derek/TheRock
1
0 Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
Files
main
TheRock/compiler/amd-llvm/llvm/test/CodeGen/AArch64/vecreduce-bitext.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

1203 lines
35 KiB
LLVM
Raw Permalink Blame History

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc -mtriple=aarch64 -verify-machineinstrs %s -o - | FileCheck %s
define zeroext i16 @and_sext_v8i8_i16(<8 x i8> %x) {
; CHECK-LABEL: and_sext_v8i8_i16:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: and x8, x8, x8, lsr #32
; CHECK-NEXT: lsr x9, x8, #16
; CHECK-NEXT: and w8, w8, w9
; CHECK-NEXT: and w8, w8, w8, lsr #8
; CHECK-NEXT: sxtb w8, w8
; CHECK-NEXT: and w0, w8, #0xffff
; CHECK-NEXT: ret
entry:
%y = sext <8 x i8> %x to <8 x i16>
%z = call i16 @llvm.vector.reduce.and.v8i16(<8 x i16> %y)
ret i16 %z
}
define zeroext i16 @and_zext_v8i8_i16(<8 x i8> %x) {
; CHECK-LABEL: and_zext_v8i8_i16:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: and x8, x8, x8, lsr #32
; CHECK-NEXT: lsr x9, x8, #16
; CHECK-NEXT: and w8, w8, w9
; CHECK-NEXT: and w8, w8, w8, lsr #8
; CHECK-NEXT: and w0, w8, #0xff
; CHECK-NEXT: ret
entry:
%y = zext <8 x i8> %x to <8 x i16>
%z = call i16 @llvm.vector.reduce.and.v8i16(<8 x i16> %y)
ret i16 %z
}
define zeroext i16 @and_sext_v16i8_i16(<16 x i8> %x) {
; CHECK-LABEL: and_sext_v16i8_i16:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov d1, v0.d[1]
; CHECK-NEXT: and v0.8b, v0.8b, v1.8b
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: and x8, x8, x8, lsr #32
; CHECK-NEXT: lsr x9, x8, #16
; CHECK-NEXT: and w8, w8, w9
; CHECK-NEXT: and w8, w8, w8, lsr #8
; CHECK-NEXT: sxtb w8, w8
; CHECK-NEXT: and w0, w8, #0xffff
; CHECK-NEXT: ret
entry:
%y = sext <16 x i8> %x to <16 x i16>
%z = call i16 @llvm.vector.reduce.and.v16i16(<16 x i16> %y)
ret i16 %z
}
define zeroext i16 @and_zext_v16i8_i16(<16 x i8> %x) {
; CHECK-LABEL: and_zext_v16i8_i16:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov d1, v0.d[1]
; CHECK-NEXT: and v0.8b, v0.8b, v1.8b
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: and x8, x8, x8, lsr #32
; CHECK-NEXT: lsr x9, x8, #16
; CHECK-NEXT: and w8, w8, w9
; CHECK-NEXT: and w8, w8, w8, lsr #8
; CHECK-NEXT: and w0, w8, #0xff
; CHECK-NEXT: ret
entry:
%y = zext <16 x i8> %x to <16 x i16>
%z = call i16 @llvm.vector.reduce.and.v16i16(<16 x i16> %y)
ret i16 %z
}
define i32 @and_sext_v8i8_i32(<8 x i8> %x) {
; CHECK-LABEL: and_sext_v8i8_i32:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: and x8, x8, x8, lsr #32
; CHECK-NEXT: lsr x9, x8, #16
; CHECK-NEXT: and w8, w8, w9
; CHECK-NEXT: and w8, w8, w8, lsr #8
; CHECK-NEXT: sxtb w0, w8
; CHECK-NEXT: ret
entry:
%y = sext <8 x i8> %x to <8 x i32>
%z = call i32 @llvm.vector.reduce.and.v8i32(<8 x i32> %y)
ret i32 %z
}
define i32 @and_zext_v8i8_i32(<8 x i8> %x) {
; CHECK-LABEL: and_zext_v8i8_i32:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: and x8, x8, x8, lsr #32
; CHECK-NEXT: lsr x9, x8, #16
; CHECK-NEXT: and w8, w8, w9
; CHECK-NEXT: and w8, w8, w8, lsr #8
; CHECK-NEXT: and w0, w8, #0xff
; CHECK-NEXT: ret
entry:
%y = zext <8 x i8> %x to <8 x i32>
%z = call i32 @llvm.vector.reduce.and.v8i32(<8 x i32> %y)
ret i32 %z
}
define i32 @and_sext_v16i8_i32(<16 x i8> %x) {
; CHECK-LABEL: and_sext_v16i8_i32:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov d1, v0.d[1]
; CHECK-NEXT: and v0.8b, v0.8b, v1.8b
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: and x8, x8, x8, lsr #32
; CHECK-NEXT: lsr x9, x8, #16
; CHECK-NEXT: and w8, w8, w9
; CHECK-NEXT: and w8, w8, w8, lsr #8
; CHECK-NEXT: sxtb w0, w8
; CHECK-NEXT: ret
entry:
%y = sext <16 x i8> %x to <16 x i32>
%z = call i32 @llvm.vector.reduce.and.v16i32(<16 x i32> %y)
ret i32 %z
}
define i32 @and_zext_v16i8_i32(<16 x i8> %x) {
; CHECK-LABEL: and_zext_v16i8_i32:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov d1, v0.d[1]
; CHECK-NEXT: and v0.8b, v0.8b, v1.8b
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: and x8, x8, x8, lsr #32
; CHECK-NEXT: lsr x9, x8, #16
; CHECK-NEXT: and w8, w8, w9
; CHECK-NEXT: and w8, w8, w8, lsr #8
; CHECK-NEXT: and w0, w8, #0xff
; CHECK-NEXT: ret
entry:
%y = zext <16 x i8> %x to <16 x i32>
%z = call i32 @llvm.vector.reduce.and.v16i32(<16 x i32> %y)
