i8(<vscale x 16 x i8> poison,
<16 x i8> <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>, i64 0)
%3 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.dupq.lane.nxv16i8(<vscale x 16 x i8> %2 , i64 0)
%4 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 0)
%5 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.cmpne.wide.nxv16i8(<vscale x 16 x i1> %1, <vscale x 16 x i8> %3, <vscale x 2 x i64> %4)
ret <vscale x 16 x i1> %5
}
; DUPQ b16
define <vscale x 8 x i1> @dupq_h_0() #0 {
; CHECK-LABEL: define <vscale x 8 x i1> @dupq_h_0(
; CHECK-SAME: ) #[[ATTR0]] {
; CHECK-NEXT: ret <vscale x 8 x i1> zeroinitializer
;
%1 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
%2 = tail call <vscale x 8 x i16> @llvm.vector.insert.nxv8i16.v8i16(<vscale x 8 x i16> poison,
<8 x i16> <i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0>, i64 0)
%3 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.dupq.lane.nxv8i16(<vscale x 8 x i16> %2 , i64 0)
%4 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 0)
%5 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.cmpne.wide.nxv8i16(<vscale x 8 x i1> %1, <vscale x 8 x i16> %3, <vscale x 2 x i64> %4)
ret <vscale x 8 x i1> %5
}
define <vscale x 8 x i1> @dupq_h_d() #0 {
; CHECK-LABEL: define <vscale x 8 x i1> @dupq_h_d(
; CHECK-SAME: ) #[[ATTR0]] {
; CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> splat (i1 true))
; CHECK-NEXT: [[TMP3:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[TMP1]])
; CHECK-NEXT: ret <vscale x 8 x i1> [[TMP3]]
;
%1 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
%2 = tail call <vscale x 8 x i16> @llvm.vector.insert.nxv8i16.v8i16(<vscale x 8 x i16> poison,
<8 x i16> <i16 1, i16 0, i16 0, i16 0, i16 1, i16 0, i16 0, i16 0>, i64 0)
%3 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.dupq.lane.nxv8i16(<vscale x 8 x i16> %2 , i64 0)
%4 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 0)
%5 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.cmpne.wide.nxv8i16(<vscale x 8 x i1> %1, <vscale x 8 x i16> %3, <vscale x 2 x i64> %4)
ret <vscale x 8 x i1> %5
}
define <vscale x 8 x i1> @dupq_h_w() #0 {
; CHECK-LABEL: define <vscale x 8 x i1> @dupq_h_w(
; CHECK-SAME: ) #[[ATTR0]] {
; CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> splat (i1 true))
; CHECK-NEXT: [[TMP3:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[TMP1]])
; CHECK-NEXT: ret <vscale x 8 x i1> [[TMP3]]
;
%1 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
%2 = tail call <vscale x 8 x i16> @llvm.vector.insert.nxv8i16.v8i16(<vscale x 8 x i16> poison,
<8 x i16> <i16 1, i16 0, i16 1, i16 0, i16 1, i16 0, i16 1, i16 0>, i64 0)
%3 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.dupq.lane.nxv8i16(<vscale x 8 x i16> %2 , i64 0)
%4 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 0)
%5 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.cmpne.wide.nxv8i16(<vscale x 8 x i1> %1, <vscale x 8 x i16> %3, <vscale x 2 x i64> %4)
ret <vscale x 8 x i1> %5
}
define <vscale x 8 x i1> @dupq_h_h() #0 {
; CHECK-LABEL: define <vscale x 8 x i1> @dupq_h_h(
; CHECK-SAME: ) #[[ATTR0]] {
; CHECK-NEXT: ret <vscale x 8 x i1> splat (i1 true)
;
%1 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
