[RISCV] Add scalable vector support for floating point FMA instructions

A follow up patch will add support for commuting operands or
changing opcode to vfmacc and friends.

Reviewed By: frasercrmck

Differential Revision: https://reviews.llvm.org/D95662

diff --git a/llvm/lib/Target/RISCV/RISCVInstrInfoVSDPatterns.td b/llvm/lib/Target/RISCV/RISCVInstrInfoVSDPatterns.td
index b45a647..6de397a 100644 (file)
--- a/llvm/lib/Target/RISCV/RISCVInstrInfoVSDPatterns.td
+++ b/llvm/lib/Target/RISCV/RISCVInstrInfoVSDPatterns.td
@@ -514,6 +514,68 @@ defm "" : VPatBinaryFPSDNode_VV_VF<fmul, "PseudoVFMUL">;
 defm "" : VPatBinaryFPSDNode_VV_VF<fdiv, "PseudoVFDIV">;
 defm "" : VPatBinaryFPSDNode_R_VF<fdiv, "PseudoVFRDIV">;
 
+// 14.6 Vector Single-Width Floating-Point Fused Multiply-Add Instructions.
+foreach fvti = AllFloatVectors in {
+  // NOTE: We choose VFMADD because it has the most commuting freedom. So it
+  // works best with how TwoAddressInstructionPass tries commuting.
+  def : Pat<(fvti.Vector (fma fvti.RegClass:$rs1, fvti.RegClass:$rd,
+                              fvti.RegClass:$rs2)),
+            (!cast<Instruction>("PseudoVFMADD_VV_"# fvti.LMul.MX)
+                 fvti.RegClass:$rd, fvti.RegClass:$rs1, fvti.RegClass:$rs2,
+                 fvti.AVL, fvti.SEW)>;
+  def : Pat<(fvti.Vector (fma fvti.RegClass:$rs1, fvti.RegClass:$rd,
+                              (fneg fvti.RegClass:$rs2))),
+            (!cast<Instruction>("PseudoVFMSUB_VV_"# fvti.LMul.MX)
+                 fvti.RegClass:$rd, fvti.RegClass:$rs1, fvti.RegClass:$rs2,
+                 fvti.AVL, fvti.SEW)>;
+  def : Pat<(fvti.Vector (fma (fneg fvti.RegClass:$rs1), fvti.RegClass:$rd,
+                              (fneg fvti.RegClass:$rs2))),
+            (!cast<Instruction>("PseudoVFNMADD_VV_"# fvti.LMul.MX)
+                 fvti.RegClass:$rd, fvti.RegClass:$rs1, fvti.RegClass:$rs2,
+                 fvti.AVL, fvti.SEW)>;
+  def : Pat<(fvti.Vector (fma (fneg fvti.RegClass:$rs1), fvti.RegClass:$rd,
+                              fvti.RegClass:$rs2)),
+            (!cast<Instruction>("PseudoVFNMSUB_VV_"# fvti.LMul.MX)
+                 fvti.RegClass:$rd, fvti.RegClass:$rs1, fvti.RegClass:$rs2,
+                 fvti.AVL, fvti.SEW)>;
+
+  // The choice of VFMADD here is arbitrary, vfmadd.vf and vfmacc.vf are equally
+  // commutable.
+  def : Pat<(fvti.Vector (fma (splat_vector fvti.ScalarRegClass:$rs1),
+                              fvti.RegClass:$rd, fvti.RegClass:$rs2)),
+            (!cast<Instruction>("PseudoVFMADD_V" # fvti.ScalarSuffix # "_" # fvti.LMul.MX)
+                 fvti.RegClass:$rd, fvti.ScalarRegClass:$rs1, fvti.RegClass:$rs2,
+                 fvti.AVL, fvti.SEW)>;
+  def : Pat<(fvti.Vector (fma (splat_vector fvti.ScalarRegClass:$rs1),
+                              fvti.RegClass:$rd, (fneg fvti.RegClass:$rs2))),
+            (!cast<Instruction>("PseudoVFMSUB_V" # fvti.ScalarSuffix # "_" # fvti.LMul.MX)
+                 fvti.RegClass:$rd, fvti.ScalarRegClass:$rs1, fvti.RegClass:$rs2,
+                 fvti.AVL, fvti.SEW)>;
+
+  def : Pat<(fvti.Vector (fma (splat_vector fvti.ScalarRegClass:$rs1),
+                              (fneg fvti.RegClass:$rd), (fneg fvti.RegClass:$rs2))),
+            (!cast<Instruction>("PseudoVFNMADD_V" # fvti.ScalarSuffix # "_" # fvti.LMul.MX)
+                 fvti.RegClass:$rd, fvti.ScalarRegClass:$rs1, fvti.RegClass:$rs2,
+                 fvti.AVL, fvti.SEW)>;
+  def : Pat<(fvti.Vector (fma (splat_vector fvti.ScalarRegClass:$rs1),
+                              (fneg fvti.RegClass:$rd), fvti.RegClass:$rs2)),
+            (!cast<Instruction>("PseudoVFNMSUB_V" # fvti.ScalarSuffix # "_" # fvti.LMul.MX)
+                 fvti.RegClass:$rd, fvti.ScalarRegClass:$rs1, fvti.RegClass:$rs2,
+                 fvti.AVL, fvti.SEW)>;
+
+  // The splat might be negated.
+  def : Pat<(fvti.Vector (fma (fneg (splat_vector fvti.ScalarRegClass:$rs1)),
+                              fvti.RegClass:$rd, (fneg fvti.RegClass:$rs2))),
+            (!cast<Instruction>("PseudoVFNMADD_V" # fvti.ScalarSuffix # "_" # fvti.LMul.MX)
+                 fvti.RegClass:$rd, fvti.ScalarRegClass:$rs1, fvti.RegClass:$rs2,
+                 fvti.AVL, fvti.SEW)>;
+  def : Pat<(fvti.Vector (fma (fneg (splat_vector fvti.ScalarRegClass:$rs1)),
+                              fvti.RegClass:$rd, fvti.RegClass:$rs2)),
+            (!cast<Instruction>("PseudoVFNMSUB_V" # fvti.ScalarSuffix # "_" # fvti.LMul.MX)
+                 fvti.RegClass:$rd, fvti.ScalarRegClass:$rs1, fvti.RegClass:$rs2,
+                 fvti.AVL, fvti.SEW)>;
+}
+
 // 14.10. Vector Floating-Point Sign-Injection Instructions
 // Handle fneg with VFSGNJN using the same input for both operands.
 foreach vti = AllFloatVectors in {

diff --git a/llvm/test/CodeGen/RISCV/rvv/vfmadd-sdnode.ll b/llvm/test/CodeGen/RISCV/rvv/vfmadd-sdnode.ll
new file mode 100644 (file)
index 0000000..b51031f
--- /dev/null
+++ b/llvm/test/CodeGen/RISCV/rvv/vfmadd-sdnode.ll
@@ -0,0 +1,391 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=riscv32 -mattr=+d,+experimental-zfh,+experimental-v -target-abi=ilp32d \
+; RUN:     -verify-machineinstrs < %s | FileCheck %s
+; RUN: llc -mtriple=riscv64 -mattr=+d,+experimental-zfh,+experimental-v -target-abi=lp64d \
+; RUN:     -verify-machineinstrs < %s | FileCheck %s
+
+; This tests a mix of vfmacc and vfmadd by using different operand orders to
+; trigger commuting in TwoAddressInstructionPass.
+
+declare <vscale x 1 x half> @llvm.fma.v1f16(<vscale x 1 x half>, <vscale x 1 x half>, <vscale x 1 x half>)
+
+define <vscale x 1 x half> @vfmadd_vv_nxv1f16(<vscale x 1 x half> %va, <vscale x 1 x half> %vb, <vscale x 1 x half> %vc) {
+; CHECK-LABEL: vfmadd_vv_nxv1f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,mf4,tu,mu
+; CHECK-NEXT:    vfmadd.vv v9, v8, v10
+; CHECK-NEXT:    vmv1r.v v8, v9
+; CHECK-NEXT:    ret
+  %vd = call <vscale x 1 x half> @llvm.fma.v1f16(<vscale x 1 x half> %va, <vscale x 1 x half> %vb, <vscale x 1 x half> %vc)
+  ret <vscale x 1 x half> %vd
+}
+
+define <vscale x 1 x half> @vfmadd_vf_nxv1f16(<vscale x 1 x half> %va, <vscale x 1 x half> %vb, half %c) {
+; CHECK-LABEL: vfmadd_vf_nxv1f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,mf4,tu,mu
+; CHECK-NEXT:    vfmadd.vf v8, fa0, v9
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 1 x half> undef, half %c, i32 0
+  %splat = shufflevector <vscale x 1 x half> %head, <vscale x 1 x half> undef, <vscale x 1 x i32> zeroinitializer
+  %vd = call <vscale x 1 x half> @llvm.fma.v1f16(<vscale x 1 x half> %va, <vscale x 1 x half> %splat, <vscale x 1 x half> %vb)
+  ret <vscale x 1 x half> %vd
+}
+
+declare <vscale x 2 x half> @llvm.fma.v2f16(<vscale x 2 x half>, <vscale x 2 x half>, <vscale x 2 x half>)
+
+define <vscale x 2 x half> @vfmadd_vv_nxv2f16(<vscale x 2 x half> %va, <vscale x 2 x half> %vb, <vscale x 2 x half> %vc) {
+; CHECK-LABEL: vfmadd_vv_nxv2f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,mf2,tu,mu
+; CHECK-NEXT:    vfmadd.vv v10, v8, v9
+; CHECK-NEXT:    vmv1r.v v8, v10
+; CHECK-NEXT:    ret
+  %vd = call <vscale x 2 x half> @llvm.fma.v2f16(<vscale x 2 x half> %va, <vscale x 2 x half> %vc, <vscale x 2 x half> %vb)
+  ret <vscale x 2 x half> %vd
+}
+
+define <vscale x 2 x half> @vfmadd_vf_nxv2f16(<vscale x 2 x half> %va, <vscale x 2 x half> %vb, half %c) {
+; CHECK-LABEL: vfmadd_vf_nxv2f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,mf2,tu,mu
+; CHECK-NEXT:    vfmadd.vf v9, fa0, v8
+; CHECK-NEXT:    vmv1r.v v8, v9
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 2 x half> undef, half %c, i32 0
+  %splat = shufflevector <vscale x 2 x half> %head, <vscale x 2 x half> undef, <vscale x 2 x i32> zeroinitializer
+  %vd = call <vscale x 2 x half> @llvm.fma.v2f16(<vscale x 2 x half> %vb, <vscale x 2 x half> %splat, <vscale x 2 x half> %va)
+  ret <vscale x 2 x half> %vd
+}
+
+declare <vscale x 4 x half> @llvm.fma.v4f16(<vscale x 4 x half>, <vscale x 4 x half>, <vscale x 4 x half>)
+
+define <vscale x 4 x half> @vfmadd_vv_nxv4f16(<vscale x 4 x half> %va, <vscale x 4 x half> %vb, <vscale x 4 x half> %vc) {
+; CHECK-LABEL: vfmadd_vv_nxv4f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,m1,tu,mu
+; CHECK-NEXT:    vfmadd.vv v8, v9, v10
+; CHECK-NEXT:    ret
+  %vd = call <vscale x 4 x half> @llvm.fma.v4f16(<vscale x 4 x half> %vb, <vscale x 4 x half> %va, <vscale x 4 x half> %vc)
+  ret <vscale x 4 x half> %vd
+}
+
+define <vscale x 4 x half> @vfmadd_vf_nxv4f16(<vscale x 4 x half> %va, <vscale x 4 x half> %vb, half %c) {
+; CHECK-LABEL: vfmadd_vf_nxv4f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,m1,tu,mu
+; CHECK-NEXT:    vfmadd.vf v8, fa0, v9
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 4 x half> undef, half %c, i32 0
+  %splat = shufflevector <vscale x 4 x half> %head, <vscale x 4 x half> undef, <vscale x 4 x i32> zeroinitializer
+  %vd = call <vscale x 4 x half> @llvm.fma.v4f16(<vscale x 4 x half> %va, <vscale x 4 x half> %splat, <vscale x 4 x half> %vb)
+  ret <vscale x 4 x half> %vd
+}
+
+declare <vscale x 8 x half> @llvm.fma.v8f16(<vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>)
+
+define <vscale x 8 x half> @vfmadd_vv_nxv8f16(<vscale x 8 x half> %va, <vscale x 8 x half> %vb, <vscale x 8 x half> %vc) {
+; CHECK-LABEL: vfmadd_vv_nxv8f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,m2,tu,mu
+; CHECK-NEXT:    vfmadd.vv v12, v10, v8
+; CHECK-NEXT:    vmv2r.v v8, v12
+; CHECK-NEXT:    ret
+  %vd = call <vscale x 8 x half> @llvm.fma.v8f16(<vscale x 8 x half> %vb, <vscale x 8 x half> %vc, <vscale x 8 x half> %va)
+  ret <vscale x 8 x half> %vd
+}
+
+define <vscale x 8 x half> @vfmadd_vf_nxv8f16(<vscale x 8 x half> %va, <vscale x 8 x half> %vb, half %c) {
+; CHECK-LABEL: vfmadd_vf_nxv8f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,m2,tu,mu
+; CHECK-NEXT:    vfmadd.vf v10, fa0, v8
+; CHECK-NEXT:    vmv2r.v v8, v10
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 8 x half> undef, half %c, i32 0
+  %splat = shufflevector <vscale x 8 x half> %head, <vscale x 8 x half> undef, <vscale x 8 x i32> zeroinitializer
+  %vd = call <vscale x 8 x half> @llvm.fma.v8f16(<vscale x 8 x half> %vb, <vscale x 8 x half> %splat, <vscale x 8 x half> %va)
+  ret <vscale x 8 x half> %vd
+}
+
+declare <vscale x 16 x half> @llvm.fma.v16f16(<vscale x 16 x half>, <vscale x 16 x half>, <vscale x 16 x half>)
+
+define <vscale x 16 x half> @vfmadd_vv_nxv16f16(<vscale x 16 x half> %va, <vscale x 16 x half> %vb, <vscale x 16 x half> %vc) {
+; CHECK-LABEL: vfmadd_vv_nxv16f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,m4,tu,mu
+; CHECK-NEXT:    vfmadd.vv v8, v16, v12
+; CHECK-NEXT:    ret
+  %vd = call <vscale x 16 x half> @llvm.fma.v16f16(<vscale x 16 x half> %vc, <vscale x 16 x half> %va, <vscale x 16 x half> %vb)
+  ret <vscale x 16 x half> %vd
+}
+
+define <vscale x 16 x half> @vfmadd_vf_nxv16f16(<vscale x 16 x half> %va, <vscale x 16 x half> %vb, half %c) {
+; CHECK-LABEL: vfmadd_vf_nxv16f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,m4,tu,mu
+; CHECK-NEXT:    vfmadd.vf v8, fa0, v12
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 16 x half> undef, half %c, i32 0
+  %splat = shufflevector <vscale x 16 x half> %head, <vscale x 16 x half> undef, <vscale x 16 x i32> zeroinitializer
+  %vd = call <vscale x 16 x half> @llvm.fma.v16f16(<vscale x 16 x half> %va, <vscale x 16 x half> %splat, <vscale x 16 x half> %vb)
