[RISCV] Implement isHighLatencyDef()

wangpc-pp · wangpc-pp · commit 3b4d653efcfe · 2025-02-17T20:03:44.000+08:00
And returns true for div/rem/sqrt/... operations.

This is an alternative if we don't support generic scheduling model.
diff --git a/llvm/lib/Target/RISCV/RISCVInstrInfo.cpp b/llvm/lib/Target/RISCV/RISCVInstrInfo.cpp
@@ -3679,6 +3679,52 @@ MachineInstr *RISCVInstrInfo::commuteInstructionImpl(MachineInstr &MI,
   return TargetInstrInfo::commuteInstructionImpl(MI, NewMI, OpIdx1, OpIdx2);
 }
 
+bool RISCVInstrInfo::isHighLatencyDef(int Opc) const {
+  switch (Opc) {
+  default:
+    return false;
+    // Integer div/rem.
+  case RISCV::DIV:
+  case RISCV::DIVW:
+  case RISCV::DIVU:
+  case RISCV::DIVUW:
+  case RISCV::REM:
+  case RISCV::REMW:
+  case RISCV::REMU:
+  case RISCV::REMUW:
+  // Floating-point div/rem/sqrt.
+  case RISCV::FDIV_H:
+  case RISCV::FDIV_S:
+  case RISCV::FDIV_D:
+  case RISCV::FDIV_H_INX:
+  case RISCV::FDIV_S_INX:
+  case RISCV::FDIV_D_INX:
+  case RISCV::FDIV_D_IN32X:
+  case RISCV::FSQRT_H:
+  case RISCV::FSQRT_S:
+  case RISCV::FSQRT_D:
+  case RISCV::FSQRT_H_INX:
+  case RISCV::FSQRT_S_INX:
+  case RISCV::FSQRT_D_INX:
+  case RISCV::FSQRT_D_IN32X:
+    // Integer div/rem.
+  case CASE_VFMA_OPCODE_VV(DIV):
+  case CASE_VFMA_OPCODE_VV(DIVU):
+  case CASE_VFMA_OPCODE_VV(REM):
+  case CASE_VFMA_OPCODE_VV(REMU):
+  // case CASE_VFMA_OPCODE_VX(DIV):
+  // case CASE_VFMA_OPCODE_VX(DIVU):
+  // case CASE_VFMA_OPCODE_VX(REM):
+  // case CASE_VFMA_OPCODE_VX(REMU):
+  // Vector floating-point div/sqrt.
+  case CASE_VFMA_OPCODE_VV(FDIV):
+  // case CASE_VFMA_OPCODE_VF(FRDIV):
+  // case CASE_VFMA_OPCODE_VV(FSQRT):
+  // case CASE_VFMA_OPCODE_VV(FRSQRT7):
+    return true;
+  }
+}
+
 #undef CASE_RVV_OPCODE_UNMASK_LMUL
 #undef CASE_RVV_OPCODE_MASK_LMUL
 #undef CASE_RVV_OPCODE_LMUL
diff --git a/llvm/lib/Target/RISCV/RISCVInstrInfo.h b/llvm/lib/Target/RISCV/RISCVInstrInfo.h
@@ -300,6 +300,8 @@ class RISCVInstrInfo : public RISCVGenInstrInfo {
   std::unique_ptr<TargetInstrInfo::PipelinerLoopInfo>
   analyzeLoopForPipelining(MachineBasicBlock *LoopBB) const override;
 
+  bool isHighLatencyDef(int Opc) const override;
+
 protected:
   const RISCVSubtarget &STI;
 