%2 = tail call <vscale x 8 x i16> @llvm.vector.insert.nxv8i16.v8i16(<vscale x 8 x i16> poison,
<8 x i16> <i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1>, i64 0)
%3 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.dupq.lane.nxv8i16(<vscale x 8 x i16> %2 , i64 0)
%4 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 0)
%5 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.cmpne.wide.nxv8i16(<vscale x 8 x i1> %1, <vscale x 8 x i16> %3, <vscale x 2 x i64> %4)
ret <vscale x 8 x i1> %5
}
; DUPQ b32
define <vscale x 4 x i1> @dupq_w_0() #0 {
; CHECK-LABEL: define <vscale x 4 x i1> @dupq_w_0(
; CHECK-SAME: ) #[[ATTR0]] {
; CHECK-NEXT: ret <vscale x 4 x i1> zeroinitializer
;
%1 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
%2 = tail call <vscale x 4 x i32> @llvm.vector.insert.nxv4i32.v4i32(<vscale x 4 x i32> poison,
<4 x i32> <i32 0, i32 0, i32 0, i32 0>, i64 0)
%3 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.dupq.lane.nxv4i32(<vscale x 4 x i32> %2 , i64 0)
%4 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 0)
%5 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.cmpne.wide.nxv4i32(<vscale x 4 x i1> %1, <vscale x 4 x i32> %3, <vscale x 2 x i64> %4)
ret <vscale x 4 x i1> %5
}
define <vscale x 4 x i1> @dupq_w_d() #0 {
; CHECK-LABEL: define <vscale x 4 x i1> @dupq_w_d(
; CHECK-SAME: ) #[[ATTR0]] {
; CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> splat (i1 true))
; CHECK-NEXT: [[TMP3:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[TMP1]])
; CHECK-NEXT: ret <vscale x 4 x i1> [[TMP3]]
;
%1 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
%2 = tail call <vscale x 4 x i32> @llvm.vector.insert.nxv4i32.v4i32(<vscale x 4 x i32> poison,
<4 x i32> <i32 1, i32 0, i32 1, i32 0>, i64 0)
%3 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.dupq.lane.nxv4i32(<vscale x 4 x i32> %2 , i64 0)
%4 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 0)
%5 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.cmpne.wide.nxv4i32(<vscale x 4 x i1> %1, <vscale x 4 x i32> %3, <vscale x 2 x i64> %4)
ret <vscale x 4 x i1> %5
}
define <vscale x 4 x i1> @dupq_w_w() #0 {
; CHECK-LABEL: define <vscale x 4 x i1> @dupq_w_w(
; CHECK-SAME: ) #[[ATTR0]] {
; CHECK-NEXT: ret <vscale x 4 x i1> splat (i1 true)
;
%1 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
%2 = tail call <vscale x 4 x i32> @llvm.vector.insert.nxv4i32.v4i32(<vscale x 4 x i32> poison,
<4 x i32> <i32 1, i32 1, i32 1, i32 1>, i64 0)
%3 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.dupq.lane.nxv4i32(<vscale x 4 x i32> %2 , i64 0)
%4 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 0)
%5 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.cmpne.wide.nxv4i32(<vscale x 4 x i1> %1, <vscale x 4 x i32> %3, <vscale x 2 x i64> %4)
ret <vscale x 4 x i1> %5
}
; DUPQ b64
define <vscale x 2 x i1> @dupq_d_0() #0 {
; CHECK-LABEL: define <vscale x 2 x i1> @dupq_d_0(
; CHECK-SAME: ) #[[ATTR0]] {
; CHECK-NEXT: ret <vscale x 2 x i1> zeroinitializer
;
%1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
%2 = tail call <vscale x 2 x i64> @llvm.vector.insert.nxv2i64.v2i64(<vscale x 2 x i64> poison,
<2 x i64> <i64 0, i64 0>, i64 0)
%3 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dupq.lane.nxv2i64(<vscale x 2 x i64> %2 , i64 0)
