diff --git a/llvm/test/CodeGen/RISCV/rvv/fold-vp-fadd-and-vp-fmul.ll b/llvm/test/CodeGen/RISCV/rvv/fold-vp-fadd-and-vp-fmul.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/RISCV/rvv/fold-vp-fadd-and-vp-fmul.ll
@@ -0,0 +1,60 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=riscv64 -mattr=+v -target-abi=lp64d -verify-machineinstrs < %s | FileCheck %s
+
+declare <vscale x 1 x double> @llvm.vp.fmul.nxv1f64(<vscale x 1 x double> %x, <vscale x 1 x double> %y, <vscale x 1 x i1> %m, i32 %vl)
+declare <vscale x 1 x double> @llvm.vp.fadd.nxv1f64(<vscale x 1 x double> %x, <vscale x 1 x double> %y, <vscale x 1 x i1> %m, i32 %vl)
+
+; (fadd (fmul x, y), z)) -> (fma x, y, z)
+define <vscale x 1 x double> @fma(<vscale x 1 x double> %x, <vscale x 1 x double> %y, <vscale x 1 x double> %z, <vscale x 1 x i1> %m, i32 zeroext %vl) {
+; CHECK-LABEL: fma:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; CHECK-NEXT:    vfmul.vv v8, v8, v9, v0.t
+; CHECK-NEXT:    vfadd.vv v8, v8, v10, v0.t
+; CHECK-NEXT:    ret
+  %1 = call fast <vscale x 1 x double> @llvm.vp.fmul.nxv1f64(<vscale x 1 x double> %x, <vscale x 1 x double> %y, <vscale x 1 x i1> %m, i32 %vl)
+  %2 = call fast <vscale x 1 x double> @llvm.vp.fadd.nxv1f64(<vscale x 1 x double> %1, <vscale x 1 x double> %z, <vscale x 1 x i1> %m, i32 %vl)
+  ret <vscale x 1 x double> %2
+}
+
+; (fadd z, (fmul x, y))) -> (fma x, y, z)
+define <vscale x 1 x double> @fma_commute(<vscale x 1 x double> %x, <vscale x 1 x double> %y, <vscale x 1 x double> %z, <vscale x 1 x i1> %m, i32 zeroext %vl) {
+; CHECK-LABEL: fma_commute:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; CHECK-NEXT:    vfmul.vv v8, v8, v9, v0.t
+; CHECK-NEXT:    vfadd.vv v8, v10, v8, v0.t
+; CHECK-NEXT:    ret
+  %1 = call fast <vscale x 1 x double> @llvm.vp.fmul.nxv1f64(<vscale x 1 x double> %x, <vscale x 1 x double> %y, <vscale x 1 x i1> %m, i32 %vl)
+  %2 = call fast <vscale x 1 x double> @llvm.vp.fadd.nxv1f64(<vscale x 1 x double> %z, <vscale x 1 x double> %1, <vscale x 1 x i1> %m, i32 %vl)
+  ret <vscale x 1 x double> %2
+}
+
+; Test operand with true mask
+define <vscale x 1 x double> @fma_true(<vscale x 1 x double> %x, <vscale x 1 x double> %y, <vscale x 1 x double> %z, <vscale x 1 x i1> %m, i32 zeroext %vl) {
+; CHECK-LABEL: fma_true:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; CHECK-NEXT:    vfmul.vv v8, v8, v9
+; CHECK-NEXT:    vfadd.vv v8, v8, v10, v0.t
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+  %true = shufflevector <vscale x 1 x i1> %head, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+  %1 = call fast <vscale x 1 x double> @llvm.vp.fmul.nxv1f64(<vscale x 1 x double> %x, <vscale x 1 x double> %y, <vscale x 1 x i1> %true, i32 %vl)
+  %2 = call fast <vscale x 1 x double> @llvm.vp.fadd.nxv1f64(<vscale x 1 x double> %1, <vscale x 1 x double> %z, <vscale x 1 x i1> %m, i32 %vl)
+  ret <vscale x 1 x double> %2
+}
+
+; Test operand with normal opcode.
+define <vscale x 1 x double> @fma_nonvp(<vscale x 1 x double> %x, <vscale x 1 x double> %y, <vscale x 1 x double> %z, <vscale x 1 x i1> %m, i32 zeroext %vl) {
+; CHECK-LABEL: fma_nonvp:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a1, zero, e64, m1, ta, ma
+; CHECK-NEXT:    vfmul.vv v8, v8, v9
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; CHECK-NEXT:    vfadd.vv v8, v8, v10, v0.t
+; CHECK-NEXT:    ret
+  %1 = fmul fast <vscale x 1 x double> %x, %y
+  %2 = call fast <vscale x 1 x double> @llvm.vp.fadd.nxv1f64(<vscale x 1 x double> %1, <vscale x 1 x double> %z, <vscale x 1 x i1> %m, i32 %vl)
+  ret <vscale x 1 x double> %2
+}