llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-div.ll

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
; RUN: opt -passes=loop-vectorize \
; RUN: -force-tail-folding-style=data-with-evl \
; RUN: -prefer-predicate-over-epilogue=predicate-dont-vectorize \
; RUN: -mtriple=riscv64 -mattr=+v -S %s | FileCheck %s --check-prefix=IF-EVL

; RUN: opt -passes=loop-vectorize \
; RUN: -force-tail-folding-style=none \
; RUN: -prefer-predicate-over-epilogue=predicate-dont-vectorize \
; RUN: -mtriple=riscv64 -mattr=+v -S %s | FileCheck %s --check-prefix=NO-VP

define void @test_sdiv(ptr noalias %a, ptr noalias %b, ptr noalias %c) {
; IF-EVL-LABEL: define void @test_sdiv(
; IF-EVL-SAME: ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0:[0-9]+]] {
; IF-EVL-NEXT:  [[LOOP_PREHEADER:.*]]:
; IF-EVL-NEXT:    br i1 false, label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
; IF-EVL:       [[VECTOR_PH]]:
; IF-EVL-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; IF-EVL-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 2
; IF-EVL-NEXT:    [[TMP2:%.*]] = sub i64 [[TMP1]], 1
; IF-EVL-NEXT:    [[N_RND_UP:%.*]] = add i64 1024, [[TMP2]]
; IF-EVL-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
; IF-EVL-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
; IF-EVL-NEXT:    [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
; IF-EVL-NEXT:    [[TMP4:%.*]] = mul i64 [[TMP3]], 2
; IF-EVL-NEXT:    br label %[[VECTOR_BODY:.*]]
; IF-EVL:       [[VECTOR_BODY]]:
; IF-EVL-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
; IF-EVL-NEXT:    [[EVL_BASED_IV:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], %[[VECTOR_BODY]] ]
; IF-EVL-NEXT:    [[AVL:%.*]] = sub i64 1024, [[EVL_BASED_IV]]
; IF-EVL-NEXT:    [[TMP5:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 [[AVL]], i32 2, i1 true)
; IF-EVL-NEXT:    [[TMP7:%.*]] = getelementptr i64, ptr [[A]], i64 [[EVL_BASED_IV]]
; IF-EVL-NEXT:    [[TMP8:%.*]] = getelementptr i64, ptr [[TMP7]], i32 0
; IF-EVL-NEXT:    [[VP_OP_LOAD:%.*]] = call <vscale x 2 x i64> @llvm.vp.load.nxv2i64.p0(ptr align 8 [[TMP8]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP5]])
; IF-EVL-NEXT:    [[TMP9:%.*]] = getelementptr i64, ptr [[B]], i64 [[EVL_BASED_IV]]
; IF-EVL-NEXT:    [[TMP10:%.*]] = getelementptr i64, ptr [[TMP9]], i32 0
; IF-EVL-NEXT:    [[VP_OP_LOAD1:%.*]] = call <vscale x 2 x i64> @llvm.vp.load.nxv2i64.p0(ptr align 8 [[TMP10]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP5]])
; IF-EVL-NEXT:    [[TMP11:%.*]] = call <vscale x 2 x i64> @llvm.vp.merge.nxv2i64(<vscale x 2 x i1> splat (i1 true), <vscale x 2 x i64> [[VP_OP_LOAD1]], <vscale x 2 x i64> splat (i64 1), i32 [[TMP5]])
; IF-EVL-NEXT:    [[VP_OP:%.*]] = sdiv <vscale x 2 x i64> [[VP_OP_LOAD]], [[TMP11]]
; IF-EVL-NEXT:    [[TMP12:%.*]] = getelementptr i64, ptr [[C]], i64 [[EVL_BASED_IV]]
; IF-EVL-NEXT:    [[TMP13:%.*]] = getelementptr i64, ptr [[TMP12]], i32 0