+  ret <vscale x 16 x half> %vd
+}
+
+declare <vscale x 32 x half> @llvm.fma.v32f16(<vscale x 32 x half>, <vscale x 32 x half>, <vscale x 32 x half>)
+
+define <vscale x 32 x half> @vfmadd_vv_nxv32f16(<vscale x 32 x half> %va, <vscale x 32 x half> %vb, <vscale x 32 x half> %vc) {
+; CHECK-LABEL: vfmadd_vv_nxv32f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a1, zero, e16,m8,ta,mu
+; CHECK-NEXT:    vle16.v v24, (a0)
+; CHECK-NEXT:    vsetvli a0, zero, e16,m8,tu,mu
+; CHECK-NEXT:    vfmadd.vv v16, v24, v8
+; CHECK-NEXT:    vmv8r.v v8, v16
+; CHECK-NEXT:    ret
+  %vd = call <vscale x 32 x half> @llvm.fma.v32f16(<vscale x 32 x half> %vc, <vscale x 32 x half> %vb, <vscale x 32 x half> %va)
+  ret <vscale x 32 x half> %vd
+}
+
+define <vscale x 32 x half> @vfmadd_vf_nxv32f16(<vscale x 32 x half> %va, <vscale x 32 x half> %vb, half %c) {
+; CHECK-LABEL: vfmadd_vf_nxv32f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,m8,tu,mu
+; CHECK-NEXT:    vfmadd.vf v16, fa0, v8
+; CHECK-NEXT:    vmv8r.v v8, v16
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 32 x half> undef, half %c, i32 0
+  %splat = shufflevector <vscale x 32 x half> %head, <vscale x 32 x half> undef, <vscale x 32 x i32> zeroinitializer
+  %vd = call <vscale x 32 x half> @llvm.fma.v32f16(<vscale x 32 x half> %vb, <vscale x 32 x half> %splat, <vscale x 32 x half> %va)
+  ret <vscale x 32 x half> %vd
+}
+
+declare <vscale x 1 x float> @llvm.fma.v1f32(<vscale x 1 x float>, <vscale x 1 x float>, <vscale x 1 x float>)
+
+define <vscale x 1 x float> @vfmadd_vv_nxv1f32(<vscale x 1 x float> %va, <vscale x 1 x float> %vb, <vscale x 1 x float> %vc) {
+; CHECK-LABEL: vfmadd_vv_nxv1f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e32,mf2,tu,mu
+; CHECK-NEXT:    vfmadd.vv v9, v8, v10
+; CHECK-NEXT:    vmv1r.v v8, v9
+; CHECK-NEXT:    ret
+  %vd = call <vscale x 1 x float> @llvm.fma.v1f32(<vscale x 1 x float> %va, <vscale x 1 x float> %vb, <vscale x 1 x float> %vc)
+  ret <vscale x 1 x float> %vd
+}
+
+define <vscale x 1 x float> @vfmadd_vf_nxv1f32(<vscale x 1 x float> %va, <vscale x 1 x float> %vb, float %c) {
+; CHECK-LABEL: vfmadd_vf_nxv1f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e32,mf2,tu,mu
+; CHECK-NEXT:    vfmadd.vf v8, fa0, v9
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 1 x float> undef, float %c, i32 0
+  %splat = shufflevector <vscale x 1 x float> %head, <vscale x 1 x float> undef, <vscale x 1 x i32> zeroinitializer
+  %vd = call <vscale x 1 x float> @llvm.fma.v1f32(<vscale x 1 x float> %va, <vscale x 1 x float> %splat, <vscale x 1 x float> %vb)
+  ret <vscale x 1 x float> %vd
+}
+
+declare <vscale x 2 x float> @llvm.fma.v2f32(<vscale x 2 x float>, <vscale x 2 x float>, <vscale x 2 x float>)
+
+define <vscale x 2 x float> @vfmadd_vv_nxv2f32(<vscale x 2 x float> %va, <vscale x 2 x float> %vb, <vscale x 2 x float> %vc) {
+; CHECK-LABEL: vfmadd_vv_nxv2f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e32,m1,tu,mu
+; CHECK-NEXT:    vfmadd.vv v10, v8, v9
+; CHECK-NEXT:    vmv1r.v v8, v10
+; CHECK-NEXT:    ret
+  %vd = call <vscale x 2 x float> @llvm.fma.v2f32(<vscale x 2 x float> %va, <vscale x 2 x float> %vc, <vscale x 2 x float> %vb)
+  ret <vscale x 2 x float> %vd
+}
+
+define <vscale x 2 x float> @vfmadd_vf_nxv2f32(<vscale x 2 x float> %va, <vscale x 2 x float> %vb, float %c) {
+; CHECK-LABEL: vfmadd_vf_nxv2f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e32,m1,tu,mu
+; CHECK-NEXT:    vfmadd.vf v9, fa0, v8
+; CHECK-NEXT:    vmv1r.v v8, v9
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 2 x float> undef, float %c, i32 0
+  %splat = shufflevector <vscale x 2 x float> %head, <vscale x 2 x float> undef, <vscale x 2 x i32> zeroinitializer
+  %vd = call <vscale x 2 x float> @llvm.fma.v2f32(<vscale x 2 x float> %vb, <vscale x 2 x float> %splat, <vscale x 2 x float> %va)
+  ret <vscale x 2 x float> %vd
+}
+
+declare <vscale x 4 x float> @llvm.fma.v4f32(<vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>)
+
+define <vscale x 4 x float> @vfmadd_vv_nxv4f32(<vscale x 4 x float> %va, <vscale x 4 x float> %vb, <vscale x 4 x float> %vc) {
+; CHECK-LABEL: vfmadd_vv_nxv4f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e32,m2,tu,mu
+; CHECK-NEXT:    vfmadd.vv v8, v10, v12
+; CHECK-NEXT:    ret
+  %vd = call <vscale x 4 x float> @llvm.fma.v4f32(<vscale x 4 x float> %vb, <vscale x 4 x float> %va, <vscale x 4 x float> %vc)
+  ret <vscale x 4 x float> %vd
+}
+
+define <vscale x 4 x float> @vfmadd_vf_nxv4f32(<vscale x 4 x float> %va, <vscale x 4 x float> %vb, float %c) {
+; CHECK-LABEL: vfmadd_vf_nxv4f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e32,m2,tu,mu
+; CHECK-NEXT:    vfmadd.vf v8, fa0, v10
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 4 x float> undef, float %c, i32 0
+  %splat = shufflevector <vscale x 4 x float> %head, <vscale x 4 x float> undef, <vscale x 4 x i32> zeroinitializer
+  %vd = call <vscale x 4 x float> @llvm.fma.v4f32(<vscale x 4 x float> %va, <vscale x 4 x float> %splat, <vscale x 4 x float> %vb)
+  ret <vscale x 4 x float> %vd
+}
+
+declare <vscale x 8 x float> @llvm.fma.v8f32(<vscale x 8 x float>, <vscale x 8 x float>, <vscale x 8 x float>)
+
+define <vscale x 8 x float> @vfmadd_vv_nxv8f32(<vscale x 8 x float> %va, <vscale x 8 x float> %vb, <vscale x 8 x float> %vc) {
+; CHECK-LABEL: vfmadd_vv_nxv8f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e32,m4,tu,mu
+; CHECK-NEXT:    vfmadd.vv v16, v12, v8
+; CHECK-NEXT:    vmv4r.v v8, v16
+; CHECK-NEXT:    ret
+  %vd = call <vscale x 8 x float> @llvm.fma.v8f32(<vscale x 8 x float> %vb, <vscale x 8 x float> %vc, <vscale x 8 x float> %va)
+  ret <vscale x 8 x float> %vd
+}
+
+define <vscale x 8 x float> @vfmadd_vf_nxv8f32(<vscale x 8 x float> %va, <vscale x 8 x float> %vb, float %c) {
+; CHECK-LABEL: vfmadd_vf_nxv8f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e32,m4,tu,mu
+; CHECK-NEXT:    vfmadd.vf v12, fa0, v8
+; CHECK-NEXT:    vmv4r.v v8, v12
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 8 x float> undef, float %c, i32 0
+  %splat = shufflevector <vscale x 8 x float> %head, <vscale x 8 x float> undef, <vscale x 8 x i32> zeroinitializer
+  %vd = call <vscale x 8 x float> @llvm.fma.v8f32(<vscale x 8 x float> %vb, <vscale x 8 x float> %splat, <vscale x 8 x float> %va)
+  ret <vscale x 8 x float> %vd
+}
+
+declare <vscale x 16 x float> @llvm.fma.v16f32(<vscale x 16 x float>, <vscale x 16 x float>, <vscale x 16 x float>)
+
+define <vscale x 16 x float> @vfmadd_vv_nxv16f32(<vscale x 16 x float> %va, <vscale x 16 x float> %vb, <vscale x 16 x float> %vc) {
+; CHECK-LABEL: vfmadd_vv_nxv16f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a1, zero, e32,m8,ta,mu
+; CHECK-NEXT:    vle32.v v24, (a0)
+; CHECK-NEXT:    vsetvli a0, zero, e32,m8,tu,mu
+; CHECK-NEXT:    vfmadd.vv v8, v24, v16
+; CHECK-NEXT:    ret
+  %vd = call <vscale x 16 x float> @llvm.fma.v16f32(<vscale x 16 x float> %vc, <vscale x 16 x float> %va, <vscale x 16 x float> %vb)
+  ret <vscale x 16 x float> %vd
+}
+
+define <vscale x 16 x float> @vfmadd_vf_nxv16f32(<vscale x 16 x float> %va, <vscale x 16 x float> %vb, float %c) {
+; CHECK-LABEL: vfmadd_vf_nxv16f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e32,m8,tu,mu
+; CHECK-NEXT:    vfmadd.vf v8, fa0, v16
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 16 x float> undef, float %c, i32 0
+  %splat = shufflevector <vscale x 16 x float> %head, <vscale x 16 x float> undef, <vscale x 16 x i32> zeroinitializer
+  %vd = call <vscale x 16 x float> @llvm.fma.v16f32(<vscale x 16 x float> %va, <vscale x 16 x float> %splat, <vscale x 16 x float> %vb)
+  ret <vscale x 16 x float> %vd
+}
+
+declare <vscale x 1 x double> @llvm.fma.v1f64(<vscale x 1 x double>, <vscale x 1 x double>, <vscale x 1 x double>)
+
+define <vscale x 1 x double> @vfmadd_vv_nxv1f64(<vscale x 1 x double> %va, <vscale x 1 x double> %vb, <vscale x 1 x double> %vc) {
+; CHECK-LABEL: vfmadd_vv_nxv1f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e64,m1,tu,mu
+; CHECK-NEXT:    vfmadd.vv v9, v8, v10
+; CHECK-NEXT:    vmv1r.v v8, v9
+; CHECK-NEXT:    ret
+  %vd = call <vscale x 1 x double> @llvm.fma.v1f64(<vscale x 1 x double> %va, <vscale x 1 x double> %vb, <vscale x 1 x double> %vc)
+  ret <vscale x 1 x double> %vd
+}
+
+define <vscale x 1 x double> @vfmadd_vf_nxv1f64(<vscale x 1 x double> %va, <vscale x 1 x double> %vb, double %c) {
+; CHECK-LABEL: vfmadd_vf_nxv1f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e64,m1,tu,mu
+; CHECK-NEXT:    vfmadd.vf v8, fa0, v9
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 1 x double> undef, double %c, i32 0
+  %splat = shufflevector <vscale x 1 x double> %head, <vscale x 1 x double> undef, <vscale x 1 x i32> zeroinitializer
+  %vd = call <vscale x 1 x double> @llvm.fma.v1f64(<vscale x 1 x double> %va, <vscale x 1 x double> %splat, <vscale x 1 x double> %vb)
+  ret <vscale x 1 x double> %vd
+}
+
+declare <vscale x 2 x double> @llvm.fma.v2f64(<vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>)
+
+define <vscale x 2 x double> @vfmadd_vv_nxv2f64(<vscale x 2 x double> %va, <vscale x 2 x double> %vb, <vscale x 2 x double> %vc) {
+; CHECK-LABEL: vfmadd_vv_nxv2f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e64,m2,tu,mu
+; CHECK-NEXT:    vfmadd.vv v12, v8, v10
+; CHECK-NEXT:    vmv2r.v v8, v12
+; CHECK-NEXT:    ret
+  %vd = call <vscale x 2 x double> @llvm.fma.v2f64(<vscale x 2 x double> %va, <vscale x 2 x double> %vc, <vscale x 2 x double> %vb)
+  ret <vscale x 2 x double> %vd
+}
+
+define <vscale x 2 x double> @vfmadd_vf_nxv2f64(<vscale x 2 x double> %va, <vscale x 2 x double> %vb, double %c) {
+; CHECK-LABEL: vfmadd_vf_nxv2f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e64,m2,tu,mu
+; CHECK-NEXT:    vfmadd.vf v10, fa0, v8
+; CHECK-NEXT:    vmv2r.v v8, v10
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 2 x double> undef, double %c, i32 0
+  %splat = shufflevector <vscale x 2 x double> %head, <vscale x 2 x double> undef, <vscale x 2 x i32> zeroinitializer
+  %vd = call <vscale x 2 x double> @llvm.fma.v2f64(<vscale x 2 x double> %vb, <vscale x 2 x double> %splat, <vscale x 2 x double> %va)
+  ret <vscale x 2 x double> %vd
+}
+
+declare <vscale x 4 x double> @llvm.fma.v4f64(<vscale x 4 x double>, <vscale x 4 x double>, <vscale x 4 x double>)
+
+define <vscale x 4 x double> @vfmadd_vv_nxv4f64(<vscale x 4 x double> %va, <vscale x 4 x double> %vb, <vscale x 4 x double> %vc) {
+; CHECK-LABEL: vfmadd_vv_nxv4f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e64,m4,tu,mu
+; CHECK-NEXT:    vfmadd.vv v8, v12, v16
+; CHECK-NEXT:    ret
+  %vd = call <vscale x 4 x double> @llvm.fma.v4f64(<vscale x 4 x double> %vb, <vscale x 4 x double> %va, <vscale x 4 x double> %vc)
+  ret <vscale x 4 x double> %vd
+}
+
+define <vscale x 4 x double> @vfmadd_vf_nxv4f64(<vscale x 4 x double> %va, <vscale x 4 x double> %vb, double %c) {
+; CHECK-LABEL: vfmadd_vf_nxv4f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e64,m4,tu,mu
+; CHECK-NEXT:    vfmadd.vf v8, fa0, v12
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 4 x double> undef, double %c, i32 0
+  %splat = shufflevector <vscale x 4 x double> %head, <vscale x 4 x double> undef, <vscale x 4 x i32> zeroinitializer
+  %vd = call <vscale x 4 x double> @llvm.fma.v4f64(<vscale x 4 x double> %va, <vscale x 4 x double> %splat, <vscale x 4 x double> %vb)
+  ret <vscale x 4 x double> %vd
+}
+
