Index: llvm/test/Analysis/CostModel/RISCV/arith-fp.ll
===================================================================
--- llvm/test/Analysis/CostModel/RISCV/arith-fp.ll
+++ llvm/test/Analysis/CostModel/RISCV/arith-fp.ll
@@ -643,6 +643,67 @@
   ret i32 undef
 }
 
+define void @fmuladd() {
+; CHECK-LABEL: 'fmuladd'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %1 = call half @llvm.fmuladd.f16(half undef, half undef, half undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %2 = call float @llvm.fmuladd.f32(float undef, float undef, float undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %3 = call double @llvm.fmuladd.f64(double undef, double undef, double undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %4 = call <2 x half> @llvm.fmuladd.v2f16(<2 x half> undef, <2 x half> undef, <2 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %5 = call <4 x half> @llvm.fmuladd.v4f16(<4 x half> undef, <4 x half> undef, <4 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %6 = call <8 x half> @llvm.fmuladd.v8f16(<8 x half> undef, <8 x half> undef, <8 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %7 = call <16 x half> @llvm.fmuladd.v16f16(<16 x half> undef, <16 x half> undef, <16 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %8 = call <2 x float> @llvm.fmuladd.v2f32(<2 x float> undef, <2 x float> undef, <2 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %9 = call <4 x float> @llvm.fmuladd.v4f32(<4 x float> undef, <4 x float> undef, <4 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %10 = call <8 x float> @llvm.fmuladd.v8f32(<8 x float> undef, <8 x float> undef, <8 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %11 = call <16 x float> @llvm.fmuladd.v16f32(<16 x float> undef, <16 x float> undef, <16 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %12 = call <2 x double> @llvm.fmuladd.v2f64(<2 x double> undef, <2 x double> undef, <2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %13 = call <4 x double> @llvm.fmuladd.v4f64(<4 x double> undef, <4 x double> undef, <4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %14 = call <8 x double> @llvm.fmuladd.v8f64(<8 x double> undef, <8 x double> undef, <8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %15 = call <16 x double> @llvm.fmuladd.v16f64(<16 x double> undef, <16 x double> undef, <16 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 2 x half> @llvm.fmuladd.nxv2f16(<vscale x 2 x half> undef, <vscale x 2 x half> undef, <vscale x 2 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 4 x half> @llvm.fmuladd.nxv4f16(<vscale x 4 x half> undef, <vscale x 4 x half> undef, <vscale x 4 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 8 x half> @llvm.fmuladd.nxv8f16(<vscale x 8 x half> undef, <vscale x 8 x half> undef, <vscale x 8 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %19 = call <vscale x 16 x half> @llvm.fmuladd.nxv16f16(<vscale x 16 x half> undef, <vscale x 16 x half> undef, <vscale x 16 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %20 = call <vscale x 2 x float> @llvm.fmuladd.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef, <vscale x 2 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %21 = call <vscale x 4 x float> @llvm.fmuladd.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef, <vscale x 4 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %22 = call <vscale x 8 x float> @llvm.fmuladd.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef, <vscale x 8 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %23 = call <vscale x 16 x float> @llvm.fmuladd.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef, <vscale x 16 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %24 = call <vscale x 2 x double> @llvm.fmuladd.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef, <vscale x 2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %25 = call <vscale x 4 x double> @llvm.fmuladd.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef, <vscale x 4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 8 x double> @llvm.fmuladd.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef, <vscale x 8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %27 = call <vscale x 16 x double> @llvm.fmuladd.nxv16f64(<vscale x 16 x double> undef, <vscale x 16 x double> undef, <vscale x 16 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
+;
+  call half @llvm.fmuladd.f16(half undef, half undef, half undef)
+  call float @llvm.fmuladd.f32(float undef, float undef, float undef)
+  call double @llvm.fmuladd.f64(double undef, double undef, double undef)
+  call <2 x half> @llvm.fmuladd.v2f16(<2 x half> undef, <2 x half> undef, <2 x half> undef)
+  call <4 x half> @llvm.fmuladd.v4f16(<4 x half> undef, <4 x half> undef, <4 x half> undef)
+  call <8 x half> @llvm.fmuladd.v8f16(<8 x half> undef, <8 x half> undef, <8 x half> undef)
+  call <16 x half> @llvm.fmuladd.v16f16(<16 x half> undef, <16 x half> undef, <16 x half> undef)
+  call <2 x float> @llvm.fmuladd.v2f32(<2 x float> undef, <2 x float> undef, <2 x float> undef)
+  call <4 x float> @llvm.fmuladd.v4f32(<4 x float> undef, <4 x float> undef, <4 x float> undef)