; IF-EVL-NEXT:    call void @llvm.vp.store.nxv2i64.p0(<vscale x 2 x i64> [[VP_OP]], ptr align 8 [[TMP13]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP5]])
; IF-EVL-NEXT:    [[TMP14:%.*]] = zext i32 [[TMP5]] to i64
; IF-EVL-NEXT:    [[INDEX_EVL_NEXT]] = add nuw i64 [[TMP14]], [[EVL_BASED_IV]]
; IF-EVL-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP4]]
; IF-EVL-NEXT:    [[TMP15:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; IF-EVL-NEXT:    br i1 [[TMP15]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; IF-EVL:       [[MIDDLE_BLOCK]]:
; IF-EVL-NEXT:    br i1 true, label %[[EXIT:.*]], label %[[SCALAR_PH]]
; IF-EVL:       [[SCALAR_PH]]:
; IF-EVL-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], %[[MIDDLE_BLOCK]] ], [ 0, %[[LOOP_PREHEADER]] ]
; IF-EVL-NEXT:    br label %[[LOOP:.*]]
; IF-EVL:       [[LOOP]]:
; IF-EVL-NEXT:    [[IV:%.*]] = phi i64 [ [[IV_NEXT:%.*]], %[[LOOP]] ], [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ]
; IF-EVL-NEXT:    [[A_GEP:%.*]] = getelementptr i64, ptr [[A]], i64 [[IV]]
; IF-EVL-NEXT:    [[TMP16:%.*]] = load i64, ptr [[A_GEP]], align 8
; IF-EVL-NEXT:    [[B_GEP:%.*]] = getelementptr i64, ptr [[B]], i64 [[IV]]
; IF-EVL-NEXT:    [[TMP17:%.*]] = load i64, ptr [[B_GEP]], align 8
; IF-EVL-NEXT:    [[TMP18:%.*]] = sdiv i64 [[TMP16]], [[TMP17]]
; IF-EVL-NEXT:    [[C_GEP:%.*]] = getelementptr i64, ptr [[C]], i64 [[IV]]
; IF-EVL-NEXT:    store i64 [[TMP18]], ptr [[C_GEP]], align 8
; IF-EVL-NEXT:    [[IV_NEXT]] = add i64 [[IV]], 1
; IF-EVL-NEXT:    [[DONE:%.*]] = icmp eq i64 [[IV_NEXT]], 1024
; IF-EVL-NEXT:    br i1 [[DONE]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP3:![0-9]+]]
; IF-EVL:       [[EXIT]]:
; IF-EVL-NEXT:    ret void
;
; NO-VP-LABEL: define void @test_sdiv(
; NO-VP-SAME: ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0:[0-9]+]] {
; NO-VP-NEXT:  [[LOOP_PREHEADER:.*]]:
; NO-VP-NEXT:    br label %[[LOOP:.*]]
; NO-VP:       [[LOOP]]:
; NO-VP-NEXT:    [[IV:%.*]] = phi i64 [ [[IV_NEXT:%.*]], %[[LOOP]] ], [ 0, %[[LOOP_PREHEADER]] ]
; NO-VP-NEXT:    [[A_GEP:%.*]] = getelementptr i64, ptr [[A]], i64 [[IV]]
; NO-VP-NEXT:    [[TMP0:%.*]] = load i64, ptr [[A_GEP]], align 8
; NO-VP-NEXT:    [[B_GEP:%.*]] = getelementptr i64, ptr [[B]], i64 [[IV]]
; NO-VP-NEXT:    [[TMP1:%.*]] = load i64, ptr [[B_GEP]], align 8
; NO-VP-NEXT:    [[TMP2:%.*]] = sdiv i64 [[TMP0]], [[TMP1]]
; NO-VP-NEXT:    [[C_GEP:%.*]] = getelementptr i64, ptr [[C]], i64 [[IV]]
; NO-VP-NEXT:    store i64 [[TMP2]], ptr [[C_GEP]], align 8
; NO-VP-NEXT:    [[IV_NEXT]] = add i64 [[IV]], 1
; NO-VP-NEXT:    [[DONE:%.*]] = icmp eq i64 [[IV_NEXT]], 1024
; NO-VP-NEXT:    br i1 [[DONE]], label %[[EXIT:.*]], label %[[LOOP]]
; NO-VP:       [[EXIT]]:
; NO-VP-NEXT:    ret void
;
loop.preheader:
  br label %loop

loop:
  %iv = phi i64 [ %iv.next, %loop ], [ 0, %loop.preheader ]
  %a.gep = getelementptr i64, ptr %a, i64 %iv
  %0 = load i64, ptr %a.gep