%4 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 0)
%5 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.cmpne.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %3, <vscale x 2 x i64> %4)
ret <vscale x 2 x i1> %5
}
define <vscale x 2 x i1> @dupq_d_d() #0 {
; CHECK-LABEL: define <vscale x 2 x i1> @dupq_d_d(
; CHECK-SAME: ) #[[ATTR0]] {
; CHECK-NEXT: ret <vscale x 2 x i1> splat (i1 true)
;
%1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
%2 = tail call <vscale x 2 x i64> @llvm.vector.insert.nxv2i64.v2i64(<vscale x 2 x i64> poison,
<2 x i64> <i64 1, i64 1>, i64 0)
%3 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dupq.lane.nxv2i64(<vscale x 2 x i64> %2 , i64 0)
%4 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 0)
%5 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.cmpne.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %3, <vscale x 2 x i64> %4)
ret <vscale x 2 x i1> %5
}
; Cases that cannot be converted
define <vscale x 2 x i1> @dupq_neg1() #0 {
; CHECK-LABEL: define <vscale x 2 x i1> @dupq_neg1(
; CHECK-SAME: ) #[[ATTR0]] {
; CHECK-NEXT: [[TMP2:%.*]] = tail call <vscale x 2 x i64> @llvm.vector.insert.nxv2i64.v2i64(<vscale x 2 x i64> poison, <2 x i64> <i64 1, i64 0>, i64 0)
; CHECK-NEXT: [[TMP3:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dupq.lane.nxv2i64(<vscale x 2 x i64> [[TMP2]], i64 0)
; CHECK-NEXT: [[TMP4:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.cmpne.nxv2i64(<vscale x 2 x i1> splat (i1 true), <vscale x 2 x i64> [[TMP3]], <vscale x 2 x i64> zeroinitializer)
; CHECK-NEXT: ret <vscale x 2 x i1> [[TMP4]]
;
%1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
%2 = tail call <vscale x 2 x i64> @llvm.vector.insert.nxv2i64.v2i64(<vscale x 2 x i64> poison,
<2 x i64> <i64 1, i64 0>, i64 0)
%3 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dupq.lane.nxv2i64(<vscale x 2 x i64> %2 , i64 0)
%4 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 0)
%5 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.cmpne.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %3, <vscale x 2 x i64> %4)
ret <vscale x 2 x i1> %5
}
define <vscale x 4 x i1> @dupq_neg2() #0 {
; CHECK-LABEL: define <vscale x 4 x i1> @dupq_neg2(
; CHECK-SAME: ) #[[ATTR0]] {
; CHECK-NEXT: [[TMP2:%.*]] = tail call <vscale x 4 x i32> @llvm.vector.insert.nxv4i32.v4i32(<vscale x 4 x i32> poison, <4 x i32> <i32 1, i32 0, i32 0, i32 1>, i64 0)
; CHECK-NEXT: [[TMP3:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.dupq.lane.nxv4i32(<vscale x 4 x i32> [[TMP2]], i64 0)
; CHECK-NEXT: [[TMP4:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.cmpne.wide.nxv4i32(<vscale x 4 x i1> splat (i1 true), <vscale x 4 x i32> [[TMP3]], <vscale x 2 x i64> zeroinitializer)
; CHECK-NEXT: ret <vscale x 4 x i1> [[TMP4]]
;
%1 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
%2 = tail call <vscale x 4 x i32> @llvm.vector.insert.nxv4i32.v4i32(<vscale x 4 x i32> poison,
<4 x i32> <i32 1, i32 0, i32 0, i32 1>, i64 0)
%3 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.dupq.lane.nxv4i32(<vscale x 4 x i32> %2 , i64 0)
%4 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 0)
%5 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.cmpne.wide.nxv4i32(<vscale x 4 x i1> %1, <vscale x 4 x i32> %3, <vscale x 2 x i64> %4)