+declare <vscale x 8 x double> @llvm.fma.v8f64(<vscale x 8 x double>, <vscale x 8 x double>, <vscale x 8 x double>)
+
+define <vscale x 8 x double> @vfmadd_vv_nxv8f64(<vscale x 8 x double> %va, <vscale x 8 x double> %vb, <vscale x 8 x double> %vc) {
+; CHECK-LABEL: vfmadd_vv_nxv8f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a1, zero, e64,m8,ta,mu
+; CHECK-NEXT:    vle64.v v24, (a0)
+; CHECK-NEXT:    vsetvli a0, zero, e64,m8,tu,mu
+; CHECK-NEXT:    vfmadd.vv v24, v16, v8
+; CHECK-NEXT:    vmv8r.v v8, v24
+; CHECK-NEXT:    ret
+  %vd = call <vscale x 8 x double> @llvm.fma.v8f64(<vscale x 8 x double> %vb, <vscale x 8 x double> %vc, <vscale x 8 x double> %va)
+  ret <vscale x 8 x double> %vd
+}
+
+define <vscale x 8 x double> @vfmadd_vf_nxv8f64(<vscale x 8 x double> %va, <vscale x 8 x double> %vb, double %c) {
+; CHECK-LABEL: vfmadd_vf_nxv8f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e64,m8,tu,mu
+; CHECK-NEXT:    vfmadd.vf v16, fa0, v8
+; CHECK-NEXT:    vmv8r.v v8, v16
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 8 x double> undef, double %c, i32 0
+  %splat = shufflevector <vscale x 8 x double> %head, <vscale x 8 x double> undef, <vscale x 8 x i32> zeroinitializer
+  %vd = call <vscale x 8 x double> @llvm.fma.v8f64(<vscale x 8 x double> %vb, <vscale x 8 x double> %splat, <vscale x 8 x double> %va)
+  ret <vscale x 8 x double> %vd
+}

diff --git a/llvm/test/CodeGen/RISCV/rvv/vfmsub-sdnode.ll b/llvm/test/CodeGen/RISCV/rvv/vfmsub-sdnode.ll
new file mode 100644 (file)
index 0000000..399d682
--- /dev/null
+++ b/llvm/test/CodeGen/RISCV/rvv/vfmsub-sdnode.ll
@@ -0,0 +1,421 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=riscv32 -mattr=+d,+experimental-zfh,+experimental-v -target-abi=ilp32d \
+; RUN:     -verify-machineinstrs < %s | FileCheck %s
+; RUN: llc -mtriple=riscv64 -mattr=+d,+experimental-zfh,+experimental-v -target-abi=lp64d \
+; RUN:     -verify-machineinstrs < %s | FileCheck %s
+
+; This tests a mix of vfmsac and vfmsub by using different operand orders to
+; trigger commuting in TwoAddressInstructionPass.
+
+declare <vscale x 1 x half> @llvm.fma.v1f16(<vscale x 1 x half>, <vscale x 1 x half>, <vscale x 1 x half>)
+
+define <vscale x 1 x half> @vfmsub_vv_nxv1f16(<vscale x 1 x half> %va, <vscale x 1 x half> %vb, <vscale x 1 x half> %vc) {
+; CHECK-LABEL: vfmsub_vv_nxv1f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,mf4,tu,mu
+; CHECK-NEXT:    vfmsub.vv v9, v8, v10
+; CHECK-NEXT:    vmv1r.v v8, v9
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 1 x half> %vc
+  %vd = call <vscale x 1 x half> @llvm.fma.v1f16(<vscale x 1 x half> %va, <vscale x 1 x half> %vb, <vscale x 1 x half> %neg)
+  ret <vscale x 1 x half> %vd
+}
+
+define <vscale x 1 x half> @vfmsub_vf_nxv1f16(<vscale x 1 x half> %va, <vscale x 1 x half> %vb, half %c) {
+; CHECK-LABEL: vfmsub_vf_nxv1f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,mf4,tu,mu
+; CHECK-NEXT:    vfmsub.vf v8, fa0, v9
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 1 x half> undef, half %c, i32 0
+  %splat = shufflevector <vscale x 1 x half> %head, <vscale x 1 x half> undef, <vscale x 1 x i32> zeroinitializer
+  %neg = fneg <vscale x 1 x half> %vb
+  %vd = call <vscale x 1 x half> @llvm.fma.v1f16(<vscale x 1 x half> %va, <vscale x 1 x half> %splat, <vscale x 1 x half> %neg)
+  ret <vscale x 1 x half> %vd
+}
+
+declare <vscale x 2 x half> @llvm.fma.v2f16(<vscale x 2 x half>, <vscale x 2 x half>, <vscale x 2 x half>)
+
+define <vscale x 2 x half> @vfmsub_vv_nxv2f16(<vscale x 2 x half> %va, <vscale x 2 x half> %vb, <vscale x 2 x half> %vc) {
+; CHECK-LABEL: vfmsub_vv_nxv2f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,mf2,tu,mu
+; CHECK-NEXT:    vfmsub.vv v10, v8, v9
+; CHECK-NEXT:    vmv1r.v v8, v10
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 2 x half> %vb
+  %vd = call <vscale x 2 x half> @llvm.fma.v2f16(<vscale x 2 x half> %va, <vscale x 2 x half> %vc, <vscale x 2 x half> %neg)
+  ret <vscale x 2 x half> %vd
+}
+
+define <vscale x 2 x half> @vfmsub_vf_nxv2f16(<vscale x 2 x half> %va, <vscale x 2 x half> %vb, half %c) {
+; CHECK-LABEL: vfmsub_vf_nxv2f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,mf2,tu,mu
+; CHECK-NEXT:    vfmsub.vf v9, fa0, v8
+; CHECK-NEXT:    vmv1r.v v8, v9
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 2 x half> undef, half %c, i32 0
+  %splat = shufflevector <vscale x 2 x half> %head, <vscale x 2 x half> undef, <vscale x 2 x i32> zeroinitializer
+  %neg = fneg <vscale x 2 x half> %va
+  %vd = call <vscale x 2 x half> @llvm.fma.v2f16(<vscale x 2 x half> %vb, <vscale x 2 x half> %splat, <vscale x 2 x half> %neg)
+  ret <vscale x 2 x half> %vd
+}
+
+declare <vscale x 4 x half> @llvm.fma.v4f16(<vscale x 4 x half>, <vscale x 4 x half>, <vscale x 4 x half>)
+
+define <vscale x 4 x half> @vfmsub_vv_nxv4f16(<vscale x 4 x half> %va, <vscale x 4 x half> %vb, <vscale x 4 x half> %vc) {
+; CHECK-LABEL: vfmsub_vv_nxv4f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,m1,tu,mu
+; CHECK-NEXT:    vfmsub.vv v8, v9, v10
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 4 x half> %vc
+  %vd = call <vscale x 4 x half> @llvm.fma.v4f16(<vscale x 4 x half> %vb, <vscale x 4 x half> %va, <vscale x 4 x half> %neg)
+  ret <vscale x 4 x half> %vd
+}
+
+define <vscale x 4 x half> @vfmsub_vf_nxv4f16(<vscale x 4 x half> %va, <vscale x 4 x half> %vb, half %c) {
+; CHECK-LABEL: vfmsub_vf_nxv4f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,m1,tu,mu
+; CHECK-NEXT:    vfmsub.vf v8, fa0, v9
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 4 x half> undef, half %c, i32 0
+  %splat = shufflevector <vscale x 4 x half> %head, <vscale x 4 x half> undef, <vscale x 4 x i32> zeroinitializer
+  %neg = fneg <vscale x 4 x half> %vb
+  %vd = call <vscale x 4 x half> @llvm.fma.v4f16(<vscale x 4 x half> %va, <vscale x 4 x half> %splat, <vscale x 4 x half> %neg)
+  ret <vscale x 4 x half> %vd
+}
+
+declare <vscale x 8 x half> @llvm.fma.v8f16(<vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>)
+
+define <vscale x 8 x half> @vfmsub_vv_nxv8f16(<vscale x 8 x half> %va, <vscale x 8 x half> %vb, <vscale x 8 x half> %vc) {
+; CHECK-LABEL: vfmsub_vv_nxv8f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,m2,tu,mu
+; CHECK-NEXT:    vfmsub.vv v12, v10, v8
+; CHECK-NEXT:    vmv2r.v v8, v12
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 8 x half> %va
+  %vd = call <vscale x 8 x half> @llvm.fma.v8f16(<vscale x 8 x half> %vb, <vscale x 8 x half> %vc, <vscale x 8 x half> %neg)
+  ret <vscale x 8 x half> %vd
+}
+
+define <vscale x 8 x half> @vfmsub_vf_nxv8f16(<vscale x 8 x half> %va, <vscale x 8 x half> %vb, half %c) {
+; CHECK-LABEL: vfmsub_vf_nxv8f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,m2,tu,mu
+; CHECK-NEXT:    vfmsub.vf v10, fa0, v8
+; CHECK-NEXT:    vmv2r.v v8, v10
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 8 x half> undef, half %c, i32 0
+  %splat = shufflevector <vscale x 8 x half> %head, <vscale x 8 x half> undef, <vscale x 8 x i32> zeroinitializer
+  %neg = fneg <vscale x 8 x half> %va
+  %vd = call <vscale x 8 x half> @llvm.fma.v8f16(<vscale x 8 x half> %vb, <vscale x 8 x half> %splat, <vscale x 8 x half> %neg)
+  ret <vscale x 8 x half> %vd
+}
+
+declare <vscale x 16 x half> @llvm.fma.v16f16(<vscale x 16 x half>, <vscale x 16 x half>, <vscale x 16 x half>)
+
+define <vscale x 16 x half> @vfmsub_vv_nxv16f16(<vscale x 16 x half> %va, <vscale x 16 x half> %vb, <vscale x 16 x half> %vc) {
+; CHECK-LABEL: vfmsub_vv_nxv16f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,m4,tu,mu
+; CHECK-NEXT:    vfmsub.vv v8, v16, v12
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 16 x half> %vb
+  %vd = call <vscale x 16 x half> @llvm.fma.v16f16(<vscale x 16 x half> %vc, <vscale x 16 x half> %va, <vscale x 16 x half> %neg)
+  ret <vscale x 16 x half> %vd
+}
+
+define <vscale x 16 x half> @vfmsub_vf_nxv16f16(<vscale x 16 x half> %va, <vscale x 16 x half> %vb, half %c) {
+; CHECK-LABEL: vfmsub_vf_nxv16f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,m4,tu,mu
+; CHECK-NEXT:    vfmsub.vf v8, fa0, v12
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 16 x half> undef, half %c, i32 0
+  %splat = shufflevector <vscale x 16 x half> %head, <vscale x 16 x half> undef, <vscale x 16 x i32> zeroinitializer
+  %neg = fneg <vscale x 16 x half> %vb
+  %vd = call <vscale x 16 x half> @llvm.fma.v16f16(<vscale x 16 x half> %va, <vscale x 16 x half> %splat, <vscale x 16 x half> %neg)
+  ret <vscale x 16 x half> %vd
+}
+
+declare <vscale x 32 x half> @llvm.fma.v32f16(<vscale x 32 x half>, <vscale x 32 x half>, <vscale x 32 x half>)
+
+define <vscale x 32 x half> @vfmsub_vv_nxv32f16(<vscale x 32 x half> %va, <vscale x 32 x half> %vb, <vscale x 32 x half> %vc) {
+; CHECK-LABEL: vfmsub_vv_nxv32f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a1, zero, e16,m8,ta,mu
+; CHECK-NEXT:    vle16.v v24, (a0)
+; CHECK-NEXT:    vsetvli a0, zero, e16,m8,tu,mu
+; CHECK-NEXT:    vfmsub.vv v16, v24, v8
+; CHECK-NEXT:    vmv8r.v v8, v16
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 32 x half> %va
+  %vd = call <vscale x 32 x half> @llvm.fma.v32f16(<vscale x 32 x half> %vc, <vscale x 32 x half> %vb, <vscale x 32 x half> %neg)
+  ret <vscale x 32 x half> %vd
+}
+
+define <vscale x 32 x half> @vfmsub_vf_nxv32f16(<vscale x 32 x half> %va, <vscale x 32 x half> %vb, half %c) {
+; CHECK-LABEL: vfmsub_vf_nxv32f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,m8,tu,mu
+; CHECK-NEXT:    vfmsub.vf v16, fa0, v8
+; CHECK-NEXT:    vmv8r.v v8, v16
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 32 x half> undef, half %c, i32 0
+  %splat = shufflevector <vscale x 32 x half> %head, <vscale x 32 x half> undef, <vscale x 32 x i32> zeroinitializer
+  %neg = fneg <vscale x 32 x half> %va
+  %vd = call <vscale x 32 x half> @llvm.fma.v32f16(<vscale x 32 x half> %vb, <vscale x 32 x half> %splat, <vscale x 32 x half> %neg)
+  ret <vscale x 32 x half> %vd
+}
+
+declare <vscale x 1 x float> @llvm.fma.v1f32(<vscale x 1 x float>, <vscale x 1 x float>, <vscale x 1 x float>)
+
+define <vscale x 1 x float> @vfmsub_vv_nxv1f32(<vscale x 1 x float> %va, <vscale x 1 x float> %vb, <vscale x 1 x float> %vc) {
+; CHECK-LABEL: vfmsub_vv_nxv1f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e32,mf2,tu,mu
+; CHECK-NEXT:    vfmsub.vv v9, v8, v10
+; CHECK-NEXT:    vmv1r.v v8, v9
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 1 x float> %vc
+  %vd = call <vscale x 1 x float> @llvm.fma.v1f32(<vscale x 1 x float> %va, <vscale x 1 x float> %vb, <vscale x 1 x float> %neg)
+  ret <vscale x 1 x float> %vd
+}
+
+define <vscale x 1 x float> @vfmsub_vf_nxv1f32(<vscale x 1 x float> %va, <vscale x 1 x float> %vb, float %c) {
+; CHECK-LABEL: vfmsub_vf_nxv1f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e32,mf2,tu,mu
+; CHECK-NEXT:    vfmsub.vf v8, fa0, v9
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 1 x float> undef, float %c, i32 0
+  %splat = shufflevector <vscale x 1 x float> %head, <vscale x 1 x float> undef, <vscale x 1 x i32> zeroinitializer
+  %neg = fneg <vscale x 1 x float> %vb
+  %vd = call <vscale x 1 x float> @llvm.fma.v1f32(<vscale x 1 x float> %va, <vscale x 1 x float> %splat, <vscale x 1 x float> %neg)
+  ret <vscale x 1 x float> %vd
+}
+
+declare <vscale x 2 x float> @llvm.fma.v2f32(<vscale x 2 x float>, <vscale x 2 x float>, <vscale x 2 x float>)
+