  %b.gep = getelementptr i64, ptr %b, i64 %iv
  %1 = load i64, ptr %b.gep
  %2 = sdiv i64 %0, %1
  %c.gep = getelementptr i64, ptr %c, i64 %iv
  store i64 %2, ptr %c.gep
  %iv.next = add i64 %iv, 1
  %done = icmp eq i64 %iv.next, 1024
  br i1 %done, label %exit, label %loop

exit:
  ret void
}


define void @test_udiv(ptr noalias %a, ptr noalias %b, ptr noalias %c) {
; IF-EVL-LABEL: define void @test_udiv(
; IF-EVL-SAME: ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
; IF-EVL-NEXT:  [[LOOP_PREHEADER:.*]]:
; IF-EVL-NEXT:    br i1 false, label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
; IF-EVL:       [[VECTOR_PH]]:
; IF-EVL-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; IF-EVL-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 2
; IF-EVL-NEXT:    [[TMP2:%.*]] = sub i64 [[TMP1]], 1
; IF-EVL-NEXT:    [[N_RND_UP:%.*]] = add i64 1024, [[TMP2]]
; IF-EVL-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
; IF-EVL-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
; IF-EVL-NEXT:    [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
; IF-EVL-NEXT:    [[TMP4:%.*]] = mul i64 [[TMP3]], 2
; IF-EVL-NEXT:    br label %[[VECTOR_BODY:.*]]
; IF-EVL:       [[VECTOR_BODY]]:
; IF-EVL-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
; IF-EVL-NEXT:    [[EVL_BASED_IV:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], %[[VECTOR_BODY]] ]
; IF-EVL-NEXT:    [[AVL:%.*]] = sub i64 1024, [[EVL_BASED_IV]]
; IF-EVL-NEXT:    [[TMP5:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 [[AVL]], i32 2, i1 true)
; IF-EVL-NEXT:    [[TMP7:%.*]] = getelementptr i64, ptr [[A]], i64 [[EVL_BASED_IV]]
; IF-EVL-NEXT:    [[TMP8:%.*]] = getelementptr i64, ptr [[TMP7]], i32 0
; IF-EVL-NEXT:    [[VP_OP_LOAD:%.*]] = call <vscale x 2 x i64> @llvm.vp.load.nxv2i64.p0(ptr align 8 [[TMP8]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP5]])
; IF-EVL-NEXT:    [[TMP9:%.*]] = getelementptr i64, ptr [[B]], i64 [[EVL_BASED_IV]]
; IF-EVL-NEXT:    [[TMP10:%.*]] = getelementptr i64, ptr [[TMP9]], i32 0
; IF-EVL-NEXT:    [[VP_OP_LOAD1:%.*]] = call <vscale x 2 x i64> @llvm.vp.load.nxv2i64.p0(ptr align 8 [[TMP10]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP5]])
; IF-EVL-NEXT:    [[TMP11:%.*]] = call <vscale x 2 x i64> @llvm.vp.merge.nxv2i64(<vscale x 2 x i1> splat (i1 true), <vscale x 2 x i64> [[VP_OP_LOAD1]], <vscale x 2 x i64> splat (i64 1), i32 [[TMP5]])
; IF-EVL-NEXT:    [[VP_OP:%.*]] = udiv <vscale x 2 x i64> [[VP_OP_LOAD]], [[TMP11]]
; IF-EVL-NEXT:    [[TMP12:%.*]] = getelementptr i64, ptr [[C]], i64 [[EVL_BASED_IV]]
; IF-EVL-NEXT:    [[TMP13:%.*]] = getelementptr i64, ptr [[TMP12]], i32 0
; IF-EVL-NEXT:    call void @llvm.vp.store.nxv2i64.p0(<vscale x 2 x i64> [[VP_OP]], ptr align 8 [[TMP13]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP5]])
; IF-EVL-NEXT:    [[TMP14:%.*]] = zext i32 [[TMP5]] to i64
; IF-EVL-NEXT:    [[INDEX_EVL_NEXT]] = add nuw i64 [[TMP14]], [[EVL_BASED_IV]]