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vwmul.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vwmul.ll
@@ -894,18 +894,18 @@ define <2 x i16> @vwmul_v2i16_multiuse(ptr %x, ptr %y, ptr %z, ptr %w) {
 ; CHECK-LABEL: vwmul_v2i16_multiuse:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 2, e16, mf4, ta, ma
-; CHECK-NEXT:    vle8.v v8, (a0)
-; CHECK-NEXT:    vle8.v v9, (a1)
-; CHECK-NEXT:    vle8.v v10, (a2)
-; CHECK-NEXT:    vle8.v v11, (a3)
-; CHECK-NEXT:    vsext.vf2 v12, v8
+; CHECK-NEXT:    vle8.v v8, (a1)
+; CHECK-NEXT:    vle8.v v9, (a2)
+; CHECK-NEXT:    vsext.vf2 v10, v8
 ; CHECK-NEXT:    vsext.vf2 v8, v9
-; CHECK-NEXT:    vsext.vf2 v9, v10
-; CHECK-NEXT:    vsext.vf2 v10, v11
-; CHECK-NEXT:    vmul.vv v11, v12, v10
-; CHECK-NEXT:    vmul.vv v10, v8, v10
-; CHECK-NEXT:    vdivu.vv v8, v8, v9
-; CHECK-NEXT:    vor.vv v9, v11, v10
+; CHECK-NEXT:    vdivu.vv v8, v10, v8
+; CHECK-NEXT:    vle8.v v9, (a0)
+; CHECK-NEXT:    vle8.v v11, (a3)
+; CHECK-NEXT:    vsext.vf2 v12, v9
+; CHECK-NEXT:    vsext.vf2 v9, v11
+; CHECK-NEXT:    vmul.vv v11, v12, v9
+; CHECK-NEXT:    vmul.vv v9, v10, v9
+; CHECK-NEXT:    vor.vv v9, v11, v9
 ; CHECK-NEXT:    vor.vv v8, v9, v8
 ; CHECK-NEXT:    ret
   %a = load <2 x i8>, ptr %x
diff --git a/llvm/test/CodeGen/RISCV/rvv/vfdiv-constrained-sdnode.ll b/llvm/test/CodeGen/RISCV/rvv/vfdiv-constrained-sdnode.ll
@@ -221,16 +221,16 @@ define <vscale x 32 x bfloat> @vfdiv_vv_nxv32bf16(<vscale x 32 x bfloat> %va, <v
 ; CHECK-NEXT:    vs8r.v v24, (a0) # Unknown-size Folded Spill
 ; CHECK-NEXT:    vfwcvtbf16.f.f.v v0, v8
 ; CHECK-NEXT:    vfwcvtbf16.f.f.v v24, v20
-; CHECK-NEXT:    vfwcvtbf16.f.f.v v16, v12
-; CHECK-NEXT:    vl8r.v v8, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT:    vl8r.v v16, (a0) # Unknown-size Folded Reload
 ; CHECK-NEXT:    vsetvli zero, zero, e32, m8, ta, ma
-; CHECK-NEXT:    vfdiv.vv v0, v0, v8
+; CHECK-NEXT:    vfdiv.vv v16, v0, v16
 ; CHECK-NEXT:    vsetvli zero, zero, e16, m4, ta, ma
-; CHECK-NEXT:    vfncvtbf16.f.f.w v8, v0
+; CHECK-NEXT:    vfwcvtbf16.f.f.v v0, v12
 ; CHECK-NEXT:    vsetvli zero, zero, e32, m8, ta, ma
-; CHECK-NEXT:    vfdiv.vv v16, v16, v24
+; CHECK-NEXT:    vfdiv.vv v24, v0, v24
 ; CHECK-NEXT:    vsetvli zero, zero, e16, m4, ta, ma
-; CHECK-NEXT:    vfncvtbf16.f.f.w v12, v16