ret <vscale x 4 x i1> %5
}
define <vscale x 4 x i1> @dupq_neg3() #0 {
; CHECK-LABEL: define <vscale x 4 x i1> @dupq_neg3(
; CHECK-SAME: ) #[[ATTR0]] {
; CHECK-NEXT: [[TMP2:%.*]] = tail call <vscale x 4 x i32> @llvm.vector.insert.nxv4i32.v4i32(<vscale x 4 x i32> poison, <4 x i32> <i32 0, i32 1, i32 0, i32 1>, i64 0)
; CHECK-NEXT: [[TMP3:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.dupq.lane.nxv4i32(<vscale x 4 x i32> [[TMP2]], i64 0)
; CHECK-NEXT: [[TMP4:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.cmpne.wide.nxv4i32(<vscale x 4 x i1> splat (i1 true), <vscale x 4 x i32> [[TMP3]], <vscale x 2 x i64> zeroinitializer)
; CHECK-NEXT: ret <vscale x 4 x i1> [[TMP4]]
;
%1 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
%2 = tail call <vscale x 4 x i32> @llvm.vector.insert.nxv4i32.v4i32(<vscale x 4 x i32> poison,
<4 x i32> <i32 0, i32 1, i32 0, i32 1>, i64 0)
%3 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.dupq.lane.nxv4i32(<vscale x 4 x i32> %2 , i64 0)
%4 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 0)
%5 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.cmpne.wide.nxv4i32(<vscale x 4 x i1> %1, <vscale x 4 x i32> %3, <vscale x 2 x i64> %4)
ret <vscale x 4 x i1> %5
}
define <vscale x 4 x i1> @dupq_neg4() #0 {
; CHECK-LABEL: define <vscale x 4 x i1> @dupq_neg4(
; CHECK-SAME: ) #[[ATTR0]] {
; CHECK-NEXT: [[TMP2:%.*]] = tail call <vscale x 4 x i32> @llvm.vector.insert.nxv4i32.v4i32(<vscale x 4 x i32> poison, <4 x i32> <i32 1, i32 1, i32 0, i32 0>, i64 0)
; CHECK-NEXT: [[TMP3:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.dupq.lane.nxv4i32(<vscale x 4 x i32> [[TMP2]], i64 0)
; CHECK-NEXT: [[TMP4:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.cmpne.wide.nxv4i32(<vscale x 4 x i1> splat (i1 true), <vscale x 4 x i32> [[TMP3]], <vscale x 2 x i64> zeroinitializer)
; CHECK-NEXT: ret <vscale x 4 x i1> [[TMP4]]
;
%1 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
%2 = tail call <vscale x 4 x i32> @llvm.vector.insert.nxv4i32.v4i32(<vscale x 4 x i32> poison,
<4 x i32> <i32 1, i32 1, i32 0, i32 0>, i64 0)
%3 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.dupq.lane.nxv4i32(<vscale x 4 x i32> %2 , i64 0)
%4 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 0)
%5 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.cmpne.wide.nxv4i32(<vscale x 4 x i1> %1, <vscale x 4 x i32> %3, <vscale x 2 x i64> %4)
ret <vscale x 4 x i1> %5
}
define <vscale x 4 x i1> @dupq_neg5() #0 {
; CHECK-LABEL: define <vscale x 4 x i1> @dupq_neg5(
; CHECK-SAME: ) #[[ATTR0]] {
; CHECK-NEXT: [[TMP2:%.*]] = tail call <vscale x 4 x i32> @llvm.vector.insert.nxv4i32.v4i32(<vscale x 4 x i32> poison, <4 x i32> <i32 0, i32 0, i32 0, i32 1>, i64 0)
; CHECK-NEXT: [[TMP3:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.dupq.lane.nxv4i32(<vscale x 4 x i32> [[TMP2]], i64 0)
; CHECK-NEXT: [[TMP4:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.cmpne.wide.nxv4i32(<vscale x 4 x i1> splat (i1 true), <vscale x 4 x i32> [[TMP3]], <vscale x 2 x i64> zeroinitializer)
; CHECK-NEXT: ret <vscale x 4 x i1> [[TMP4]]
;
%1 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
%2 = tail call <vscale x 4 x i32> @llvm.vector.insert.nxv4i32.v4i32(<vscale x 4 x i32> poison,