+define <vscale x 2 x float> @vfmsub_vv_nxv2f32(<vscale x 2 x float> %va, <vscale x 2 x float> %vb, <vscale x 2 x float> %vc) {
+; CHECK-LABEL: vfmsub_vv_nxv2f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e32,m1,tu,mu
+; CHECK-NEXT:    vfmsub.vv v10, v8, v9
+; CHECK-NEXT:    vmv1r.v v8, v10
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 2 x float> %vb
+  %vd = call <vscale x 2 x float> @llvm.fma.v2f32(<vscale x 2 x float> %va, <vscale x 2 x float> %vc, <vscale x 2 x float> %neg)
+  ret <vscale x 2 x float> %vd
+}
+
+define <vscale x 2 x float> @vfmsub_vf_nxv2f32(<vscale x 2 x float> %va, <vscale x 2 x float> %vb, float %c) {
+; CHECK-LABEL: vfmsub_vf_nxv2f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e32,m1,tu,mu
+; CHECK-NEXT:    vfmsub.vf v9, fa0, v8
+; CHECK-NEXT:    vmv1r.v v8, v9
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 2 x float> undef, float %c, i32 0
+  %splat = shufflevector <vscale x 2 x float> %head, <vscale x 2 x float> undef, <vscale x 2 x i32> zeroinitializer
+  %neg = fneg <vscale x 2 x float> %va
+  %vd = call <vscale x 2 x float> @llvm.fma.v2f32(<vscale x 2 x float> %vb, <vscale x 2 x float> %splat, <vscale x 2 x float> %neg)
+  ret <vscale x 2 x float> %vd
+}
+
+declare <vscale x 4 x float> @llvm.fma.v4f32(<vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>)
+
+define <vscale x 4 x float> @vfmsub_vv_nxv4f32(<vscale x 4 x float> %va, <vscale x 4 x float> %vb, <vscale x 4 x float> %vc) {
+; CHECK-LABEL: vfmsub_vv_nxv4f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e32,m2,tu,mu
+; CHECK-NEXT:    vfmsub.vv v8, v10, v12
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 4 x float> %vc
+  %vd = call <vscale x 4 x float> @llvm.fma.v4f32(<vscale x 4 x float> %vb, <vscale x 4 x float> %va, <vscale x 4 x float> %neg)
+  ret <vscale x 4 x float> %vd
+}
+
+define <vscale x 4 x float> @vfmsub_vf_nxv4f32(<vscale x 4 x float> %va, <vscale x 4 x float> %vb, float %c) {
+; CHECK-LABEL: vfmsub_vf_nxv4f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e32,m2,tu,mu
+; CHECK-NEXT:    vfmsub.vf v8, fa0, v10
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 4 x float> undef, float %c, i32 0
+  %splat = shufflevector <vscale x 4 x float> %head, <vscale x 4 x float> undef, <vscale x 4 x i32> zeroinitializer
+  %neg = fneg <vscale x 4 x float> %vb
+  %vd = call <vscale x 4 x float> @llvm.fma.v4f32(<vscale x 4 x float> %va, <vscale x 4 x float> %splat, <vscale x 4 x float> %neg)
+  ret <vscale x 4 x float> %vd
+}
+
+declare <vscale x 8 x float> @llvm.fma.v8f32(<vscale x 8 x float>, <vscale x 8 x float>, <vscale x 8 x float>)
+
+define <vscale x 8 x float> @vfmsub_vv_nxv8f32(<vscale x 8 x float> %va, <vscale x 8 x float> %vb, <vscale x 8 x float> %vc) {
+; CHECK-LABEL: vfmsub_vv_nxv8f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e32,m4,tu,mu
+; CHECK-NEXT:    vfmsub.vv v16, v12, v8
+; CHECK-NEXT:    vmv4r.v v8, v16
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 8 x float> %va
+  %vd = call <vscale x 8 x float> @llvm.fma.v8f32(<vscale x 8 x float> %vb, <vscale x 8 x float> %vc, <vscale x 8 x float> %neg)
+  ret <vscale x 8 x float> %vd
+}
+
+define <vscale x 8 x float> @vfmsub_vf_nxv8f32(<vscale x 8 x float> %va, <vscale x 8 x float> %vb, float %c) {
+; CHECK-LABEL: vfmsub_vf_nxv8f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e32,m4,tu,mu
+; CHECK-NEXT:    vfmsub.vf v12, fa0, v8
+; CHECK-NEXT:    vmv4r.v v8, v12
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 8 x float> undef, float %c, i32 0
+  %splat = shufflevector <vscale x 8 x float> %head, <vscale x 8 x float> undef, <vscale x 8 x i32> zeroinitializer
+  %neg = fneg <vscale x 8 x float> %va
+  %vd = call <vscale x 8 x float> @llvm.fma.v8f32(<vscale x 8 x float> %vb, <vscale x 8 x float> %splat, <vscale x 8 x float> %neg)
+  ret <vscale x 8 x float> %vd
+}
+
+declare <vscale x 16 x float> @llvm.fma.v16f32(<vscale x 16 x float>, <vscale x 16 x float>, <vscale x 16 x float>)
+
+define <vscale x 16 x float> @vfmsub_vv_nxv16f32(<vscale x 16 x float> %va, <vscale x 16 x float> %vb, <vscale x 16 x float> %vc) {
+; CHECK-LABEL: vfmsub_vv_nxv16f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a1, zero, e32,m8,ta,mu
+; CHECK-NEXT:    vle32.v v24, (a0)
+; CHECK-NEXT:    vsetvli a0, zero, e32,m8,tu,mu
+; CHECK-NEXT:    vfmsub.vv v8, v24, v16
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 16 x float> %vb
+  %vd = call <vscale x 16 x float> @llvm.fma.v16f32(<vscale x 16 x float> %vc, <vscale x 16 x float> %va, <vscale x 16 x float> %neg)
+  ret <vscale x 16 x float> %vd
+}
+
+define <vscale x 16 x float> @vfmsub_vf_nxv16f32(<vscale x 16 x float> %va, <vscale x 16 x float> %vb, float %c) {
+; CHECK-LABEL: vfmsub_vf_nxv16f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e32,m8,tu,mu
+; CHECK-NEXT:    vfmsub.vf v8, fa0, v16
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 16 x float> undef, float %c, i32 0
+  %splat = shufflevector <vscale x 16 x float> %head, <vscale x 16 x float> undef, <vscale x 16 x i32> zeroinitializer
+  %neg = fneg <vscale x 16 x float> %vb
+  %vd = call <vscale x 16 x float> @llvm.fma.v16f32(<vscale x 16 x float> %va, <vscale x 16 x float> %splat, <vscale x 16 x float> %neg)
+  ret <vscale x 16 x float> %vd
+}
+
+declare <vscale x 1 x double> @llvm.fma.v1f64(<vscale x 1 x double>, <vscale x 1 x double>, <vscale x 1 x double>)
+
+define <vscale x 1 x double> @vfmsub_vv_nxv1f64(<vscale x 1 x double> %va, <vscale x 1 x double> %vb, <vscale x 1 x double> %vc) {
+; CHECK-LABEL: vfmsub_vv_nxv1f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e64,m1,tu,mu
+; CHECK-NEXT:    vfmsub.vv v9, v8, v10
+; CHECK-NEXT:    vmv1r.v v8, v9
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 1 x double> %vc
+  %vd = call <vscale x 1 x double> @llvm.fma.v1f64(<vscale x 1 x double> %va, <vscale x 1 x double> %vb, <vscale x 1 x double> %neg)
+  ret <vscale x 1 x double> %vd
+}
+
+define <vscale x 1 x double> @vfmsub_vf_nxv1f64(<vscale x 1 x double> %va, <vscale x 1 x double> %vb, double %c) {
+; CHECK-LABEL: vfmsub_vf_nxv1f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e64,m1,tu,mu
+; CHECK-NEXT:    vfmsub.vf v8, fa0, v9
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 1 x double> undef, double %c, i32 0
+  %splat = shufflevector <vscale x 1 x double> %head, <vscale x 1 x double> undef, <vscale x 1 x i32> zeroinitializer
+  %neg = fneg <vscale x 1 x double> %vb
+  %vd = call <vscale x 1 x double> @llvm.fma.v1f64(<vscale x 1 x double> %va, <vscale x 1 x double> %splat, <vscale x 1 x double> %neg)
+  ret <vscale x 1 x double> %vd
+}
+
+declare <vscale x 2 x double> @llvm.fma.v2f64(<vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>)
+
+define <vscale x 2 x double> @vfmsub_vv_nxv2f64(<vscale x 2 x double> %va, <vscale x 2 x double> %vb, <vscale x 2 x double> %vc) {
+; CHECK-LABEL: vfmsub_vv_nxv2f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e64,m2,tu,mu
+; CHECK-NEXT:    vfmsub.vv v12, v8, v10
+; CHECK-NEXT:    vmv2r.v v8, v12
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 2 x double> %vb
+  %vd = call <vscale x 2 x double> @llvm.fma.v2f64(<vscale x 2 x double> %va, <vscale x 2 x double> %vc, <vscale x 2 x double> %neg)
+  ret <vscale x 2 x double> %vd
+}
+
+define <vscale x 2 x double> @vfmsub_vf_nxv2f64(<vscale x 2 x double> %va, <vscale x 2 x double> %vb, double %c) {
+; CHECK-LABEL: vfmsub_vf_nxv2f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e64,m2,tu,mu
+; CHECK-NEXT:    vfmsub.vf v10, fa0, v8
+; CHECK-NEXT:    vmv2r.v v8, v10
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 2 x double> undef, double %c, i32 0
+  %splat = shufflevector <vscale x 2 x double> %head, <vscale x 2 x double> undef, <vscale x 2 x i32> zeroinitializer
+  %neg = fneg <vscale x 2 x double> %va
+  %vd = call <vscale x 2 x double> @llvm.fma.v2f64(<vscale x 2 x double> %vb, <vscale x 2 x double> %splat, <vscale x 2 x double> %neg)
+  ret <vscale x 2 x double> %vd
+}
+
+declare <vscale x 4 x double> @llvm.fma.v4f64(<vscale x 4 x double>, <vscale x 4 x double>, <vscale x 4 x double>)
+
+define <vscale x 4 x double> @vfmsub_vv_nxv4f64(<vscale x 4 x double> %va, <vscale x 4 x double> %vb, <vscale x 4 x double> %vc) {
+; CHECK-LABEL: vfmsub_vv_nxv4f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e64,m4,tu,mu
+; CHECK-NEXT:    vfmsub.vv v8, v12, v16
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 4 x double> %vc
+  %vd = call <vscale x 4 x double> @llvm.fma.v4f64(<vscale x 4 x double> %vb, <vscale x 4 x double> %va, <vscale x 4 x double> %neg)
+  ret <vscale x 4 x double> %vd
+}
+
+define <vscale x 4 x double> @vfmsub_vf_nxv4f64(<vscale x 4 x double> %va, <vscale x 4 x double> %vb, double %c) {
+; CHECK-LABEL: vfmsub_vf_nxv4f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e64,m4,tu,mu
+; CHECK-NEXT:    vfmsub.vf v8, fa0, v12
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 4 x double> undef, double %c, i32 0
+  %splat = shufflevector <vscale x 4 x double> %head, <vscale x 4 x double> undef, <vscale x 4 x i32> zeroinitializer
+  %neg = fneg <vscale x 4 x double> %vb
+  %vd = call <vscale x 4 x double> @llvm.fma.v4f64(<vscale x 4 x double> %va, <vscale x 4 x double> %splat, <vscale x 4 x double> %neg)
+  ret <vscale x 4 x double> %vd
+}
+
+declare <vscale x 8 x double> @llvm.fma.v8f64(<vscale x 8 x double>, <vscale x 8 x double>, <vscale x 8 x double>)
+
+define <vscale x 8 x double> @vfmsub_vv_nxv8f64(<vscale x 8 x double> %va, <vscale x 8 x double> %vb, <vscale x 8 x double> %vc) {
+; CHECK-LABEL: vfmsub_vv_nxv8f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a1, zero, e64,m8,ta,mu
+; CHECK-NEXT:    vle64.v v24, (a0)
+; CHECK-NEXT:    vsetvli a0, zero, e64,m8,tu,mu
+; CHECK-NEXT:    vfmsub.vv v24, v16, v8
+; CHECK-NEXT:    vmv8r.v v8, v24
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 8 x double> %va
+  %vd = call <vscale x 8 x double> @llvm.fma.v8f64(<vscale x 8 x double> %vb, <vscale x 8 x double> %vc, <vscale x 8 x double> %neg)
+  ret <vscale x 8 x double> %vd
+}
+
+define <vscale x 8 x double> @vfmsub_vf_nxv8f64(<vscale x 8 x double> %va, <vscale x 8 x double> %vb, double %c) {
+; CHECK-LABEL: vfmsub_vf_nxv8f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e64,m8,tu,mu
+; CHECK-NEXT:    vfmsub.vf v16, fa0, v8
+; CHECK-NEXT:    vmv8r.v v8, v16
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 8 x double> undef, double %c, i32 0
+  %splat = shufflevector <vscale x 8 x double> %head, <vscale x 8 x double> undef, <vscale x 8 x i32> zeroinitializer
+  %neg = fneg <vscale x 8 x double> %va
+  %vd = call <vscale x 8 x double> @llvm.fma.v8f64(<vscale x 8 x double> %vb, <vscale x 8 x double> %splat, <vscale x 8 x double> %neg)
+  ret <vscale x 8 x double> %vd
+}

diff --git a/llvm/test/CodeGen/RISCV/rvv/vfnmadd-sdnode.ll b/llvm/test/CodeGen/RISCV/rvv/vfnmadd-sdnode.ll
new file mode 100644 (file)
index 0000000..9f3c72c
--- /dev/null
+++ b/llvm/test/CodeGen/RISCV/rvv/vfnmadd-sdnode.ll
@@ -0,0 +1,447 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=riscv32 -mattr=+d,+experimental-zfh,+experimental-v -target-abi=ilp32d \
+; RUN:     -verify-machineinstrs < %s | FileCheck %s
+; RUN: llc -mtriple=riscv64 -mattr=+d,+experimental-zfh,+experimental-v -target-abi=lp64d \
+; RUN:     -verify-machineinstrs < %s | FileCheck %s
+
+; This tests a mix of vfnmacc and vfnmadd by using different operand orders to
+; trigger commuting in TwoAddressInstructionPass.
