llvm/test/Transforms/LoopVectorize/RISCV/safe-dep-distance.ll

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -passes=loop-vectorize -scalable-vectorization=on -riscv-v-vector-bits-min=-1 -mtriple riscv64-linux-gnu -mattr=+v,+f -S 2>%t | FileCheck %s

target datalayout = "e-m:e-p:64:64-i64:64-i128:128-n64-S128"
target triple = "riscv64"

; Dependence distance between read and write is greater than the trip
; count of the loop.  Thus, values written are never read for any
; valid vectorization of the loop.
define void @test(ptr %p) {
; CHECK-LABEL: @test(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 2
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 200, [[TMP1]]
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 2
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 200, [[TMP3]]
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 200, [[N_MOD_VF]]
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP4:%.*]] = add i64 [[INDEX]], 0
; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr i64, ptr [[P:%.*]], i64 [[TMP4]]
; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr i64, ptr [[TMP5]], i32 0
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 2 x i64>, ptr [[TMP6]], align 32
; CHECK-NEXT:    [[TMP7:%.*]] = add i64 [[TMP4]], 200
; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr i64, ptr [[P]], i64 [[TMP7]]
; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr i64, ptr [[TMP8]], i32 0
; CHECK-NEXT:    store <vscale x 2 x i64> [[WIDE_LOAD]], ptr [[TMP9]], align 32
; CHECK-NEXT:    [[TMP10:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP11:%.*]] = mul i64 [[TMP10]], 2
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP11]]
; CHECK-NEXT:    [[TMP12:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP12]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 200, [[N_VEC]]
; CHECK-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT:    br label [[LOOP:%.*]]
; CHECK:       loop:
; CHECK-NEXT:    [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[LOOP]] ]
; CHECK-NEXT:    [[A1:%.*]] = getelementptr i64, ptr [[P]], i64 [[IV]]
; CHECK-NEXT:    [[V:%.*]] = load i64, ptr [[A1]], align 32
; CHECK-NEXT:    [[OFFSET:%.*]] = add i64 [[IV]], 200
; CHECK-NEXT:    [[A2:%.*]] = getelementptr i64, ptr [[P]], i64 [[OFFSET]]
; CHECK-NEXT:    store i64 [[V]], ptr [[A2]], align 32
; CHECK-NEXT:    [[IV_NEXT]] = add i64 [[IV]], 1
; CHECK-NEXT:    [[CMP:%.*]] = icmp ne i64 [[IV]], 199
; CHECK-NEXT:    br i1 [[CMP]], label [[LOOP]], label [[EXIT]], !llvm.loop [[LOOP3:![0-9]+]]
; CHECK:       exit:
; CHECK-NEXT:    ret void
;
entry:
  br label %loop

loop:
  %iv = phi i64 [0, %entry], [%iv.next, %loop]
  %a1 = getelementptr i64, ptr %p, i64 %iv
  %v = load i64, ptr %a1, align 32
  %offset = add i64 %iv, 200
  %a2 = getelementptr i64, ptr %p, i64 %offset
  store i64 %v, ptr %a2, align 32
  %iv.next = add i64 %iv, 1
  %cmp = icmp ne i64 %iv, 199
  br i1 %cmp, label %loop, label %exit

exit:
  ret void
}

; Dependence distance is less than trip count, thus we must prove that
; chosen VF guaranteed to be less than dependence distance.
define void @test_may_clobber(ptr %p) {
; CHECK-LABEL: @test_may_clobber(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr i64, ptr [[P:%.*]], i64 [[TMP0]]
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr i64, ptr [[TMP1]], i32 0
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i64>, ptr [[TMP2]], align 32
; CHECK-NEXT:    [[TMP3:%.*]] = add i64 [[TMP0]], 100
; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr i64, ptr [[P]], i64 [[TMP3]]
; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr i64, ptr [[TMP4]], i32 0
; CHECK-NEXT:    store <4 x i64> [[WIDE_LOAD]], ptr [[TMP5]], align 32
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT:    [[TMP6:%.*]] = icmp eq i64 [[INDEX_NEXT]], 200
; CHECK-NEXT:    br i1 [[TMP6]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 200, 200
; CHECK-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 200, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT:    br label [[LOOP:%.*]]
; CHECK:       loop:
; CHECK-NEXT:    [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[LOOP]] ]
; CHECK-NEXT:    [[A1:%.*]] = getelementptr i64, ptr [[P]], i64 [[IV]]
; CHECK-NEXT:    [[V:%.*]] = load i64, ptr [[A1]], align 32
; CHECK-NEXT:    [[OFFSET:%.*]] = add i64 [[IV]], 100
; CHECK-NEXT:    [[A2:%.*]] = getelementptr i64, ptr [[P]], i64 [[OFFSET]]
; CHECK-NEXT:    store i64 [[V]], ptr [[A2]], align 32
; CHECK-NEXT:    [[IV_NEXT]] = add i64 [[IV]], 1
; CHECK-NEXT:    [[CMP:%.*]] = icmp ne i64 [[IV]], 199
; CHECK-NEXT:    br i1 [[CMP]], label [[LOOP]], label [[EXIT]], !llvm.loop [[LOOP5:![0-9]+]]
; CHECK:       exit:
; CHECK-NEXT:    ret void
;
entry:
  br label %loop

loop:
  %iv = phi i64 [0, %entry], [%iv.next, %loop]
  %a1 = getelementptr i64, ptr %p, i64 %iv
  %v = load i64, ptr %a1, align 32
  %offset = add i64 %iv, 100
  %a2 = getelementptr i64, ptr %p, i64 %offset
  store i64 %v, ptr %a2, align 32
  %iv.next = add i64 %iv, 1
  %cmp = icmp ne i64 %iv, 199
  br i1 %cmp, label %loop, label %exit