+; CHECK-NEXT:    vfncvtbf16.f.f.w v8, v16
+; CHECK-NEXT:    vfncvtbf16.f.f.w v12, v24
 ; CHECK-NEXT:    csrr a0, vlenb
 ; CHECK-NEXT:    slli a0, a0, 3
 ; CHECK-NEXT:    add sp, sp, a0
@@ -249,32 +249,42 @@ define <vscale x 32 x bfloat> @vfdiv_vf_nxv32bf16(<vscale x 32 x bfloat> %va, bf
 ; CHECK-NEXT:    addi sp, sp, -16
 ; CHECK-NEXT:    .cfi_def_cfa_offset 16
 ; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 3
+; CHECK-NEXT:    slli a0, a0, 4
 ; CHECK-NEXT:    sub sp, sp, a0
-; CHECK-NEXT:    .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 8 * vlenb
+; CHECK-NEXT:    .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x10, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 16 * vlenb
 ; CHECK-NEXT:    fmv.x.h a0, fa0
 ; CHECK-NEXT:    vsetvli a1, zero, e16, m4, ta, ma
 ; CHECK-NEXT:    vfwcvtbf16.f.f.v v16, v8
 ; CHECK-NEXT:    addi a1, sp, 16
 ; CHECK-NEXT:    vs8r.v v16, (a1) # Unknown-size Folded Spill
-; CHECK-NEXT:    vfwcvtbf16.f.f.v v24, v12
 ; CHECK-NEXT:    vsetvli a1, zero, e16, m8, ta, ma
-; CHECK-NEXT:    vmv.v.x v8, a0
+; CHECK-NEXT:    vmv.v.x v16, a0
 ; CHECK-NEXT:    vsetvli a0, zero, e16, m4, ta, ma
-; CHECK-NEXT:    vfwcvtbf16.f.f.v v0, v8
-; CHECK-NEXT:    vfwcvtbf16.f.f.v v16, v12
+; CHECK-NEXT:    vfwcvtbf16.f.f.v v0, v16
+; CHECK-NEXT:    vfwcvtbf16.f.f.v v24, v20
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    slli a0, a0, 3
+; CHECK-NEXT:    add a0, sp, a0
+; CHECK-NEXT:    addi a0, a0, 16
+; CHECK-NEXT:    vs8r.v v24, (a0) # Unknown-size Folded Spill
 ; CHECK-NEXT:    addi a0, sp, 16
-; CHECK-NEXT:    vl8r.v v8, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT:    vl8r.v v16, (a0) # Unknown-size Folded Reload
 ; CHECK-NEXT:    vsetvli zero, zero, e32, m8, ta, ma
-; CHECK-NEXT:    vfdiv.vv v0, v8, v0
+; CHECK-NEXT:    vfdiv.vv v24, v16, v0
 ; CHECK-NEXT:    vsetvli zero, zero, e16, m4, ta, ma
-; CHECK-NEXT:    vfncvtbf16.f.f.w v8, v0
+; CHECK-NEXT:    vfwcvtbf16.f.f.v v0, v12
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    slli a0, a0, 3
+; CHECK-NEXT:    add a0, sp, a0
+; CHECK-NEXT:    addi a0, a0, 16
+; CHECK-NEXT:    vl8r.v v8, (a0) # Unknown-size Folded Reload
 ; CHECK-NEXT:    vsetvli zero, zero, e32, m8, ta, ma
-; CHECK-NEXT:    vfdiv.vv v16, v24, v16
+; CHECK-NEXT:    vfdiv.vv v16, v0, v8