ret i32 %z
}
define i64 @and_sext_v8i8_i64(<8 x i8> %x) {
; CHECK-LABEL: and_sext_v8i8_i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: and x8, x8, x8, lsr #32
; CHECK-NEXT: lsr x9, x8, #16
; CHECK-NEXT: and w8, w8, w9
; CHECK-NEXT: and w8, w8, w8, lsr #8
; CHECK-NEXT: sxtb x0, w8
; CHECK-NEXT: ret
entry:
%y = sext <8 x i8> %x to <8 x i64>
%z = call i64 @llvm.vector.reduce.and.v8i64(<8 x i64> %y)
ret i64 %z
}
define i64 @and_zext_v8i8_i64(<8 x i8> %x) {
; CHECK-LABEL: and_zext_v8i8_i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: and x8, x8, x8, lsr #32
; CHECK-NEXT: lsr x9, x8, #16
; CHECK-NEXT: and w8, w8, w9
; CHECK-NEXT: and w8, w8, w8, lsr #8
; CHECK-NEXT: and x0, x8, #0xff
; CHECK-NEXT: ret
entry:
%y = zext <8 x i8> %x to <8 x i64>
%z = call i64 @llvm.vector.reduce.and.v8i64(<8 x i64> %y)
ret i64 %z
}
define i64 @and_sext_v16i8_i64(<16 x i8> %x) {
; CHECK-LABEL: and_sext_v16i8_i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov d1, v0.d[1]
; CHECK-NEXT: and v0.8b, v0.8b, v1.8b
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: and x8, x8, x8, lsr #32
; CHECK-NEXT: lsr x9, x8, #16
; CHECK-NEXT: and w8, w8, w9
; CHECK-NEXT: and w8, w8, w8, lsr #8
; CHECK-NEXT: sxtb x0, w8
; CHECK-NEXT: ret
entry:
%y = sext <16 x i8> %x to <16 x i64>
%z = call i64 @llvm.vector.reduce.and.v16i64(<16 x i64> %y)
ret i64 %z
}
define i64 @and_zext_v16i8_i64(<16 x i8> %x) {
; CHECK-LABEL: and_zext_v16i8_i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov d1, v0.d[1]
; CHECK-NEXT: and v0.8b, v0.8b, v1.8b
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: and x8, x8, x8, lsr #32
; CHECK-NEXT: lsr x9, x8, #16
; CHECK-NEXT: and w8, w8, w9
; CHECK-NEXT: and w8, w8, w8, lsr #8
; CHECK-NEXT: and x0, x8, #0xff
; CHECK-NEXT: ret
entry:
%y = zext <16 x i8> %x to <16 x i64>
%z = call i64 @llvm.vector.reduce.and.v16i64(<16 x i64> %y)
ret i64 %z
}
define i32 @and_sext_v4i16_i32(<4 x i16> %x) {
; CHECK-LABEL: and_sext_v4i16_i32:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: lsr x9, x8, #32
; CHECK-NEXT: and w8, w8, w9
; CHECK-NEXT: and w8, w8, w8, lsr #16
; CHECK-NEXT: sxth w0, w8
; CHECK-NEXT: ret
entry:
%y = sext <4 x i16> %x to <4 x i32>
%z = call i32 @llvm.vector.reduce.and.v4i32(<4 x i32> %y)
ret i32 %z
}
define i32 @and_zext_v4i16_i32(<4 x i16> %x) {
; CHECK-LABEL: and_zext_v4i16_i32:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: and x8, x8, x8, lsr #32
; CHECK-NEXT: lsr x9, x8, #16
; CHECK-NEXT: and w0, w8, w9
; CHECK-NEXT: ret
entry:
%y = zext <4 x i16> %x to <4 x i32>
%z = call i32 @llvm.vector.reduce.and.v4i32(<4 x i32> %y)
ret i32 %z
}
define i32 @and_sext_v8i16_i32(<8 x i16> %x) {
; CHECK-LABEL: and_sext_v8i16_i32:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov d1, v0.d[1]
; CHECK-NEXT: and v0.8b, v0.8b, v1.8b
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: lsr x9, x8, #32
; CHECK-NEXT: and w8, w8, w9
; CHECK-NEXT: and w8, w8, w8, lsr #16
; CHECK-NEXT: sxth w0, w8
; CHECK-NEXT: ret
entry:
%y = sext <8 x i16> %x to <8 x i32>
%z = call i32 @llvm.vector.reduce.and.v8i32(<8 x i32> %y)
ret i32 %z
}
define i32 @and_zext_v8i16_i32(<8 x i16> %x) {
; CHECK-LABEL: and_zext_v8i16_i32:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov d1, v0.d[1]
; CHECK-NEXT: and v0.8b, v0.8b, v1.8b
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: and x8, x8, x8, lsr #32
; CHECK-NEXT: lsr x9, x8, #16
; CHECK-NEXT: and w0, w8, w9
; CHECK-NEXT: ret
entry:
%y = zext <8 x i16> %x to <8 x i32>
%z = call i32 @llvm.vector.reduce.and.v8i32(<8 x i32> %y)
ret i32 %z
}
define i64 @and_sext_v4i16_i64(<4 x i16> %x) {
; CHECK-LABEL: and_sext_v4i16_i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: lsr x9, x8, #32
; CHECK-NEXT: and w8, w8, w9
; CHECK-NEXT: and w8, w8, w8, lsr #16
; CHECK-NEXT: sxth x0, w8
; CHECK-NEXT: ret
entry:
%y = sext <4 x i16> %x to <4 x i64>
%z = call i64 @llvm.vector.reduce.and.v4i64(<4 x i64> %y)
ret i64 %z
}
define i64 @and_zext_v4i16_i64(<4 x i16> %x) {
; CHECK-LABEL: and_zext_v4i16_i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: and x8, x8, x8, lsr #32
; CHECK-NEXT: lsr x9, x8, #16
; CHECK-NEXT: and w0, w8, w9
; CHECK-NEXT: ret
entry:
%y = zext <4 x i16> %x to <4 x i64>