+
+declare <vscale x 1 x half> @llvm.fma.v1f16(<vscale x 1 x half>, <vscale x 1 x half>, <vscale x 1 x half>)
+
+define <vscale x 1 x half> @vfnmsub_vv_nxv1f16(<vscale x 1 x half> %va, <vscale x 1 x half> %vb, <vscale x 1 x half> %vc) {
+; CHECK-LABEL: vfnmsub_vv_nxv1f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,mf4,tu,mu
+; CHECK-NEXT:    vfnmadd.vv v9, v8, v10
+; CHECK-NEXT:    vmv1r.v v8, v9
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 1 x half> %va
+  %neg2 = fneg <vscale x 1 x half> %vc
+  %vd = call <vscale x 1 x half> @llvm.fma.v1f16(<vscale x 1 x half> %neg, <vscale x 1 x half> %vb, <vscale x 1 x half> %neg2)
+  ret <vscale x 1 x half> %vd
+}
+
+define <vscale x 1 x half> @vfnmsub_vf_nxv1f16(<vscale x 1 x half> %va, <vscale x 1 x half> %vb, half %c) {
+; CHECK-LABEL: vfnmsub_vf_nxv1f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,mf4,tu,mu
+; CHECK-NEXT:    vfnmadd.vf v8, fa0, v9
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 1 x half> undef, half %c, i32 0
+  %splat = shufflevector <vscale x 1 x half> %head, <vscale x 1 x half> undef, <vscale x 1 x i32> zeroinitializer
+  %neg = fneg <vscale x 1 x half> %va
+  %neg2 = fneg <vscale x 1 x half> %vb
+  %vd = call <vscale x 1 x half> @llvm.fma.v1f16(<vscale x 1 x half> %neg, <vscale x 1 x half> %splat, <vscale x 1 x half> %neg2)
+  ret <vscale x 1 x half> %vd
+}
+
+declare <vscale x 2 x half> @llvm.fma.v2f16(<vscale x 2 x half>, <vscale x 2 x half>, <vscale x 2 x half>)
+
+define <vscale x 2 x half> @vfnmsub_vv_nxv2f16(<vscale x 2 x half> %va, <vscale x 2 x half> %vb, <vscale x 2 x half> %vc) {
+; CHECK-LABEL: vfnmsub_vv_nxv2f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,mf2,tu,mu
+; CHECK-NEXT:    vfnmadd.vv v10, v8, v9
+; CHECK-NEXT:    vmv1r.v v8, v10
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 2 x half> %va
+  %neg2 = fneg <vscale x 2 x half> %vb
+  %vd = call <vscale x 2 x half> @llvm.fma.v2f16(<vscale x 2 x half> %neg, <vscale x 2 x half> %vc, <vscale x 2 x half> %neg2)
+  ret <vscale x 2 x half> %vd
+}
+
+define <vscale x 2 x half> @vfnmsub_vf_nxv2f16(<vscale x 2 x half> %va, <vscale x 2 x half> %vb, half %c) {
+; CHECK-LABEL: vfnmsub_vf_nxv2f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,mf2,tu,mu
+; CHECK-NEXT:    vfnmadd.vf v8, fa0, v9
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 2 x half> undef, half %c, i32 0
+  %splat = shufflevector <vscale x 2 x half> %head, <vscale x 2 x half> undef, <vscale x 2 x i32> zeroinitializer
+  %neg = fneg <vscale x 2 x half> %va
+  %neg2 = fneg <vscale x 2 x half> %vb
+  %vd = call <vscale x 2 x half> @llvm.fma.v2f16(<vscale x 2 x half> %splat, <vscale x 2 x half> %neg, <vscale x 2 x half> %neg2)
+  ret <vscale x 2 x half> %vd
+}
+
+declare <vscale x 4 x half> @llvm.fma.v4f16(<vscale x 4 x half>, <vscale x 4 x half>, <vscale x 4 x half>)
+
+define <vscale x 4 x half> @vfnmsub_vv_nxv4f16(<vscale x 4 x half> %va, <vscale x 4 x half> %vb, <vscale x 4 x half> %vc) {
+; CHECK-LABEL: vfnmsub_vv_nxv4f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,m1,tu,mu
+; CHECK-NEXT:    vfnmadd.vv v8, v9, v10
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 4 x half> %vb
+  %neg2 = fneg <vscale x 4 x half> %vc
+  %vd = call <vscale x 4 x half> @llvm.fma.v4f16(<vscale x 4 x half> %neg, <vscale x 4 x half> %va, <vscale x 4 x half> %neg2)
+  ret <vscale x 4 x half> %vd
+}
+
+define <vscale x 4 x half> @vfnmsub_vf_nxv4f16(<vscale x 4 x half> %va, <vscale x 4 x half> %vb, half %c) {
+; CHECK-LABEL: vfnmsub_vf_nxv4f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,m1,tu,mu
+; CHECK-NEXT:    vfnmadd.vf v8, fa0, v9
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 4 x half> undef, half %c, i32 0
+  %splat = shufflevector <vscale x 4 x half> %head, <vscale x 4 x half> undef, <vscale x 4 x i32> zeroinitializer
+  %neg = fneg <vscale x 4 x half> %splat
+  %neg2 = fneg <vscale x 4 x half> %vb
+  %vd = call <vscale x 4 x half> @llvm.fma.v4f16(<vscale x 4 x half> %va, <vscale x 4 x half> %neg, <vscale x 4 x half> %neg2)
+  ret <vscale x 4 x half> %vd
+}
+
+declare <vscale x 8 x half> @llvm.fma.v8f16(<vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>)
+
+define <vscale x 8 x half> @vfnmsub_vv_nxv8f16(<vscale x 8 x half> %va, <vscale x 8 x half> %vb, <vscale x 8 x half> %vc) {
+; CHECK-LABEL: vfnmsub_vv_nxv8f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,m2,tu,mu
+; CHECK-NEXT:    vfnmadd.vv v12, v10, v8
+; CHECK-NEXT:    vmv2r.v v8, v12
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 8 x half> %vb
+  %neg2 = fneg <vscale x 8 x half> %va
+  %vd = call <vscale x 8 x half> @llvm.fma.v8f16(<vscale x 8 x half> %neg, <vscale x 8 x half> %vc, <vscale x 8 x half> %neg2)
+  ret <vscale x 8 x half> %vd
+}
+
+define <vscale x 8 x half> @vfnmsub_vf_nxv8f16(<vscale x 8 x half> %va, <vscale x 8 x half> %vb, half %c) {
+; CHECK-LABEL: vfnmsub_vf_nxv8f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,m2,tu,mu
+; CHECK-NEXT:    vfnmadd.vf v10, fa0, v8
+; CHECK-NEXT:    vmv2r.v v8, v10
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 8 x half> undef, half %c, i32 0
+  %splat = shufflevector <vscale x 8 x half> %head, <vscale x 8 x half> undef, <vscale x 8 x i32> zeroinitializer
+  %neg = fneg <vscale x 8 x half> %splat
+  %neg2 = fneg <vscale x 8 x half> %va
+  %vd = call <vscale x 8 x half> @llvm.fma.v8f16(<vscale x 8 x half> %vb, <vscale x 8 x half> %neg, <vscale x 8 x half> %neg2)
+  ret <vscale x 8 x half> %vd
+}
+
+declare <vscale x 16 x half> @llvm.fma.v16f16(<vscale x 16 x half>, <vscale x 16 x half>, <vscale x 16 x half>)
+
+define <vscale x 16 x half> @vfnmsub_vv_nxv16f16(<vscale x 16 x half> %va, <vscale x 16 x half> %vb, <vscale x 16 x half> %vc) {
+; CHECK-LABEL: vfnmsub_vv_nxv16f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,m4,tu,mu
+; CHECK-NEXT:    vfnmadd.vv v8, v16, v12
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 16 x half> %vc
+  %neg2 = fneg <vscale x 16 x half> %vb
+  %vd = call <vscale x 16 x half> @llvm.fma.v16f16(<vscale x 16 x half> %neg, <vscale x 16 x half> %va, <vscale x 16 x half> %neg2)
+  ret <vscale x 16 x half> %vd
+}
+
+define <vscale x 16 x half> @vfnmsub_vf_nxv16f16(<vscale x 16 x half> %va, <vscale x 16 x half> %vb, half %c) {
+; CHECK-LABEL: vfnmsub_vf_nxv16f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,m4,tu,mu
+; CHECK-NEXT:    vfnmadd.vf v8, fa0, v12
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 16 x half> undef, half %c, i32 0
+  %splat = shufflevector <vscale x 16 x half> %head, <vscale x 16 x half> undef, <vscale x 16 x i32> zeroinitializer
+  %neg = fneg <vscale x 16 x half> %splat
+  %neg2 = fneg <vscale x 16 x half> %vb
+  %vd = call <vscale x 16 x half> @llvm.fma.v16f16(<vscale x 16 x half> %neg, <vscale x 16 x half> %va, <vscale x 16 x half> %neg2)
+  ret <vscale x 16 x half> %vd
+}
+
+declare <vscale x 32 x half> @llvm.fma.v32f16(<vscale x 32 x half>, <vscale x 32 x half>, <vscale x 32 x half>)
+
+define <vscale x 32 x half> @vfnmsub_vv_nxv32f16(<vscale x 32 x half> %va, <vscale x 32 x half> %vb, <vscale x 32 x half> %vc) {
+; CHECK-LABEL: vfnmsub_vv_nxv32f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a1, zero, e16,m8,ta,mu
+; CHECK-NEXT:    vle16.v v24, (a0)
+; CHECK-NEXT:    vsetvli a0, zero, e16,m8,tu,mu
+; CHECK-NEXT:    vfnmadd.vv v8, v24, v16
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 32 x half> %vc
+  %neg2 = fneg <vscale x 32 x half> %vb
+  %vd = call <vscale x 32 x half> @llvm.fma.v32f16(<vscale x 32 x half> %neg, <vscale x 32 x half> %va, <vscale x 32 x half> %neg2)
+  ret <vscale x 32 x half> %vd
+}
+
+define <vscale x 32 x half> @vfnmsub_vf_nxv32f16(<vscale x 32 x half> %va, <vscale x 32 x half> %vb, half %c) {
+; CHECK-LABEL: vfnmsub_vf_nxv32f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,m8,tu,mu
+; CHECK-NEXT:    vfnmadd.vf v16, fa0, v8
+; CHECK-NEXT:    vmv8r.v v8, v16
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 32 x half> undef, half %c, i32 0
+  %splat = shufflevector <vscale x 32 x half> %head, <vscale x 32 x half> undef, <vscale x 32 x i32> zeroinitializer
+  %neg = fneg <vscale x 32 x half> %splat
+  %neg2 = fneg <vscale x 32 x half> %va
+  %vd = call <vscale x 32 x half> @llvm.fma.v32f16(<vscale x 32 x half> %neg, <vscale x 32 x half> %vb, <vscale x 32 x half> %neg2)
+  ret <vscale x 32 x half> %vd
+}
+
+declare <vscale x 1 x float> @llvm.fma.v1f32(<vscale x 1 x float>, <vscale x 1 x float>, <vscale x 1 x float>)
+
+define <vscale x 1 x float> @vfnmsub_vv_nxv1f32(<vscale x 1 x float> %va, <vscale x 1 x float> %vb, <vscale x 1 x float> %vc) {
+; CHECK-LABEL: vfnmsub_vv_nxv1f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e32,mf2,tu,mu
+; CHECK-NEXT:    vfnmadd.vv v8, v9, v10
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 1 x float> %vb
+  %neg2 = fneg <vscale x 1 x float> %vc
+  %vd = call <vscale x 1 x float> @llvm.fma.v1f32(<vscale x 1 x float> %va, <vscale x 1 x float> %neg, <vscale x 1 x float> %neg2)
+  ret <vscale x 1 x float> %vd
+}
+
+define <vscale x 1 x float> @vfnmsub_vf_nxv1f32(<vscale x 1 x float> %va, <vscale x 1 x float> %vb, float %c) {
+; CHECK-LABEL: vfnmsub_vf_nxv1f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e32,mf2,tu,mu
+; CHECK-NEXT:    vfnmadd.vf v8, fa0, v9
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 1 x float> undef, float %c, i32 0
+  %splat = shufflevector <vscale x 1 x float> %head, <vscale x 1 x float> undef, <vscale x 1 x i32> zeroinitializer
+  %neg = fneg <vscale x 1 x float> %va
+  %neg2 = fneg <vscale x 1 x float> %vb
+  %vd = call <vscale x 1 x float> @llvm.fma.v1f32(<vscale x 1 x float> %neg, <vscale x 1 x float> %splat, <vscale x 1 x float> %neg2)
+  ret <vscale x 1 x float> %vd
+}
+
+declare <vscale x 2 x float> @llvm.fma.v2f32(<vscale x 2 x float>, <vscale x 2 x float>, <vscale x 2 x float>)
+
+define <vscale x 2 x float> @vfnmsub_vv_nxv2f32(<vscale x 2 x float> %va, <vscale x 2 x float> %vb, <vscale x 2 x float> %vc) {
+; CHECK-LABEL: vfnmsub_vv_nxv2f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e32,m1,tu,mu
+; CHECK-NEXT:    vfnmadd.vv v8, v10, v9
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 2 x float> %vc
+  %neg2 = fneg <vscale x 2 x float> %vb
+  %vd = call <vscale x 2 x float> @llvm.fma.v2f32(<vscale x 2 x float> %va, <vscale x 2 x float> %neg, <vscale x 2 x float> %neg2)
+  ret <vscale x 2 x float> %vd
+}
+
+define <vscale x 2 x float> @vfnmsub_vf_nxv2f32(<vscale x 2 x float> %va, <vscale x 2 x float> %vb, float %c) {
+; CHECK-LABEL: vfnmsub_vf_nxv2f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e32,m1,tu,mu
+; CHECK-NEXT:    vfnmadd.vf v8, fa0, v9
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 2 x float> undef, float %c, i32 0
+  %splat = shufflevector <vscale x 2 x float> %head, <vscale x 2 x float> undef, <vscale x 2 x i32> zeroinitializer
+  %neg = fneg <vscale x 2 x float> %va
+  %neg2 = fneg <vscale x 2 x float> %vb
+  %vd = call <vscale x 2 x float> @llvm.fma.v2f32(<vscale x 2 x float> %splat, <vscale x 2 x float> %neg, <vscale x 2 x float> %neg2)