<4 x i32> <i32 0, i32 0, i32 0, i32 1>, i64 0)
%3 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.dupq.lane.nxv4i32(<vscale x 4 x i32> %2 , i64 0)
%4 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 0)
%5 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.cmpne.wide.nxv4i32(<vscale x 4 x i1> %1, <vscale x 4 x i32> %3, <vscale x 2 x i64> %4)
ret <vscale x 4 x i1> %5
}
define <vscale x 4 x i1> @dupq_neg6(i1 %a) #0 {
; CHECK-LABEL: define <vscale x 4 x i1> @dupq_neg6(
; CHECK-SAME: i1 [[A:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: [[TMP2:%.*]] = zext i1 [[A]] to i32
; CHECK-NEXT: [[TMP3:%.*]] = insertelement <4 x i32> <i32 1, i32 1, i32 1, i32 poison>, i32 [[TMP2]], i64 3
; CHECK-NEXT: [[TMP4:%.*]] = tail call <vscale x 4 x i32> @llvm.vector.insert.nxv4i32.v4i32(<vscale x 4 x i32> poison, <4 x i32> [[TMP3]], i64 0)
; CHECK-NEXT: [[TMP5:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.dupq.lane.nxv4i32(<vscale x 4 x i32> [[TMP4]], i64 0)
; CHECK-NEXT: [[TMP6:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.cmpne.wide.nxv4i32(<vscale x 4 x i1> splat (i1 true), <vscale x 4 x i32> [[TMP5]], <vscale x 2 x i64> zeroinitializer)
; CHECK-NEXT: ret <vscale x 4 x i1> [[TMP6]]
;
%1 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
%2 = zext i1 %a to i32
%3 = insertelement <4 x i32> <i32 1, i32 1, i32 1, i32 poison>, i32 %2, i32 3
%4 = tail call <vscale x 4 x i32> @llvm.vector.insert.nxv4i32.v4i32(<vscale x 4 x i32> poison, <4 x i32> %3, i64 0)
%5 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.dupq.lane.nxv4i32(<vscale x 4 x i32> %4 , i64 0)
%6 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 0)
%7 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.cmpne.wide.nxv4i32(<vscale x 4 x i1> %1, <vscale x 4 x i32> %5, <vscale x 2 x i64> %6)
ret <vscale x 4 x i1> %7
}
define <vscale x 2 x i1> @dupq_neg7() #0 {
; CHECK-LABEL: define <vscale x 2 x i1> @dupq_neg7(
; CHECK-SAME: ) #[[ATTR0]] {
; CHECK-NEXT: [[TMP2:%.*]] = tail call <vscale x 2 x i64> @llvm.vector.insert.nxv2i64.v2i64(<vscale x 2 x i64> poison, <2 x i64> splat (i64 1), i64 2)
; CHECK-NEXT: [[TMP3:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dupq.lane.nxv2i64(<vscale x 2 x i64> [[TMP2]], i64 0)
; CHECK-NEXT: [[TMP4:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.cmpne.nxv2i64(<vscale x 2 x i1> splat (i1 true), <vscale x 2 x i64> [[TMP3]], <vscale x 2 x i64> zeroinitializer)
; CHECK-NEXT: ret <vscale x 2 x i1> [[TMP4]]
;
%1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
%2 = tail call <vscale x 2 x i64> @llvm.vector.insert.nxv2i64.v2i64(<vscale x 2 x i64> poison,
<2 x i64> <i64 1, i64 1>, i64 2)
%3 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dupq.lane.nxv2i64(<vscale x 2 x i64> %2 , i64 0)
%4 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 0)
%5 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.cmpne.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %3, <vscale x 2 x i64> %4)
ret <vscale x 2 x i1> %5
}
define <vscale x 2 x i1> @dupq_neg8() #0 {
; CHECK-LABEL: define <vscale x 2 x i1> @dupq_neg8(
; CHECK-SAME: ) #[[ATTR0]] {
; CHECK-NEXT: [[TMP2:%.*]] = tail call <vscale x 2 x i64> @llvm.vector.insert.nxv2i64.v2i64(<vscale x 2 x i64> poison, <2 x i64> splat (i64 1), i64 0)
