Index: llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
===================================================================
--- llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -1437,9 +1437,13 @@
     return (Cost + 1) * LT.first;
 
   case ISD::FADD:
+  case ISD::FSUB:
+  case ISD::FMUL:
+  case ISD::FDIV:
+  case ISD::FNEG:
     // These nodes are marked as 'custom' just to lower them to SVE.
     // We know said lowering will incur no additional cost.
-    if (isa<FixedVectorType>(Ty) && !Ty->getScalarType()->isFP128Ty())
+    if (!Ty->getScalarType()->isFP128Ty())
       return (Cost + 2) * LT.first;
 
     return Cost + BaseT::getArithmeticInstrCost(Opcode, Ty, CostKind, Opd1Info,
Index: llvm/test/Analysis/CostModel/AArch64/arith-fp-sve.ll
===================================================================
--- /dev/null
+++ llvm/test/Analysis/CostModel/AArch64/arith-fp-sve.ll
@@ -0,0 +1,134 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
+; RUN: opt < %s -enable-no-nans-fp-math -cost-model -analyze -mtriple=aarch64 -mattr=+fullfp16 -mattr=+sve | FileCheck %s
+
+define void @fadd() {
+; CHECK-LABEL: 'fadd'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F16 = fadd <vscale x 4 x half> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F16 = fadd <vscale x 8 x half> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = fadd <vscale x 16 x half> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F32 = fadd <vscale x 2 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = fadd <vscale x 4 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = fadd <vscale x 8 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = fadd <vscale x 2 x double> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = fadd <vscale x 4 x double> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+  %V4F16 = fadd <vscale x 4 x half> undef, undef
+  %V8F16 = fadd <vscale x 8 x half> undef, undef
+  %V16F16 = fadd <vscale x 16 x half> undef, undef
+
+  %V2F32 = fadd <vscale x 2 x float> undef, undef
+  %V4F32 = fadd <vscale x 4 x float> undef, undef
+  %V8F32 = fadd <vscale x 8 x float> undef, undef
+
+  %V2F64 = fadd <vscale x 2 x double> undef, undef
+  %V4F64 = fadd <vscale x 4 x double> undef, undef
+
+  ret void
+}
+
+define void @fsub() {
+; CHECK-LABEL: 'fsub'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F16 = fsub <vscale x 4 x half> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F16 = fsub <vscale x 8 x half> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = fsub <vscale x 16 x half> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F32 = fsub <vscale x 2 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = fsub <vscale x 4 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = fsub <vscale x 8 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = fsub <vscale x 2 x double> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = fsub <vscale x 4 x double> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+  %V4F16 = fsub <vscale x 4 x half> undef, undef
+  %V8F16 = fsub <vscale x 8 x half> undef, undef
+  %V16F16 = fsub <vscale x 16 x half> undef, undef
+
+  %V2F32 = fsub <vscale x 2 x float> undef, undef
+  %V4F32 = fsub <vscale x 4 x float> undef, undef
+  %V8F32 = fsub <vscale x 8 x float> undef, undef
+
+  %V2F64 = fsub <vscale x 2 x double> undef, undef
+  %V4F64 = fsub <vscale x 4 x double> undef, undef
+
+  ret void
+}
+
+define void @fneg() {
+; CHECK-LABEL: 'fneg'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F16 = fneg <vscale x 2 x half> undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F16 = fneg <vscale x 4 x half> undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F16 = fneg <vscale x 8 x half> undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = fneg <vscale x 16 x half> undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F32 = fneg <vscale x 2 x float> undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = fneg <vscale x 4 x float> undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = fneg <vscale x 8 x float> undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = fneg <vscale x 2 x double> undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = fneg <vscale x 4 x double> undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+  %V2F16 = fneg <vscale x 2 x half> undef
+  %V4F16 = fneg <vscale x 4 x half> undef
+  %V8F16 = fneg <vscale x 8 x half> undef
+  %V16F16 = fneg <vscale x 16 x half> undef
+
+  %V2F32 = fneg <vscale x 2 x float> undef
+  %V4F32 = fneg <vscale x 4 x float> undef
+  %V8F32 = fneg <vscale x 8 x float> undef
+
+  %V2F64 = fneg <vscale x 2 x double> undef
+  %V4F64 = fneg <vscale x 4 x double> undef
+
+  ret void
+}
+
+define void @fmul() {
+; CHECK-LABEL: 'fmul'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F16 = fmul <vscale x 4 x half> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F16 = fmul <vscale x 8 x half> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = fmul <vscale x 16 x half> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F32 = fmul <vscale x 2 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = fmul <vscale x 4 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = fmul <vscale x 8 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = fmul <vscale x 2 x double> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = fmul <vscale x 4 x double> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+  %V4F16 = fmul <vscale x 4 x half> undef, undef
+  %V8F16 = fmul <vscale x 8 x half> undef, undef
+  %V16F16 = fmul <vscale x 16 x half> undef, undef
+
+  %V2F32 = fmul <vscale x 2 x float> undef, undef
+  %V4F32 = fmul <vscale x 4 x float> undef, undef
+  %V8F32 = fmul <vscale x 8 x float> undef, undef
+
+  %V2F64 = fmul <vscale x 2 x double> undef, undef
+  %V4F64 = fmul <vscale x 4 x double> undef, undef
+
+  ret void
+}
+
+define void @fdiv() {
+; CHECK-LABEL: 'fdiv'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F16 = fdiv <vscale x 4 x half> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F16 = fdiv <vscale x 8 x half> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = fdiv <vscale x 16 x half> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F32 = fdiv <vscale x 2 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = fdiv <vscale x 4 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = fdiv <vscale x 8 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = fdiv <vscale x 2 x double> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = fdiv <vscale x 4 x double> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+  %V4F16 = fdiv <vscale x 4 x half> undef, undef
+  %V8F16 = fdiv <vscale x 8 x half> undef, undef
+  %V16F16 = fdiv <vscale x 16 x half> undef, undef
+
+  %V2F32 = fdiv <vscale x 2 x float> undef, undef
+  %V4F32 = fdiv <vscale x 4 x float> undef, undef
+  %V8F32 = fdiv <vscale x 8 x float> undef, undef
+
+  %V2F64 = fdiv <vscale x 2 x double> undef, undef
+  %V4F64 = fdiv <vscale x 4 x double> undef, undef
+
+  ret void
+}
Index: llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll
===================================================================
--- llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll
+++ llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll
@@ -59,7 +59,7 @@
   %smax_nxv4i64 = call i64 @llvm.vector.reduce.smax.nxv4i64(<vscale x 4 x i64> %v1)
 
 ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %fadd_nxv4f32 = call fast float @llvm.vector.reduce.fadd.nxv4f32(float 0.000000e+00, <vscale x 4 x float> %v2)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %fadd_nxv4f64 = call fast double @llvm.vector.reduce.fadd.nxv4f64(double 0.000000e+00, <vscale x 4 x double> %v3)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %fadd_nxv4f64 = call fast double @llvm.vector.reduce.fadd.nxv4f64(double 0.000000e+00, <vscale x 4 x double> %v3)
 ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %fmin_nxv4f32 = call fast float @llvm.vector.reduce.fmin.nxv4f32(<vscale x 4 x float> %v2)
 ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %fmin_nxv4f64 = call fast double @llvm.vector.reduce.fmin.nxv4f64(<vscale x 4 x double> %v3)
 ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %fmax_nxv4f32 = call fast float @llvm.vector.reduce.fmax.nxv4f32(<vscale x 4 x float> %v2)
Index: llvm/test/Analysis/CostModel/AArch64/sve-math.ll
===================================================================
--- llvm/test/Analysis/CostModel/AArch64/sve-math.ll
+++ llvm/test/Analysis/CostModel/AArch64/sve-math.ll
@@ -8,7 +8,7 @@
 
 define <vscale x 2 x double> @fadd_v2f64(<vscale x 2 x double> %a, <vscale x 2 x double> %b) {
 ; THRU-LABEL: 'fadd_v2f64'
-; THRU-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %r = fadd <vscale x 2 x double> %a, %b
+; THRU-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %r = fadd <vscale x 2 x double> %a, %b
 ; THRU-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <vscale x 2 x double> %r
 ;
 ; LATE-LABEL: 'fadd_v2f64'