+  ret <vscale x 2 x float> %vd
+}
+
+declare <vscale x 4 x float> @llvm.fma.v4f32(<vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>)
+
+define <vscale x 4 x float> @vfnmsub_vv_nxv4f32(<vscale x 4 x float> %va, <vscale x 4 x float> %vb, <vscale x 4 x float> %vc) {
+; CHECK-LABEL: vfnmsub_vv_nxv4f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e32,m2,tu,mu
+; CHECK-NEXT:    vfnmadd.vv v10, v8, v12
+; CHECK-NEXT:    vmv2r.v v8, v10
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 4 x float> %va
+  %neg2 = fneg <vscale x 4 x float> %vc
+  %vd = call <vscale x 4 x float> @llvm.fma.v4f32(<vscale x 4 x float> %vb, <vscale x 4 x float> %neg, <vscale x 4 x float> %neg2)
+  ret <vscale x 4 x float> %vd
+}
+
+define <vscale x 4 x float> @vfnmsub_vf_nxv4f32(<vscale x 4 x float> %va, <vscale x 4 x float> %vb, float %c) {
+; CHECK-LABEL: vfnmsub_vf_nxv4f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e32,m2,tu,mu
+; CHECK-NEXT:    vfnmadd.vf v8, fa0, v10
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 4 x float> undef, float %c, i32 0
+  %splat = shufflevector <vscale x 4 x float> %head, <vscale x 4 x float> undef, <vscale x 4 x i32> zeroinitializer
+  %neg = fneg <vscale x 4 x float> %splat
+  %neg2 = fneg <vscale x 4 x float> %vb
+  %vd = call <vscale x 4 x float> @llvm.fma.v4f32(<vscale x 4 x float> %va, <vscale x 4 x float> %neg, <vscale x 4 x float> %neg2)
+  ret <vscale x 4 x float> %vd
+}
+
+declare <vscale x 8 x float> @llvm.fma.v8f32(<vscale x 8 x float>, <vscale x 8 x float>, <vscale x 8 x float>)
+
+define <vscale x 8 x float> @vfnmsub_vv_nxv8f32(<vscale x 8 x float> %va, <vscale x 8 x float> %vb, <vscale x 8 x float> %vc) {
+; CHECK-LABEL: vfnmsub_vv_nxv8f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e32,m4,tu,mu
+; CHECK-NEXT:    vfnmadd.vv v12, v16, v8
+; CHECK-NEXT:    vmv4r.v v8, v12
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 8 x float> %vc
+  %neg2 = fneg <vscale x 8 x float> %va
+  %vd = call <vscale x 8 x float> @llvm.fma.v8f32(<vscale x 8 x float> %vb, <vscale x 8 x float> %neg, <vscale x 8 x float> %neg2)
+  ret <vscale x 8 x float> %vd
+}
+
+define <vscale x 8 x float> @vfnmsub_vf_nxv8f32(<vscale x 8 x float> %va, <vscale x 8 x float> %vb, float %c) {
+; CHECK-LABEL: vfnmsub_vf_nxv8f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e32,m4,tu,mu
+; CHECK-NEXT:    vfnmadd.vf v12, fa0, v8
+; CHECK-NEXT:    vmv4r.v v8, v12
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 8 x float> undef, float %c, i32 0
+  %splat = shufflevector <vscale x 8 x float> %head, <vscale x 8 x float> undef, <vscale x 8 x i32> zeroinitializer
+  %neg = fneg <vscale x 8 x float> %splat
+  %neg2 = fneg <vscale x 8 x float> %va
+  %vd = call <vscale x 8 x float> @llvm.fma.v8f32(<vscale x 8 x float> %vb, <vscale x 8 x float> %neg, <vscale x 8 x float> %neg2)
+  ret <vscale x 8 x float> %vd
+}
+
+declare <vscale x 16 x float> @llvm.fma.v16f32(<vscale x 16 x float>, <vscale x 16 x float>, <vscale x 16 x float>)
+
+define <vscale x 16 x float> @vfnmsub_vv_nxv16f32(<vscale x 16 x float> %va, <vscale x 16 x float> %vb, <vscale x 16 x float> %vc) {
+; CHECK-LABEL: vfnmsub_vv_nxv16f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a1, zero, e32,m8,ta,mu
+; CHECK-NEXT:    vle32.v v24, (a0)
+; CHECK-NEXT:    vsetvli a0, zero, e32,m8,tu,mu
+; CHECK-NEXT:    vfnmadd.vv v24, v8, v16
+; CHECK-NEXT:    vmv8r.v v8, v24
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 16 x float> %va
+  %neg2 = fneg <vscale x 16 x float> %vb
+  %vd = call <vscale x 16 x float> @llvm.fma.v16f32(<vscale x 16 x float> %vc, <vscale x 16 x float> %neg, <vscale x 16 x float> %neg2)
+  ret <vscale x 16 x float> %vd
+}
+
+define <vscale x 16 x float> @vfnmsub_vf_nxv16f32(<vscale x 16 x float> %va, <vscale x 16 x float> %vb, float %c) {
+; CHECK-LABEL: vfnmsub_vf_nxv16f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e32,m8,tu,mu
+; CHECK-NEXT:    vfnmadd.vf v8, fa0, v16
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 16 x float> undef, float %c, i32 0
+  %splat = shufflevector <vscale x 16 x float> %head, <vscale x 16 x float> undef, <vscale x 16 x i32> zeroinitializer
+  %neg = fneg <vscale x 16 x float> %splat
+  %neg2 = fneg <vscale x 16 x float> %vb
+  %vd = call <vscale x 16 x float> @llvm.fma.v16f32(<vscale x 16 x float> %neg, <vscale x 16 x float> %va, <vscale x 16 x float> %neg2)
+  ret <vscale x 16 x float> %vd
+}
+
+declare <vscale x 1 x double> @llvm.fma.v1f64(<vscale x 1 x double>, <vscale x 1 x double>, <vscale x 1 x double>)
+
+define <vscale x 1 x double> @vfnmsub_vv_nxv1f64(<vscale x 1 x double> %va, <vscale x 1 x double> %vb, <vscale x 1 x double> %vc) {
+; CHECK-LABEL: vfnmsub_vv_nxv1f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e64,m1,tu,mu
+; CHECK-NEXT:    vfnmadd.vv v10, v9, v8
+; CHECK-NEXT:    vmv1r.v v8, v10
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 1 x double> %vb
+  %neg2 = fneg <vscale x 1 x double> %va
+  %vd = call <vscale x 1 x double> @llvm.fma.v1f64(<vscale x 1 x double> %vc, <vscale x 1 x double> %neg, <vscale x 1 x double> %neg2)
+  ret <vscale x 1 x double> %vd
+}
+
+define <vscale x 1 x double> @vfnmsub_vf_nxv1f64(<vscale x 1 x double> %va, <vscale x 1 x double> %vb, double %c) {
+; CHECK-LABEL: vfnmsub_vf_nxv1f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e64,m1,tu,mu
+; CHECK-NEXT:    vfnmadd.vf v8, fa0, v9
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 1 x double> undef, double %c, i32 0
+  %splat = shufflevector <vscale x 1 x double> %head, <vscale x 1 x double> undef, <vscale x 1 x i32> zeroinitializer
+  %neg = fneg <vscale x 1 x double> %va
+  %neg2 = fneg <vscale x 1 x double> %vb
+  %vd = call <vscale x 1 x double> @llvm.fma.v1f64(<vscale x 1 x double> %neg, <vscale x 1 x double> %splat, <vscale x 1 x double> %neg2)
+  ret <vscale x 1 x double> %vd
+}
+
+declare <vscale x 2 x double> @llvm.fma.v2f64(<vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>)
+
+define <vscale x 2 x double> @vfnmsub_vv_nxv2f64(<vscale x 2 x double> %va, <vscale x 2 x double> %vb, <vscale x 2 x double> %vc) {
+; CHECK-LABEL: vfnmsub_vv_nxv2f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e64,m2,tu,mu
+; CHECK-NEXT:    vfnmadd.vv v12, v8, v10
+; CHECK-NEXT:    vmv2r.v v8, v12
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 2 x double> %va
+  %neg2 = fneg <vscale x 2 x double> %vb
+  %vd = call <vscale x 2 x double> @llvm.fma.v2f64(<vscale x 2 x double> %neg, <vscale x 2 x double> %vc, <vscale x 2 x double> %neg2)
+  ret <vscale x 2 x double> %vd
+}
+
+define <vscale x 2 x double> @vfnmsub_vf_nxv2f64(<vscale x 2 x double> %va, <vscale x 2 x double> %vb, double %c) {
+; CHECK-LABEL: vfnmsub_vf_nxv2f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e64,m2,tu,mu
+; CHECK-NEXT:    vfnmadd.vf v8, fa0, v10
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 2 x double> undef, double %c, i32 0
+  %splat = shufflevector <vscale x 2 x double> %head, <vscale x 2 x double> undef, <vscale x 2 x i32> zeroinitializer
+  %neg = fneg <vscale x 2 x double> %va
+  %neg2 = fneg <vscale x 2 x double> %vb
+  %vd = call <vscale x 2 x double> @llvm.fma.v2f64(<vscale x 2 x double> %splat, <vscale x 2 x double> %neg, <vscale x 2 x double> %neg2)
+  ret <vscale x 2 x double> %vd
+}
+
+declare <vscale x 4 x double> @llvm.fma.v4f64(<vscale x 4 x double>, <vscale x 4 x double>, <vscale x 4 x double>)
+
+define <vscale x 4 x double> @vfnmsub_vv_nxv4f64(<vscale x 4 x double> %va, <vscale x 4 x double> %vb, <vscale x 4 x double> %vc) {
+; CHECK-LABEL: vfnmsub_vv_nxv4f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e64,m4,tu,mu
+; CHECK-NEXT:    vfnmadd.vv v8, v12, v16
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 4 x double> %vb
+  %neg2 = fneg <vscale x 4 x double> %vc
+  %vd = call <vscale x 4 x double> @llvm.fma.v4f64(<vscale x 4 x double> %neg, <vscale x 4 x double> %va, <vscale x 4 x double> %neg2)
+  ret <vscale x 4 x double> %vd
+}
+
+define <vscale x 4 x double> @vfnmsub_vf_nxv4f64(<vscale x 4 x double> %va, <vscale x 4 x double> %vb, double %c) {
+; CHECK-LABEL: vfnmsub_vf_nxv4f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e64,m4,tu,mu
+; CHECK-NEXT:    vfnmadd.vf v8, fa0, v12
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 4 x double> undef, double %c, i32 0
+  %splat = shufflevector <vscale x 4 x double> %head, <vscale x 4 x double> undef, <vscale x 4 x i32> zeroinitializer
+  %neg = fneg <vscale x 4 x double> %splat
+  %neg2 = fneg <vscale x 4 x double> %vb
+  %vd = call <vscale x 4 x double> @llvm.fma.v4f64(<vscale x 4 x double> %va, <vscale x 4 x double> %neg, <vscale x 4 x double> %neg2)
+  ret <vscale x 4 x double> %vd
+}
+
+declare <vscale x 8 x double> @llvm.fma.v8f64(<vscale x 8 x double>, <vscale x 8 x double>, <vscale x 8 x double>)
+
+define <vscale x 8 x double> @vfnmsub_vv_nxv8f64(<vscale x 8 x double> %va, <vscale x 8 x double> %vb, <vscale x 8 x double> %vc) {
+; CHECK-LABEL: vfnmsub_vv_nxv8f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a1, zero, e64,m8,ta,mu
+; CHECK-NEXT:    vle64.v v24, (a0)
+; CHECK-NEXT:    vsetvli a0, zero, e64,m8,tu,mu
+; CHECK-NEXT:    vfnmadd.vv v24, v16, v8
+; CHECK-NEXT:    vmv8r.v v8, v24
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 8 x double> %vb
+  %neg2 = fneg <vscale x 8 x double> %va
+  %vd = call <vscale x 8 x double> @llvm.fma.v8f64(<vscale x 8 x double> %neg, <vscale x 8 x double> %vc, <vscale x 8 x double> %neg2)
+  ret <vscale x 8 x double> %vd
+}
+
+define <vscale x 8 x double> @vfnmsub_vf_nxv8f64(<vscale x 8 x double> %va, <vscale x 8 x double> %vb, double %c) {
+; CHECK-LABEL: vfnmsub_vf_nxv8f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e64,m8,tu,mu
+; CHECK-NEXT:    vfnmadd.vf v16, fa0, v8
+; CHECK-NEXT:    vmv8r.v v8, v16
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 8 x double> undef, double %c, i32 0
+  %splat = shufflevector <vscale x 8 x double> %head, <vscale x 8 x double> undef, <vscale x 8 x i32> zeroinitializer
+  %neg = fneg <vscale x 8 x double> %splat
+  %neg2 = fneg <vscale x 8 x double> %va
+  %vd = call <vscale x 8 x double> @llvm.fma.v8f64(<vscale x 8 x double> %vb, <vscale x 8 x double> %neg, <vscale x 8 x double> %neg2)
+  ret <vscale x 8 x double> %vd
+}

diff --git a/llvm/test/CodeGen/RISCV/rvv/vfnmsub-sdnode.ll b/llvm/test/CodeGen/RISCV/rvv/vfnmsub-sdnode.ll
new file mode 100644 (file)
index 0000000..ed94896
--- /dev/null
+++ b/llvm/test/CodeGen/RISCV/rvv/vfnmsub-sdnode.ll
@@ -0,0 +1,417 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=riscv32 -mattr=+d,+experimental-zfh,+experimental-v -target-abi=ilp32d \
+; RUN:     -verify-machineinstrs < %s | FileCheck %s
+; RUN: llc -mtriple=riscv64 -mattr=+d,+experimental-zfh,+experimental-v -target-abi=lp64d \
+; RUN:     -verify-machineinstrs < %s | FileCheck %s
+
+; This tests a mix of vfnmsac and vfnmsub by using different operand orders to
+; trigger commuting in TwoAddressInstructionPass.
