Page MenuHomePhabricator
Differential D43582 Diff 137030 test/Transforms/SLPVectorizer/X86/insert-after-bundle.ll

Changeset View

Standalone View

View Options

test/Transforms/SLPVectorizer/X86/insert-after-bundle.ll

Show First 20 Lines • Show All 406 Lines • ▼ Show 20 Lines
} }
@ib = local_unnamed_addr global [64 x i32] [i32 1, i32 1, i32 0, i32 0, i32 1, i32 0, i32 1, i32 0, i32 1, i32 1, i32 0, i32 0, i32 1, i32 0, i32 1, i32 0, i32 1, i32 1, i32 0, i32 0, i32 1, i32 0, i32 1, i32 0, i32 1, i32 1, i32 0, i32 0, i32 1, i32 0, i32 1, i32 0, i32 1, i32 1, i32 0, i32 0, i32 1, i32 0, i32 1, i32 0, i32 1, i32 1, i32 0, i32 0, i32 1, i32 0, i32 1, i32 0, i32 1, i32 1, i32 0, i32 0, i32 1, i32 0, i32 1, i32 0, i32 1, i32 1, i32 0, i32 0, i32 1, i32 0, i32 1, i32 0], align 16 @ib = local_unnamed_addr global [64 x i32] [i32 1, i32 1, i32 0, i32 0, i32 1, i32 0, i32 1, i32 0, i32 1, i32 1, i32 0, i32 0, i32 1, i32 0, i32 1, i32 0, i32 1, i32 1, i32 0, i32 0, i32 1, i32 0, i32 1, i32 0, i32 1, i32 1, i32 0, i32 0, i32 1, i32 0, i32 1, i32 0, i32 1, i32 1, i32 0, i32 0, i32 1, i32 0, i32 1, i32 0, i32 1, i32 1, i32 0, i32 0, i32 1, i32 0, i32 1, i32 0, i32 1, i32 1, i32 0, i32 0, i32 1, i32 0, i32 1, i32 0, i32 1, i32 1, i32 0, i32 0, i32 1, i32 0, i32 1, i32 0], align 16
@ia = common local_unnamed_addr global [64 x i32] zeroinitializer, align 16 @ia = common local_unnamed_addr global [64 x i32] zeroinitializer, align 16
define i32 @foo1() local_unnamed_addr #0 { define i32 @foo1() local_unnamed_addr #0 {
; CHECK-LABEL: @foo1( ; CHECK-LABEL: @foo1(
; CHECK-NEXT: entry: ; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = load <4 x i32>, <4 x i32>* bitcast ([64 x i32]* @ib to <4 x i32>*), align 16 ; CHECK-NEXT: [[TMP0:%.*]] = load <64 x i32>, <64 x i32>* bitcast ([64 x i32]* @ib to <64 x i32>*), align 16
; CHECK-NEXT: [[TMP1:%.*]] = xor <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>, [[TMP0]] ; CHECK-NEXT: [[TMP1:%.*]] = xor <64 x i32> <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1>, [[TMP0]]
; CHECK-NEXT: store <4 x i32> [[TMP1]], <4 x i32>* bitcast ([64 x i32]* @ia to <4 x i32>*), align 16 ; CHECK-NEXT: store <64 x i32> [[TMP1]], <64 x i32>* bitcast ([64 x i32]* @ia to <64 x i32>*), align 16
; CHECK-NEXT: [[TMP2:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([64 x i32], [64 x i32]* @ib, i64 0, i64 4) to <4 x i32>*), align 16
; CHECK-NEXT: [[TMP3:%.*]] = xor <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>, [[TMP2]]
; CHECK-NEXT: store <4 x i32> [[TMP3]], <4 x i32>* bitcast (i32* getelementptr inbounds ([64 x i32], [64 x i32]* @ia, i64 0, i64 4) to <4 x i32>*), align 16
; CHECK-NEXT: [[TMP4:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([64 x i32], [64 x i32]* @ib, i64 0, i64 8) to <4 x i32>*), align 16
; CHECK-NEXT: [[TMP5:%.*]] = xor <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>, [[TMP4]]
; CHECK-NEXT: store <4 x i32> [[TMP5]], <4 x i32>* bitcast (i32* getelementptr inbounds ([64 x i32], [64 x i32]* @ia, i64 0, i64 8) to <4 x i32>*), align 16
; CHECK-NEXT: [[TMP6:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([64 x i32], [64 x i32]* @ib, i64 0, i64 12) to <4 x i32>*), align 16
; CHECK-NEXT: [[TMP7:%.*]] = xor <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>, [[TMP6]]
; CHECK-NEXT: store <4 x i32> [[TMP7]], <4 x i32>* bitcast (i32* getelementptr inbounds ([64 x i32], [64 x i32]* @ia, i64 0, i64 12) to <4 x i32>*), align 16
; CHECK-NEXT: [[TMP8:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([64 x i32], [64 x i32]* @ib, i64 0, i64 16) to <4 x i32>*), align 16
