If IVUpdateMayOverflow is false, we proved that the induction increment cannot overflow in the vector loop. This allows setting NUW in some cases when folding the tail. PR: https://github.com/llvm/llvm-project/pull/111758
190 lines
11 KiB
LLVM
190 lines
11 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 4
|
|
; RUN: opt -passes=loop-vectorize -mtriple=s390x -mcpu=z14 -S %s | FileCheck %s
|
|
|
|
define void @test(ptr %p, i40 %a) {
|
|
; CHECK-LABEL: define void @test(
|
|
; CHECK-SAME: ptr [[P:%.*]], i40 [[A:%.*]]) #[[ATTR0:[0-9]+]] {
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
|
|
; CHECK: vector.ph:
|
|
; CHECK-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <16 x i40> poison, i40 [[A]], i64 0
|
|
; CHECK-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <16 x i40> [[BROADCAST_SPLATINSERT1]], <16 x i40> poison, <16 x i32> zeroinitializer
|
|
; CHECK-NEXT: [[TMP1:%.*]] = shl <16 x i40> [[BROADCAST_SPLAT2]], splat (i40 24)
|
|
; CHECK-NEXT: [[TMP2:%.*]] = ashr <16 x i40> [[TMP1]], splat (i40 28)
|
|
; CHECK-NEXT: [[TMP3:%.*]] = trunc <16 x i40> [[TMP2]] to <16 x i32>
|
|
; CHECK-NEXT: [[TMP4:%.*]] = trunc <16 x i32> [[TMP3]] to <16 x i1>
|
|
; CHECK-NEXT: [[TMP5:%.*]] = icmp eq <16 x i1> [[TMP4]], zeroinitializer
|
|
; CHECK-NEXT: [[TMP6:%.*]] = icmp ult <16 x i1> zeroinitializer, [[TMP5]]
|
|
; CHECK-NEXT: [[TMP7:%.*]] = or <16 x i1> [[TMP6]], splat (i1 true)
|
|
; CHECK-NEXT: [[TMP8:%.*]] = icmp sgt <16 x i1> [[TMP7]], zeroinitializer
|
|
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
|
|
; CHECK: vector.body:
|
|
; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_STORE_CONTINUE32:%.*]] ]
|
|
; CHECK-NEXT: [[BROADCAST_SPLATINSERT2:%.*]] = insertelement <16 x i32> poison, i32 [[INDEX]], i64 0
|
|
; CHECK-NEXT: [[BROADCAST_SPLAT3:%.*]] = shufflevector <16 x i32> [[BROADCAST_SPLATINSERT2]], <16 x i32> poison, <16 x i32> zeroinitializer
|
|
; CHECK-NEXT: [[VEC_IV:%.*]] = add <16 x i32> [[BROADCAST_SPLAT3]], <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
|
|
; CHECK-NEXT: [[TMP0:%.*]] = icmp ule <16 x i32> [[VEC_IV]], splat (i32 9)
|
|
; CHECK-NEXT: [[TMP9:%.*]] = extractelement <16 x i1> [[TMP0]], i32 0
|
|
; CHECK-NEXT: br i1 [[TMP9]], label [[PRED_STORE_IF:%.*]], label [[PRED_STORE_CONTINUE:%.*]]
|
|
; CHECK: pred.store.if:
|
|
; CHECK-NEXT: [[TMP10:%.*]] = extractelement <16 x i1> [[TMP8]], i32 0
|
|
; CHECK-NEXT: store i1 [[TMP10]], ptr [[P]], align 1
|
|
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE]]
|
|
; CHECK: pred.store.continue:
|
|
; CHECK-NEXT: [[TMP11:%.*]] = extractelement <16 x i1> [[TMP0]], i32 1
|
|
; CHECK-NEXT: br i1 [[TMP11]], label [[PRED_STORE_IF3:%.*]], label [[PRED_STORE_CONTINUE4:%.*]]
|
|
; CHECK: pred.store.if3:
|
|
; CHECK-NEXT: [[TMP12:%.*]] = extractelement <16 x i1> [[TMP8]], i32 0
|
|
