[llvm] [VPlan] Use llvm.masked.{u, s}{div, rem} for predicated division (PR #191377)

[Luke Lau via llvm-commits]

================
@@ -683,29 +671,44 @@ define void @udiv_sdiv_with_invariant_divisors(i8 %x, i16 %y, i1 %c, ptr %p) {
 ; FIXED-NEXT:  entry:
 ; FIXED-NEXT:    br label [[VECTOR_PH:%.*]]
 ; FIXED:       vector.ph:
-; FIXED-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i16> poison, i16 [[Y:%.*]], i64 0
-; FIXED-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i16> [[BROADCAST_SPLATINSERT]], <4 x i16> poison, <4 x i32> zeroinitializer
-; FIXED-NEXT:    [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <4 x i8> poison, i8 [[X:%.*]], i64 0
-; FIXED-NEXT:    [[BROADCAST_SPLAT2:%.*]] = shufflevector <4 x i8> [[BROADCAST_SPLATINSERT1]], <4 x i8> poison, <4 x i32> zeroinitializer
-; FIXED-NEXT:    [[TMP0:%.*]] = select i1 [[C:%.*]], <4 x i8> splat (i8 1), <4 x i8> [[BROADCAST_SPLAT2]]
-; FIXED-NEXT:    [[TMP1:%.*]] = select i1 [[C]], <4 x i16> splat (i16 1), <4 x i16> [[BROADCAST_SPLAT]]
+; FIXED-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <8 x i1> poison, i1 [[C:%.*]], i64 0
+; FIXED-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <8 x i1> [[BROADCAST_SPLATINSERT]], <8 x i1> poison, <8 x i32> zeroinitializer
+; FIXED-NEXT:    [[TMP0:%.*]] = xor <8 x i1> [[BROADCAST_SPLAT]], splat (i1 true)
+; FIXED-NEXT:    [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <8 x i8> poison, i8 [[X:%.*]], i64 0
+; FIXED-NEXT:    [[BROADCAST_SPLAT2:%.*]] = shufflevector <8 x i8> [[BROADCAST_SPLATINSERT1]], <8 x i8> poison, <8 x i32> zeroinitializer
+; FIXED-NEXT:    [[BROADCAST_SPLATINSERT3:%.*]] = insertelement <8 x i16> poison, i16 [[Y:%.*]], i64 0
+; FIXED-NEXT:    [[BROADCAST_SPLAT4:%.*]] = shufflevector <8 x i16> [[BROADCAST_SPLATINSERT3]], <8 x i16> poison, <8 x i32> zeroinitializer
 ; FIXED-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; FIXED:       vector.body:
-; FIXED-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; FIXED-NEXT:    [[VEC_IND:%.*]] = phi <4 x i8> [ <i8 -12, i8 -11, i8 -10, i8 -9>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
-; FIXED-NEXT:    [[TMP3:%.*]] = udiv <4 x i8> [[VEC_IND]], [[TMP0]]
-; FIXED-NEXT:    [[TMP4:%.*]] = zext <4 x i8> [[TMP3]] to <4 x i16>
-; FIXED-NEXT:    [[TMP5:%.*]] = sdiv <4 x i16> [[TMP4]], [[TMP1]]
-; FIXED-NEXT:    [[TMP6:%.*]] = sext <4 x i16> [[TMP5]] to <4 x i32>
-; FIXED-NEXT:    [[PREDPHI:%.*]] = select i1 [[C]], <4 x i32> zeroinitializer, <4 x i32> [[TMP6]]
-; FIXED-NEXT:    [[TMP7:%.*]] = extractelement <4 x i32> [[PREDPHI]], i32 3
+; FIXED-NEXT:    [[TMP1:%.*]] = call <8 x i8> @llvm.masked.udiv.v8i8(<8 x i8> <i8 -12, i8 -11, i8 -10, i8 -9, i8 -8, i8 -7, i8 -6, i8 -5>, <8 x i8> [[BROADCAST_SPLAT2]], <8 x i1> [[TMP0]])
----------------
lukel97 wrote:

This diff is now gone after #192543 but it's really just because we've removed the select costs. The above item about the known trip count could probably still be explored

https://github.com/llvm/llvm-project/pull/191377