 ; CHECK-NEXT:    vsetvli zero, zero, e16, m4, ta, ma
+; CHECK-NEXT:    vfncvtbf16.f.f.w v8, v24
 ; CHECK-NEXT:    vfncvtbf16.f.f.w v12, v16
 ; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 3
+; CHECK-NEXT:    slli a0, a0, 4
 ; CHECK-NEXT:    add sp, sp, a0
 ; CHECK-NEXT:    .cfi_def_cfa sp, 16
 ; CHECK-NEXT:    addi sp, sp, 16
@@ -573,16 +583,16 @@ define <vscale x 32 x half> @vfdiv_vv_nxv32f16(<vscale x 32 x half> %va, <vscale
 ; ZVFHMIN-NEXT:    vs8r.v v24, (a0) # Unknown-size Folded Spill
 ; ZVFHMIN-NEXT:    vfwcvt.f.f.v v0, v8
 ; ZVFHMIN-NEXT:    vfwcvt.f.f.v v24, v20
-; ZVFHMIN-NEXT:    vfwcvt.f.f.v v16, v12
-; ZVFHMIN-NEXT:    vl8r.v v8, (a0) # Unknown-size Folded Reload
+; ZVFHMIN-NEXT:    vl8r.v v16, (a0) # Unknown-size Folded Reload
 ; ZVFHMIN-NEXT:    vsetvli zero, zero, e32, m8, ta, ma
-; ZVFHMIN-NEXT:    vfdiv.vv v0, v0, v8
+; ZVFHMIN-NEXT:    vfdiv.vv v16, v0, v16
 ; ZVFHMIN-NEXT:    vsetvli zero, zero, e16, m4, ta, ma
-; ZVFHMIN-NEXT:    vfncvt.f.f.w v8, v0
+; ZVFHMIN-NEXT:    vfwcvt.f.f.v v0, v12
 ; ZVFHMIN-NEXT:    vsetvli zero, zero, e32, m8, ta, ma
-; ZVFHMIN-NEXT:    vfdiv.vv v16, v16, v24
+; ZVFHMIN-NEXT:    vfdiv.vv v24, v0, v24
 ; ZVFHMIN-NEXT:    vsetvli zero, zero, e16, m4, ta, ma
-; ZVFHMIN-NEXT:    vfncvt.f.f.w v12, v16
+; ZVFHMIN-NEXT:    vfncvt.f.f.w v8, v16
+; ZVFHMIN-NEXT:    vfncvt.f.f.w v12, v24
 ; ZVFHMIN-NEXT:    csrr a0, vlenb
 ; ZVFHMIN-NEXT:    slli a0, a0, 3
 ; ZVFHMIN-NEXT:    add sp, sp, a0
@@ -607,32 +617,42 @@ define <vscale x 32 x half> @vfdiv_vf_nxv32f16(<vscale x 32 x half> %va, half %b
 ; ZVFHMIN-NEXT:    addi sp, sp, -16
 ; ZVFHMIN-NEXT:    .cfi_def_cfa_offset 16
 ; ZVFHMIN-NEXT:    csrr a0, vlenb
-; ZVFHMIN-NEXT:    slli a0, a0, 3
+; ZVFHMIN-NEXT:    slli a0, a0, 4
 ; ZVFHMIN-NEXT:    sub sp, sp, a0
-; ZVFHMIN-NEXT:    .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 8 * vlenb
+; ZVFHMIN-NEXT:    .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x10, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 16 * vlenb
 ; ZVFHMIN-NEXT:    fmv.x.h a0, fa0
 ; ZVFHMIN-NEXT:    vsetvli a1, zero, e16, m4, ta, ma
 ; ZVFHMIN-NEXT:    vfwcvt.f.f.v v16, v8
 ; ZVFHMIN-NEXT:    addi a1, sp, 16
 ; ZVFHMIN-NEXT:    vs8r.v v16, (a1) # Unknown-size Folded Spill
-; ZVFHMIN-NEXT:    vfwcvt.f.f.v v24, v12