%z = call i64 @llvm.vector.reduce.and.v4i64(<4 x i64> %y)
ret i64 %z
}
define i64 @and_sext_v8i16_i64(<8 x i16> %x) {
; CHECK-LABEL: and_sext_v8i16_i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov d1, v0.d[1]
; CHECK-NEXT: and v0.8b, v0.8b, v1.8b
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: lsr x9, x8, #32
; CHECK-NEXT: and w8, w8, w9
; CHECK-NEXT: and w8, w8, w8, lsr #16
; CHECK-NEXT: sxth x0, w8
; CHECK-NEXT: ret
entry:
%y = sext <8 x i16> %x to <8 x i64>
%z = call i64 @llvm.vector.reduce.and.v8i64(<8 x i64> %y)
ret i64 %z
}
define i64 @and_zext_v8i16_i64(<8 x i16> %x) {
; CHECK-LABEL: and_zext_v8i16_i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov d1, v0.d[1]
; CHECK-NEXT: and v0.8b, v0.8b, v1.8b
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: and x8, x8, x8, lsr #32
; CHECK-NEXT: lsr x9, x8, #16
; CHECK-NEXT: and w0, w8, w9
; CHECK-NEXT: ret
entry:
%y = zext <8 x i16> %x to <8 x i64>
%z = call i64 @llvm.vector.reduce.and.v8i64(<8 x i64> %y)
ret i64 %z
}
define i64 @and_sext_v2i32_i64(<2 x i32> %x) {
; CHECK-LABEL: and_sext_v2i32_i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: lsr x9, x8, #32
; CHECK-NEXT: and w8, w8, w9
; CHECK-NEXT: sxtw x0, w8
; CHECK-NEXT: ret
entry:
%y = sext <2 x i32> %x to <2 x i64>
%z = call i64 @llvm.vector.reduce.and.v2i64(<2 x i64> %y)
ret i64 %z
}
define i64 @and_zext_v2i32_i64(<2 x i32> %x) {
; CHECK-LABEL: and_zext_v2i32_i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: lsr x9, x8, #32
; CHECK-NEXT: and w0, w8, w9
; CHECK-NEXT: ret
entry:
%y = zext <2 x i32> %x to <2 x i64>
%z = call i64 @llvm.vector.reduce.and.v2i64(<2 x i64> %y)
ret i64 %z
}
define i64 @and_sext_v4i32_i64(<4 x i32> %x) {
; CHECK-LABEL: and_sext_v4i32_i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov d1, v0.d[1]
; CHECK-NEXT: and v0.8b, v0.8b, v1.8b
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: lsr x9, x8, #32
; CHECK-NEXT: and w8, w8, w9
; CHECK-NEXT: sxtw x0, w8
; CHECK-NEXT: ret
entry:
%y = sext <4 x i32> %x to <4 x i64>
%z = call i64 @llvm.vector.reduce.and.v4i64(<4 x i64> %y)
ret i64 %z
}
define i64 @and_zext_v4i32_i64(<4 x i32> %x) {
; CHECK-LABEL: and_zext_v4i32_i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov d1, v0.d[1]
; CHECK-NEXT: and v0.8b, v0.8b, v1.8b
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: lsr x9, x8, #32
; CHECK-NEXT: and w0, w8, w9
; CHECK-NEXT: ret
entry:
%y = zext <4 x i32> %x to <4 x i64>
%z = call i64 @llvm.vector.reduce.and.v4i64(<4 x i64> %y)
ret i64 %z
}
define zeroext i16 @or_sext_v8i8_i16(<8 x i8> %x) {
; CHECK-LABEL: or_sext_v8i8_i16:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: orr x8, x8, x8, lsr #32
; CHECK-NEXT: lsr x9, x8, #16
; CHECK-NEXT: orr w8, w8, w9
; CHECK-NEXT: orr w8, w8, w8, lsr #8
; CHECK-NEXT: sxtb w8, w8
; CHECK-NEXT: and w0, w8, #0xffff
; CHECK-NEXT: ret
entry:
%y = sext <8 x i8> %x to <8 x i16>
%z = call i16 @llvm.vector.reduce.or.v8i16(<8 x i16> %y)
ret i16 %z
}
define zeroext i16 @or_zext_v8i8_i16(<8 x i8> %x) {
; CHECK-LABEL: or_zext_v8i8_i16:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: orr x8, x8, x8, lsr #32
; CHECK-NEXT: lsr x9, x8, #16
; CHECK-NEXT: orr w8, w8, w9
; CHECK-NEXT: orr w8, w8, w8, lsr #8
; CHECK-NEXT: and w0, w8, #0xff
; CHECK-NEXT: ret
entry:
%y = zext <8 x i8> %x to <8 x i16>
%z = call i16 @llvm.vector.reduce.or.v8i16(<8 x i16> %y)
ret i16 %z
}
define zeroext i16 @or_sext_v16i8_i16(<16 x i8> %x) {
; CHECK-LABEL: or_sext_v16i8_i16:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov d1, v0.d[1]
; CHECK-NEXT: orr v0.8b, v0.8b, v1.8b
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: orr x8, x8, x8, lsr #32
; CHECK-NEXT: lsr x9, x8, #16
; CHECK-NEXT: orr w8, w8, w9
; CHECK-NEXT: orr w8, w8, w8, lsr #8
; CHECK-NEXT: sxtb w8, w8
; CHECK-NEXT: and w0, w8, #0xffff
; CHECK-NEXT: ret
entry:
%y = sext <16 x i8> %x to <16 x i16>
%z = call i16 @llvm.vector.reduce.or.v16i16(<16 x i16> %y)
ret i16 %z
}
define zeroext i16 @or_zext_v16i8_i16(<16 x i8> %x) {
; CHECK-LABEL: or_zext_v16i8_i16:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov d1, v0.d[1]
; CHECK-NEXT: orr v0.8b, v0.8b, v1.8b
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: orr x8, x8, x8, lsr #32
