[LV] Disable forcing interleaving for uncountable early exit loops (#147993)

Interleaving does not currently work properly when vectorising loops
with uncountable early exits. Interleaving is already disabled for
normal vectorisation and for the pragma/hint - this patch also disables
it when using -force-vector-interleave.

Author: david-arm

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

@@ -10061,8 +10061,7 @@ bool LoopVectorizePass::processLoop(Loop *L) {
   // Get user vectorization factor and interleave count.
   ElementCount UserVF = Hints.getWidth();
   unsigned UserIC = Hints.getInterleave();
-  if (LVL.hasUncountableEarlyExit() && UserIC != 1 &&
-      !VectorizerParams::isInterleaveForced()) {
+  if (LVL.hasUncountableEarlyExit() && UserIC != 1) {
     UserIC = 1;
     reportVectorizationInfo("Interleaving not supported for loops "
                             "with uncountable early exits",

llvm/test/Transforms/LoopVectorize/AArch64/single-early-exit-interleave.ll

@@ -14,60 +14,29 @@ define i64 @same_exit_block_pre_inc_use1() #0 {
 ; CHECK-NEXT:    call void @init_mem(ptr [[P1]], i64 1024)
 ; CHECK-NEXT:    call void @init_mem(ptr [[P2]], i64 1024)
 ; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP1:%.*]] = mul nuw i64 [[TMP0]], 64
-; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 510, [[TMP1]]
-; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK-NEXT:    [[TMP1:%.*]] = mul nuw i64 [[TMP0]], 16
+; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; CHECK:       vector.ph:
 ; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP3:%.*]] = mul nuw i64 [[TMP2]], 64
+; CHECK-NEXT:    [[TMP3:%.*]] = mul nuw i64 [[TMP2]], 16
 ; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 510, [[TMP3]]
 ; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 510, [[N_MOD_VF]]
 ; CHECK-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP5:%.*]] = mul nuw i64 [[TMP4]], 64
+; CHECK-NEXT:    [[TMP5:%.*]] = mul nuw i64 [[TMP4]], 16
 ; CHECK-NEXT:    [[INDEX_NEXT:%.*]] = add i64 3, [[N_VEC]]
 ; CHECK-NEXT:    br label [[LOOP:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX1:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT3:%.*]], [[LOOP]] ]
 ; CHECK-NEXT:    [[OFFSET_IDX:%.*]] = add i64 3, [[INDEX1]]
 ; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i8, ptr [[P1]], i64 [[OFFSET_IDX]]
 ; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr inbounds i8, ptr [[TMP7]], i32 0
-; CHECK-NEXT:    [[TMP18:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP19:%.*]] = mul nuw i64 [[TMP18]], 16
-; CHECK-NEXT:    [[TMP29:%.*]] = getelementptr inbounds i8, ptr [[TMP7]], i64 [[TMP19]]
-; CHECK-NEXT:    [[TMP36:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP37:%.*]] = mul nuw i64 [[TMP36]], 32
-; CHECK-NEXT:    [[TMP38:%.*]] = getelementptr inbounds i8, ptr [[TMP7]], i64 [[TMP37]]
-; CHECK-NEXT:    [[TMP39:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP40:%.*]] = mul nuw i64 [[TMP39]], 48
-; CHECK-NEXT:    [[TMP41:%.*]] = getelementptr inbounds i8, ptr [[TMP7]], i64 [[TMP40]]
-; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 16 x i8>, ptr [[TMP8]], align 1
-; CHECK-NEXT:    [[WIDE_LOAD5:%.*]] = load <vscale x 16 x i8>, ptr [[TMP29]], align 1
-; CHECK-NEXT:    [[WIDE_LOAD3:%.*]] = load <vscale x 16 x i8>, ptr [[TMP38]], align 1
-; CHECK-NEXT:    [[WIDE_LOAD4:%.*]] = load <vscale x 16 x i8>, ptr [[TMP41]], align 1
+; CHECK-NEXT:    [[WIDE_LOAD4:%.*]] = load <vscale x 16 x i8>, ptr [[TMP8]], align 1
 ; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr inbounds i8, ptr [[P2]], i64 [[OFFSET_IDX]]
 ; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr inbounds i8, ptr [[TMP9]], i32 0
-; CHECK-NEXT:    [[TMP20:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP21:%.*]] = mul nuw i64 [[TMP20]], 16
-; CHECK-NEXT:    [[TMP22:%.*]] = getelementptr inbounds i8, ptr [[TMP9]], i64 [[TMP21]]
-; CHECK-NEXT:    [[TMP23:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP24:%.*]] = mul nuw i64 [[TMP23]], 32