 ; ZVFHMIN-NEXT:    vsetvli a1, zero, e16, m8, ta, ma
-; ZVFHMIN-NEXT:    vmv.v.x v8, a0
+; ZVFHMIN-NEXT:    vmv.v.x v16, a0
 ; ZVFHMIN-NEXT:    vsetvli a0, zero, e16, m4, ta, ma
-; ZVFHMIN-NEXT:    vfwcvt.f.f.v v0, v8
-; ZVFHMIN-NEXT:    vfwcvt.f.f.v v16, v12
+; ZVFHMIN-NEXT:    vfwcvt.f.f.v v0, v16
+; ZVFHMIN-NEXT:    vfwcvt.f.f.v v24, v20
+; ZVFHMIN-NEXT:    csrr a0, vlenb
+; ZVFHMIN-NEXT:    slli a0, a0, 3
+; ZVFHMIN-NEXT:    add a0, sp, a0
+; ZVFHMIN-NEXT:    addi a0, a0, 16
+; ZVFHMIN-NEXT:    vs8r.v v24, (a0) # Unknown-size Folded Spill
 ; ZVFHMIN-NEXT:    addi a0, sp, 16
-; ZVFHMIN-NEXT:    vl8r.v v8, (a0) # Unknown-size Folded Reload
+; ZVFHMIN-NEXT:    vl8r.v v16, (a0) # Unknown-size Folded Reload
 ; ZVFHMIN-NEXT:    vsetvli zero, zero, e32, m8, ta, ma
-; ZVFHMIN-NEXT:    vfdiv.vv v0, v8, v0
+; ZVFHMIN-NEXT:    vfdiv.vv v24, v16, v0
 ; ZVFHMIN-NEXT:    vsetvli zero, zero, e16, m4, ta, ma
-; ZVFHMIN-NEXT:    vfncvt.f.f.w v8, v0
+; ZVFHMIN-NEXT:    vfwcvt.f.f.v v0, v12
+; ZVFHMIN-NEXT:    csrr a0, vlenb
+; ZVFHMIN-NEXT:    slli a0, a0, 3
+; ZVFHMIN-NEXT:    add a0, sp, a0
+; ZVFHMIN-NEXT:    addi a0, a0, 16
+; ZVFHMIN-NEXT:    vl8r.v v8, (a0) # Unknown-size Folded Reload
 ; ZVFHMIN-NEXT:    vsetvli zero, zero, e32, m8, ta, ma
-; ZVFHMIN-NEXT:    vfdiv.vv v16, v24, v16
+; ZVFHMIN-NEXT:    vfdiv.vv v16, v0, v8
 ; ZVFHMIN-NEXT:    vsetvli zero, zero, e16, m4, ta, ma
+; ZVFHMIN-NEXT:    vfncvt.f.f.w v8, v24
 ; ZVFHMIN-NEXT:    vfncvt.f.f.w v12, v16
 ; ZVFHMIN-NEXT:    csrr a0, vlenb
-; ZVFHMIN-NEXT:    slli a0, a0, 3
+; ZVFHMIN-NEXT:    slli a0, a0, 4
 ; ZVFHMIN-NEXT:    add sp, sp, a0
 ; ZVFHMIN-NEXT:    .cfi_def_cfa sp, 16
 ; ZVFHMIN-NEXT:    addi sp, sp, 16
diff --git a/llvm/test/CodeGen/RISCV/rvv/vfdiv-sdnode.ll b/llvm/test/CodeGen/RISCV/rvv/vfdiv-sdnode.ll
@@ -200,16 +200,16 @@ define <vscale x 32 x bfloat> @vfdiv_vv_nxv32bf16(<vscale x 32 x bfloat> %va, <v
 ; CHECK-NEXT:    vs8r.v v24, (a0) # Unknown-size Folded Spill
 ; CHECK-NEXT:    vfwcvtbf16.f.f.v v0, v8
 ; CHECK-NEXT:    vfwcvtbf16.f.f.v v24, v20
-; CHECK-NEXT:    vfwcvtbf16.f.f.v v16, v12
-; CHECK-NEXT:    vl8r.v v8, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT:    vl8r.v v16, (a0) # Unknown-size Folded Reload
 ; CHECK-NEXT:    vsetvli zero, zero, e32, m8, ta, ma