+
+declare <vscale x 1 x half> @llvm.fma.v1f16(<vscale x 1 x half>, <vscale x 1 x half>, <vscale x 1 x half>)
+
+define <vscale x 1 x half> @vfnmsub_vv_nxv1f16(<vscale x 1 x half> %va, <vscale x 1 x half> %vb, <vscale x 1 x half> %vc) {
+; CHECK-LABEL: vfnmsub_vv_nxv1f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,mf4,tu,mu
+; CHECK-NEXT:    vfnmsub.vv v9, v8, v10
+; CHECK-NEXT:    vmv1r.v v8, v9
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 1 x half> %va
+  %vd = call <vscale x 1 x half> @llvm.fma.v1f16(<vscale x 1 x half> %neg, <vscale x 1 x half> %vb, <vscale x 1 x half> %vc)
+  ret <vscale x 1 x half> %vd
+}
+
+define <vscale x 1 x half> @vfnmsub_vf_nxv1f16(<vscale x 1 x half> %va, <vscale x 1 x half> %vb, half %c) {
+; CHECK-LABEL: vfnmsub_vf_nxv1f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,mf4,tu,mu
+; CHECK-NEXT:    vfnmsub.vf v8, fa0, v9
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 1 x half> undef, half %c, i32 0
+  %splat = shufflevector <vscale x 1 x half> %head, <vscale x 1 x half> undef, <vscale x 1 x i32> zeroinitializer
+  %neg = fneg <vscale x 1 x half> %va
+  %vd = call <vscale x 1 x half> @llvm.fma.v1f16(<vscale x 1 x half> %neg, <vscale x 1 x half> %splat, <vscale x 1 x half> %vb)
+  ret <vscale x 1 x half> %vd
+}
+
+declare <vscale x 2 x half> @llvm.fma.v2f16(<vscale x 2 x half>, <vscale x 2 x half>, <vscale x 2 x half>)
+
+define <vscale x 2 x half> @vfnmsub_vv_nxv2f16(<vscale x 2 x half> %va, <vscale x 2 x half> %vb, <vscale x 2 x half> %vc) {
+; CHECK-LABEL: vfnmsub_vv_nxv2f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,mf2,tu,mu
+; CHECK-NEXT:    vfnmsub.vv v10, v8, v9
+; CHECK-NEXT:    vmv1r.v v8, v10
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 2 x half> %va
+  %vd = call <vscale x 2 x half> @llvm.fma.v2f16(<vscale x 2 x half> %neg, <vscale x 2 x half> %vc, <vscale x 2 x half> %vb)
+  ret <vscale x 2 x half> %vd
+}
+
+define <vscale x 2 x half> @vfnmsub_vf_nxv2f16(<vscale x 2 x half> %va, <vscale x 2 x half> %vb, half %c) {
+; CHECK-LABEL: vfnmsub_vf_nxv2f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,mf2,tu,mu
+; CHECK-NEXT:    vfnmsub.vf v8, fa0, v9
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 2 x half> undef, half %c, i32 0
+  %splat = shufflevector <vscale x 2 x half> %head, <vscale x 2 x half> undef, <vscale x 2 x i32> zeroinitializer
+  %neg = fneg <vscale x 2 x half> %va
+  %vd = call <vscale x 2 x half> @llvm.fma.v2f16(<vscale x 2 x half> %splat, <vscale x 2 x half> %neg, <vscale x 2 x half> %vb)
+  ret <vscale x 2 x half> %vd
+}
+
+declare <vscale x 4 x half> @llvm.fma.v4f16(<vscale x 4 x half>, <vscale x 4 x half>, <vscale x 4 x half>)
+
+define <vscale x 4 x half> @vfnmsub_vv_nxv4f16(<vscale x 4 x half> %va, <vscale x 4 x half> %vb, <vscale x 4 x half> %vc) {
+; CHECK-LABEL: vfnmsub_vv_nxv4f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,m1,tu,mu
+; CHECK-NEXT:    vfnmsub.vv v8, v9, v10
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 4 x half> %vb
+  %vd = call <vscale x 4 x half> @llvm.fma.v4f16(<vscale x 4 x half> %neg, <vscale x 4 x half> %va, <vscale x 4 x half> %vc)
+  ret <vscale x 4 x half> %vd
+}
+
+define <vscale x 4 x half> @vfnmsub_vf_nxv4f16(<vscale x 4 x half> %va, <vscale x 4 x half> %vb, half %c) {
+; CHECK-LABEL: vfnmsub_vf_nxv4f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,m1,tu,mu
+; CHECK-NEXT:    vfnmsub.vf v8, fa0, v9
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 4 x half> undef, half %c, i32 0
+  %splat = shufflevector <vscale x 4 x half> %head, <vscale x 4 x half> undef, <vscale x 4 x i32> zeroinitializer
+  %neg = fneg <vscale x 4 x half> %splat
+  %vd = call <vscale x 4 x half> @llvm.fma.v4f16(<vscale x 4 x half> %va, <vscale x 4 x half> %neg, <vscale x 4 x half> %vb)
+  ret <vscale x 4 x half> %vd
+}
+
+declare <vscale x 8 x half> @llvm.fma.v8f16(<vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>)
+
+define <vscale x 8 x half> @vfnmsub_vv_nxv8f16(<vscale x 8 x half> %va, <vscale x 8 x half> %vb, <vscale x 8 x half> %vc) {
+; CHECK-LABEL: vfnmsub_vv_nxv8f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,m2,tu,mu
+; CHECK-NEXT:    vfnmsub.vv v12, v10, v8
+; CHECK-NEXT:    vmv2r.v v8, v12
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 8 x half> %vb
+  %vd = call <vscale x 8 x half> @llvm.fma.v8f16(<vscale x 8 x half> %neg, <vscale x 8 x half> %vc, <vscale x 8 x half> %va)
+  ret <vscale x 8 x half> %vd
+}
+
+define <vscale x 8 x half> @vfnmsub_vf_nxv8f16(<vscale x 8 x half> %va, <vscale x 8 x half> %vb, half %c) {
+; CHECK-LABEL: vfnmsub_vf_nxv8f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,m2,tu,mu
+; CHECK-NEXT:    vfnmsub.vf v10, fa0, v8
+; CHECK-NEXT:    vmv2r.v v8, v10
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 8 x half> undef, half %c, i32 0
+  %splat = shufflevector <vscale x 8 x half> %head, <vscale x 8 x half> undef, <vscale x 8 x i32> zeroinitializer
+  %neg = fneg <vscale x 8 x half> %splat
+  %vd = call <vscale x 8 x half> @llvm.fma.v8f16(<vscale x 8 x half> %vb, <vscale x 8 x half> %neg, <vscale x 8 x half> %va)
+  ret <vscale x 8 x half> %vd
+}
+
+declare <vscale x 16 x half> @llvm.fma.v16f16(<vscale x 16 x half>, <vscale x 16 x half>, <vscale x 16 x half>)
+
+define <vscale x 16 x half> @vfnmsub_vv_nxv16f16(<vscale x 16 x half> %va, <vscale x 16 x half> %vb, <vscale x 16 x half> %vc) {
+; CHECK-LABEL: vfnmsub_vv_nxv16f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,m4,tu,mu
+; CHECK-NEXT:    vfnmsub.vv v8, v16, v12
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 16 x half> %vc
+  %vd = call <vscale x 16 x half> @llvm.fma.v16f16(<vscale x 16 x half> %neg, <vscale x 16 x half> %va, <vscale x 16 x half> %vb)
+  ret <vscale x 16 x half> %vd
+}
+
+define <vscale x 16 x half> @vfnmsub_vf_nxv16f16(<vscale x 16 x half> %va, <vscale x 16 x half> %vb, half %c) {
+; CHECK-LABEL: vfnmsub_vf_nxv16f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,m4,tu,mu
+; CHECK-NEXT:    vfnmsub.vf v8, fa0, v12
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 16 x half> undef, half %c, i32 0
+  %splat = shufflevector <vscale x 16 x half> %head, <vscale x 16 x half> undef, <vscale x 16 x i32> zeroinitializer
+  %neg = fneg <vscale x 16 x half> %splat
+  %vd = call <vscale x 16 x half> @llvm.fma.v16f16(<vscale x 16 x half> %neg, <vscale x 16 x half> %va, <vscale x 16 x half> %vb)
+  ret <vscale x 16 x half> %vd
+}
+
+declare <vscale x 32 x half> @llvm.fma.v32f16(<vscale x 32 x half>, <vscale x 32 x half>, <vscale x 32 x half>)
+
+define <vscale x 32 x half> @vfnmsub_vv_nxv32f16(<vscale x 32 x half> %va, <vscale x 32 x half> %vb, <vscale x 32 x half> %vc) {
+; CHECK-LABEL: vfnmsub_vv_nxv32f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a1, zero, e16,m8,ta,mu
+; CHECK-NEXT:    vle16.v v24, (a0)
+; CHECK-NEXT:    vsetvli a0, zero, e16,m8,tu,mu
+; CHECK-NEXT:    vfnmsub.vv v8, v24, v16
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 32 x half> %vc
+  %vd = call <vscale x 32 x half> @llvm.fma.v32f16(<vscale x 32 x half> %neg, <vscale x 32 x half> %va, <vscale x 32 x half> %vb)
+  ret <vscale x 32 x half> %vd
+}
+
+define <vscale x 32 x half> @vfnmsub_vf_nxv32f16(<vscale x 32 x half> %va, <vscale x 32 x half> %vb, half %c) {
+; CHECK-LABEL: vfnmsub_vf_nxv32f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e16,m8,tu,mu
+; CHECK-NEXT:    vfnmsub.vf v16, fa0, v8
+; CHECK-NEXT:    vmv8r.v v8, v16
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 32 x half> undef, half %c, i32 0
+  %splat = shufflevector <vscale x 32 x half> %head, <vscale x 32 x half> undef, <vscale x 32 x i32> zeroinitializer
+  %neg = fneg <vscale x 32 x half> %splat
+  %vd = call <vscale x 32 x half> @llvm.fma.v32f16(<vscale x 32 x half> %neg, <vscale x 32 x half> %vb, <vscale x 32 x half> %va)
+  ret <vscale x 32 x half> %vd
+}
+
+declare <vscale x 1 x float> @llvm.fma.v1f32(<vscale x 1 x float>, <vscale x 1 x float>, <vscale x 1 x float>)
+
+define <vscale x 1 x float> @vfnmsub_vv_nxv1f32(<vscale x 1 x float> %va, <vscale x 1 x float> %vb, <vscale x 1 x float> %vc) {
+; CHECK-LABEL: vfnmsub_vv_nxv1f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e32,mf2,tu,mu
+; CHECK-NEXT:    vfnmsub.vv v8, v9, v10
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 1 x float> %vb
+  %vd = call <vscale x 1 x float> @llvm.fma.v1f32(<vscale x 1 x float> %va, <vscale x 1 x float> %neg, <vscale x 1 x float> %vc)
+  ret <vscale x 1 x float> %vd
+}
+
+define <vscale x 1 x float> @vfnmsub_vf_nxv1f32(<vscale x 1 x float> %va, <vscale x 1 x float> %vb, float %c) {
+; CHECK-LABEL: vfnmsub_vf_nxv1f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e32,mf2,tu,mu
+; CHECK-NEXT:    vfnmsub.vf v8, fa0, v9
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 1 x float> undef, float %c, i32 0
+  %splat = shufflevector <vscale x 1 x float> %head, <vscale x 1 x float> undef, <vscale x 1 x i32> zeroinitializer
+  %neg = fneg <vscale x 1 x float> %va
+  %vd = call <vscale x 1 x float> @llvm.fma.v1f32(<vscale x 1 x float> %neg, <vscale x 1 x float> %splat, <vscale x 1 x float> %vb)
+  ret <vscale x 1 x float> %vd
+}
+
+declare <vscale x 2 x float> @llvm.fma.v2f32(<vscale x 2 x float>, <vscale x 2 x float>, <vscale x 2 x float>)
+
+define <vscale x 2 x float> @vfnmsub_vv_nxv2f32(<vscale x 2 x float> %va, <vscale x 2 x float> %vb, <vscale x 2 x float> %vc) {
+; CHECK-LABEL: vfnmsub_vv_nxv2f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e32,m1,tu,mu
+; CHECK-NEXT:    vfnmsub.vv v8, v10, v9
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 2 x float> %vc
+  %vd = call <vscale x 2 x float> @llvm.fma.v2f32(<vscale x 2 x float> %va, <vscale x 2 x float> %neg, <vscale x 2 x float> %vb)
+  ret <vscale x 2 x float> %vd
+}
+
+define <vscale x 2 x float> @vfnmsub_vf_nxv2f32(<vscale x 2 x float> %va, <vscale x 2 x float> %vb, float %c) {
+; CHECK-LABEL: vfnmsub_vf_nxv2f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e32,m1,tu,mu
+; CHECK-NEXT:    vfnmsub.vf v8, fa0, v9
