[LLVM][CodeGen][AArch64] Don't scalarise v8{f16,bf16} vsetcc operations.

I have also removed custom promotion code for the v4{f16,bf16} cases
because the same common code can be used.

Author: paulwalker-arm

llvm/lib/Target/AArch64/AArch64ISelLowering.cpp

@@ -840,18 +840,21 @@ AArch64TargetLowering::AArch64TargetLowering(const TargetMachine &TM,
     setOperationPromotedToType(ISD::FRINT,      V4Narrow, MVT::v4f32);
     setOperationPromotedToType(ISD::FNEARBYINT, V4Narrow, MVT::v4f32);
     setOperationPromotedToType(ISD::FCANONICALIZE, V4Narrow, MVT::v4f32);
+    setOperationPromotedToType(ISD::SETCC,         V4Narrow, MVT::v4f32);
 
     setOperationAction(ISD::FABS,        V4Narrow, Legal);
-    setOperationAction(ISD::FNEG, 	 V4Narrow, Legal);
+    setOperationAction(ISD::FNEG,        V4Narrow, Legal);
     setOperationAction(ISD::FMA,         V4Narrow, Expand);
-    setOperationAction(ISD::SETCC,       V4Narrow, Custom);
     setOperationAction(ISD::BR_CC,       V4Narrow, Expand);
     setOperationAction(ISD::SELECT,      V4Narrow, Expand);
     setOperationAction(ISD::SELECT_CC,   V4Narrow, Expand);
     setOperationAction(ISD::FCOPYSIGN,   V4Narrow, Custom);
     setOperationAction(ISD::FSQRT,       V4Narrow, Expand);
 
     auto V8Narrow = MVT::getVectorVT(ScalarVT, 8);
+    setOperationPromotedToType(ISD::FCANONICALIZE, V8Narrow, MVT::v8f32);
+    setOperationPromotedToType(ISD::SETCC,         V8Narrow, MVT::v8f32);
+
     setOperationAction(ISD::FABS,        V8Narrow, Legal);
     setOperationAction(ISD::FADD,        V8Narrow, Legal);
     setOperationAction(ISD::FCEIL,       V8Narrow, Legal);
@@ -861,19 +864,17 @@ AArch64TargetLowering::AArch64TargetLowering(const TargetMachine &TM,
     setOperationAction(ISD::FMA,         V8Narrow, Expand);
     setOperationAction(ISD::FMUL,        V8Narrow, Legal);
     setOperationAction(ISD::FNEARBYINT,  V8Narrow, Legal);
-    setOperationAction(ISD::FNEG, 	 V8Narrow, Legal);
+    setOperationAction(ISD::FNEG,        V8Narrow, Legal);
     setOperationAction(ISD::FROUND,      V8Narrow, Legal);
     setOperationAction(ISD::FROUNDEVEN,  V8Narrow, Legal);
     setOperationAction(ISD::FRINT,       V8Narrow, Legal);
     setOperationAction(ISD::FSQRT,       V8Narrow, Expand);
     setOperationAction(ISD::FSUB,        V8Narrow, Legal);
     setOperationAction(ISD::FTRUNC,      V8Narrow, Legal);
-    setOperationAction(ISD::SETCC,       V8Narrow, Expand);
     setOperationAction(ISD::BR_CC,       V8Narrow, Expand);
     setOperationAction(ISD::SELECT,      V8Narrow, Expand);
     setOperationAction(ISD::SELECT_CC,   V8Narrow, Expand);
     setOperationAction(ISD::FP_EXTEND,   V8Narrow, Expand);
-    setOperationPromotedToType(ISD::FCANONICALIZE, V8Narrow, MVT::v8f32);
   };
 
   if (!Subtarget->hasFullFP16()) {
@@ -15898,6 +15899,11 @@ SDValue AArch64TargetLowering::LowerVSETCC(SDValue Op,
   if (LHS.getValueType().getVectorElementType().isInteger())
     return Op;
 
+  assert((!Subtarget->hasFullFP16() &&
+          LHS.getValueType().getVectorElementType() != MVT::f16) ||
+         LHS.getValueType().getVectorElementType() != MVT::bf16 ||
+         LHS.getValueType().getVectorElementType() != MVT::f128);
+
   // Lower isnan(x) | isnan(never-nan) to x != x.
   // Lower !isnan(x) & !isnan(never-nan) to x == x.
   if (CC == ISD::SETUO || CC == ISD::SETO) {
@@ -15916,26 +15922,6 @@ SDValue AArch64TargetLowering::LowerVSETCC(SDValue Op,
     }
   }
 