; CHECK-NEXT: lsr x9, x8, #16
; CHECK-NEXT: orr w8, w8, w9
; CHECK-NEXT: orr w8, w8, w8, lsr #8
; CHECK-NEXT: and w0, w8, #0xff
; CHECK-NEXT: ret
entry:
%y = zext <16 x i8> %x to <16 x i16>
%z = call i16 @llvm.vector.reduce.or.v16i16(<16 x i16> %y)
ret i16 %z
}
define i32 @or_sext_v8i8_i32(<8 x i8> %x) {
; CHECK-LABEL: or_sext_v8i8_i32:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: orr x8, x8, x8, lsr #32
; CHECK-NEXT: lsr x9, x8, #16
; CHECK-NEXT: orr w8, w8, w9
; CHECK-NEXT: orr w8, w8, w8, lsr #8
; CHECK-NEXT: sxtb w0, w8
; CHECK-NEXT: ret
entry:
%y = sext <8 x i8> %x to <8 x i32>
%z = call i32 @llvm.vector.reduce.or.v8i32(<8 x i32> %y)
ret i32 %z
}
define i32 @or_zext_v8i8_i32(<8 x i8> %x) {
; CHECK-LABEL: or_zext_v8i8_i32:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: orr x8, x8, x8, lsr #32
; CHECK-NEXT: lsr x9, x8, #16
; CHECK-NEXT: orr w8, w8, w9
; CHECK-NEXT: orr w8, w8, w8, lsr #8
; CHECK-NEXT: and w0, w8, #0xff
; CHECK-NEXT: ret
entry:
%y = zext <8 x i8> %x to <8 x i32>
%z = call i32 @llvm.vector.reduce.or.v8i32(<8 x i32> %y)
ret i32 %z
}
define i32 @or_sext_v16i8_i32(<16 x i8> %x) {
; CHECK-LABEL: or_sext_v16i8_i32:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov d1, v0.d[1]
; CHECK-NEXT: orr v0.8b, v0.8b, v1.8b
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: orr x8, x8, x8, lsr #32
; CHECK-NEXT: lsr x9, x8, #16
; CHECK-NEXT: orr w8, w8, w9
; CHECK-NEXT: orr w8, w8, w8, lsr #8
; CHECK-NEXT: sxtb w0, w8
; CHECK-NEXT: ret
entry:
%y = sext <16 x i8> %x to <16 x i32>
%z = call i32 @llvm.vector.reduce.or.v16i32(<16 x i32> %y)
ret i32 %z
}
define i32 @or_zext_v16i8_i32(<16 x i8> %x) {
; CHECK-LABEL: or_zext_v16i8_i32:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov d1, v0.d[1]
; CHECK-NEXT: orr v0.8b, v0.8b, v1.8b
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: orr x8, x8, x8, lsr #32
; CHECK-NEXT: lsr x9, x8, #16
; CHECK-NEXT: orr w8, w8, w9
; CHECK-NEXT: orr w8, w8, w8, lsr #8
; CHECK-NEXT: and w0, w8, #0xff
; CHECK-NEXT: ret
entry:
%y = zext <16 x i8> %x to <16 x i32>
%z = call i32 @llvm.vector.reduce.or.v16i32(<16 x i32> %y)
ret i32 %z
}
define i64 @or_sext_v8i8_i64(<8 x i8> %x) {
; CHECK-LABEL: or_sext_v8i8_i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: orr x8, x8, x8, lsr #32
; CHECK-NEXT: lsr x9, x8, #16
; CHECK-NEXT: orr w8, w8, w9
; CHECK-NEXT: orr w8, w8, w8, lsr #8
; CHECK-NEXT: sxtb x0, w8
; CHECK-NEXT: ret
entry:
%y = sext <8 x i8> %x to <8 x i64>
%z = call i64 @llvm.vector.reduce.or.v8i64(<8 x i64> %y)
ret i64 %z
}
define i64 @or_zext_v8i8_i64(<8 x i8> %x) {
; CHECK-LABEL: or_zext_v8i8_i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: orr x8, x8, x8, lsr #32
; CHECK-NEXT: lsr x9, x8, #16
; CHECK-NEXT: orr w8, w8, w9
; CHECK-NEXT: orr w8, w8, w8, lsr #8
; CHECK-NEXT: and x0, x8, #0xff
; CHECK-NEXT: ret
entry:
%y = zext <8 x i8> %x to <8 x i64>
%z = call i64 @llvm.vector.reduce.or.v8i64(<8 x i64> %y)
ret i64 %z
}
define i64 @or_sext_v16i8_i64(<16 x i8> %x) {
; CHECK-LABEL: or_sext_v16i8_i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov d1, v0.d[1]
; CHECK-NEXT: orr v0.8b, v0.8b, v1.8b
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: orr x8, x8, x8, lsr #32
; CHECK-NEXT: lsr x9, x8, #16
; CHECK-NEXT: orr w8, w8, w9
; CHECK-NEXT: orr w8, w8, w8, lsr #8
; CHECK-NEXT: sxtb x0, w8
; CHECK-NEXT: ret
entry:
%y = sext <16 x i8> %x to <16 x i64>
%z = call i64 @llvm.vector.reduce.or.v16i64(<16 x i64> %y)
ret i64 %z
}
define i64 @or_zext_v16i8_i64(<16 x i8> %x) {
; CHECK-LABEL: or_zext_v16i8_i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov d1, v0.d[1]
; CHECK-NEXT: orr v0.8b, v0.8b, v1.8b
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: orr x8, x8, x8, lsr #32
; CHECK-NEXT: lsr x9, x8, #16
; CHECK-NEXT: orr w8, w8, w9
; CHECK-NEXT: orr w8, w8, w8, lsr #8
; CHECK-NEXT: and x0, x8, #0xff
; CHECK-NEXT: ret
entry:
%y = zext <16 x i8> %x to <16 x i64>
%z = call i64 @llvm.vector.reduce.or.v16i64(<16 x i64> %y)
ret i64 %z
}
define i32 @or_sext_v4i16_i32(<4 x i16> %x) {
; CHECK-LABEL: or_sext_v4i16_i32:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: lsr x9, x8, #32
; CHECK-NEXT: orr w8, w8, w9
; CHECK-NEXT: orr w8, w8, w8, lsr #16
; CHECK-NEXT: sxth w0, w8