; IF-EVL-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP4]]
; IF-EVL-NEXT:    [[TMP15:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; IF-EVL-NEXT:    br i1 [[TMP15]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
; IF-EVL:       [[MIDDLE_BLOCK]]:
; IF-EVL-NEXT:    br i1 true, label %[[EXIT:.*]], label %[[SCALAR_PH]]
; IF-EVL:       [[SCALAR_PH]]:
; IF-EVL-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], %[[MIDDLE_BLOCK]] ], [ 0, %[[LOOP_PREHEADER]] ]
; IF-EVL-NEXT:    br label %[[LOOP:.*]]
; IF-EVL:       [[LOOP]]:
; IF-EVL-NEXT:    [[IV:%.*]] = phi i64 [ [[IV_NEXT:%.*]], %[[LOOP]] ], [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ]
; IF-EVL-NEXT:    [[A_GEP:%.*]] = getelementptr i64, ptr [[A]], i64 [[IV]]
; IF-EVL-NEXT:    [[TMP16:%.*]] = load i64, ptr [[A_GEP]], align 8
; IF-EVL-NEXT:    [[B_GEP:%.*]] = getelementptr i64, ptr [[B]], i64 [[IV]]
; IF-EVL-NEXT:    [[TMP17:%.*]] = load i64, ptr [[B_GEP]], align 8
; IF-EVL-NEXT:    [[TMP18:%.*]] = udiv i64 [[TMP16]], [[TMP17]]
; IF-EVL-NEXT:    [[C_GEP:%.*]] = getelementptr i64, ptr [[C]], i64 [[IV]]
; IF-EVL-NEXT:    store i64 [[TMP18]], ptr [[C_GEP]], align 8
; IF-EVL-NEXT:    [[IV_NEXT]] = add i64 [[IV]], 1
; IF-EVL-NEXT:    [[DONE:%.*]] = icmp eq i64 [[IV_NEXT]], 1024
; IF-EVL-NEXT:    br i1 [[DONE]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP5:![0-9]+]]
; IF-EVL:       [[EXIT]]:
; IF-EVL-NEXT:    ret void
;
; NO-VP-LABEL: define void @test_udiv(
; NO-VP-SAME: ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
; NO-VP-NEXT:  [[LOOP_PREHEADER:.*]]:
; NO-VP-NEXT:    br label %[[LOOP:.*]]
; NO-VP:       [[LOOP]]:
; NO-VP-NEXT:    [[IV:%.*]] = phi i64 [ [[IV_NEXT:%.*]], %[[LOOP]] ], [ 0, %[[LOOP_PREHEADER]] ]
; NO-VP-NEXT:    [[A_GEP:%.*]] = getelementptr i64, ptr [[A]], i64 [[IV]]
; NO-VP-NEXT:    [[TMP0:%.*]] = load i64, ptr [[A_GEP]], align 8
; NO-VP-NEXT:    [[B_GEP:%.*]] = getelementptr i64, ptr [[B]], i64 [[IV]]
; NO-VP-NEXT:    [[TMP1:%.*]] = load i64, ptr [[B_GEP]], align 8
; NO-VP-NEXT:    [[TMP2:%.*]] = udiv i64 [[TMP0]], [[TMP1]]
; NO-VP-NEXT:    [[C_GEP:%.*]] = getelementptr i64, ptr [[C]], i64 [[IV]]
; NO-VP-NEXT:    store i64 [[TMP2]], ptr [[C_GEP]], align 8
; NO-VP-NEXT:    [[IV_NEXT]] = add i64 [[IV]], 1
; NO-VP-NEXT:    [[DONE:%.*]] = icmp eq i64 [[IV_NEXT]], 1024
; NO-VP-NEXT:    br i1 [[DONE]], label %[[EXIT:.*]], label %[[LOOP]]
; NO-VP:       [[EXIT]]:
; NO-VP-NEXT:    ret void
;
loop.preheader:
  br label %loop

loop:
  %iv = phi i64 [ %iv.next, %loop ], [ 0, %loop.preheader ]
  %a.gep = getelementptr i64, ptr %a, i64 %iv
  %0 = load i64, ptr %a.gep
  %b.gep = getelementptr i64, ptr %b, i64 %iv
  %1 = load i64, ptr %b.gep
  %2 = udiv i64 %0, %1
  %c.gep = getelementptr i64, ptr %c, i64 %iv
  store i64 %2, ptr %c.gep
  %iv.next = add i64 %iv, 1
  %done = icmp eq i64 %iv.next, 1024
  br i1 %done, label %exit, label %loop

exit:
  ret void
}

define void @test_srem(ptr noalias %a, ptr noalias %b, ptr noalias %c) {