-; CHECK-NEXT:    vfdiv.vv v0, v0, v8
+; CHECK-NEXT:    vfdiv.vv v16, v0, v16
 ; CHECK-NEXT:    vsetvli zero, zero, e16, m4, ta, ma
-; CHECK-NEXT:    vfncvtbf16.f.f.w v8, v0
+; CHECK-NEXT:    vfwcvtbf16.f.f.v v0, v12
 ; CHECK-NEXT:    vsetvli zero, zero, e32, m8, ta, ma
-; CHECK-NEXT:    vfdiv.vv v16, v16, v24
+; CHECK-NEXT:    vfdiv.vv v24, v0, v24
 ; CHECK-NEXT:    vsetvli zero, zero, e16, m4, ta, ma
-; CHECK-NEXT:    vfncvtbf16.f.f.w v12, v16
+; CHECK-NEXT:    vfncvtbf16.f.f.w v8, v16
+; CHECK-NEXT:    vfncvtbf16.f.f.w v12, v24
 ; CHECK-NEXT:    csrr a0, vlenb
 ; CHECK-NEXT:    slli a0, a0, 3
 ; CHECK-NEXT:    add sp, sp, a0
@@ -224,39 +224,23 @@ define <vscale x 32 x bfloat> @vfdiv_vv_nxv32bf16(<vscale x 32 x bfloat> %va, <v
 define <vscale x 32 x bfloat> @vfdiv_vf_nxv32bf16(<vscale x 32 x bfloat> %va, bfloat %b) {
 ; CHECK-LABEL: vfdiv_vf_nxv32bf16:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    addi sp, sp, -16
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 3
-; CHECK-NEXT:    sub sp, sp, a0
-; CHECK-NEXT:    .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 8 * vlenb
 ; CHECK-NEXT:    fmv.x.h a0, fa0
 ; CHECK-NEXT:    vsetvli a1, zero, e16, m4, ta, ma
 ; CHECK-NEXT:    vfwcvtbf16.f.f.v v16, v8
-; CHECK-NEXT:    addi a1, sp, 16
-; CHECK-NEXT:    vs8r.v v16, (a1) # Unknown-size Folded Spill
 ; CHECK-NEXT:    vfwcvtbf16.f.f.v v24, v12
 ; CHECK-NEXT:    vsetvli a1, zero, e16, m8, ta, ma
 ; CHECK-NEXT:    vmv.v.x v8, a0
 ; CHECK-NEXT:    vsetvli a0, zero, e16, m4, ta, ma
 ; CHECK-NEXT:    vfwcvtbf16.f.f.v v0, v8
-; CHECK-NEXT:    vfwcvtbf16.f.f.v v16, v12
-; CHECK-NEXT:    addi a0, sp, 16
-; CHECK-NEXT:    vl8r.v v8, (a0) # Unknown-size Folded Reload
 ; CHECK-NEXT:    vsetvli zero, zero, e32, m8, ta, ma
-; CHECK-NEXT:    vfdiv.vv v0, v8, v0
+; CHECK-NEXT:    vfdiv.vv v16, v16, v0
 ; CHECK-NEXT:    vsetvli zero, zero, e16, m4, ta, ma
-; CHECK-NEXT:    vfncvtbf16.f.f.w v8, v0
+; CHECK-NEXT:    vfwcvtbf16.f.f.v v0, v12
 ; CHECK-NEXT:    vsetvli zero, zero, e32, m8, ta, ma
-; CHECK-NEXT:    vfdiv.vv v16, v24, v16
+; CHECK-NEXT:    vfdiv.vv v24, v24, v0
 ; CHECK-NEXT:    vsetvli zero, zero, e16, m4, ta, ma
-; CHECK-NEXT:    vfncvtbf16.f.f.w v12, v16
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 3
