llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-gatherscatter.ll

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -S -instcombine -dce < %s | FileCheck %s

target triple = "aarch64-unknown-linux-gnu"

;;
;; Gathers.
;;

define <vscale x 2 x double> @test_ld1_gather_index_nxv2f64_stride1(<vscale x 2 x i1> %pred, double* %x, i64 %base) #0 {
; CHECK-LABEL: @test_ld1_gather_index_nxv2f64_stride1(
; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr double, double* [[X:%.*]], i64 [[BASE:%.*]]
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast double* [[TMP1]] to <vscale x 2 x double>*
; CHECK-NEXT:    [[LD:%.*]] = call <vscale x 2 x double> @llvm.masked.load.nxv2f64.p0nxv2f64(<vscale x 2 x double>* [[TMP2]], i32 1, <vscale x 2 x i1> [[PRED:%.*]], <vscale x 2 x double> zeroinitializer)
; CHECK-NEXT:    ret <vscale x 2 x double> [[LD]]
;
  %idx = tail call <vscale x 2 x i64> @llvm.aarch64.sve.index.nxv2i64(i64 %base, i64 1)
  %ld = tail call <vscale x 2 x double> @llvm.aarch64.sve.ld1.gather.index.nxv2f64(<vscale x 2 x i1> %pred, double* %x, <vscale x 2 x i64> %idx)
  ret <vscale x 2 x double> %ld
}

define <vscale x 2 x double> @test_ld1_gather_index_nxv2f64_stride2_negtest(<vscale x 2 x i1> %pred, double* %x, i64 %base) #0 {
; CHECK-LABEL: @test_ld1_gather_index_nxv2f64_stride2_negtest(
; CHECK-NEXT:    [[IDX:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.index.nxv2i64(i64 [[BASE:%.*]], i64 2)
; CHECK-NEXT:    [[LD:%.*]] = tail call <vscale x 2 x double> @llvm.aarch64.sve.ld1.gather.index.nxv2f64(<vscale x 2 x i1> [[PRED:%.*]], double* [[X:%.*]], <vscale x 2 x i64> [[IDX]])
; CHECK-NEXT:    ret <vscale x 2 x double> [[LD]]
;
  %idx = tail call <vscale x 2 x i64> @llvm.aarch64.sve.index.nxv2i64(i64 %base, i64 2)
  %ld = tail call <vscale x 2 x double> @llvm.aarch64.sve.ld1.gather.index.nxv2f64(<vscale x 2 x i1> %pred, double* %x, <vscale x 2 x i64> %idx)
  ret <vscale x 2 x double> %ld
}

define <vscale x 2 x double> @test_ld1_gather_index_nxv2f64_stride1_align8(<vscale x 2 x i1> %pred, double* align 8 %x, i64 %base) #0 {
; CHECK-LABEL: @test_ld1_gather_index_nxv2f64_stride1_align8(
; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr double, double* [[X:%.*]], i64 [[BASE:%.*]]
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast double* [[TMP1]] to <vscale x 2 x double>*
; CHECK-NEXT:    [[LD:%.*]] = call <vscale x 2 x double> @llvm.masked.load.nxv2f64.p0nxv2f64(<vscale x 2 x double>* [[TMP2]], i32 8, <vscale x 2 x i1> [[PRED:%.*]], <vscale x 2 x double> zeroinitializer)
; CHECK-NEXT:    ret <vscale x 2 x double> [[LD]]
;
  %idx = tail call <vscale x 2 x i64> @llvm.aarch64.sve.index.nxv2i64(i64 %base, i64 1)
  %ld = tail call <vscale x 2 x double> @llvm.aarch64.sve.ld1.gather.index.nxv2f64(<vscale x 2 x i1> %pred, double* %x, <vscale x 2 x i64> %idx)
  ret <vscale x 2 x double> %ld
}

;;
;; Scatters.
;;

define void @test_st1_scatter_index_nxv2f64_stride1(<vscale x 2 x i1> %pred, double* %x, i64 %base, <vscale x 2 x double> %val) #0 {
; CHECK-LABEL: @test_st1_scatter_index_nxv2f64_stride1(
; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr double, double* [[X:%.*]], i64 [[BASE:%.*]]
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast double* [[TMP1]] to <vscale x 2 x double>*
; CHECK-NEXT:    call void @llvm.masked.store.nxv2f64.p0nxv2f64(<vscale x 2 x double> [[VAL:%.*]], <vscale x 2 x double>* [[TMP2]], i32 1, <vscale x 2 x i1> [[PRED:%.*]])
; CHECK-NEXT:    ret void
;
  %idx = tail call <vscale x 2 x i64> @llvm.aarch64.sve.index.nxv2i64(i64 %base, i64 1)
  tail call void @llvm.aarch64.sve.st1.scatter.index.nxv2f64(<vscale x 2 x double> %val, <vscale x 2 x i1> %pred, double* %x, <vscale x 2 x i64> %idx)
  ret void
}

define void @test_st1_scatter_index_nxv2f64_stride2_negtest(<vscale x 2 x i1> %pred, double* %x, i64 %base, <vscale x 2 x double> %val) #0 {
; CHECK-LABEL: @test_st1_scatter_index_nxv2f64_stride2_negtest(
; CHECK-NEXT:    [[IDX:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.index.nxv2i64(i64 [[BASE:%.*]], i64 2)
; CHECK-NEXT:    tail call void @llvm.aarch64.sve.st1.scatter.index.nxv2f64(<vscale x 2 x double> [[VAL:%.*]], <vscale x 2 x i1> [[PRED:%.*]], double* [[X:%.*]], <vscale x 2 x i64> [[IDX]])
; CHECK-NEXT:    ret void
;
  %idx = tail call <vscale x 2 x i64> @llvm.aarch64.sve.index.nxv2i64(i64 %base, i64 2)
  tail call void @llvm.aarch64.sve.st1.scatter.index.nxv2f64(<vscale x 2 x double> %val, <vscale x 2 x i1> %pred, double* %x, <vscale x 2 x i64> %idx)
  ret void
}

define void @test_st1_scatter_index_nxv2f64_stride1_align8(<vscale x 2 x i1> %pred, double* align 8 %x, i64 %base, <vscale x 2 x double> %val) #0 {
; CHECK-LABEL: @test_st1_scatter_index_nxv2f64_stride1_align8(
; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr double, double* [[X:%.*]], i64 [[BASE:%.*]]
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast double* [[TMP1]] to <vscale x 2 x double>*
; CHECK-NEXT:    call void @llvm.masked.store.nxv2f64.p0nxv2f64(<vscale x 2 x double> [[VAL:%.*]], <vscale x 2 x double>* [[TMP2]], i32 8, <vscale x 2 x i1> [[PRED:%.*]])
; CHECK-NEXT:    ret void
;
  %idx = tail call <vscale x 2 x i64> @llvm.aarch64.sve.index.nxv2i64(i64 %base, i64 1)
  tail call void @llvm.aarch64.sve.st1.scatter.index.nxv2f64(<vscale x 2 x double> %val, <vscale x 2 x i1> %pred, double* %x, <vscale x 2 x i64> %idx)
  ret void
}

declare <vscale x 2 x i64> @llvm.aarch64.sve.index.nxv2i64(i64, i64)
declare <vscale x 2 x double> @llvm.aarch64.sve.ld1.gather.index.nxv2f64(<vscale x 2 x i1>, double*, <vscale x 2 x i64>)
declare void @llvm.aarch64.sve.st1.scatter.index.nxv2f64(<vscale x 2 x double>, <vscale x 2 x i1>, double*, <vscale x 2 x i64>)

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