[llvm] LV: clamp VF with TC only when scalar epilogue is needed (PR #91253)

[Florian Hahn via llvm-commits]

================
@@ -252,36 +252,46 @@ for.end:                                          ; preds = %for.body
 define void @trip16_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture noundef readonly %src) #0 {
 ; CHECK-LABEL: @trip16_i8(
 ; CHECK-NEXT:  entry:
-; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 8
+; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 16, [[TMP1]]
+; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; CHECK:       vector.ph:
+; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 8
+; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 16, [[TMP3]]
+; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 16, [[N_MOD_VF]]
+; CHECK-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP5:%.*]] = mul i64 [[TMP4]], 8
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
-; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i8, ptr [[SRC:%.*]], i64 [[TMP0]]
-; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i8, ptr [[TMP1]], i32 0
-; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <16 x i8>, ptr [[TMP2]], align 1
-; CHECK-NEXT:    [[TMP3:%.*]] = shl <16 x i8> [[WIDE_LOAD]], <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
-; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i8, ptr [[DST:%.*]], i64 [[TMP0]]
-; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i8, ptr [[TMP4]], i32 0
-; CHECK-NEXT:    [[WIDE_LOAD1:%.*]] = load <16 x i8>, ptr [[TMP5]], align 1
-; CHECK-NEXT:    [[TMP6:%.*]] = add <16 x i8> [[TMP3]], [[WIDE_LOAD1]]
-; CHECK-NEXT:    store <16 x i8> [[TMP6]], ptr [[TMP5]], align 1
-; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 16
+; CHECK-NEXT:    [[TMP6:%.*]] = add i64 [[INDEX]], 0
+; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i8, ptr [[SRC:%.*]], i64 [[TMP6]]
+; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr inbounds i8, ptr [[TMP7]], i32 0
+; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 8 x i8>, ptr [[TMP8]], align 1
+; CHECK-NEXT:    [[TMP9:%.*]] = shl <vscale x 8 x i8> [[WIDE_LOAD]], shufflevector (<vscale x 8 x i8> insertelement (<vscale x 8 x i8> poison, i8 1, i64 0), <vscale x 8 x i8> poison, <vscale x 8 x i32> zeroinitializer)
+; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr inbounds i8, ptr [[DST:%.*]], i64 [[TMP6]]
+; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr inbounds i8, ptr [[TMP10]], i32 0
+; CHECK-NEXT:    [[WIDE_LOAD1:%.*]] = load <vscale x 8 x i8>, ptr [[TMP11]], align 1
+; CHECK-NEXT:    [[TMP12:%.*]] = add <vscale x 8 x i8> [[TMP9]], [[WIDE_LOAD1]]
+; CHECK-NEXT:    store <vscale x 8 x i8> [[TMP12]], ptr [[TMP11]], align 1
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP5]]
----------------
fhahn wrote:

Are any of the test changes profitable? I'd assume at least for this one vectorizing with VF 16 as done previously is more profitable, as we know that we execute exactly one vector iteration?

https://github.com/llvm/llvm-project/pull/91253