; CHECK-NEXT: ret
entry:
%y = sext <4 x i16> %x to <4 x i32>
%z = call i32 @llvm.vector.reduce.or.v4i32(<4 x i32> %y)
ret i32 %z
}
define i32 @or_zext_v4i16_i32(<4 x i16> %x) {
; CHECK-LABEL: or_zext_v4i16_i32:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: lsr x9, x8, #32
; CHECK-NEXT: orr w8, w8, w9
; CHECK-NEXT: orr w8, w8, w8, lsr #16
; CHECK-NEXT: and w0, w8, #0xffff
; CHECK-NEXT: ret
entry:
%y = zext <4 x i16> %x to <4 x i32>
%z = call i32 @llvm.vector.reduce.or.v4i32(<4 x i32> %y)
ret i32 %z
}
define i32 @or_sext_v8i16_i32(<8 x i16> %x) {
; CHECK-LABEL: or_sext_v8i16_i32:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov d1, v0.d[1]
; CHECK-NEXT: orr v0.8b, v0.8b, v1.8b
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: lsr x9, x8, #32
; CHECK-NEXT: orr w8, w8, w9
; CHECK-NEXT: orr w8, w8, w8, lsr #16
; CHECK-NEXT: sxth w0, w8
; CHECK-NEXT: ret
entry:
%y = sext <8 x i16> %x to <8 x i32>
%z = call i32 @llvm.vector.reduce.or.v8i32(<8 x i32> %y)
ret i32 %z
}
define i32 @or_zext_v8i16_i32(<8 x i16> %x) {
; CHECK-LABEL: or_zext_v8i16_i32:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov d1, v0.d[1]
; CHECK-NEXT: orr v0.8b, v0.8b, v1.8b
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: lsr x9, x8, #32
; CHECK-NEXT: orr w8, w8, w9
; CHECK-NEXT: orr w8, w8, w8, lsr #16
; CHECK-NEXT: and w0, w8, #0xffff
; CHECK-NEXT: ret
entry:
%y = zext <8 x i16> %x to <8 x i32>
%z = call i32 @llvm.vector.reduce.or.v8i32(<8 x i32> %y)
ret i32 %z
}
define i64 @or_sext_v4i16_i64(<4 x i16> %x) {
; CHECK-LABEL: or_sext_v4i16_i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: lsr x9, x8, #32
; CHECK-NEXT: orr w8, w8, w9
; CHECK-NEXT: orr w8, w8, w8, lsr #16
; CHECK-NEXT: sxth x0, w8
; CHECK-NEXT: ret
entry:
%y = sext <4 x i16> %x to <4 x i64>
%z = call i64 @llvm.vector.reduce.or.v4i64(<4 x i64> %y)
ret i64 %z
}
define i64 @or_zext_v4i16_i64(<4 x i16> %x) {
; CHECK-LABEL: or_zext_v4i16_i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: lsr x9, x8, #32
; CHECK-NEXT: orr w8, w8, w9
; CHECK-NEXT: orr w8, w8, w8, lsr #16
; CHECK-NEXT: and x0, x8, #0xffff
; CHECK-NEXT: ret
entry:
%y = zext <4 x i16> %x to <4 x i64>
%z = call i64 @llvm.vector.reduce.or.v4i64(<4 x i64> %y)
ret i64 %z
}
define i64 @or_sext_v8i16_i64(<8 x i16> %x) {
; CHECK-LABEL: or_sext_v8i16_i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov d1, v0.d[1]
; CHECK-NEXT: orr v0.8b, v0.8b, v1.8b
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: lsr x9, x8, #32
; CHECK-NEXT: orr w8, w8, w9
; CHECK-NEXT: orr w8, w8, w8, lsr #16
; CHECK-NEXT: sxth x0, w8
; CHECK-NEXT: ret
entry:
%y = sext <8 x i16> %x to <8 x i64>
%z = call i64 @llvm.vector.reduce.or.v8i64(<8 x i64> %y)
ret i64 %z
}
define i64 @or_zext_v8i16_i64(<8 x i16> %x) {
; CHECK-LABEL: or_zext_v8i16_i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov d1, v0.d[1]
; CHECK-NEXT: orr v0.8b, v0.8b, v1.8b
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: lsr x9, x8, #32
; CHECK-NEXT: orr w8, w8, w9
; CHECK-NEXT: orr w8, w8, w8, lsr #16
; CHECK-NEXT: and x0, x8, #0xffff
; CHECK-NEXT: ret
entry:
%y = zext <8 x i16> %x to <8 x i64>
%z = call i64 @llvm.vector.reduce.or.v8i64(<8 x i64> %y)
ret i64 %z
}
define i64 @or_sext_v2i32_i64(<2 x i32> %x) {
; CHECK-LABEL: or_sext_v2i32_i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: lsr x9, x8, #32
; CHECK-NEXT: orr w8, w8, w9
; CHECK-NEXT: sxtw x0, w8
; CHECK-NEXT: ret
entry:
%y = sext <2 x i32> %x to <2 x i64>
%z = call i64 @llvm.vector.reduce.or.v2i64(<2 x i64> %y)
ret i64 %z
}
define i64 @or_zext_v2i32_i64(<2 x i32> %x) {
; CHECK-LABEL: or_zext_v2i32_i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: lsr x9, x8, #32
; CHECK-NEXT: orr w0, w8, w9
; CHECK-NEXT: ret
entry:
%y = zext <2 x i32> %x to <2 x i64>
%z = call i64 @llvm.vector.reduce.or.v2i64(<2 x i64> %y)
ret i64 %z
}
define i64 @or_sext_v4i32_i64(<4 x i32> %x) {
; CHECK-LABEL: or_sext_v4i32_i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov d1, v0.d[1]
; CHECK-NEXT: orr v0.8b, v0.8b, v1.8b
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: lsr x9, x8, #32
; CHECK-NEXT: orr w8, w8, w9
; CHECK-NEXT: sxtw x0, w8
; CHECK-NEXT: ret
entry:
%y = sext <4 x i32> %x to <4 x i64>