; IF-EVL-LABEL: define void @test_srem(
; IF-EVL-SAME: ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
; IF-EVL-NEXT:  [[LOOP_PREHEADER:.*]]:
; IF-EVL-NEXT:    br i1 false, label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
; IF-EVL:       [[VECTOR_PH]]:
; IF-EVL-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; IF-EVL-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 2
; IF-EVL-NEXT:    [[TMP2:%.*]] = sub i64 [[TMP1]], 1
; IF-EVL-NEXT:    [[N_RND_UP:%.*]] = add i64 1024, [[TMP2]]
; IF-EVL-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
; IF-EVL-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
; IF-EVL-NEXT:    [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
; IF-EVL-NEXT:    [[TMP4:%.*]] = mul i64 [[TMP3]], 2
; IF-EVL-NEXT:    br label %[[VECTOR_BODY:.*]]
; IF-EVL:       [[VECTOR_BODY]]:
; IF-EVL-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
; IF-EVL-NEXT:    [[EVL_BASED_IV:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], %[[VECTOR_BODY]] ]
; IF-EVL-NEXT:    [[AVL:%.*]] = sub i64 1024, [[EVL_BASED_IV]]
; IF-EVL-NEXT:    [[TMP5:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 [[AVL]], i32 2, i1 true)
; IF-EVL-NEXT:    [[TMP7:%.*]] = getelementptr i64, ptr [[A]], i64 [[EVL_BASED_IV]]
; IF-EVL-NEXT:    [[TMP8:%.*]] = getelementptr i64, ptr [[TMP7]], i32 0
; IF-EVL-NEXT:    [[VP_OP_LOAD:%.*]] = call <vscale x 2 x i64> @llvm.vp.load.nxv2i64.p0(ptr align 8 [[TMP8]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP5]])
; IF-EVL-NEXT:    [[TMP9:%.*]] = getelementptr i64, ptr [[B]], i64 [[EVL_BASED_IV]]
; IF-EVL-NEXT:    [[TMP10:%.*]] = getelementptr i64, ptr [[TMP9]], i32 0
; IF-EVL-NEXT:    [[VP_OP_LOAD1:%.*]] = call <vscale x 2 x i64> @llvm.vp.load.nxv2i64.p0(ptr align 8 [[TMP10]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP5]])
; IF-EVL-NEXT:    [[TMP11:%.*]] = call <vscale x 2 x i64> @llvm.vp.merge.nxv2i64(<vscale x 2 x i1> splat (i1 true), <vscale x 2 x i64> [[VP_OP_LOAD1]], <vscale x 2 x i64> splat (i64 1), i32 [[TMP5]])
; IF-EVL-NEXT:    [[VP_OP:%.*]] = srem <vscale x 2 x i64> [[VP_OP_LOAD]], [[TMP11]]
; IF-EVL-NEXT:    [[TMP12:%.*]] = getelementptr i64, ptr [[C]], i64 [[EVL_BASED_IV]]
; IF-EVL-NEXT:    [[TMP13:%.*]] = getelementptr i64, ptr [[TMP12]], i32 0
; IF-EVL-NEXT:    call void @llvm.vp.store.nxv2i64.p0(<vscale x 2 x i64> [[VP_OP]], ptr align 8 [[TMP13]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP5]])
; IF-EVL-NEXT:    [[TMP14:%.*]] = zext i32 [[TMP5]] to i64
; IF-EVL-NEXT:    [[INDEX_EVL_NEXT]] = add nuw i64 [[TMP14]], [[EVL_BASED_IV]]
; IF-EVL-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP4]]
; IF-EVL-NEXT:    [[TMP15:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; IF-EVL-NEXT:    br i1 [[TMP15]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
; IF-EVL:       [[MIDDLE_BLOCK]]:
; IF-EVL-NEXT:    br i1 true, label %[[EXIT:.*]], label %[[SCALAR_PH]]