-  const bool FullFP16 = DAG.getSubtarget<AArch64Subtarget>().hasFullFP16();
-
-  // Make v4f16 (only) fcmp operations utilise vector instructions
-  // v8f16 support will be a litle more complicated
-  if ((!FullFP16 && LHS.getValueType().getVectorElementType() == MVT::f16) ||
-      LHS.getValueType().getVectorElementType() == MVT::bf16) {
-    if (LHS.getValueType().getVectorNumElements() == 4) {
-      LHS = DAG.getNode(ISD::FP_EXTEND, dl, MVT::v4f32, LHS);
-      RHS = DAG.getNode(ISD::FP_EXTEND, dl, MVT::v4f32, RHS);
-      SDValue NewSetcc = DAG.getSetCC(dl, MVT::v4i16, LHS, RHS, CC);
-      DAG.ReplaceAllUsesWith(Op, NewSetcc);
-      CmpVT = MVT::v4i32;
-    } else
-      return SDValue();
-  }
-
-  assert((!FullFP16 && LHS.getValueType().getVectorElementType() != MVT::f16) ||
-         LHS.getValueType().getVectorElementType() != MVT::bf16 ||
-         LHS.getValueType().getVectorElementType() != MVT::f128);
-
   // Unfortunately, the mapping of LLVM FP CC's onto AArch64 CC's isn't totally
   // clean.  Some of them require two branches to implement.
   AArch64CC::CondCode CC1, CC2;

llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp

@@ -4241,11 +4241,6 @@ InstructionCost AArch64TTIImpl::getCmpSelInstrCost(
         ValScalarTy->isBFloatTy()) {
       auto *ValVTy = cast<FixedVectorType>(ValTy);
 
-      // FIXME: We currently scalarise these.
-      if (ValVTy->getNumElements() > 4)
-        return BaseT::getCmpSelInstrCost(Opcode, ValTy, CondTy, VecPred,
-                                         CostKind, Op1Info, Op2Info, I);
-
       // Without dedicated instructions we promote [b]f16 compares to f32.
       auto *PromotedTy =
           VectorType::get(Type::getFloatTy(ValTy->getContext()), ValVTy);

llvm/test/Analysis/CostModel/AArch64/cmp.ll

@@ -17,10 +17,10 @@ define void @cmps() {
 ; CHECK-NEXT:  Cost Model: Found costs of 1 for: %cf32 = fcmp ogt float undef, undef
 ; CHECK-NEXT:  Cost Model: Found costs of 1 for: %cf64 = fcmp ogt double undef, undef
 ; CHECK-NEXT:  Cost Model: Found costs of 1 for: %cbf64 = fcmp ogt bfloat undef, undef
-; CHECK-NEXT:  Cost Model: Found costs of RThru:22 CodeSize:1 Lat:1 SizeLat:1 for: %cfv816 = fcmp olt <8 x half> undef, undef
+; CHECK-NEXT:  Cost Model: Found costs of RThru:7 CodeSize:1 Lat:1 SizeLat:1 for: %cfv816 = fcmp olt <8 x half> undef, undef
 ; CHECK-NEXT:  Cost Model: Found costs of 1 for: %cfv432 = fcmp oge <4 x float> undef, undef
 ; CHECK-NEXT:  Cost Model: Found costs of 1 for: %cfv264 = fcmp oge <2 x double> undef, undef
-; CHECK-NEXT:  Cost Model: Found costs of RThru:22 CodeSize:1 Lat:1 SizeLat:1 for: %cbfv816 = fcmp olt <8 x bfloat> undef, undef
+; CHECK-NEXT:  Cost Model: Found costs of RThru:7 CodeSize:1 Lat:1 SizeLat:1 for: %cbfv816 = fcmp olt <8 x bfloat> undef, undef
 ; CHECK-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
 ;
   %c8 = icmp slt i8 undef, undef

llvm/test/Analysis/CostModel/AArch64/vector-select.ll

@@ -119,7 +119,7 @@ define <4 x half> @v4f16_select_ogt(<4 x half> %a, <4 x half> %b, <4 x half> %c)
 