; CHECK-NEXT: [[TMP9:%.*]] = xor <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>, [[TMP8]]
; CHECK-NEXT: store <4 x i32> [[TMP9]], <4 x i32>* bitcast (i32* getelementptr inbounds ([64 x i32], [64 x i32]* @ia, i64 0, i64 16) to <4 x i32>*), align 16
; CHECK-NEXT: [[TMP10:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([64 x i32], [64 x i32]* @ib, i64 0, i64 20) to <4 x i32>*), align 16
; CHECK-NEXT: [[TMP11:%.*]] = xor <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>, [[TMP10]]
; CHECK-NEXT: store <4 x i32> [[TMP11]], <4 x i32>* bitcast (i32* getelementptr inbounds ([64 x i32], [64 x i32]* @ia, i64 0, i64 20) to <4 x i32>*), align 16
; CHECK-NEXT: [[TMP12:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([64 x i32], [64 x i32]* @ib, i64 0, i64 24) to <4 x i32>*), align 16
; CHECK-NEXT: [[TMP13:%.*]] = xor <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>, [[TMP12]]
; CHECK-NEXT: store <4 x i32> [[TMP13]], <4 x i32>* bitcast (i32* getelementptr inbounds ([64 x i32], [64 x i32]* @ia, i64 0, i64 24) to <4 x i32>*), align 16
; CHECK-NEXT: [[TMP14:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([64 x i32], [64 x i32]* @ib, i64 0, i64 28) to <4 x i32>*), align 16
; CHECK-NEXT: [[TMP15:%.*]] = xor <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>, [[TMP14]]
; CHECK-NEXT: store <4 x i32> [[TMP15]], <4 x i32>* bitcast (i32* getelementptr inbounds ([64 x i32], [64 x i32]* @ia, i64 0, i64 28) to <4 x i32>*), align 16
; CHECK-NEXT: [[TMP16:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([64 x i32], [64 x i32]* @ib, i64 0, i64 32) to <4 x i32>*), align 16
; CHECK-NEXT: [[TMP17:%.*]] = xor <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>, [[TMP16]]
; CHECK-NEXT: store <4 x i32> [[TMP17]], <4 x i32>* bitcast (i32* getelementptr inbounds ([64 x i32], [64 x i32]* @ia, i64 0, i64 32) to <4 x i32>*), align 16
; CHECK-NEXT: [[TMP18:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([64 x i32], [64 x i32]* @ib, i64 0, i64 36) to <4 x i32>*), align 16
; CHECK-NEXT: [[TMP19:%.*]] = xor <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>, [[TMP18]]
; CHECK-NEXT: store <4 x i32> [[TMP19]], <4 x i32>* bitcast (i32* getelementptr inbounds ([64 x i32], [64 x i32]* @ia, i64 0, i64 36) to <4 x i32>*), align 16
; CHECK-NEXT: [[TMP20:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([64 x i32], [64 x i32]* @ib, i64 0, i64 40) to <4 x i32>*), align 16
; CHECK-NEXT: [[TMP21:%.*]] = xor <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>, [[TMP20]]
; CHECK-NEXT: store <4 x i32> [[TMP21]], <4 x i32>* bitcast (i32* getelementptr inbounds ([64 x i32], [64 x i32]* @ia, i64 0, i64 40) to <4 x i32>*), align 16
; CHECK-NEXT: [[TMP22:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([64 x i32], [64 x i32]* @ib, i64 0, i64 44) to <4 x i32>*), align 16
; CHECK-NEXT: [[TMP23:%.*]] = xor <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>, [[TMP22]]
; CHECK-NEXT: store <4 x i32> [[TMP23]], <4 x i32>* bitcast (i32* getelementptr inbounds ([64 x i32], [64 x i32]* @ia, i64 0, i64 44) to <4 x i32>*), align 16
; CHECK-NEXT: [[TMP24:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([64 x i32], [64 x i32]* @ib, i64 0, i64 48) to <4 x i32>*), align 16
; CHECK-NEXT: [[TMP25:%.*]] = xor <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>, [[TMP24]]
; CHECK-NEXT: store <4 x i32> [[TMP25]], <4 x i32>* bitcast (i32* getelementptr inbounds ([64 x i32], [64 x i32]* @ia, i64 0, i64 48) to <4 x i32>*), align 16