; IF-EVL:       [[SCALAR_PH]]:
; IF-EVL-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], %[[MIDDLE_BLOCK]] ], [ 0, %[[LOOP_PREHEADER]] ]
; IF-EVL-NEXT:    br label %[[LOOP:.*]]
; IF-EVL:       [[LOOP]]:
; IF-EVL-NEXT:    [[IV:%.*]] = phi i64 [ [[IV_NEXT:%.*]], %[[LOOP]] ], [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ]
; IF-EVL-NEXT:    [[A_GEP:%.*]] = getelementptr i64, ptr [[A]], i64 [[IV]]
; IF-EVL-NEXT:    [[TMP16:%.*]] = load i64, ptr [[A_GEP]], align 8
; IF-EVL-NEXT:    [[B_GEP:%.*]] = getelementptr i64, ptr [[B]], i64 [[IV]]
; IF-EVL-NEXT:    [[TMP17:%.*]] = load i64, ptr [[B_GEP]], align 8
; IF-EVL-NEXT:    [[TMP18:%.*]] = srem i64 [[TMP16]], [[TMP17]]
; IF-EVL-NEXT:    [[C_GEP:%.*]] = getelementptr i64, ptr [[C]], i64 [[IV]]
; IF-EVL-NEXT:    store i64 [[TMP18]], ptr [[C_GEP]], align 8
; IF-EVL-NEXT:    [[IV_NEXT]] = add i64 [[IV]], 1
; IF-EVL-NEXT:    [[DONE:%.*]] = icmp eq i64 [[IV_NEXT]], 1024
; IF-EVL-NEXT:    br i1 [[DONE]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP7:![0-9]+]]
; IF-EVL:       [[EXIT]]:
; IF-EVL-NEXT:    ret void
;
; NO-VP-LABEL: define void @test_srem(
; NO-VP-SAME: ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
; NO-VP-NEXT:  [[LOOP_PREHEADER:.*]]:
; NO-VP-NEXT:    br label %[[LOOP:.*]]
; NO-VP:       [[LOOP]]:
; NO-VP-NEXT:    [[IV:%.*]] = phi i64 [ [[IV_NEXT:%.*]], %[[LOOP]] ], [ 0, %[[LOOP_PREHEADER]] ]
; NO-VP-NEXT:    [[A_GEP:%.*]] = getelementptr i64, ptr [[A]], i64 [[IV]]
; NO-VP-NEXT:    [[TMP0:%.*]] = load i64, ptr [[A_GEP]], align 8
; NO-VP-NEXT:    [[B_GEP:%.*]] = getelementptr i64, ptr [[B]], i64 [[IV]]
; NO-VP-NEXT:    [[TMP1:%.*]] = load i64, ptr [[B_GEP]], align 8
; NO-VP-NEXT:    [[TMP2:%.*]] = srem i64 [[TMP0]], [[TMP1]]
; NO-VP-NEXT:    [[C_GEP:%.*]] = getelementptr i64, ptr [[C]], i64 [[IV]]
; NO-VP-NEXT:    store i64 [[TMP2]], ptr [[C_GEP]], align 8
; NO-VP-NEXT:    [[IV_NEXT]] = add i64 [[IV]], 1
; NO-VP-NEXT:    [[DONE:%.*]] = icmp eq i64 [[IV_NEXT]], 1024
; NO-VP-NEXT:    br i1 [[DONE]], label %[[EXIT:.*]], label %[[LOOP]]
; NO-VP:       [[EXIT]]:
; NO-VP-NEXT:    ret void
;
loop.preheader:
  br label %loop

loop:
  %iv = phi i64 [ %iv.next, %loop ], [ 0, %loop.preheader ]
  %a.gep = getelementptr i64, ptr %a, i64 %iv
  %0 = load i64, ptr %a.gep
  %b.gep = getelementptr i64, ptr %b, i64 %iv
  %1 = load i64, ptr %b.gep
  %2 = srem i64 %0, %1
  %c.gep = getelementptr i64, ptr %c, i64 %iv
  store i64 %2, ptr %c.gep
  %iv.next = add i64 %iv, 1
  %done = icmp eq i64 %iv.next, 1024
  br i1 %done, label %exit, label %loop

exit:
  ret void
}

define void @test_urem(ptr noalias %a, ptr noalias %b, ptr noalias %c) {
; IF-EVL-LABEL: define void @test_urem(
; IF-EVL-SAME: ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
; IF-EVL-NEXT:  [[LOOP_PREHEADER:.*]]:
; IF-EVL-NEXT:    br i1 false, label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
; IF-EVL:       [[VECTOR_PH]]:
; IF-EVL-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; IF-EVL-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 2
; IF-EVL-NEXT:    [[TMP2:%.*]] = sub i64 [[TMP1]], 1
; IF-EVL-NEXT:    [[N_RND_UP:%.*]] = add i64 1024, [[TMP2]]
; IF-EVL-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
; IF-EVL-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
; IF-EVL-NEXT:    [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
; IF-EVL-NEXT:    [[TMP4:%.*]] = mul i64 [[TMP3]], 2
; IF-EVL-NEXT:    br label %[[VECTOR_BODY:.*]]
; IF-EVL:       [[VECTOR_BODY]]:
; IF-EVL-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
; IF-EVL-NEXT:    [[EVL_BASED_IV:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], %[[VECTOR_BODY]] ]
; IF-EVL-NEXT:    [[AVL:%.*]] = sub i64 1024, [[EVL_BASED_IV]]
; IF-EVL-NEXT:    [[TMP5:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 [[AVL]], i32 2, i1 true)
; IF-EVL-NEXT:    [[TMP7:%.*]] = getelementptr i64, ptr [[A]], i64 [[EVL_BASED_IV]]
; IF-EVL-NEXT:    [[TMP8:%.*]] = getelementptr i64, ptr [[TMP7]], i32 0
; IF-EVL-NEXT:    [[VP_OP_LOAD:%.*]] = call <vscale x 2 x i64> @llvm.vp.load.nxv2i64.p0(ptr align 8 [[TMP8]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP5]])
; IF-EVL-NEXT:    [[TMP9:%.*]] = getelementptr i64, ptr [[B]], i64 [[EVL_BASED_IV]]
; IF-EVL-NEXT:    [[TMP10:%.*]] = getelementptr i64, ptr [[TMP9]], i32 0
; IF-EVL-NEXT:    [[VP_OP_LOAD1:%.*]] = call <vscale x 2 x i64> @llvm.vp.load.nxv2i64.p0(ptr align 8 [[TMP10]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP5]])
; IF-EVL-NEXT:    [[TMP11:%.*]] = call <vscale x 2 x i64> @llvm.vp.merge.nxv2i64(<vscale x 2 x i1> splat (i1 true), <vscale x 2 x i64> [[VP_OP_LOAD1]], <vscale x 2 x i64> splat (i64 1), i32 [[TMP5]])
; IF-EVL-NEXT:    [[VP_OP:%.*]] = urem <vscale x 2 x i64> [[VP_OP_LOAD]], [[TMP11]]
; IF-EVL-NEXT:    [[TMP12:%.*]] = getelementptr i64, ptr [[C]], i64 [[EVL_BASED_IV]]
; IF-EVL-NEXT:    [[TMP13:%.*]] = getelementptr i64, ptr [[TMP12]], i32 0
; IF-EVL-NEXT:    call void @llvm.vp.store.nxv2i64.p0(<vscale x 2 x i64> [[VP_OP]], ptr align 8 [[TMP13]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP5]])
; IF-EVL-NEXT:    [[TMP14:%.*]] = zext i32 [[TMP5]] to i64
; IF-EVL-NEXT:    [[INDEX_EVL_NEXT]] = add nuw i64 [[TMP14]], [[EVL_BASED_IV]]
; IF-EVL-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP4]]
; IF-EVL-NEXT:    [[TMP15:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; IF-EVL-NEXT:    br i1 [[TMP15]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
; IF-EVL:       [[MIDDLE_BLOCK]]:
; IF-EVL-NEXT:    br i1 true, label %[[EXIT:.*]], label %[[SCALAR_PH]]
; IF-EVL:       [[SCALAR_PH]]:
; IF-EVL-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], %[[MIDDLE_BLOCK]] ], [ 0, %[[LOOP_PREHEADER]] ]
; IF-EVL-NEXT:    br label %[[LOOP:.*]]
; IF-EVL:       [[LOOP]]:
; IF-EVL-NEXT:    [[IV:%.*]] = phi i64 [ [[IV_NEXT:%.*]], %[[LOOP]] ], [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ]