exit:
  ret void
}

; Trviailly no overlap due to maximum possible value of VLEN and LMUL
define void @trivial_due_max_vscale(ptr %p) {
; CHECK-LABEL: @trivial_due_max_vscale(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 2
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 200, [[TMP1]]
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 2
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 200, [[TMP3]]
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 200, [[N_MOD_VF]]
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP4:%.*]] = add i64 [[INDEX]], 0
; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr i64, ptr [[P:%.*]], i64 [[TMP4]]
; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr i64, ptr [[TMP5]], i32 0
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 2 x i64>, ptr [[TMP6]], align 32
; CHECK-NEXT:    [[TMP7:%.*]] = add i64 [[TMP4]], 8192
; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr i64, ptr [[P]], i64 [[TMP7]]
; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr i64, ptr [[TMP8]], i32 0
; CHECK-NEXT:    store <vscale x 2 x i64> [[WIDE_LOAD]], ptr [[TMP9]], align 32
; CHECK-NEXT:    [[TMP10:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP11:%.*]] = mul i64 [[TMP10]], 2
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP11]]
; CHECK-NEXT:    [[TMP12:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP12]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 200, [[N_VEC]]
; CHECK-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT:    br label [[LOOP:%.*]]
; CHECK:       loop:
; CHECK-NEXT:    [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[LOOP]] ]
; CHECK-NEXT:    [[A1:%.*]] = getelementptr i64, ptr [[P]], i64 [[IV]]
; CHECK-NEXT:    [[V:%.*]] = load i64, ptr [[A1]], align 32
; CHECK-NEXT:    [[OFFSET:%.*]] = add i64 [[IV]], 8192
; CHECK-NEXT:    [[A2:%.*]] = getelementptr i64, ptr [[P]], i64 [[OFFSET]]
; CHECK-NEXT:    store i64 [[V]], ptr [[A2]], align 32
; CHECK-NEXT:    [[IV_NEXT]] = add i64 [[IV]], 1
; CHECK-NEXT:    [[CMP:%.*]] = icmp ne i64 [[IV]], 199
; CHECK-NEXT:    br i1 [[CMP]], label [[LOOP]], label [[EXIT]], !llvm.loop [[LOOP7:![0-9]+]]
; CHECK:       exit:
; CHECK-NEXT:    ret void
;
entry:
  br label %loop

loop:
  %iv = phi i64 [0, %entry], [%iv.next, %loop]
  %a1 = getelementptr i64, ptr %p, i64 %iv
  %v = load i64, ptr %a1, align 32
  %offset = add i64 %iv, 8192
  %a2 = getelementptr i64, ptr %p, i64 %offset
  store i64 %v, ptr %a2, align 32
  %iv.next = add i64 %iv, 1
  %cmp = icmp ne i64 %iv, 199
  br i1 %cmp, label %loop, label %exit

exit:
  ret void
}

; Dependence distance could be violated via LMUL>=2 or interleaving
define void @no_high_lmul_or_interleave(ptr %p) {
; CHECK-LABEL: @no_high_lmul_or_interleave(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 2
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 200, [[TMP1]]
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 2
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 200, [[TMP3]]
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 200, [[N_MOD_VF]]
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP4:%.*]] = add i64 [[INDEX]], 0
; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr i64, ptr [[P:%.*]], i64 [[TMP4]]
; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr i64, ptr [[TMP5]], i32 0
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 2 x i64>, ptr [[TMP6]], align 32
; CHECK-NEXT:    [[TMP7:%.*]] = add i64 [[TMP4]], 1024
; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr i64, ptr [[P]], i64 [[TMP7]]
; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr i64, ptr [[TMP8]], i32 0
; CHECK-NEXT:    store <vscale x 2 x i64> [[WIDE_LOAD]], ptr [[TMP9]], align 32
; CHECK-NEXT:    [[TMP10:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP11:%.*]] = mul i64 [[TMP10]], 2
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP11]]
; CHECK-NEXT:    [[TMP12:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP12]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 200, [[N_VEC]]
; CHECK-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT:    br label [[LOOP:%.*]]
; CHECK:       loop:
; CHECK-NEXT:    [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[LOOP]] ]
; CHECK-NEXT:    [[A1:%.*]] = getelementptr i64, ptr [[P]], i64 [[IV]]
; CHECK-NEXT:    [[V:%.*]] = load i64, ptr [[A1]], align 32
; CHECK-NEXT:    [[OFFSET:%.*]] = add i64 [[IV]], 1024
; CHECK-NEXT:    [[A2:%.*]] = getelementptr i64, ptr [[P]], i64 [[OFFSET]]
; CHECK-NEXT:    store i64 [[V]], ptr [[A2]], align 32
; CHECK-NEXT:    [[IV_NEXT]] = add i64 [[IV]], 1
; CHECK-NEXT:    [[CMP:%.*]] = icmp ne i64 [[IV]], 199
; CHECK-NEXT:    br i1 [[CMP]], label [[LOOP]], label [[EXIT]], !llvm.loop [[LOOP9:![0-9]+]]
; CHECK:       exit:
; CHECK-NEXT:    ret void
;
entry:
  br label %loop

loop:
  %iv = phi i64 [0, %entry], [%iv.next, %loop]
  %a1 = getelementptr i64, ptr %p, i64 %iv
  %v = load i64, ptr %a1, align 32
  %offset = add i64 %iv, 1024
  %a2 = getelementptr i64, ptr %p, i64 %offset
  store i64 %v, ptr %a2, align 32
  %iv.next = add i64 %iv, 1
  %cmp = icmp ne i64 %iv, 199
  br i1 %cmp, label %loop, label %exit

exit:
  ret void
}