[llvm] [VPlan] Compute the cost for vector icmp and fcmp (PR #193268)

[John Brawn via llvm-commits]

================
@@ -573,54 +573,14 @@ define void @wide_iv_trunc(ptr %dst, i64 %N) {
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp ult i64 [[N]], 8
 ; CHECK-NEXT:    br i1 [[CMP]], label %[[LOOP_PREHEADER:.*]], label %[[EXIT:.*]]
 ; CHECK:       [[LOOP_PREHEADER]]:
-; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[N]], 1
-; CHECK-NEXT:    br label %[[VECTOR_PH:.*]]
-; CHECK:       [[VECTOR_PH]]:
-; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i64 [[TMP0]], 3
-; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], 4
-; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
-; CHECK-NEXT:    [[TRIP_COUNT_MINUS_1:%.*]] = sub i64 [[TMP0]], 1
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> poison, i64 [[TRIP_COUNT_MINUS_1]], i64 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> poison, <4 x i32> zeroinitializer
 ; CHECK-NEXT:    br label %[[VECTOR_BODY:.*]]
 ; CHECK:       [[VECTOR_BODY]]:
-; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[PRED_STORE_CONTINUE6:.*]] ]
-; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <4 x i64> [ <i64 0, i64 1, i64 2, i64 3>, %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], %[[PRED_STORE_CONTINUE6]] ]
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ [[IV_NEXT:%.*]], %[[VECTOR_BODY]] ], [ 0, %[[LOOP_PREHEADER]] ]
 ; CHECK-NEXT:    [[TMP1:%.*]] = trunc i64 [[INDEX]] to i32
-; CHECK-NEXT:    [[TMP2:%.*]] = icmp ule <4 x i64> [[VEC_IND]], [[BROADCAST_SPLAT]]
-; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x i1> [[TMP2]], i64 0
-; CHECK-NEXT:    br i1 [[TMP3]], label %[[PRED_STORE_IF:.*]], label %[[PRED_STORE_CONTINUE:.*]]
-; CHECK:       [[PRED_STORE_IF]]:
 ; CHECK-NEXT:    store i32 [[TMP1]], ptr [[DST]], align 4
-; CHECK-NEXT:    br label %[[PRED_STORE_CONTINUE]]
-; CHECK:       [[PRED_STORE_CONTINUE]]:
-; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <4 x i1> [[TMP2]], i64 1
-; CHECK-NEXT:    br i1 [[TMP5]], label %[[PRED_STORE_IF1:.*]], label %[[PRED_STORE_CONTINUE2:.*]]
-; CHECK:       [[PRED_STORE_IF1]]:
-; CHECK-NEXT:    [[TMP6:%.*]] = add i32 [[TMP1]], 1
-; CHECK-NEXT:    store i32 [[TMP6]], ptr [[DST]], align 4
-; CHECK-NEXT:    br label %[[PRED_STORE_CONTINUE2]]
-; CHECK:       [[PRED_STORE_CONTINUE2]]:
-; CHECK-NEXT:    [[TMP7:%.*]] = extractelement <4 x i1> [[TMP2]], i64 2
-; CHECK-NEXT:    br i1 [[TMP7]], label %[[PRED_STORE_IF3:.*]], label %[[PRED_STORE_CONTINUE4:.*]]
-; CHECK:       [[PRED_STORE_IF3]]:
-; CHECK-NEXT:    [[TMP8:%.*]] = add i32 [[TMP1]], 2
-; CHECK-NEXT:    store i32 [[TMP8]], ptr [[DST]], align 4
-; CHECK-NEXT:    br label %[[PRED_STORE_CONTINUE4]]
-; CHECK:       [[PRED_STORE_CONTINUE4]]:
-; CHECK-NEXT:    [[TMP9:%.*]] = extractelement <4 x i1> [[TMP2]], i64 3
-; CHECK-NEXT:    br i1 [[TMP9]], label %[[PRED_STORE_IF5:.*]], label %[[PRED_STORE_CONTINUE6]]
-; CHECK:       [[PRED_STORE_IF5]]:
-; CHECK-NEXT:    [[TMP10:%.*]] = add i32 [[TMP1]], 3
-; CHECK-NEXT:    store i32 [[TMP10]], ptr [[DST]], align 4
-; CHECK-NEXT:    br label %[[PRED_STORE_CONTINUE6]]
-; CHECK:       [[PRED_STORE_CONTINUE6]]:
-; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
-; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i64> [[VEC_IND]], splat (i64 4)
-; CHECK-NEXT:    [[TMP11:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT:    br i1 [[TMP11]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP27:![0-9]+]]
-; CHECK:       [[MIDDLE_BLOCK]]:
-; CHECK-NEXT:    br label %[[EXIT_LOOPEXIT:.*]]
+; CHECK-NEXT:    [[IV_NEXT]] = add i64 [[INDEX]], 1
+; CHECK-NEXT:    [[EC:%.*]] = icmp eq i64 [[INDEX]], [[N]]
+; CHECK-NEXT:    br i1 [[EC]], label %[[EXIT_LOOPEXIT:.*]], label %[[VECTOR_BODY]]
----------------
john-brawn-arm wrote:

Done

https://github.com/llvm/llvm-project/pull/193268