; IF-EVL-NEXT:    [[A_GEP:%.*]] = getelementptr i64, ptr [[A]], i64 [[IV]]
; IF-EVL-NEXT:    [[TMP16:%.*]] = load i64, ptr [[A_GEP]], align 8
; IF-EVL-NEXT:    [[B_GEP:%.*]] = getelementptr i64, ptr [[B]], i64 [[IV]]
; IF-EVL-NEXT:    [[TMP17:%.*]] = load i64, ptr [[B_GEP]], align 8
; IF-EVL-NEXT:    [[TMP18:%.*]] = urem i64 [[TMP16]], [[TMP17]]
; IF-EVL-NEXT:    [[C_GEP:%.*]] = getelementptr i64, ptr [[C]], i64 [[IV]]
; IF-EVL-NEXT:    store i64 [[TMP18]], ptr [[C_GEP]], align 8
; IF-EVL-NEXT:    [[IV_NEXT]] = add i64 [[IV]], 1
; IF-EVL-NEXT:    [[DONE:%.*]] = icmp eq i64 [[IV_NEXT]], 1024
; IF-EVL-NEXT:    br i1 [[DONE]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP9:![0-9]+]]
; IF-EVL:       [[EXIT]]:
; IF-EVL-NEXT:    ret void
;
; NO-VP-LABEL: define void @test_urem(
; NO-VP-SAME: ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
; NO-VP-NEXT:  [[LOOP_PREHEADER:.*]]:
; NO-VP-NEXT:    br label %[[LOOP:.*]]
; NO-VP:       [[LOOP]]:
; NO-VP-NEXT:    [[IV:%.*]] = phi i64 [ [[IV_NEXT:%.*]], %[[LOOP]] ], [ 0, %[[LOOP_PREHEADER]] ]
; NO-VP-NEXT:    [[A_GEP:%.*]] = getelementptr i64, ptr [[A]], i64 [[IV]]
; NO-VP-NEXT:    [[TMP0:%.*]] = load i64, ptr [[A_GEP]], align 8
; NO-VP-NEXT:    [[B_GEP:%.*]] = getelementptr i64, ptr [[B]], i64 [[IV]]
; NO-VP-NEXT:    [[TMP1:%.*]] = load i64, ptr [[B_GEP]], align 8
; NO-VP-NEXT:    [[TMP2:%.*]] = urem i64 [[TMP0]], [[TMP1]]
; NO-VP-NEXT:    [[C_GEP:%.*]] = getelementptr i64, ptr [[C]], i64 [[IV]]
; NO-VP-NEXT:    store i64 [[TMP2]], ptr [[C_GEP]], align 8
; NO-VP-NEXT:    [[IV_NEXT]] = add i64 [[IV]], 1
; NO-VP-NEXT:    [[DONE:%.*]] = icmp eq i64 [[IV_NEXT]], 1024
; NO-VP-NEXT:    br i1 [[DONE]], label %[[EXIT:.*]], label %[[LOOP]]
; NO-VP:       [[EXIT]]:
; NO-VP-NEXT:    ret void
;
loop.preheader:
  br label %loop

loop:
  %iv = phi i64 [ %iv.next, %loop ], [ 0, %loop.preheader ]
  %a.gep = getelementptr i64, ptr %a, i64 %iv
  %0 = load i64, ptr %a.gep
  %b.gep = getelementptr i64, ptr %b, i64 %iv
  %1 = load i64, ptr %b.gep
  %2 = urem i64 %0, %1
  %c.gep = getelementptr i64, ptr %c, i64 %iv
  store i64 %2, ptr %c.gep
  %iv.next = add i64 %iv, 1
  %done = icmp eq i64 %iv.next, 1024
  br i1 %done, label %exit, label %loop

exit:
  ret void
}
;.
; IF-EVL: [[LOOP0]] = distinct !{[[LOOP0]], [[META1:![0-9]+]], [[META2:![0-9]+]]}
; IF-EVL: [[META1]] = !{!"llvm.loop.isvectorized", i32 1}
; IF-EVL: [[META2]] = !{!"llvm.loop.unroll.runtime.disable"}
; IF-EVL: [[LOOP3]] = distinct !{[[LOOP3]], [[META2]], [[META1]]}
; IF-EVL: [[LOOP4]] = distinct !{[[LOOP4]], [[META1]], [[META2]]}
; IF-EVL: [[LOOP5]] = distinct !{[[LOOP5]], [[META2]], [[META1]]}
; IF-EVL: [[LOOP6]] = distinct !{[[LOOP6]], [[META1]], [[META2]]}
; IF-EVL: [[LOOP7]] = distinct !{[[LOOP7]], [[META2]], [[META1]]}
; IF-EVL: [[LOOP8]] = distinct !{[[LOOP8]], [[META1]], [[META2]]}
; IF-EVL: [[LOOP9]] = distinct !{[[LOOP9]], [[META2]], [[META1]]}
;.