-; CHECK-NEXT:    [[TMP25:%.*]] = getelementptr inbounds i8, ptr [[TMP9]], i64 [[TMP24]]
-; CHECK-NEXT:    [[TMP26:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP27:%.*]] = mul nuw i64 [[TMP26]], 48
-; CHECK-NEXT:    [[TMP28:%.*]] = getelementptr inbounds i8, ptr [[TMP9]], i64 [[TMP27]]
-; CHECK-NEXT:    [[WIDE_LOAD2:%.*]] = load <vscale x 16 x i8>, ptr [[TMP10]], align 1
-; CHECK-NEXT:    [[WIDE_LOAD6:%.*]] = load <vscale x 16 x i8>, ptr [[TMP22]], align 1
-; CHECK-NEXT:    [[WIDE_LOAD7:%.*]] = load <vscale x 16 x i8>, ptr [[TMP25]], align 1
-; CHECK-NEXT:    [[WIDE_LOAD8:%.*]] = load <vscale x 16 x i8>, ptr [[TMP28]], align 1
-; CHECK-NEXT:    [[TMP11:%.*]] = icmp ne <vscale x 16 x i8> [[WIDE_LOAD]], [[WIDE_LOAD2]]
-; CHECK-NEXT:    [[TMP30:%.*]] = icmp ne <vscale x 16 x i8> [[WIDE_LOAD5]], [[WIDE_LOAD6]]
-; CHECK-NEXT:    [[TMP31:%.*]] = icmp ne <vscale x 16 x i8> [[WIDE_LOAD3]], [[WIDE_LOAD7]]
+; CHECK-NEXT:    [[WIDE_LOAD8:%.*]] = load <vscale x 16 x i8>, ptr [[TMP10]], align 1
 ; CHECK-NEXT:    [[TMP32:%.*]] = icmp ne <vscale x 16 x i8> [[WIDE_LOAD4]], [[WIDE_LOAD8]]
 ; CHECK-NEXT:    [[INDEX_NEXT3]] = add nuw i64 [[INDEX1]], [[TMP5]]
-; CHECK-NEXT:    [[TMP33:%.*]] = or <vscale x 16 x i1> [[TMP11]], [[TMP30]]
-; CHECK-NEXT:    [[TMP34:%.*]] = or <vscale x 16 x i1> [[TMP33]], [[TMP31]]
-; CHECK-NEXT:    [[TMP35:%.*]] = or <vscale x 16 x i1> [[TMP34]], [[TMP32]]
-; CHECK-NEXT:    [[TMP12:%.*]] = call i1 @llvm.vector.reduce.or.nxv16i1(<vscale x 16 x i1> [[TMP35]])
+; CHECK-NEXT:    [[TMP12:%.*]] = call i1 @llvm.vector.reduce.or.nxv16i1(<vscale x 16 x i1> [[TMP32]])
 ; CHECK-NEXT:    [[TMP13:%.*]] = icmp eq i64 [[INDEX_NEXT3]], [[N_VEC]]
 ; CHECK-NEXT:    [[TMP14:%.*]] = or i1 [[TMP12]], [[TMP13]]
 ; CHECK-NEXT:    br i1 [[TMP14]], label [[MIDDLE_SPLIT:%.*]], label [[LOOP]], !llvm.loop [[LOOP0:![0-9]+]]
@@ -77,26 +46,7 @@ define i64 @same_exit_block_pre_inc_use1() #0 {
 ; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 510, [[N_VEC]]
 ; CHECK-NEXT:    br i1 [[CMP_N]], label [[LOOP_END:%.*]], label [[SCALAR_PH]]
 ; CHECK:       vector.early.exit:
-; CHECK-NEXT:    [[TMP63:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP42:%.*]] = mul nuw i64 [[TMP63]], 16
-; CHECK-NEXT:    [[TMP44:%.*]] = call i64 @llvm.experimental.cttz.elts.i64.nxv16i1(<vscale x 16 x i1> [[TMP32]], i1 true)
-; CHECK-NEXT:    [[TMP62:%.*]] = mul i64 [[TMP42]], 3
-; CHECK-NEXT:    [[TMP45:%.*]] = add i64 [[TMP62]], [[TMP44]]
-; CHECK-NEXT:    [[TMP46:%.*]] = call i64 @llvm.experimental.cttz.elts.i64.nxv16i1(<vscale x 16 x i1> [[TMP31]], i1 true)
-; CHECK-NEXT:    [[TMP58:%.*]] = mul i64 [[TMP42]], 2
-; CHECK-NEXT:    [[TMP50:%.*]] = add i64 [[TMP58]], [[TMP46]]
-; CHECK-NEXT:    [[TMP47:%.*]] = icmp ne i64 [[TMP46]], [[TMP42]]
-; CHECK-NEXT:    [[TMP51:%.*]] = select i1 [[TMP47]], i64 [[TMP50]], i64 [[TMP45]]
-; CHECK-NEXT:    [[TMP52:%.*]] = call i64 @llvm.experimental.cttz.elts.i64.nxv16i1(<vscale x 16 x i1> [[TMP30]], i1 true)
-; CHECK-NEXT:    [[TMP64:%.*]] = mul i64 [[TMP42]], 1
-; CHECK-NEXT:    [[TMP56:%.*]] = add i64 [[TMP64]], [[TMP52]]
-; CHECK-NEXT:    [[TMP53:%.*]] = icmp ne i64 [[TMP52]], [[TMP42]]
-; CHECK-NEXT:    [[TMP57:%.*]] = select i1 [[TMP53]], i64 [[TMP56]], i64 [[TMP51]]
-; CHECK-NEXT:    [[TMP15:%.*]] = call i64 @llvm.experimental.cttz.elts.i64.nxv16i1(<vscale x 16 x i1> [[TMP11]], i1 true)
-; CHECK-NEXT:    [[TMP65:%.*]] = mul i64 [[TMP42]], 0
-; CHECK-NEXT:    [[TMP60:%.*]] = add i64 [[TMP65]], [[TMP15]]
-; CHECK-NEXT:    [[TMP59:%.*]] = icmp ne i64 [[TMP15]], [[TMP42]]
-; CHECK-NEXT:    [[TMP61:%.*]] = select i1 [[TMP59]], i64 [[TMP60]], i64 [[TMP57]]
+; CHECK-NEXT:    [[TMP61:%.*]] = call i64 @llvm.experimental.cttz.elts.i64.nxv16i1(<vscale x 16 x i1> [[TMP32]], i1 true)
 ; CHECK-NEXT:    [[TMP16:%.*]] = add i64 [[INDEX1]], [[TMP61]]
 ; CHECK-NEXT:    [[TMP17:%.*]] = add i64 3, [[TMP16]]
 ; CHECK-NEXT:    br label [[LOOP_END]]