 define <8 x half> @v8f16_select_ogt(<8 x half> %a, <8 x half> %b, <8 x half> %c) {
 ; COST-NOFP16-LABEL: 'v8f16_select_ogt'
-; COST-NOFP16-NEXT:  Cost Model: Found costs of RThru:22 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp ogt <8 x half> %a, %b
+; COST-NOFP16-NEXT:  Cost Model: Found costs of RThru:7 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp ogt <8 x half> %a, %b
 ; COST-NOFP16-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:1 SizeLat:1 for: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
 ; COST-NOFP16-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <8 x half> %s.1
 ;
@@ -179,7 +179,7 @@ define <4 x bfloat> @v4bf16_select_ogt(<4 x bfloat> %a, <4 x bfloat> %b, <4 x bf
 
 define <8 x bfloat> @v8bf16_select_ogt(<8 x bfloat> %a, <8 x bfloat> %b, <8 x bfloat> %c) {
 ; COST-LABEL: 'v8bf16_select_ogt'
-; COST-NEXT:  Cost Model: Found costs of RThru:22 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp ogt <8 x bfloat> %a, %b
+; COST-NEXT:  Cost Model: Found costs of RThru:7 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp ogt <8 x bfloat> %a, %b
 ; COST-NEXT:  Cost Model: Found costs of RThru:22 CodeSize:1 Lat:1 SizeLat:1 for: %s.1 = select <8 x i1> %cmp.1, <8 x bfloat> %a, <8 x bfloat> %c
 ; COST-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <8 x bfloat> %s.1
 ;
@@ -206,7 +206,7 @@ define <4 x half> @v4f16_select_oge(<4 x half> %a, <4 x half> %b, <4 x half> %c)
 
 define <8 x half> @v8f16_select_oge(<8 x half> %a, <8 x half> %b, <8 x half> %c) {
 ; COST-NOFP16-LABEL: 'v8f16_select_oge'
-; COST-NOFP16-NEXT:  Cost Model: Found costs of RThru:22 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp oge <8 x half> %a, %b
+; COST-NOFP16-NEXT:  Cost Model: Found costs of RThru:7 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp oge <8 x half> %a, %b
 ; COST-NOFP16-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:1 SizeLat:1 for: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
 ; COST-NOFP16-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <8 x half> %s.1
 ;
@@ -266,7 +266,7 @@ define <4 x bfloat> @v4bf16_select_oge(<4 x bfloat> %a, <4 x bfloat> %b, <4 x bf
 
 define <8 x bfloat> @v8bf16_select_oge(<8 x bfloat> %a, <8 x bfloat> %b, <8 x bfloat> %c) {
 ; COST-LABEL: 'v8bf16_select_oge'
-; COST-NEXT:  Cost Model: Found costs of RThru:22 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp oge <8 x bfloat> %a, %b
+; COST-NEXT:  Cost Model: Found costs of RThru:7 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp oge <8 x bfloat> %a, %b
 ; COST-NEXT:  Cost Model: Found costs of RThru:22 CodeSize:1 Lat:1 SizeLat:1 for: %s.1 = select <8 x i1> %cmp.1, <8 x bfloat> %a, <8 x bfloat> %c
 ; COST-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <8 x bfloat> %s.1
 ;
@@ -293,7 +293,7 @@ define <4 x half> @v4f16_select_olt(<4 x half> %a, <4 x half> %b, <4 x half> %c)
 
 define <8 x half> @v8f16_select_olt(<8 x half> %a, <8 x half> %b, <8 x half> %c) {
 ; COST-NOFP16-LABEL: 'v8f16_select_olt'
-; COST-NOFP16-NEXT:  Cost Model: Found costs of RThru:22 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp olt <8 x half> %a, %b
+; COST-NOFP16-NEXT:  Cost Model: Found costs of RThru:7 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp olt <8 x half> %a, %b
 ; COST-NOFP16-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:1 SizeLat:1 for: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
 ; COST-NOFP16-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <8 x half> %s.1
 ;
@@ -353,7 +353,7 @@ define <4 x bfloat> @v4bf16_select_olt(<4 x bfloat> %a, <4 x bfloat> %b, <4 x bf
 
