llvm/test/Transforms/LoopVectorize/multiple-strides-vectorization.ll

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -loop-vectorize -force-vector-width=4 -S < %s | FileCheck %s

; This is the test case from PR26314.
; When we were retrying dependence checking with memchecks only,
; the loop-invariant access in the inner loop was incorrectly determined to be wrapping
; because it was not strided in the inner loop.
; Improved wrapping detection allows vectorization in the following case.

; #define Z 32
; typedef struct s {
;       int v1[Z];
;       int v2[Z];
;       int v3[Z][Z];
; } s;
;
; void slow_function (s* const obj, int z) {
;    for (int j=0; j<Z; j++) {
;        for (int k=0; k<z; k++) {
;            int x = obj->v1[k] + obj->v2[j];
;            obj->v3[j][k] += x;
;        }
;    }
; }

target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"

%struct.s = type { [32 x i32], [32 x i32], [32 x [32 x i32]] }

define void @Test(%struct.s* nocapture %obj, i64 %z) #0 {
; CHECK-LABEL: @Test(
; CHECK-NEXT:    [[OBJ4:%.*]] = bitcast %struct.s* [[OBJ:%.*]] to i8*
; CHECK-NEXT:    [[SCEVGEP5:%.*]] = getelementptr [[STRUCT_S:%.*]], %struct.s* [[OBJ]], i64 0, i32 0, i64 [[Z:%.*]]
; CHECK-NEXT:    [[SCEVGEP56:%.*]] = bitcast i32* [[SCEVGEP5]] to i8*
; CHECK-NEXT:    br label [[DOTOUTER_PREHEADER:%.*]]
; CHECK:       .outer.preheader:
; CHECK-NEXT:    [[I:%.*]] = phi i64 [ 0, [[TMP0:%.*]] ], [ [[I_NEXT:%.*]], [[DOTOUTER:%.*]] ]
; CHECK-NEXT:    [[SCEVGEP:%.*]] = getelementptr [[STRUCT_S]], %struct.s* [[OBJ]], i64 0, i32 2, i64 [[I]], i64 0
; CHECK-NEXT:    [[SCEVGEP1:%.*]] = bitcast i32* [[SCEVGEP]] to i8*
; CHECK-NEXT:    [[SCEVGEP2:%.*]] = getelementptr [[STRUCT_S]], %struct.s* [[OBJ]], i64 0, i32 2, i64 [[I]], i64 [[Z]]
; CHECK-NEXT:    [[SCEVGEP23:%.*]] = bitcast i32* [[SCEVGEP2]] to i8*
; CHECK-NEXT:    [[SCEVGEP7:%.*]] = getelementptr [[STRUCT_S]], %struct.s* [[OBJ]], i64 0, i32 1, i64 [[I]]
; CHECK-NEXT:    [[SCEVGEP78:%.*]] = bitcast i32* [[SCEVGEP7]] to i8*
; CHECK-NEXT:    [[TMP1:%.*]] = add i64 [[I]], 1
; CHECK-NEXT:    [[SCEVGEP9:%.*]] = getelementptr [[STRUCT_S]], %struct.s* [[OBJ]], i64 0, i32 1, i64 [[TMP1]]
; CHECK-NEXT:    [[SCEVGEP910:%.*]] = bitcast i32* [[SCEVGEP9]] to i8*
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.s* [[OBJ]], i64 0, i32 1, i64 [[I]]
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[Z]], 4
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_MEMCHECK:%.*]]
; CHECK:       vector.memcheck:
; CHECK-NEXT:    [[BOUND0:%.*]] = icmp ult i8* [[SCEVGEP1]], [[SCEVGEP56]]
; CHECK-NEXT:    [[BOUND1:%.*]] = icmp ult i8* [[OBJ4]], [[SCEVGEP23]]
; CHECK-NEXT:    [[FOUND_CONFLICT:%.*]] = and i1 [[BOUND0]], [[BOUND1]]
; CHECK-NEXT:    [[BOUND011:%.*]] = icmp ult i8* [[SCEVGEP1]], [[SCEVGEP910]]
; CHECK-NEXT:    [[BOUND112:%.*]] = icmp ult i8* [[SCEVGEP78]], [[SCEVGEP23]]
; CHECK-NEXT:    [[FOUND_CONFLICT13:%.*]] = and i1 [[BOUND011]], [[BOUND112]]
; CHECK-NEXT:    [[CONFLICT_RDX:%.*]] = or i1 [[FOUND_CONFLICT]], [[FOUND_CONFLICT13]]
; CHECK-NEXT:    br i1 [[CONFLICT_RDX]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[Z]], 4
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[Z]], [[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:    [[TMP3:%.*]] = add i64 [[INDEX]], 0
; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.s* [[OBJ]], i64 0, i32 0, i64 [[TMP3]]
; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i32, i32* [[TMP4]], i32 0
; CHECK-NEXT:    [[TMP6:%.*]] = bitcast i32* [[TMP5]] to <4 x i32>*
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP6]], align 4, !alias.scope !0