; CHECK-NEXT: store i1 [[TMP12]], ptr [[P]], align 1
|
|
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE4]]
|
|
; CHECK: pred.store.continue4:
|
|
; CHECK-NEXT: [[TMP13:%.*]] = extractelement <16 x i1> [[TMP0]], i32 2
|
|
; CHECK-NEXT: br i1 [[TMP13]], label [[PRED_STORE_IF5:%.*]], label [[PRED_STORE_CONTINUE6:%.*]]
|
|
; CHECK: pred.store.if5:
|
|
; CHECK-NEXT: [[TMP14:%.*]] = extractelement <16 x i1> [[TMP8]], i32 0
|
|
; CHECK-NEXT: store i1 [[TMP14]], ptr [[P]], align 1
|
|
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE6]]
|
|
; CHECK: pred.store.continue6:
|
|
; CHECK-NEXT: [[TMP15:%.*]] = extractelement <16 x i1> [[TMP0]], i32 3
|
|
; CHECK-NEXT: br i1 [[TMP15]], label [[PRED_STORE_IF7:%.*]], label [[PRED_STORE_CONTINUE8:%.*]]
|
|
; CHECK: pred.store.if7:
|
|
; CHECK-NEXT: [[TMP16:%.*]] = extractelement <16 x i1> [[TMP8]], i32 0
|
|
; CHECK-NEXT: store i1 [[TMP16]], ptr [[P]], align 1
|
|
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE8]]
|
|
; CHECK: pred.store.continue8:
|
|
; CHECK-NEXT: [[TMP17:%.*]] = extractelement <16 x i1> [[TMP0]], i32 4
|
|
; CHECK-NEXT: br i1 [[TMP17]], label [[PRED_STORE_IF9:%.*]], label [[PRED_STORE_CONTINUE10:%.*]]
|
|
; CHECK: pred.store.if9:
|
|
; CHECK-NEXT: [[TMP18:%.*]] = extractelement <16 x i1> [[TMP8]], i32 0
|
|
; CHECK-NEXT: store i1 [[TMP18]], ptr [[P]], align 1
|
|
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE10]]
|
|
; CHECK: pred.store.continue10:
|
|
; CHECK-NEXT: [[TMP19:%.*]] = extractelement <16 x i1> [[TMP0]], i32 5
|
|
; CHECK-NEXT: br i1 [[TMP19]], label [[PRED_STORE_IF11:%.*]], label [[PRED_STORE_CONTINUE12:%.*]]
|
|
; CHECK: pred.store.if11:
|
|
; CHECK-NEXT: [[TMP20:%.*]] = extractelement <16 x i1> [[TMP8]], i32 0
|
|
; CHECK-NEXT: store i1 [[TMP20]], ptr [[P]], align 1
|
|
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE12]]
|
|
; CHECK: pred.store.continue12:
|
|
; CHECK-NEXT: [[TMP21:%.*]] = extractelement <16 x i1> [[TMP0]], i32 6
|
|
; CHECK-NEXT: br i1 [[TMP21]], label [[PRED_STORE_IF13:%.*]], label [[PRED_STORE_CONTINUE14:%.*]]
|
|
; CHECK: pred.store.if13:
|
|
; CHECK-NEXT: [[TMP22:%.*]] = extractelement <16 x i1> [[TMP8]], i32 0
|
|
; CHECK-NEXT: store i1 [[TMP22]], ptr [[P]], align 1
|
|
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE14]]
|
|
; CHECK: pred.store.continue14:
|
|
; CHECK-NEXT: [[TMP23:%.*]] = extractelement <16 x i1> [[TMP0]], i32 7
|
|
; CHECK-NEXT: br i1 [[TMP23]], label [[PRED_STORE_IF15:%.*]], label [[PRED_STORE_CONTINUE16:%.*]]
|
|
; CHECK: pred.store.if15:
|
|
; CHECK-NEXT: [[TMP24:%.*]] = extractelement <16 x i1> [[TMP8]], i32 0
|
|
; CHECK-NEXT: store i1 [[TMP24]], ptr [[P]], align 1
|
|
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE16]]
|
|
; CHECK: pred.store.continue16:
|
|
; CHECK-NEXT: [[TMP25:%.*]] = extractelement <16 x i1> [[TMP0]], i32 8