 define <8 x bfloat> @v8bf16_select_olt(<8 x bfloat> %a, <8 x bfloat> %b, <8 x bfloat> %c) {
 ; COST-LABEL: 'v8bf16_select_olt'
-; COST-NEXT:  Cost Model: Found costs of RThru:22 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp olt <8 x bfloat> %a, %b
+; COST-NEXT:  Cost Model: Found costs of RThru:7 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp olt <8 x bfloat> %a, %b
 ; COST-NEXT:  Cost Model: Found costs of RThru:22 CodeSize:1 Lat:1 SizeLat:1 for: %s.1 = select <8 x i1> %cmp.1, <8 x bfloat> %a, <8 x bfloat> %c
 ; COST-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <8 x bfloat> %s.1
 ;
@@ -380,7 +380,7 @@ define <4 x half> @v4f16_select_ole(<4 x half> %a, <4 x half> %b, <4 x half> %c)
 
 define <8 x half> @v8f16_select_ole(<8 x half> %a, <8 x half> %b, <8 x half> %c) {
 ; COST-NOFP16-LABEL: 'v8f16_select_ole'
-; COST-NOFP16-NEXT:  Cost Model: Found costs of RThru:22 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp ole <8 x half> %a, %b
+; COST-NOFP16-NEXT:  Cost Model: Found costs of RThru:7 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp ole <8 x half> %a, %b
 ; COST-NOFP16-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:1 SizeLat:1 for: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
 ; COST-NOFP16-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <8 x half> %s.1
 ;
@@ -440,7 +440,7 @@ define <4 x bfloat> @v4bf16_select_ole(<4 x bfloat> %a, <4 x bfloat> %b, <4 x bf
 
 define <8 x bfloat> @v8bf16_select_ole(<8 x bfloat> %a, <8 x bfloat> %b, <8 x bfloat> %c) {
 ; COST-LABEL: 'v8bf16_select_ole'
-; COST-NEXT:  Cost Model: Found costs of RThru:22 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp ole <8 x bfloat> %a, %b
+; COST-NEXT:  Cost Model: Found costs of RThru:7 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp ole <8 x bfloat> %a, %b
 ; COST-NEXT:  Cost Model: Found costs of RThru:22 CodeSize:1 Lat:1 SizeLat:1 for: %s.1 = select <8 x i1> %cmp.1, <8 x bfloat> %a, <8 x bfloat> %c
 ; COST-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <8 x bfloat> %s.1
 ;
@@ -467,7 +467,7 @@ define <4 x half> @v4f16_select_oeq(<4 x half> %a, <4 x half> %b, <4 x half> %c)
 
 define <8 x half> @v8f16_select_oeq(<8 x half> %a, <8 x half> %b, <8 x half> %c) {
 ; COST-NOFP16-LABEL: 'v8f16_select_oeq'
-; COST-NOFP16-NEXT:  Cost Model: Found costs of RThru:22 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp oeq <8 x half> %a, %b
+; COST-NOFP16-NEXT:  Cost Model: Found costs of RThru:7 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp oeq <8 x half> %a, %b
 ; COST-NOFP16-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:1 SizeLat:1 for: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
 ; COST-NOFP16-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <8 x half> %s.1
 ;
@@ -527,7 +527,7 @@ define <4 x bfloat> @v4bf16_select_oeq(<4 x bfloat> %a, <4 x bfloat> %b, <4 x bf
 
 define <8 x bfloat> @v8bf16_select_oeq(<8 x bfloat> %a, <8 x bfloat> %b, <8 x bfloat> %c) {
 ; COST-LABEL: 'v8bf16_select_oeq'
-; COST-NEXT:  Cost Model: Found costs of RThru:22 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp oeq <8 x bfloat> %a, %b
+; COST-NEXT:  Cost Model: Found costs of RThru:7 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp oeq <8 x bfloat> %a, %b
 ; COST-NEXT:  Cost Model: Found costs of RThru:22 CodeSize:1 Lat:1 SizeLat:1 for: %s.1 = select <8 x i1> %cmp.1, <8 x bfloat> %a, <8 x bfloat> %c
 ; COST-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <8 x bfloat> %s.1
 ;
@@ -554,7 +554,7 @@ define <4 x half> @v4f16_select_one(<4 x half> %a, <4 x half> %b, <4 x half> %c)
 
 define <8 x half> @v8f16_select_one(<8 x half> %a, <8 x half> %b, <8 x half> %c) {
 ; COST-NOFP16-LABEL: 'v8f16_select_one'
-; COST-NOFP16-NEXT:  Cost Model: Found costs of RThru:22 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp one <8 x half> %a, %b
+; COST-NOFP16-NEXT:  Cost Model: Found costs of RThru:7 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp one <8 x half> %a, %b
 ; COST-NOFP16-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:1 SizeLat:1 for: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
 ; COST-NOFP16-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <8 x half> %s.1
 ;
@@ -614,7 +614,7 @@ define <4 x bfloat> @v4bf16_select_one(<4 x bfloat> %a, <4 x bfloat> %b, <4 x bf
 