%z = call i64 @llvm.vector.reduce.or.v4i64(<4 x i64> %y)
ret i64 %z
}
define i64 @or_zext_v4i32_i64(<4 x i32> %x) {
; CHECK-LABEL: or_zext_v4i32_i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov d1, v0.d[1]
; CHECK-NEXT: orr v0.8b, v0.8b, v1.8b
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: lsr x9, x8, #32
; CHECK-NEXT: orr w0, w8, w9
; CHECK-NEXT: ret
entry:
%y = zext <4 x i32> %x to <4 x i64>
%z = call i64 @llvm.vector.reduce.or.v4i64(<4 x i64> %y)
ret i64 %z
}
define zeroext i16 @xor_sext_v8i8_i16(<8 x i8> %x) {
; CHECK-LABEL: xor_sext_v8i8_i16:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: eor x8, x8, x8, lsr #32
; CHECK-NEXT: lsr x9, x8, #16
; CHECK-NEXT: eor w8, w8, w9
; CHECK-NEXT: eor w8, w8, w8, lsr #8
; CHECK-NEXT: sxtb w8, w8
; CHECK-NEXT: and w0, w8, #0xffff
; CHECK-NEXT: ret
entry:
%y = sext <8 x i8> %x to <8 x i16>
%z = call i16 @llvm.vector.reduce.xor.v8i16(<8 x i16> %y)
ret i16 %z
}
define zeroext i16 @xor_zext_v8i8_i16(<8 x i8> %x) {
; CHECK-LABEL: xor_zext_v8i8_i16:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: eor x8, x8, x8, lsr #32
; CHECK-NEXT: lsr x9, x8, #16
; CHECK-NEXT: eor w8, w8, w9
; CHECK-NEXT: eor w8, w8, w8, lsr #8
; CHECK-NEXT: and w0, w8, #0xff
; CHECK-NEXT: ret
entry:
%y = zext <8 x i8> %x to <8 x i16>
%z = call i16 @llvm.vector.reduce.xor.v8i16(<8 x i16> %y)
ret i16 %z
}
define zeroext i16 @xor_sext_v16i8_i16(<16 x i8> %x) {
; CHECK-LABEL: xor_sext_v16i8_i16:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov d1, v0.d[1]
; CHECK-NEXT: eor v0.8b, v0.8b, v1.8b
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: eor x8, x8, x8, lsr #32
; CHECK-NEXT: lsr x9, x8, #16
; CHECK-NEXT: eor w8, w8, w9
; CHECK-NEXT: eor w8, w8, w8, lsr #8
; CHECK-NEXT: sxtb w8, w8
; CHECK-NEXT: and w0, w8, #0xffff
; CHECK-NEXT: ret
entry:
%y = sext <16 x i8> %x to <16 x i16>
%z = call i16 @llvm.vector.reduce.xor.v16i16(<16 x i16> %y)
ret i16 %z
}
define zeroext i16 @xor_zext_v16i8_i16(<16 x i8> %x) {
; CHECK-LABEL: xor_zext_v16i8_i16:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov d1, v0.d[1]
; CHECK-NEXT: eor v0.8b, v0.8b, v1.8b
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: eor x8, x8, x8, lsr #32
; CHECK-NEXT: lsr x9, x8, #16
; CHECK-NEXT: eor w8, w8, w9
; CHECK-NEXT: eor w8, w8, w8, lsr #8
; CHECK-NEXT: and w0, w8, #0xff
; CHECK-NEXT: ret
entry:
%y = zext <16 x i8> %x to <16 x i16>
%z = call i16 @llvm.vector.reduce.xor.v16i16(<16 x i16> %y)
ret i16 %z
}
define i32 @xor_sext_v8i8_i32(<8 x i8> %x) {
; CHECK-LABEL: xor_sext_v8i8_i32:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: eor x8, x8, x8, lsr #32
; CHECK-NEXT: lsr x9, x8, #16
; CHECK-NEXT: eor w8, w8, w9
; CHECK-NEXT: eor w8, w8, w8, lsr #8
; CHECK-NEXT: sxtb w0, w8
; CHECK-NEXT: ret
entry:
%y = sext <8 x i8> %x to <8 x i32>
%z = call i32 @llvm.vector.reduce.xor.v8i32(<8 x i32> %y)
ret i32 %z
}
define i32 @xor_zext_v8i8_i32(<8 x i8> %x) {
; CHECK-LABEL: xor_zext_v8i8_i32:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: eor x8, x8, x8, lsr #32
; CHECK-NEXT: lsr x9, x8, #16
; CHECK-NEXT: eor w8, w8, w9
; CHECK-NEXT: eor w8, w8, w8, lsr #8
; CHECK-NEXT: and w0, w8, #0xff
; CHECK-NEXT: ret
entry:
%y = zext <8 x i8> %x to <8 x i32>
%z = call i32 @llvm.vector.reduce.xor.v8i32(<8 x i32> %y)
ret i32 %z
}
define i32 @xor_sext_v16i8_i32(<16 x i8> %x) {
; CHECK-LABEL: xor_sext_v16i8_i32:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov d1, v0.d[1]
; CHECK-NEXT: eor v0.8b, v0.8b, v1.8b
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: eor x8, x8, x8, lsr #32
; CHECK-NEXT: lsr x9, x8, #16
; CHECK-NEXT: eor w8, w8, w9
; CHECK-NEXT: eor w8, w8, w8, lsr #8
; CHECK-NEXT: sxtb w0, w8
; CHECK-NEXT: ret
entry:
%y = sext <16 x i8> %x to <16 x i32>
%z = call i32 @llvm.vector.reduce.xor.v16i32(<16 x i32> %y)
ret i32 %z
}
define i32 @xor_zext_v16i8_i32(<16 x i8> %x) {
; CHECK-LABEL: xor_zext_v16i8_i32:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov d1, v0.d[1]
; CHECK-NEXT: eor v0.8b, v0.8b, v1.8b
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: eor x8, x8, x8, lsr #32
; CHECK-NEXT: lsr x9, x8, #16
; CHECK-NEXT: eor w8, w8, w9
; CHECK-NEXT: eor w8, w8, w8, lsr #8
; CHECK-NEXT: and w0, w8, #0xff
; CHECK-NEXT: ret
entry:
%y = zext <16 x i8> %x to <16 x i32>
%z = call i32 @llvm.vector.reduce.xor.v16i32(<16 x i32> %y)
ret i32 %z
}
define i64 @xor_sext_v8i8_i64(<8 x i8> %x) {
; CHECK-LABEL: xor_sext_v8i8_i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: eor x8, x8, x8, lsr #32
; CHECK-NEXT: lsr x9, x8, #16
; CHECK-NEXT: eor w8, w8, w9
; CHECK-NEXT: eor w8, w8, w8, lsr #8
; CHECK-NEXT: sxtb x0, w8
; CHECK-NEXT: ret
entry:
%y = sext <8 x i8> %x to <8 x i64>
%z = call i64 @llvm.vector.reduce.xor.v8i64(<8 x i64> %y)
ret i64 %z
}
define i64 @xor_zext_v8i8_i64(<8 x i8> %x) {
; CHECK-LABEL: xor_zext_v8i8_i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: eor x8, x8, x8, lsr #32
; CHECK-NEXT: lsr x9, x8, #16
; CHECK-NEXT: eor w8, w8, w9
; CHECK-NEXT: eor w8, w8, w8, lsr #8
; CHECK-NEXT: and x0, x8, #0xff
; CHECK-NEXT: ret
entry:
%y = zext <8 x i8> %x to <8 x i64>
%z = call i64 @llvm.vector.reduce.xor.v8i64(<8 x i64> %y)
ret i64 %z
}
define i64 @xor_sext_v16i8_i64(<16 x i8> %x) {
; CHECK-LABEL: xor_sext_v16i8_i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov d1, v0.d[1]
; CHECK-NEXT: eor v0.8b, v0.8b, v1.8b
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: eor x8, x8, x8, lsr #32
; CHECK-NEXT: lsr x9, x8, #16
; CHECK-NEXT: eor w8, w8, w9
; CHECK-NEXT: eor w8, w8, w8, lsr #8
; CHECK-NEXT: sxtb x0, w8
; CHECK-NEXT: ret
entry:
%y = sext <16 x i8> %x to <16 x i64>
%z = call i64 @llvm.vector.reduce.xor.v16i64(<16 x i64> %y)
ret i64 %z
}
define i64 @xor_zext_v16i8_i64(<16 x i8> %x) {
; CHECK-LABEL: xor_zext_v16i8_i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov d1, v0.d[1]
; CHECK-NEXT: eor v0.8b, v0.8b, v1.8b
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: eor x8, x8, x8, lsr #32
; CHECK-NEXT: lsr x9, x8, #16
; CHECK-NEXT: eor w8, w8, w9
; CHECK-NEXT: eor w8, w8, w8, lsr #8
; CHECK-NEXT: and x0, x8, #0xff
; CHECK-NEXT: ret
entry:
%y = zext <16 x i8> %x to <16 x i64>
%z = call i64 @llvm.vector.reduce.xor.v16i64(<16 x i64> %y)
ret i64 %z
}
define i32 @xor_sext_v4i16_i32(<4 x i16> %x) {
; CHECK-LABEL: xor_sext_v4i16_i32:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: lsr x9, x8, #32
; CHECK-NEXT: eor w8, w8, w9
; CHECK-NEXT: eor w8, w8, w8, lsr #16
; CHECK-NEXT: sxth w0, w8
; CHECK-NEXT: ret
entry:
%y = sext <4 x i16> %x to <4 x i32>
%z = call i32 @llvm.vector.reduce.xor.v4i32(<4 x i32> %y)
ret i32 %z
}
define i32 @xor_zext_v4i16_i32(<4 x i16> %x) {
; CHECK-LABEL: xor_zext_v4i16_i32:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: lsr x9, x8, #32
; CHECK-NEXT: eor w8, w8, w9
; CHECK-NEXT: eor w8, w8, w8, lsr #16
; CHECK-NEXT: and w0, w8, #0xffff
; CHECK-NEXT: ret
entry:
%y = zext <4 x i16> %x to <4 x i32>
%z = call i32 @llvm.vector.reduce.xor.v4i32(<4 x i32> %y)
ret i32 %z
}
define i32 @xor_sext_v8i16_i32(<8 x i16> %x) {
; CHECK-LABEL: xor_sext_v8i16_i32:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov d1, v0.d[1]
; CHECK-NEXT: eor v0.8b, v0.8b, v1.8b
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: lsr x9, x8, #32
; CHECK-NEXT: eor w8, w8, w9
; CHECK-NEXT: eor w8, w8, w8, lsr #16
; CHECK-NEXT: sxth w0, w8
; CHECK-NEXT: ret
entry:
%y = sext <8 x i16> %x to <8 x i32>
%z = call i32 @llvm.vector.reduce.xor.v8i32(<8 x i32> %y)
ret i32 %z
}
define i32 @xor_zext_v8i16_i32(<8 x i16> %x) {
; CHECK-LABEL: xor_zext_v8i16_i32:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov d1, v0.d[1]
; CHECK-NEXT: eor v0.8b, v0.8b, v1.8b
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: lsr x9, x8, #32
; CHECK-NEXT: eor w8, w8, w9
; CHECK-NEXT: eor w8, w8, w8, lsr #16
; CHECK-NEXT: and w0, w8, #0xffff
; CHECK-NEXT: ret
entry:
%y = zext <8 x i16> %x to <8 x i32>
%z = call i32 @llvm.vector.reduce.xor.v8i32(<8 x i32> %y)
ret i32 %z
}
define i64 @xor_sext_v4i16_i64(<4 x i16> %x) {
; CHECK-LABEL: xor_sext_v4i16_i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: lsr x9, x8, #32
; CHECK-NEXT: eor w8, w8, w9
; CHECK-NEXT: eor w8, w8, w8, lsr #16
; CHECK-NEXT: sxth x0, w8
; CHECK-NEXT: ret
entry:
%y = sext <4 x i16> %x to <4 x i64>
%z = call i64 @llvm.vector.reduce.xor.v4i64(<4 x i64> %y)
ret i64 %z
}
define i64 @xor_zext_v4i16_i64(<4 x i16> %x) {
; CHECK-LABEL: xor_zext_v4i16_i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: lsr x9, x8, #32
