TheRock/compiler/amd-llvm/llvm/test/CodeGen/AArch64/partial-reduction-add.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 4
; RUN: llc -force-vector-interleave=1 -o - %s | FileCheck %s

target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
target triple = "aarch64-none-unknown-elf"

define <4 x i32> @partial_reduce_add_fixed(<4 x i32> %accumulator, <4 x i32> %0) #0 {
; CHECK-LABEL: partial_reduce_add_fixed:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    add v0.4s, v0.4s, v1.4s
; CHECK-NEXT:    ret
entry:
  %partial.reduce = call <4 x i32> @llvm.vector.partial.reduce.add.v4i32.v4i32.v4i32(<4 x i32> %accumulator, <4 x i32> %0)
  ret <4 x i32> %partial.reduce
}

define <4 x i32> @partial_reduce_add_fixed_half(<4 x i32> %accumulator, <8 x i32> %0) #0 {
; CHECK-LABEL: partial_reduce_add_fixed_half:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    add v0.4s, v0.4s, v1.4s
; CHECK-NEXT:    add v0.4s, v0.4s, v2.4s
; CHECK-NEXT:    ret
entry:
  %partial.reduce = call <4 x i32> @llvm.vector.partial.reduce.add.v4i32.v4i32.v8i32(<4 x i32> %accumulator, <8 x i32> %0)
  ret <4 x i32> %partial.reduce
}

define <vscale x 4 x i32> @partial_reduce_add(<vscale x 4 x i32> %accumulator, <vscale x 4 x i32> %0) #0 {
; CHECK-LABEL: partial_reduce_add:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    add z0.s, z0.s, z1.s
; CHECK-NEXT:    ret
entry:
  %partial.reduce = call <vscale x 4 x i32> @llvm.vector.partial.reduce.add.nxv4i32.nxv4i32.nxv4i32(<vscale x 4 x i32> %accumulator, <vscale x 4 x i32> %0)
  ret <vscale x 4 x i32> %partial.reduce
}

define <vscale x 4 x i32> @partial_reduce_add_half(<vscale x 4 x i32> %accumulator, <vscale x 8 x i32> %0) #0 {
; CHECK-LABEL: partial_reduce_add_half:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    add z0.s, z0.s, z1.s
; CHECK-NEXT:    add z0.s, z0.s, z2.s
; CHECK-NEXT:    ret
entry:
  %partial.reduce = call <vscale x 4 x i32> @llvm.vector.partial.reduce.add.nxv4i32.nxv4i32.nxv8i32(<vscale x 4 x i32> %accumulator, <vscale x 8 x i32> %0)
  ret <vscale x 4 x i32> %partial.reduce
}

define <vscale x 4 x i32> @partial_reduce_add_quart(<vscale x 4 x i32> %accumulator, <vscale x 16 x i32> %0) #0 {
; CHECK-LABEL: partial_reduce_add_quart:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    add z2.s, z2.s, z3.s
; CHECK-NEXT:    add z0.s, z0.s, z1.s
; CHECK-NEXT:    add z0.s, z0.s, z2.s
; CHECK-NEXT:    add z0.s, z0.s, z4.s
; CHECK-NEXT:    ret
entry:
  %partial.reduce = call <vscale x 4 x i32> @llvm.vector.partial.reduce.add.nxv4i32.nxv4i32.nxv16i32(<vscale x 4 x i32> %accumulator, <vscale x 16 x i32> %0)
  ret <vscale x 4 x i32> %partial.reduce
}

define <vscale x 8 x i32> @partial_reduce_add_half_8(<vscale x 8 x i32> %accumulator, <vscale x 16 x i32> %0) #0 {
; CHECK-LABEL: partial_reduce_add_half_8:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    add z0.s, z0.s, z2.s
; CHECK-NEXT:    add z1.s, z1.s, z4.s
; CHECK-NEXT:    add z0.s, z0.s, z3.s
; CHECK-NEXT:    add z1.s, z1.s, z5.s
; CHECK-NEXT:    ret
entry:
  %partial.reduce = call <vscale x 8 x i32> @llvm.vector.partial.reduce.add.nxv8i32.nxv8i32.nxv16i32(<vscale x 8 x i32> %accumulator, <vscale x 16 x i32> %0)
  ret <vscale x 8 x i32> %partial.reduce
}

declare <vscale x 4 x i32> @llvm.vector.partial.reduce.add.nxv4i32.nxv4i32.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 4 x i32> @llvm.vector.partial.reduce.add.nxv4i32.nxv4i32.nxv8i32(<vscale x 4 x i32>, <vscale x 8 x i32>)
declare <vscale x 4 x i32> @llvm.vector.partial.reduce.add.nxv4i32.nxv4i32.nxv16i32(<vscale x 4 x i32>, <vscale x 16 x i32>)
declare <vscale x 8 x i32> @llvm.vector.partial.reduce.add.nxv8i32.nxv8i32.nxv16i32(<vscale x 8 x i32>, <vscale x 16 x i32>)

declare i32 @llvm.vector.reduce.add.nxv4i32(<vscale x 4 x i32>)
declare i32 @llvm.vector.reduce.add.nxv8i32(<vscale x 8 x i32>)

attributes #0 = { "target-features"="+sve2" }