; CHECK-NEXT: [[TMP3:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dupq.lane.nxv2i64(<vscale x 2 x i64> [[TMP2]], i64 1)
; CHECK-NEXT: [[TMP4:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.cmpne.nxv2i64(<vscale x 2 x i1> splat (i1 true), <vscale x 2 x i64> [[TMP3]], <vscale x 2 x i64> zeroinitializer)
; CHECK-NEXT: ret <vscale x 2 x i1> [[TMP4]]
;
%1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
%2 = tail call <vscale x 2 x i64> @llvm.vector.insert.nxv2i64.v2i64(<vscale x 2 x i64> poison,
<2 x i64> <i64 1, i64 1>, i64 0)
%3 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dupq.lane.nxv2i64(<vscale x 2 x i64> %2 , i64 1)
%4 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 0)
%5 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.cmpne.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %3, <vscale x 2 x i64> %4)
ret <vscale x 2 x i1> %5
}
define <vscale x 2 x i1> @dupq_neg9(<vscale x 2 x i64> %x) #0 {
; CHECK-LABEL: define <vscale x 2 x i1> @dupq_neg9(
; CHECK-SAME: <vscale x 2 x i64> [[X:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: [[TMP2:%.*]] = tail call <vscale x 2 x i64> @llvm.vector.insert.nxv2i64.v2i64(<vscale x 2 x i64> [[X]], <2 x i64> splat (i64 1), i64 0)
; CHECK-NEXT: [[TMP3:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dupq.lane.nxv2i64(<vscale x 2 x i64> [[TMP2]], i64 0)
; CHECK-NEXT: [[TMP4:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.cmpne.nxv2i64(<vscale x 2 x i1> splat (i1 true), <vscale x 2 x i64> [[TMP3]], <vscale x 2 x i64> zeroinitializer)
; CHECK-NEXT: ret <vscale x 2 x i1> [[TMP4]]
;
%1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
%2 = tail call <vscale x 2 x i64> @llvm.vector.insert.nxv2i64.v2i64(<vscale x 2 x i64> %x,
<2 x i64> <i64 1, i64 1>, i64 0)
%3 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dupq.lane.nxv2i64(<vscale x 2 x i64> %2 , i64 0)
%4 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 0)
%5 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.cmpne.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %3, <vscale x 2 x i64> %4)
ret <vscale x 2 x i1> %5
}
define <vscale x 2 x i1> @dupq_neg10() #0 {
; CHECK-LABEL: define <vscale x 2 x i1> @dupq_neg10(
; CHECK-SAME: ) #[[ATTR0]] {
; CHECK-NEXT: [[TMP2:%.*]] = tail call <vscale x 2 x i64> @llvm.vector.insert.nxv2i64.v2i64(<vscale x 2 x i64> poison, <2 x i64> splat (i64 1), i64 0)
; CHECK-NEXT: [[TMP3:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dupq.lane.nxv2i64(<vscale x 2 x i64> [[TMP2]], i64 0)
; CHECK-NEXT: [[TMP4:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.cmpne.nxv2i64(<vscale x 2 x i1> splat (i1 true), <vscale x 2 x i64> [[TMP3]], <vscale x 2 x i64> splat (i64 1))
; CHECK-NEXT: ret <vscale x 2 x i1> [[TMP4]]
;
%1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
%2 = tail call <vscale x 2 x i64> @llvm.vector.insert.nxv2i64.v2i64(<vscale x 2 x i64> poison,
<2 x i64> <i64 1, i64 1>, i64 0)
%3 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dupq.lane.nxv2i64(<vscale x 2 x i64> %2 , i64 0)
%4 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 1)
%5 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.cmpne.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %3, <vscale x 2 x i64> %4)