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 2 x float> undef, float %c, i32 0
+  %splat = shufflevector <vscale x 2 x float> %head, <vscale x 2 x float> undef, <vscale x 2 x i32> zeroinitializer
+  %neg = fneg <vscale x 2 x float> %va
+  %vd = call <vscale x 2 x float> @llvm.fma.v2f32(<vscale x 2 x float> %splat, <vscale x 2 x float> %neg, <vscale x 2 x float> %vb)
+  ret <vscale x 2 x float> %vd
+}
+
+declare <vscale x 4 x float> @llvm.fma.v4f32(<vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>)
+
+define <vscale x 4 x float> @vfnmsub_vv_nxv4f32(<vscale x 4 x float> %va, <vscale x 4 x float> %vb, <vscale x 4 x float> %vc) {
+; CHECK-LABEL: vfnmsub_vv_nxv4f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e32,m2,tu,mu
+; CHECK-NEXT:    vfnmsub.vv v10, v8, v12
+; CHECK-NEXT:    vmv2r.v v8, v10
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 4 x float> %va
+  %vd = call <vscale x 4 x float> @llvm.fma.v4f32(<vscale x 4 x float> %vb, <vscale x 4 x float> %neg, <vscale x 4 x float> %vc)
+  ret <vscale x 4 x float> %vd
+}
+
+define <vscale x 4 x float> @vfnmsub_vf_nxv4f32(<vscale x 4 x float> %va, <vscale x 4 x float> %vb, float %c) {
+; CHECK-LABEL: vfnmsub_vf_nxv4f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e32,m2,tu,mu
+; CHECK-NEXT:    vfnmsub.vf v8, fa0, v10
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 4 x float> undef, float %c, i32 0
+  %splat = shufflevector <vscale x 4 x float> %head, <vscale x 4 x float> undef, <vscale x 4 x i32> zeroinitializer
+  %neg = fneg <vscale x 4 x float> %splat
+  %vd = call <vscale x 4 x float> @llvm.fma.v4f32(<vscale x 4 x float> %va, <vscale x 4 x float> %neg, <vscale x 4 x float> %vb)
+  ret <vscale x 4 x float> %vd
+}
+
+declare <vscale x 8 x float> @llvm.fma.v8f32(<vscale x 8 x float>, <vscale x 8 x float>, <vscale x 8 x float>)
+
+define <vscale x 8 x float> @vfnmsub_vv_nxv8f32(<vscale x 8 x float> %va, <vscale x 8 x float> %vb, <vscale x 8 x float> %vc) {
+; CHECK-LABEL: vfnmsub_vv_nxv8f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e32,m4,tu,mu
+; CHECK-NEXT:    vfnmsub.vv v12, v16, v8
+; CHECK-NEXT:    vmv4r.v v8, v12
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 8 x float> %vc
+  %vd = call <vscale x 8 x float> @llvm.fma.v8f32(<vscale x 8 x float> %vb, <vscale x 8 x float> %neg, <vscale x 8 x float> %va)
+  ret <vscale x 8 x float> %vd
+}
+
+define <vscale x 8 x float> @vfnmsub_vf_nxv8f32(<vscale x 8 x float> %va, <vscale x 8 x float> %vb, float %c) {
+; CHECK-LABEL: vfnmsub_vf_nxv8f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e32,m4,tu,mu
+; CHECK-NEXT:    vfnmsub.vf v12, fa0, v8
+; CHECK-NEXT:    vmv4r.v v8, v12
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 8 x float> undef, float %c, i32 0
+  %splat = shufflevector <vscale x 8 x float> %head, <vscale x 8 x float> undef, <vscale x 8 x i32> zeroinitializer
+  %neg = fneg <vscale x 8 x float> %splat
+  %vd = call <vscale x 8 x float> @llvm.fma.v8f32(<vscale x 8 x float> %vb, <vscale x 8 x float> %neg, <vscale x 8 x float> %va)
+  ret <vscale x 8 x float> %vd
+}
+
+declare <vscale x 16 x float> @llvm.fma.v16f32(<vscale x 16 x float>, <vscale x 16 x float>, <vscale x 16 x float>)
+
+define <vscale x 16 x float> @vfnmsub_vv_nxv16f32(<vscale x 16 x float> %va, <vscale x 16 x float> %vb, <vscale x 16 x float> %vc) {
+; CHECK-LABEL: vfnmsub_vv_nxv16f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a1, zero, e32,m8,ta,mu
+; CHECK-NEXT:    vle32.v v24, (a0)
+; CHECK-NEXT:    vsetvli a0, zero, e32,m8,tu,mu
+; CHECK-NEXT:    vfnmsub.vv v24, v8, v16
+; CHECK-NEXT:    vmv8r.v v8, v24
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 16 x float> %va
+  %vd = call <vscale x 16 x float> @llvm.fma.v16f32(<vscale x 16 x float> %vc, <vscale x 16 x float> %neg, <vscale x 16 x float> %vb)
+  ret <vscale x 16 x float> %vd
+}
+
+define <vscale x 16 x float> @vfnmsub_vf_nxv16f32(<vscale x 16 x float> %va, <vscale x 16 x float> %vb, float %c) {
+; CHECK-LABEL: vfnmsub_vf_nxv16f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e32,m8,tu,mu
+; CHECK-NEXT:    vfnmsub.vf v8, fa0, v16
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 16 x float> undef, float %c, i32 0
+  %splat = shufflevector <vscale x 16 x float> %head, <vscale x 16 x float> undef, <vscale x 16 x i32> zeroinitializer
+  %neg = fneg <vscale x 16 x float> %splat
+  %vd = call <vscale x 16 x float> @llvm.fma.v16f32(<vscale x 16 x float> %neg, <vscale x 16 x float> %va, <vscale x 16 x float> %vb)
+  ret <vscale x 16 x float> %vd
+}
+
+declare <vscale x 1 x double> @llvm.fma.v1f64(<vscale x 1 x double>, <vscale x 1 x double>, <vscale x 1 x double>)
+
+define <vscale x 1 x double> @vfnmsub_vv_nxv1f64(<vscale x 1 x double> %va, <vscale x 1 x double> %vb, <vscale x 1 x double> %vc) {
+; CHECK-LABEL: vfnmsub_vv_nxv1f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e64,m1,tu,mu
+; CHECK-NEXT:    vfnmsub.vv v10, v9, v8
+; CHECK-NEXT:    vmv1r.v v8, v10
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 1 x double> %vb
+  %vd = call <vscale x 1 x double> @llvm.fma.v1f64(<vscale x 1 x double> %vc, <vscale x 1 x double> %neg, <vscale x 1 x double> %va)
+  ret <vscale x 1 x double> %vd
+}
+
+define <vscale x 1 x double> @vfnmsub_vf_nxv1f64(<vscale x 1 x double> %va, <vscale x 1 x double> %vb, double %c) {
+; CHECK-LABEL: vfnmsub_vf_nxv1f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e64,m1,tu,mu
+; CHECK-NEXT:    vfnmsub.vf v8, fa0, v9
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 1 x double> undef, double %c, i32 0
+  %splat = shufflevector <vscale x 1 x double> %head, <vscale x 1 x double> undef, <vscale x 1 x i32> zeroinitializer
+  %neg = fneg <vscale x 1 x double> %va
+  %vd = call <vscale x 1 x double> @llvm.fma.v1f64(<vscale x 1 x double> %neg, <vscale x 1 x double> %splat, <vscale x 1 x double> %vb)
+  ret <vscale x 1 x double> %vd
+}
+
+declare <vscale x 2 x double> @llvm.fma.v2f64(<vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>)
+
+define <vscale x 2 x double> @vfnmsub_vv_nxv2f64(<vscale x 2 x double> %va, <vscale x 2 x double> %vb, <vscale x 2 x double> %vc) {
+; CHECK-LABEL: vfnmsub_vv_nxv2f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e64,m2,tu,mu
+; CHECK-NEXT:    vfnmsub.vv v12, v8, v10
+; CHECK-NEXT:    vmv2r.v v8, v12
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 2 x double> %va
+  %vd = call <vscale x 2 x double> @llvm.fma.v2f64(<vscale x 2 x double> %neg, <vscale x 2 x double> %vc, <vscale x 2 x double> %vb)
+  ret <vscale x 2 x double> %vd
+}
+
+define <vscale x 2 x double> @vfnmsub_vf_nxv2f64(<vscale x 2 x double> %va, <vscale x 2 x double> %vb, double %c) {
+; CHECK-LABEL: vfnmsub_vf_nxv2f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e64,m2,tu,mu
+; CHECK-NEXT:    vfnmsub.vf v8, fa0, v10
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 2 x double> undef, double %c, i32 0
+  %splat = shufflevector <vscale x 2 x double> %head, <vscale x 2 x double> undef, <vscale x 2 x i32> zeroinitializer
+  %neg = fneg <vscale x 2 x double> %va
+  %vd = call <vscale x 2 x double> @llvm.fma.v2f64(<vscale x 2 x double> %splat, <vscale x 2 x double> %neg, <vscale x 2 x double> %vb)
+  ret <vscale x 2 x double> %vd
+}
+
+declare <vscale x 4 x double> @llvm.fma.v4f64(<vscale x 4 x double>, <vscale x 4 x double>, <vscale x 4 x double>)
+
+define <vscale x 4 x double> @vfnmsub_vv_nxv4f64(<vscale x 4 x double> %va, <vscale x 4 x double> %vb, <vscale x 4 x double> %vc) {
+; CHECK-LABEL: vfnmsub_vv_nxv4f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e64,m4,tu,mu
+; CHECK-NEXT:    vfnmsub.vv v8, v12, v16
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 4 x double> %vb
+  %vd = call <vscale x 4 x double> @llvm.fma.v4f64(<vscale x 4 x double> %neg, <vscale x 4 x double> %va, <vscale x 4 x double> %vc)
+  ret <vscale x 4 x double> %vd
+}
+
+define <vscale x 4 x double> @vfnmsub_vf_nxv4f64(<vscale x 4 x double> %va, <vscale x 4 x double> %vb, double %c) {
+; CHECK-LABEL: vfnmsub_vf_nxv4f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e64,m4,tu,mu
+; CHECK-NEXT:    vfnmsub.vf v8, fa0, v12
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 4 x double> undef, double %c, i32 0
+  %splat = shufflevector <vscale x 4 x double> %head, <vscale x 4 x double> undef, <vscale x 4 x i32> zeroinitializer
+  %neg = fneg <vscale x 4 x double> %splat
+  %vd = call <vscale x 4 x double> @llvm.fma.v4f64(<vscale x 4 x double> %va, <vscale x 4 x double> %neg, <vscale x 4 x double> %vb)
+  ret <vscale x 4 x double> %vd
+}
+
+declare <vscale x 8 x double> @llvm.fma.v8f64(<vscale x 8 x double>, <vscale x 8 x double>, <vscale x 8 x double>)
+
+define <vscale x 8 x double> @vfnmsub_vv_nxv8f64(<vscale x 8 x double> %va, <vscale x 8 x double> %vb, <vscale x 8 x double> %vc) {
+; CHECK-LABEL: vfnmsub_vv_nxv8f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a1, zero, e64,m8,ta,mu
+; CHECK-NEXT:    vle64.v v24, (a0)
+; CHECK-NEXT:    vsetvli a0, zero, e64,m8,tu,mu
+; CHECK-NEXT:    vfnmsub.vv v24, v16, v8
+; CHECK-NEXT:    vmv8r.v v8, v24
+; CHECK-NEXT:    ret
+  %neg = fneg <vscale x 8 x double> %vb
+  %vd = call <vscale x 8 x double> @llvm.fma.v8f64(<vscale x 8 x double> %neg, <vscale x 8 x double> %vc, <vscale x 8 x double> %va)
+  ret <vscale x 8 x double> %vd
+}
+
+define <vscale x 8 x double> @vfnmsub_vf_nxv8f64(<vscale x 8 x double> %va, <vscale x 8 x double> %vb, double %c) {
+; CHECK-LABEL: vfnmsub_vf_nxv8f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e64,m8,tu,mu
+; CHECK-NEXT:    vfnmsub.vf v16, fa0, v8
+; CHECK-NEXT:    vmv8r.v v8, v16
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 8 x double> undef, double %c, i32 0
+  %splat = shufflevector <vscale x 8 x double> %head, <vscale x 8 x double> undef, <vscale x 8 x i32> zeroinitializer
+  %neg = fneg <vscale x 8 x double> %splat
+  %vd = call <vscale x 8 x double> @llvm.fma.v8f64(<vscale x 8 x double> %vb, <vscale x 8 x double> %neg, <vscale x 8 x double> %va)
+  ret <vscale x 8 x double> %vd
+}