; CHECK-NEXT: [[TMP26:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([64 x i32], [64 x i32]* @ib, i64 0, i64 52) to <4 x i32>*), align 16
; CHECK-NEXT: [[TMP27:%.*]] = xor <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>, [[TMP26]]
; CHECK-NEXT: store <4 x i32> [[TMP27]], <4 x i32>* bitcast (i32* getelementptr inbounds ([64 x i32], [64 x i32]* @ia, i64 0, i64 52) to <4 x i32>*), align 16
; CHECK-NEXT: [[TMP28:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([64 x i32], [64 x i32]* @ib, i64 0, i64 56) to <4 x i32>*), align 16
; CHECK-NEXT: [[TMP29:%.*]] = xor <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>, [[TMP28]]
; CHECK-NEXT: store <4 x i32> [[TMP29]], <4 x i32>* bitcast (i32* getelementptr inbounds ([64 x i32], [64 x i32]* @ia, i64 0, i64 56) to <4 x i32>*), align 16
; CHECK-NEXT: [[TMP30:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([64 x i32], [64 x i32]* @ib, i64 0, i64 60) to <4 x i32>*), align 16
; CHECK-NEXT: [[TMP31:%.*]] = xor <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>, [[TMP30]]
; CHECK-NEXT: store <4 x i32> [[TMP31]], <4 x i32>* bitcast (i32* getelementptr inbounds ([64 x i32], [64 x i32]* @ia, i64 0, i64 60) to <4 x i32>*), align 16
; CHECK-NEXT: br label [[FOR_BODY5:%.*]] ; CHECK-NEXT: br label [[FOR_BODY5:%.*]]
; CHECK: for.cond3: ; CHECK: for.cond3:
; CHECK-NEXT: [[INDVARS_IV_NEXT:%.*]] = add nuw nsw i64 [[INDVARS_IV:%.*]], 1 ; CHECK-NEXT: [[INDVARS_IV_NEXT:%.*]] = add nuw nsw i64 [[INDVARS_IV:%.*]], 1
; CHECK-NEXT: [[CMP4:%.*]] = icmp ult i64 [[INDVARS_IV]], 63 ; CHECK-NEXT: [[CMP4:%.*]] = icmp ult i64 [[INDVARS_IV]], 63
; CHECK-NEXT: br i1 [[CMP4]], label [[FOR_BODY5]], label [[FOR_END14:%.*]] ; CHECK-NEXT: br i1 [[CMP4]], label [[FOR_BODY5]], label [[FOR_END14:%.*]]
; CHECK: for.body5: ; CHECK: for.body5:
; CHECK-NEXT: [[INDVARS_IV]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDVARS_IV_NEXT]], [[FOR_COND3:%.*]] ] ; CHECK-NEXT: [[INDVARS_IV]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDVARS_IV_NEXT]], [[FOR_COND3:%.*]] ]
; CHECK-NEXT: [[ARRAYIDX7:%.*]] = getelementptr inbounds [64 x i32], [64 x i32]* @ia, i64 0, i64 [[INDVARS_IV]] ; CHECK-NEXT: [[ARRAYIDX7:%.*]] = getelementptr inbounds [64 x i32], [64 x i32]* @ia, i64 0, i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP32:%.*]] = load i32, i32* [[ARRAYIDX7]], align 4 ; CHECK-NEXT: [[TMP2:%.*]] = load i32, i32* [[ARRAYIDX7]], align 4
; CHECK-NEXT: [[ARRAYIDX9:%.*]] = getelementptr inbounds [64 x i32], [64 x i32]* @ib, i64 0, i64 [[INDVARS_IV]] ; CHECK-NEXT: [[ARRAYIDX9:%.*]] = getelementptr inbounds [64 x i32], [64 x i32]* @ib, i64 0, i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP33:%.*]] = load i32, i32* [[ARRAYIDX9]], align 4 ; CHECK-NEXT: [[TMP3:%.*]] = load i32, i32* [[ARRAYIDX9]], align 4
; CHECK-NEXT: [[NEG10:%.*]] = xor i32 [[TMP33]], -1 ; CHECK-NEXT: [[NEG10:%.*]] = xor i32 [[TMP3]], -1
; CHECK-NEXT: [[CMP11:%.*]] = icmp eq i32 [[TMP32]], [[NEG10]] ; CHECK-NEXT: [[CMP11:%.*]] = icmp eq i32 [[TMP2]], [[NEG10]]
; CHECK-NEXT: br i1 [[CMP11]], label [[FOR_COND3]], label [[IF_THEN:%.*]] ; CHECK-NEXT: br i1 [[CMP11]], label [[FOR_COND3]], label [[IF_THEN:%.*]]
; CHECK: if.then: ; CHECK: if.then:
; CHECK-NEXT: tail call void @abort() ; CHECK-NEXT: tail call void @abort()
; CHECK-NEXT: unreachable ; CHECK-NEXT: unreachable
; CHECK: for.end14: ; CHECK: for.end14:
; CHECK-NEXT: ret i32 0 ; CHECK-NEXT: ret i32 0
; ;
entry: entry:
▲ Show 20 Lines • Show All 218 Lines • Show Last 20 Lines