; CHECK-NEXT:    [[TMP7:%.*]] = load i32, i32* [[TMP2]], align 4, !alias.scope !3
; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> poison, i32 [[TMP7]], i32 0
; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> poison, <4 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP8:%.*]] = add nsw <4 x i32> [[BROADCAST_SPLAT]], [[WIDE_LOAD]]
; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.s* [[OBJ]], i64 0, i32 2, i64 [[I]], i64 [[TMP3]]
; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr inbounds i32, i32* [[TMP9]], i32 0
; CHECK-NEXT:    [[TMP11:%.*]] = bitcast i32* [[TMP10]] to <4 x i32>*
; CHECK-NEXT:    [[WIDE_LOAD14:%.*]] = load <4 x i32>, <4 x i32>* [[TMP11]], align 4, !alias.scope !5, !noalias !7
; CHECK-NEXT:    [[TMP12:%.*]] = add nsw <4 x i32> [[TMP8]], [[WIDE_LOAD14]]
; CHECK-NEXT:    [[TMP13:%.*]] = bitcast i32* [[TMP10]] to <4 x i32>*
; CHECK-NEXT:    store <4 x i32> [[TMP12]], <4 x i32>* [[TMP13]], align 4, !alias.scope !5, !noalias !7
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT:    [[TMP14:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP14]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[Z]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[CMP_N]], label [[DOTOUTER]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[DOTOUTER_PREHEADER]] ], [ 0, [[VECTOR_MEMCHECK]] ]
; CHECK-NEXT:    br label [[DOTINNER:%.*]]
; CHECK:       .exit:
; CHECK-NEXT:    ret void
; CHECK:       .outer:
; CHECK-NEXT:    [[I_NEXT]] = add nuw nsw i64 [[I]], 1
; CHECK-NEXT:    [[EXITCOND_OUTER:%.*]] = icmp eq i64 [[I_NEXT]], 32
; CHECK-NEXT:    br i1 [[EXITCOND_OUTER]], label [[DOTEXIT:%.*]], label [[DOTOUTER_PREHEADER]]
; CHECK:       .inner:
; CHECK-NEXT:    [[J:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[J_NEXT:%.*]], [[DOTINNER]] ]
; CHECK-NEXT:    [[TMP15:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.s* [[OBJ]], i64 0, i32 0, i64 [[J]]
; CHECK-NEXT:    [[TMP16:%.*]] = load i32, i32* [[TMP15]], align 4
; CHECK-NEXT:    [[TMP17:%.*]] = load i32, i32* [[TMP2]], align 4
; CHECK-NEXT:    [[TMP18:%.*]] = add nsw i32 [[TMP17]], [[TMP16]]
; CHECK-NEXT:    [[TMP19:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.s* [[OBJ]], i64 0, i32 2, i64 [[I]], i64 [[J]]
; CHECK-NEXT:    [[TMP20:%.*]] = load i32, i32* [[TMP19]], align 4
; CHECK-NEXT:    [[TMP21:%.*]] = add nsw i32 [[TMP18]], [[TMP20]]
; CHECK-NEXT:    store i32 [[TMP21]], i32* [[TMP19]], align 4
; CHECK-NEXT:    [[J_NEXT]] = add nuw nsw i64 [[J]], 1
; CHECK-NEXT:    [[EXITCOND_INNER:%.*]] = icmp eq i64 [[J_NEXT]], [[Z]]
; CHECK-NEXT:    br i1 [[EXITCOND_INNER]], label [[DOTOUTER]], label [[DOTINNER]], !llvm.loop [[LOOP10:![0-9]+]]
;
  br label %.outer.preheader


.outer.preheader:
  %i = phi i64 [ 0, %0 ], [ %i.next, %.outer ]
  %1 = getelementptr inbounds %struct.s, %struct.s* %obj, i64 0, i32 1, i64 %i
  br label %.inner

.exit:
  ret void

.outer:
  %i.next = add nuw nsw i64 %i, 1
  %exitcond.outer = icmp eq i64 %i.next, 32
  br i1 %exitcond.outer, label %.exit, label %.outer.preheader

.inner:
  %j = phi i64 [ 0, %.outer.preheader ], [ %j.next, %.inner ]
  %2 = getelementptr inbounds %struct.s, %struct.s* %obj, i64 0, i32 0, i64 %j
  %3 = load i32, i32* %2
  %4 = load i32, i32* %1
  %5 = add nsw i32 %4, %3
  %6 = getelementptr inbounds %struct.s, %struct.s* %obj, i64 0, i32 2, i64 %i, i64 %j
  %7 = load i32, i32* %6
  %8 = add nsw i32 %5, %7
  store i32 %8, i32* %6
  %j.next = add nuw nsw i64 %j, 1
  %exitcond.inner = icmp eq i64 %j.next, %z
  br i1 %exitcond.inner, label %.outer, label %.inner
}