|
|
; CHECK-NEXT: br i1 [[TMP25]], label [[PRED_STORE_IF17:%.*]], label [[PRED_STORE_CONTINUE18:%.*]]
|
|
; CHECK: pred.store.if17:
|
|
; CHECK-NEXT: [[TMP26:%.*]] = extractelement <16 x i1> [[TMP8]], i32 0
|
|
; CHECK-NEXT: store i1 [[TMP26]], ptr [[P]], align 1
|
|
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE18]]
|
|
; CHECK: pred.store.continue18:
|
|
; CHECK-NEXT: [[TMP27:%.*]] = extractelement <16 x i1> [[TMP0]], i32 9
|
|
; CHECK-NEXT: br i1 [[TMP27]], label [[PRED_STORE_IF19:%.*]], label [[PRED_STORE_CONTINUE20:%.*]]
|
|
; CHECK: pred.store.if19:
|
|
; CHECK-NEXT: [[TMP28:%.*]] = extractelement <16 x i1> [[TMP8]], i32 0
|
|
; CHECK-NEXT: store i1 [[TMP28]], ptr [[P]], align 1
|
|
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE20]]
|
|
; CHECK: pred.store.continue20:
|
|
; CHECK-NEXT: [[TMP29:%.*]] = extractelement <16 x i1> [[TMP0]], i32 10
|
|
; CHECK-NEXT: br i1 [[TMP29]], label [[PRED_STORE_IF21:%.*]], label [[PRED_STORE_CONTINUE22:%.*]]
|
|
; CHECK: pred.store.if21:
|
|
; CHECK-NEXT: [[TMP30:%.*]] = extractelement <16 x i1> [[TMP8]], i32 0
|
|
; CHECK-NEXT: store i1 [[TMP30]], ptr [[P]], align 1
|
|
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE22]]
|
|
; CHECK: pred.store.continue22:
|
|
; CHECK-NEXT: [[TMP31:%.*]] = extractelement <16 x i1> [[TMP0]], i32 11
|
|
; CHECK-NEXT: br i1 [[TMP31]], label [[PRED_STORE_IF23:%.*]], label [[PRED_STORE_CONTINUE24:%.*]]
|
|
; CHECK: pred.store.if23:
|
|
; CHECK-NEXT: [[TMP32:%.*]] = extractelement <16 x i1> [[TMP8]], i32 0
|
|
; CHECK-NEXT: store i1 [[TMP32]], ptr [[P]], align 1
|
|
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE24]]
|
|
; CHECK: pred.store.continue24:
|
|
; CHECK-NEXT: [[TMP33:%.*]] = extractelement <16 x i1> [[TMP0]], i32 12
|
|
; CHECK-NEXT: br i1 [[TMP33]], label [[PRED_STORE_IF25:%.*]], label [[PRED_STORE_CONTINUE26:%.*]]
|
|
; CHECK: pred.store.if25:
|
|
; CHECK-NEXT: [[TMP34:%.*]] = extractelement <16 x i1> [[TMP8]], i32 0
|
|
; CHECK-NEXT: store i1 [[TMP34]], ptr [[P]], align 1
|
|
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE26]]
|
|
; CHECK: pred.store.continue26:
|
|
; CHECK-NEXT: [[TMP35:%.*]] = extractelement <16 x i1> [[TMP0]], i32 13
|
|
; CHECK-NEXT: br i1 [[TMP35]], label [[PRED_STORE_IF27:%.*]], label [[PRED_STORE_CONTINUE28:%.*]]
|
|
; CHECK: pred.store.if27:
|
|
; CHECK-NEXT: [[TMP36:%.*]] = extractelement <16 x i1> [[TMP8]], i32 0
|
|
; CHECK-NEXT: store i1 [[TMP36]], ptr [[P]], align 1
|
|
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE28]]
|
|
; CHECK: pred.store.continue28:
|
|
; CHECK-NEXT: [[TMP37:%.*]] = extractelement <16 x i1> [[TMP0]], i32 14
|
|
; CHECK-NEXT: br i1 [[TMP37]], label [[PRED_STORE_IF29:%.*]], label [[PRED_STORE_CONTINUE30:%.*]]
|
|
; CHECK: pred.store.if29:
|
|
; CHECK-NEXT: [[TMP38:%.*]] = extractelement <16 x i1> [[TMP8]], i32 0
