[llvm] [VPlan] Impl VPlan-based pattern match for ExtendedRed and MulAccRed (NFCI) (PR #113903)

[Elvis Wang via llvm-commits]

================
@@ -187,26 +187,36 @@ define i32 @add_i16_i32(ptr nocapture readonly %x, i32 %n) {
 ; IF-EVL-INLOOP-NEXT:    [[N_RND_UP:%.*]] = add i32 [[N]], [[TMP2]]
 ; IF-EVL-INLOOP-NEXT:    [[N_MOD_VF:%.*]] = urem i32 [[N_RND_UP]], [[TMP1]]
 ; IF-EVL-INLOOP-NEXT:    [[N_VEC:%.*]] = sub i32 [[N_RND_UP]], [[N_MOD_VF]]
+; IF-EVL-INLOOP-NEXT:    [[TRIP_COUNT_MINUS_1:%.*]] = sub i32 [[N]], 1
 ; IF-EVL-INLOOP-NEXT:    [[TMP3:%.*]] = call i32 @llvm.vscale.i32()
 ; IF-EVL-INLOOP-NEXT:    [[TMP4:%.*]] = mul i32 [[TMP3]], 8
+; IF-EVL-INLOOP-NEXT:    [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <vscale x 8 x i32> poison, i32 [[TRIP_COUNT_MINUS_1]], i64 0
+; IF-EVL-INLOOP-NEXT:    [[BROADCAST_SPLAT2:%.*]] = shufflevector <vscale x 8 x i32> [[BROADCAST_SPLATINSERT1]], <vscale x 8 x i32> poison, <vscale x 8 x i32> zeroinitializer
 ; IF-EVL-INLOOP-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; IF-EVL-INLOOP:       vector.body:
 ; IF-EVL-INLOOP-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; IF-EVL-INLOOP-NEXT:    [[EVL_BASED_IV:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; IF-EVL-INLOOP-NEXT:    [[VEC_PHI:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[TMP11:%.*]], [[VECTOR_BODY]] ]
-; IF-EVL-INLOOP-NEXT:    [[TMP5:%.*]] = sub i32 [[N]], [[EVL_BASED_IV]]
-; IF-EVL-INLOOP-NEXT:    [[TMP6:%.*]] = call i32 @llvm.experimental.get.vector.length.i32(i32 [[TMP5]], i32 8, i1 true)
-; IF-EVL-INLOOP-NEXT:    [[TMP7:%.*]] = add i32 [[EVL_BASED_IV]], 0
-; IF-EVL-INLOOP-NEXT:    [[TMP8:%.*]] = getelementptr inbounds i16, ptr [[X:%.*]], i32 [[TMP7]]
-; IF-EVL-INLOOP-NEXT:    [[TMP9:%.*]] = getelementptr inbounds i16, ptr [[TMP8]], i32 0
-; IF-EVL-INLOOP-NEXT:    [[VP_OP_LOAD:%.*]] = call <vscale x 8 x i16> @llvm.vp.load.nxv8i16.p0(ptr align 2 [[TMP9]], <vscale x 8 x i1> splat (i1 true), i32 [[TMP6]])
-; IF-EVL-INLOOP-NEXT:    [[TMP14:%.*]] = call <vscale x 8 x i32> @llvm.vp.sext.nxv8i32.nxv8i16(<vscale x 8 x i16> [[VP_OP_LOAD]], <vscale x 8 x i1> splat (i1 true), i32 [[TMP6]])
-; IF-EVL-INLOOP-NEXT:    [[TMP10:%.*]] = call i32 @llvm.vp.reduce.add.nxv8i32(i32 0, <vscale x 8 x i32> [[TMP14]], <vscale x 8 x i1> splat (i1 true), i32 [[TMP6]])
-; IF-EVL-INLOOP-NEXT:    [[TMP11]] = add i32 [[TMP10]], [[VEC_PHI]]
-; IF-EVL-INLOOP-NEXT:    [[INDEX_EVL_NEXT]] = add nuw i32 [[TMP6]], [[EVL_BASED_IV]]
+; IF-EVL-INLOOP-NEXT:    [[AVL:%.*]] = sub i32 [[N]], [[EVL_BASED_IV]]
+; IF-EVL-INLOOP-NEXT:    [[TMP5:%.*]] = call i32 @llvm.experimental.get.vector.length.i32(i32 [[AVL]], i32 8, i1 true)
+; IF-EVL-INLOOP-NEXT:    [[TMP6:%.*]] = add i32 [[EVL_BASED_IV]], 0
+; IF-EVL-INLOOP-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 8 x i32> poison, i32 [[EVL_BASED_IV]], i64 0
+; IF-EVL-INLOOP-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 8 x i32> [[BROADCAST_SPLATINSERT]], <vscale x 8 x i32> poison, <vscale x 8 x i32> zeroinitializer
+; IF-EVL-INLOOP-NEXT:    [[TMP7:%.*]] = call <vscale x 8 x i32> @llvm.stepvector.nxv8i32()
+; IF-EVL-INLOOP-NEXT:    [[TMP8:%.*]] = add <vscale x 8 x i32> zeroinitializer, [[TMP7]]
+; IF-EVL-INLOOP-NEXT:    [[VEC_IV:%.*]] = add <vscale x 8 x i32> [[BROADCAST_SPLAT]], [[TMP8]]
+; IF-EVL-INLOOP-NEXT:    [[TMP9:%.*]] = icmp ule <vscale x 8 x i32> [[VEC_IV]], [[BROADCAST_SPLAT2]]
+; IF-EVL-INLOOP-NEXT:    [[TMP10:%.*]] = getelementptr inbounds i16, ptr [[X:%.*]], i32 [[TMP6]]
+; IF-EVL-INLOOP-NEXT:    [[TMP15:%.*]] = getelementptr inbounds i16, ptr [[TMP10]], i32 0
+; IF-EVL-INLOOP-NEXT:    [[VP_OP_LOAD:%.*]] = call <vscale x 8 x i16> @llvm.vp.load.nxv8i16.p0(ptr align 2 [[TMP15]], <vscale x 8 x i1> splat (i1 true), i32 [[TMP5]])
+; IF-EVL-INLOOP-NEXT:    [[TMP12:%.*]] = sext <vscale x 8 x i16> [[VP_OP_LOAD]] to <vscale x 8 x i32>
+; IF-EVL-INLOOP-NEXT:    [[TMP17:%.*]] = select <vscale x 8 x i1> [[TMP9]], <vscale x 8 x i32> [[TMP12]], <vscale x 8 x i32> zeroinitializer
+; IF-EVL-INLOOP-NEXT:    [[TMP14:%.*]] = call i32 @llvm.vector.reduce.add.nxv8i32(<vscale x 8 x i32> [[TMP17]])
+; IF-EVL-INLOOP-NEXT:    [[TMP11]] = add i32 [[TMP14]], [[VEC_PHI]]
+; IF-EVL-INLOOP-NEXT:    [[INDEX_EVL_NEXT]] = add nuw i32 [[TMP5]], [[EVL_BASED_IV]]
----------------
ElvisWang123 wrote:

Prevent create these abstract recipes when using tail-folding with EVL since we haven't supported yet.

https://github.com/llvm/llvm-project/pull/113903