+  call <8 x float> @llvm.fmuladd.v8f32(<8 x float> undef, <8 x float> undef, <8 x float> undef)
+  call <16 x float> @llvm.fmuladd.v16f32(<16 x float> undef, <16 x float> undef, <16 x float> undef)
+  call <2 x double> @llvm.fmuladd.v2f64(<2 x double> undef, <2 x double> undef, <2 x double> undef)
+  call <4 x double> @llvm.fmuladd.v4f64(<4 x double> undef, <4 x double> undef, <4 x double> undef)
+  call <8 x double> @llvm.fmuladd.v8f64(<8 x double> undef, <8 x double> undef, <8 x double> undef)
+  call <16 x double> @llvm.fmuladd.v16f64(<16 x double> undef, <16 x double> undef, <16 x double> undef)
+  call <vscale x 2 x half> @llvm.fmuladd.nxv2f16(<vscale x 2 x half> undef, <vscale x 2 x half> undef, <vscale x 2 x half> undef)
+  call <vscale x 4 x half> @llvm.fmuladd.nxv4f16(<vscale x 4 x half> undef, <vscale x 4 x half> undef, <vscale x 4 x half> undef)
+  call <vscale x 8 x half> @llvm.fmuladd.nxv8f16(<vscale x 8 x half> undef, <vscale x 8 x half> undef, <vscale x 8 x half> undef)
+  call <vscale x 16 x half> @llvm.fmuladd.nxv16f16(<vscale x 16 x half> undef, <vscale x 16 x half> undef, <vscale x 16 x half> undef)
+  call <vscale x 2 x float> @llvm.fmuladd.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef, <vscale x 2 x float> undef)
+  call <vscale x 4 x float> @llvm.fmuladd.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef, <vscale x 4 x float> undef)
+  call <vscale x 8 x float> @llvm.fmuladd.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef, <vscale x 8 x float> undef)
+  call <vscale x 16 x float> @llvm.fmuladd.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef, <vscale x 16 x float> undef)
+  call <vscale x 2 x double> @llvm.fmuladd.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef, <vscale x 2 x double> undef)
+  call <vscale x 4 x double> @llvm.fmuladd.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef, <vscale x 4 x double> undef)
+  call <vscale x 8 x double> @llvm.fmuladd.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef, <vscale x 8 x double> undef)
+  call <vscale x 16 x double> @llvm.fmuladd.nxv16f64(<vscale x 16 x double> undef, <vscale x 16 x double> undef, <vscale x 16 x double> undef)
+  ret void
+}
+
 declare half @llvm.copysign.f16(half, half)
 declare float @llvm.copysign.f32(float, float)
 declare double @llvm.copysign.f64(double, double)
@@ -722,3 +783,31 @@
 declare <vscale x 2 x double> @llvm.fma.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>)
 declare <vscale x 4 x double> @llvm.fma.nxv4f64(<vscale x 4 x double>, <vscale x 4 x double>, <vscale x 4 x double>)
 declare <vscale x 8 x double> @llvm.fma.nxv8f64(<vscale x 8 x double>, <vscale x 8 x double>, <vscale x 8 x double>)
+
+declare half @llvm.fmuladd.f16(half, half, half)
+declare float @llvm.fmuladd.f32(float, float, float)
+declare double @llvm.fmuladd.f64(double, double, double)
+declare <2 x half> @llvm.fmuladd.v2f16(<2 x half>, <2 x half>, <2 x half>)
+declare <4 x half> @llvm.fmuladd.v4f16(<4 x half>, <4 x half>, <4 x half>)
+declare <8 x half> @llvm.fmuladd.v8f16(<8 x half>, <8 x half>, <8 x half>)
+declare <16 x half> @llvm.fmuladd.v16f16(<16 x half>, <16 x half>, <16 x half>)
+declare <2 x float> @llvm.fmuladd.v2f32(<2 x float>, <2 x float>, <2 x float>)
+declare <4 x float> @llvm.fmuladd.v4f32(<4 x float>, <4 x float>, <4 x float>)
+declare <8 x float> @llvm.fmuladd.v8f32(<8 x float>, <8 x float>, <8 x float>)
+declare <16 x float> @llvm.fmuladd.v16f32(<16 x float>, <16 x float>, <16 x float>)
+declare <2 x double> @llvm.fmuladd.v2f64(<2 x double>, <2 x double>, <2 x double>)
+declare <4 x double> @llvm.fmuladd.v4f64(<4 x double>, <4 x double>, <4 x double>)
+declare <8 x double> @llvm.fmuladd.v8f64(<8 x double>, <8 x double>, <8 x double>)
+declare <16 x double> @llvm.fmuladd.v16f64(<16 x double>, <16 x double>, <16 x double>)
+declare <vscale x 2 x half> @llvm.fmuladd.nxv2f16(<vscale x 2 x half>, <vscale x 2 x half>, <vscale x 2 x half>)
+declare <vscale x 4 x half> @llvm.fmuladd.nxv4f16(<vscale x 4 x half>, <vscale x 4 x half>, <vscale x 4 x half>)
+declare <vscale x 8 x half> @llvm.fmuladd.nxv8f16(<vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>)
+declare <vscale x 16 x half> @llvm.fmuladd.nxv16f16(<vscale x 16 x half>, <vscale x 16 x half>, <vscale x 16 x half>)
+declare <vscale x 2 x float> @llvm.fmuladd.nxv2f32(<vscale x 2 x float>, <vscale x 2 x float>, <vscale x 2 x float>)
+declare <vscale x 4 x float> @llvm.fmuladd.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>)
+declare <vscale x 8 x float> @llvm.fmuladd.nxv8f32(<vscale x 8 x float>, <vscale x 8 x float>, <vscale x 8 x float>)
+declare <vscale x 16 x float> @llvm.fmuladd.nxv16f32(<vscale x 16 x float>, <vscale x 16 x float>, <vscale x 16 x float>)
+declare <vscale x 2 x double> @llvm.fmuladd.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>)
+declare <vscale x 4 x double> @llvm.fmuladd.nxv4f64(<vscale x 4 x double>, <vscale x 4 x double>, <vscale x 4 x double>)
+declare <vscale x 8 x double> @llvm.fmuladd.nxv8f64(<vscale x 8 x double>, <vscale x 8 x double>, <vscale x 8 x double>)
+declare <vscale x 16 x double> @llvm.fmuladd.nxv16f64(<vscale x 16 x double>, <vscale x 16 x double>, <vscale x 16 x double>)