ret <vscale x 2 x i1> %5
}
define <vscale x 2 x i1> @dupq_neg11(<vscale x 2 x i1> %pg) #0 {
; CHECK-LABEL: define <vscale x 2 x i1> @dupq_neg11(
; CHECK-SAME: <vscale x 2 x i1> [[PG:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: [[TMP1:%.*]] = tail call <vscale x 2 x i64> @llvm.vector.insert.nxv2i64.v2i64(<vscale x 2 x i64> poison, <2 x i64> splat (i64 1), i64 0)
; CHECK-NEXT: [[TMP2:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dupq.lane.nxv2i64(<vscale x 2 x i64> [[TMP1]], i64 0)
; CHECK-NEXT: [[TMP3:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.cmpne.nxv2i64(<vscale x 2 x i1> [[PG]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> zeroinitializer)
; CHECK-NEXT: ret <vscale x 2 x i1> [[TMP3]]
;
%1 = tail call <vscale x 2 x i64> @llvm.vector.insert.nxv2i64.v2i64(<vscale x 2 x i64> poison,
<2 x i64> <i64 1, i64 1>, i64 0)
%2 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dupq.lane.nxv2i64(<vscale x 2 x i64> %1 , i64 0)
%3 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 0)
%4 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.cmpne.nxv2i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %2, <vscale x 2 x i64> %3)
ret <vscale x 2 x i1> %4
}
define <vscale x 2 x i1> @dupq_neg12() #0 {
; CHECK-LABEL: define <vscale x 2 x i1> @dupq_neg12(
; CHECK-SAME: ) #[[ATTR0]] {
; CHECK-NEXT: [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 15)
; CHECK-NEXT: [[TMP2:%.*]] = tail call <vscale x 2 x i64> @llvm.vector.insert.nxv2i64.v2i64(<vscale x 2 x i64> poison, <2 x i64> splat (i64 1), i64 0)
; CHECK-NEXT: [[TMP3:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dupq.lane.nxv2i64(<vscale x 2 x i64> [[TMP2]], i64 0)
; CHECK-NEXT: [[TMP4:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.cmpne.nxv2i64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x i64> [[TMP3]], <vscale x 2 x i64> zeroinitializer)
; CHECK-NEXT: ret <vscale x 2 x i1> [[TMP4]]
;
%1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 15)
%2 = tail call <vscale x 2 x i64> @llvm.vector.insert.nxv2i64.v2i64(<vscale x 2 x i64> poison,
<2 x i64> <i64 1, i64 1>, i64 0)
%3 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dupq.lane.nxv2i64(<vscale x 2 x i64> %2 , i64 0)
%4 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 0)
%5 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.cmpne.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %3, <vscale x 2 x i64> %4)
ret <vscale x 2 x i1> %5
}
define <vscale x 2 x i1> @dupq_neg13(<vscale x 2 x i64> %x) #0 {
; CHECK-LABEL: define <vscale x 2 x i1> @dupq_neg13(
; CHECK-SAME: <vscale x 2 x i64> [[X:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: [[TMP2:%.*]] = tail call <vscale x 2 x i64> @llvm.vector.insert.nxv2i64.v2i64(<vscale x 2 x i64> poison, <2 x i64> splat (i64 1), i64 0)
; CHECK-NEXT: [[TMP3:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dupq.lane.nxv2i64(<vscale x 2 x i64> [[TMP2]], i64 0)
; CHECK-NEXT: [[TMP4:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.cmpne.nxv2i64(<vscale x 2 x i1> splat (i1 true), <vscale x 2 x i64> [[TMP3]], <vscale x 2 x i64> [[X]])
; CHECK-NEXT: ret <vscale x 2 x i1> [[TMP4]]
;
%1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
%2 = tail call <vscale x 2 x i64> @llvm.vector.insert.nxv2i64.v2i64(<vscale x 2 x i64> poison,