; CHECK-NEXT: eor w8, w8, w9
; CHECK-NEXT: eor w8, w8, w8, lsr #16
; CHECK-NEXT: and x0, x8, #0xffff
; CHECK-NEXT: ret
entry:
%y = zext <4 x i16> %x to <4 x i64>
%z = call i64 @llvm.vector.reduce.xor.v4i64(<4 x i64> %y)
ret i64 %z
}
define i64 @xor_sext_v8i16_i64(<8 x i16> %x) {
; CHECK-LABEL: xor_sext_v8i16_i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov d1, v0.d[1]
; CHECK-NEXT: eor v0.8b, v0.8b, v1.8b
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: lsr x9, x8, #32
; CHECK-NEXT: eor w8, w8, w9
; CHECK-NEXT: eor w8, w8, w8, lsr #16
; CHECK-NEXT: sxth x0, w8
; CHECK-NEXT: ret
entry:
%y = sext <8 x i16> %x to <8 x i64>
%z = call i64 @llvm.vector.reduce.xor.v8i64(<8 x i64> %y)
ret i64 %z
}
define i64 @xor_zext_v8i16_i64(<8 x i16> %x) {
; CHECK-LABEL: xor_zext_v8i16_i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov d1, v0.d[1]
; CHECK-NEXT: eor v0.8b, v0.8b, v1.8b
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: lsr x9, x8, #32
; CHECK-NEXT: eor w8, w8, w9
; CHECK-NEXT: eor w8, w8, w8, lsr #16
; CHECK-NEXT: and x0, x8, #0xffff
; CHECK-NEXT: ret
entry:
%y = zext <8 x i16> %x to <8 x i64>
%z = call i64 @llvm.vector.reduce.xor.v8i64(<8 x i64> %y)
ret i64 %z
}
define i64 @xor_sext_v2i32_i64(<2 x i32> %x) {
; CHECK-LABEL: xor_sext_v2i32_i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: lsr x9, x8, #32
; CHECK-NEXT: eor w8, w8, w9
; CHECK-NEXT: sxtw x0, w8
; CHECK-NEXT: ret
entry:
%y = sext <2 x i32> %x to <2 x i64>
%z = call i64 @llvm.vector.reduce.xor.v2i64(<2 x i64> %y)
ret i64 %z
}
define i64 @xor_zext_v2i32_i64(<2 x i32> %x) {
; CHECK-LABEL: xor_zext_v2i32_i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: lsr x9, x8, #32
; CHECK-NEXT: eor w0, w8, w9
; CHECK-NEXT: ret
entry:
%y = zext <2 x i32> %x to <2 x i64>
%z = call i64 @llvm.vector.reduce.xor.v2i64(<2 x i64> %y)
ret i64 %z
}
define i64 @xor_sext_v4i32_i64(<4 x i32> %x) {
; CHECK-LABEL: xor_sext_v4i32_i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov d1, v0.d[1]
; CHECK-NEXT: eor v0.8b, v0.8b, v1.8b
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: lsr x9, x8, #32
; CHECK-NEXT: eor w8, w8, w9
; CHECK-NEXT: sxtw x0, w8
; CHECK-NEXT: ret
entry:
%y = sext <4 x i32> %x to <4 x i64>
%z = call i64 @llvm.vector.reduce.xor.v4i64(<4 x i64> %y)
ret i64 %z
}
define i64 @xor_zext_v4i32_i64(<4 x i32> %x) {
; CHECK-LABEL: xor_zext_v4i32_i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov d1, v0.d[1]
; CHECK-NEXT: eor v0.8b, v0.8b, v1.8b
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: lsr x9, x8, #32
; CHECK-NEXT: eor w0, w8, w9
; CHECK-NEXT: ret
entry:
%y = zext <4 x i32> %x to <4 x i64>
%z = call i64 @llvm.vector.reduce.xor.v4i64(<4 x i64> %y)
ret i64 %z
}
declare i16 @llvm.vector.reduce.and.v16i16(<16 x i16>)
declare i16 @llvm.vector.reduce.and.v8i16(<8 x i16>)
declare i16 @llvm.vector.reduce.or.v16i16(<16 x i16>)
declare i16 @llvm.vector.reduce.or.v8i16(<8 x i16>)
declare i16 @llvm.vector.reduce.xor.v16i16(<16 x i16>)
declare i16 @llvm.vector.reduce.xor.v8i16(<8 x i16>)
declare i32 @llvm.vector.reduce.and.v16i32(<16 x i32>)
declare i32 @llvm.vector.reduce.and.v4i32(<4 x i32>)
declare i32 @llvm.vector.reduce.and.v8i32(<8 x i32>)
declare i32 @llvm.vector.reduce.or.v16i32(<16 x i32>)
declare i32 @llvm.vector.reduce.or.v4i32(<4 x i32>)
declare i32 @llvm.vector.reduce.or.v8i32(<8 x i32>)
declare i32 @llvm.vector.reduce.xor.v16i32(<16 x i32>)
declare i32 @llvm.vector.reduce.xor.v4i32(<4 x i32>)
declare i32 @llvm.vector.reduce.xor.v8i32(<8 x i32>)
declare i64 @llvm.vector.reduce.and.v16i64(<16 x i64>)
declare i64 @llvm.vector.reduce.and.v2i64(<2 x i64>)
declare i64 @llvm.vector.reduce.and.v4i64(<4 x i64>)
declare i64 @llvm.vector.reduce.and.v8i64(<8 x i64>)
declare i64 @llvm.vector.reduce.or.v16i64(<16 x i64>)
declare i64 @llvm.vector.reduce.or.v2i64(<2 x i64>)
declare i64 @llvm.vector.reduce.or.v4i64(<4 x i64>)
declare i64 @llvm.vector.reduce.or.v8i64(<8 x i64>)
declare i64 @llvm.vector.reduce.xor.v16i64(<16 x i64>)
declare i64 @llvm.vector.reduce.xor.v2i64(<2 x i64>)
declare i64 @llvm.vector.reduce.xor.v4i64(<4 x i64>)
declare i64 @llvm.vector.reduce.xor.v8i64(<8 x i64>)
Reference in new issue View Git Blame Copy Permalink