 define <8 x bfloat> @v8bf16_select_one(<8 x bfloat> %a, <8 x bfloat> %b, <8 x bfloat> %c) {
 ; COST-LABEL: 'v8bf16_select_one'
-; COST-NEXT:  Cost Model: Found costs of RThru:22 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp one <8 x bfloat> %a, %b
+; COST-NEXT:  Cost Model: Found costs of RThru:7 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp one <8 x bfloat> %a, %b
 ; COST-NEXT:  Cost Model: Found costs of RThru:22 CodeSize:1 Lat:1 SizeLat:1 for: %s.1 = select <8 x i1> %cmp.1, <8 x bfloat> %a, <8 x bfloat> %c
 ; COST-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <8 x bfloat> %s.1
 ;
@@ -641,7 +641,7 @@ define <4 x half> @v4f16_select_une(<4 x half> %a, <4 x half> %b, <4 x half> %c)
 
 define <8 x half> @v8f16_select_une(<8 x half> %a, <8 x half> %b, <8 x half> %c) {
 ; COST-NOFP16-LABEL: 'v8f16_select_une'
-; COST-NOFP16-NEXT:  Cost Model: Found costs of RThru:22 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp une <8 x half> %a, %b
+; COST-NOFP16-NEXT:  Cost Model: Found costs of RThru:7 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp une <8 x half> %a, %b
 ; COST-NOFP16-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:1 SizeLat:1 for: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
 ; COST-NOFP16-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <8 x half> %s.1
 ;
@@ -701,7 +701,7 @@ define <4 x bfloat> @v4bf16_select_une(<4 x bfloat> %a, <4 x bfloat> %b, <4 x bf
 
 define <8 x bfloat> @v8bf16_select_une(<8 x bfloat> %a, <8 x bfloat> %b, <8 x bfloat> %c) {
 ; COST-LABEL: 'v8bf16_select_une'
-; COST-NEXT:  Cost Model: Found costs of RThru:22 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp une <8 x bfloat> %a, %b
+; COST-NEXT:  Cost Model: Found costs of RThru:7 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp une <8 x bfloat> %a, %b
 ; COST-NEXT:  Cost Model: Found costs of RThru:22 CodeSize:1 Lat:1 SizeLat:1 for: %s.1 = select <8 x i1> %cmp.1, <8 x bfloat> %a, <8 x bfloat> %c
 ; COST-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <8 x bfloat> %s.1
 ;
@@ -728,7 +728,7 @@ define <4 x half> @v4f16_select_ord(<4 x half> %a, <4 x half> %b, <4 x half> %c)
 
 define <8 x half> @v8f16_select_ord(<8 x half> %a, <8 x half> %b, <8 x half> %c) {
 ; COST-NOFP16-LABEL: 'v8f16_select_ord'
-; COST-NOFP16-NEXT:  Cost Model: Found costs of RThru:22 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp ord <8 x half> %a, %b
+; COST-NOFP16-NEXT:  Cost Model: Found costs of RThru:7 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp ord <8 x half> %a, %b
 ; COST-NOFP16-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:1 SizeLat:1 for: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
 ; COST-NOFP16-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <8 x half> %s.1
 ;
@@ -788,7 +788,7 @@ define <4 x bfloat> @v4bf16_select_ord(<4 x bfloat> %a, <4 x bfloat> %b, <4 x bf
 
 define <8 x bfloat> @v8bf16_select_ord(<8 x bfloat> %a, <8 x bfloat> %b, <8 x bfloat> %c) {
 ; COST-LABEL: 'v8bf16_select_ord'
-; COST-NEXT:  Cost Model: Found costs of RThru:22 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp ord <8 x bfloat> %a, %b
+; COST-NEXT:  Cost Model: Found costs of RThru:7 CodeSize:1 Lat:1 SizeLat:1 for: %cmp.1 = fcmp ord <8 x bfloat> %a, %b
 ; COST-NEXT:  Cost Model: Found costs of RThru:22 CodeSize:1 Lat:1 SizeLat:1 for: %s.1 = select <8 x i1> %cmp.1, <8 x bfloat> %a, <8 x bfloat> %c
 ; COST-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <8 x bfloat> %s.1
 ;