<2 x i64> <i64 1, i64 1>, i64 0)
%3 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dupq.lane.nxv2i64(<vscale x 2 x i64> %2 , i64 0)
%4 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.cmpne.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %3, <vscale x 2 x i64> %x)
ret <vscale x 2 x i1> %4
}
define <vscale x 16 x i1> @dupq_b_idx(i64 %idx) #0 {
; CHECK-LABEL: define <vscale x 16 x i1> @dupq_b_idx(
; CHECK-SAME: i64 [[IDX:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: [[TMP2:%.*]] = tail call <vscale x 16 x i8> @llvm.vector.insert.nxv16i8.v16i8(<vscale x 16 x i8> poison, <16 x i8> zeroinitializer, i64 0)
; CHECK-NEXT: [[TMP3:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.dupq.lane.nxv16i8(<vscale x 16 x i8> [[TMP2]], i64 [[IDX]])
; CHECK-NEXT: [[TMP4:%.*]] = tail call <vscale x 16 x i1> @llvm.aarch64.sve.cmpne.wide.nxv16i8(<vscale x 16 x i1> splat (i1 true), <vscale x 16 x i8> [[TMP3]], <vscale x 2 x i64> zeroinitializer)
; CHECK-NEXT: ret <vscale x 16 x i1> [[TMP4]]
;
%1 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
%2 = tail call <vscale x 16 x i8> @llvm.vector.insert.nxv16i8.v16i8(<vscale x 16 x i8> poison,
<16 x i8> <i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0>, i64 0)
%3 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.dupq.lane.nxv16i8(<vscale x 16 x i8> %2 , i64 %idx)
%4 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 0)
%5 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.cmpne.wide.nxv16i8(<vscale x 16 x i1> %1, <vscale x 16 x i8> %3, <vscale x 2 x i64> %4)
ret <vscale x 16 x i1> %5
}
declare <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32)
declare <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32)
declare <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32)
declare <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32)
declare <vscale x 16 x i8> @llvm.vector.insert.nxv16i8.v16i8(<vscale x 16 x i8>, <16 x i8>, i64)
declare <vscale x 8 x i16> @llvm.vector.insert.nxv8i16.v8i16(<vscale x 8 x i16>, <8 x i16>, i64)
declare <vscale x 4 x i32> @llvm.vector.insert.nxv4i32.v4i32(<vscale x 4 x i32>, <4 x i32>, i64)
declare <vscale x 2 x i64> @llvm.vector.insert.nxv2i64.v2i64(<vscale x 2 x i64>, <2 x i64>, i64)
declare <vscale x 16 x i8> @llvm.aarch64.sve.dupq.lane.nxv16i8(<vscale x 16 x i8>, i64)
declare <vscale x 8 x i16> @llvm.aarch64.sve.dupq.lane.nxv8i16(<vscale x 8 x i16>, i64)
declare <vscale x 4 x i32> @llvm.aarch64.sve.dupq.lane.nxv4i32(<vscale x 4 x i32>, i64)
declare <vscale x 2 x i64> @llvm.aarch64.sve.dupq.lane.nxv2i64(<vscale x 2 x i64>, i64)
declare <vscale x 16 x i1> @llvm.aarch64.sve.cmpne.wide.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 2 x i64>)
declare <vscale x 8 x i1> @llvm.aarch64.sve.cmpne.wide.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 2 x i64>)
declare <vscale x 4 x i1> @llvm.aarch64.sve.cmpne.wide.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 2 x i64>)
declare <vscale x 2 x i1> @llvm.aarch64.sve.cmpne.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, <vscale x 2 x i64>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64)
attributes #0 = { "target-features"="+sve" }
Reference in new issue View Git Blame Copy Permalink