|
|
; CHECK-NEXT: store i1 [[TMP38]], ptr [[P]], align 1
|
|
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE30]]
|
|
; CHECK: pred.store.continue30:
|
|
; CHECK-NEXT: [[TMP39:%.*]] = extractelement <16 x i1> [[TMP0]], i32 15
|
|
; CHECK-NEXT: br i1 [[TMP39]], label [[PRED_STORE_IF31:%.*]], label [[PRED_STORE_CONTINUE32]]
|
|
; CHECK: pred.store.if31:
|
|
; CHECK-NEXT: [[TMP40:%.*]] = extractelement <16 x i1> [[TMP8]], i32 0
|
|
; CHECK-NEXT: store i1 [[TMP40]], ptr [[P]], align 1
|
|
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE32]]
|
|
; CHECK: pred.store.continue32:
|
|
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 16
|
|
; CHECK-NEXT: br i1 true, label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
|
|
; CHECK: middle.block:
|
|
; CHECK-NEXT: br i1 true, label [[EXIT:%.*]], label [[SCALAR_PH]]
|
|
; CHECK: scalar.ph:
|
|
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i32 [ 16, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
|
|
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
|
|
; CHECK: for.body:
|
|
; CHECK-NEXT: [[IV:%.*]] = phi i32 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[FOR_BODY]] ]
|
|
; CHECK-NEXT: [[SHL:%.*]] = shl i40 [[A]], 24
|
|
; CHECK-NEXT: [[ASHR:%.*]] = ashr i40 [[SHL]], 28
|
|
; CHECK-NEXT: [[TRUNC:%.*]] = trunc i40 [[ASHR]] to i32
|
|
; CHECK-NEXT: [[ICMP_EQ:%.*]] = icmp eq i32 [[TRUNC]], 0
|
|
; CHECK-NEXT: [[ZEXT:%.*]] = zext i1 [[ICMP_EQ]] to i32
|
|
; CHECK-NEXT: [[ICMP_ULT:%.*]] = icmp ult i32 0, [[ZEXT]]
|
|
; CHECK-NEXT: [[OR:%.*]] = or i1 [[ICMP_ULT]], true
|
|
; CHECK-NEXT: [[ICMP_SGT:%.*]] = icmp sgt i1 [[OR]], false
|
|
; CHECK-NEXT: store i1 [[ICMP_SGT]], ptr [[P]], align 1
|
|
; CHECK-NEXT: [[IV_NEXT]] = add i32 [[IV]], 1
|
|
; CHECK-NEXT: [[COND:%.*]] = icmp ult i32 [[IV_NEXT]], 10
|
|
; CHECK-NEXT: br i1 [[COND]], label [[FOR_BODY]], label [[EXIT]], !llvm.loop [[LOOP3:![0-9]+]]
|
|
; CHECK: exit:
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%iv = phi i32 [ 0, %entry ], [ %iv.next, %for.body ]
|
|
%shl = shl i40 %a, 24
|
|
%ashr = ashr i40 %shl, 28
|
|
%trunc = trunc i40 %ashr to i32
|
|
%icmp.eq = icmp eq i32 %trunc, 0
|
|
%zext = zext i1 %icmp.eq to i32
|
|
%icmp.ult = icmp ult i32 0, %zext
|
|
%or = or i1 %icmp.ult, true
|
|
%icmp.sgt = icmp sgt i1 %or, false
|
|
store i1 %icmp.sgt, ptr %p, align 1
|
|
%iv.next = add i32 %iv, 1
|
|
%cond = icmp ult i32 %iv.next, 10
|
|
br i1 %cond, label %for.body, label %exit
|
|
|
|
exit: ; preds = %for.body
|
|
ret void
|
|
}
|
|
;.
|
|
; CHECK: [[LOOP0]] = distinct !{[[LOOP0]], [[META1:![0-9]+]], [[META2:![0-9]+]]}
|
|
; CHECK: [[META1]] = !{!"llvm.loop.isvectorized", i32 1}
|
|
; CHECK: [[META2]] = !{!"llvm.loop.unroll.runtime.disable"}
|
|
; CHECK: [[LOOP3]] = distinct !{[[LOOP3]], [[META2]], [[META1]]}
|
|
;.
|