-; CHECK-NEXT:    add sp, sp, a0
-; CHECK-NEXT:    .cfi_def_cfa sp, 16
-; CHECK-NEXT:    addi sp, sp, 16
-; CHECK-NEXT:    .cfi_def_cfa_offset 0
+; CHECK-NEXT:    vfncvtbf16.f.f.w v8, v16
+; CHECK-NEXT:    vfncvtbf16.f.f.w v12, v24
 ; CHECK-NEXT:    ret
   %head = insertelement <vscale x 32 x bfloat> poison, bfloat %b, i32 0
   %splat = shufflevector <vscale x 32 x bfloat> %head, <vscale x 32 x bfloat> poison, <vscale x 32 x i32> zeroinitializer
@@ -528,16 +512,16 @@ define <vscale x 32 x half> @vfdiv_vv_nxv32f16(<vscale x 32 x half> %va, <vscale
 ; ZVFHMIN-NEXT:    vs8r.v v24, (a0) # Unknown-size Folded Spill
 ; ZVFHMIN-NEXT:    vfwcvt.f.f.v v0, v8
 ; ZVFHMIN-NEXT:    vfwcvt.f.f.v v24, v20
-; ZVFHMIN-NEXT:    vfwcvt.f.f.v v16, v12
-; ZVFHMIN-NEXT:    vl8r.v v8, (a0) # Unknown-size Folded Reload
+; ZVFHMIN-NEXT:    vl8r.v v16, (a0) # Unknown-size Folded Reload
 ; ZVFHMIN-NEXT:    vsetvli zero, zero, e32, m8, ta, ma
-; ZVFHMIN-NEXT:    vfdiv.vv v0, v0, v8
+; ZVFHMIN-NEXT:    vfdiv.vv v16, v0, v16
 ; ZVFHMIN-NEXT:    vsetvli zero, zero, e16, m4, ta, ma
-; ZVFHMIN-NEXT:    vfncvt.f.f.w v8, v0
+; ZVFHMIN-NEXT:    vfwcvt.f.f.v v0, v12
 ; ZVFHMIN-NEXT:    vsetvli zero, zero, e32, m8, ta, ma
-; ZVFHMIN-NEXT:    vfdiv.vv v16, v16, v24
+; ZVFHMIN-NEXT:    vfdiv.vv v24, v0, v24
 ; ZVFHMIN-NEXT:    vsetvli zero, zero, e16, m4, ta, ma
-; ZVFHMIN-NEXT:    vfncvt.f.f.w v12, v16
+; ZVFHMIN-NEXT:    vfncvt.f.f.w v8, v16
+; ZVFHMIN-NEXT:    vfncvt.f.f.w v12, v24
 ; ZVFHMIN-NEXT:    csrr a0, vlenb
 ; ZVFHMIN-NEXT:    slli a0, a0, 3
 ; ZVFHMIN-NEXT:    add sp, sp, a0
@@ -558,39 +542,23 @@ define <vscale x 32 x half> @vfdiv_vf_nxv32f16(<vscale x 32 x half> %va, half %b
 ;
 ; ZVFHMIN-LABEL: vfdiv_vf_nxv32f16:
 ; ZVFHMIN:       # %bb.0:
-; ZVFHMIN-NEXT:    addi sp, sp, -16
-; ZVFHMIN-NEXT:    .cfi_def_cfa_offset 16
-; ZVFHMIN-NEXT:    csrr a0, vlenb
-; ZVFHMIN-NEXT:    slli a0, a0, 3
-; ZVFHMIN-NEXT:    sub sp, sp, a0
-; ZVFHMIN-NEXT:    .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 8 * vlenb
 ; ZVFHMIN-NEXT:    fmv.x.h a0, fa0
 ; ZVFHMIN-NEXT:    vsetvli a1, zero, e16, m4, ta, ma
 ; ZVFHMIN-NEXT:    vfwcvt.f.f.v v16, v8
-; ZVFHMIN-NEXT:    addi a1, sp, 16
-; ZVFHMIN-NEXT:    vs8r.v v16, (a1) # Unknown-size Folded Spill
 ; ZVFHMIN-NEXT:    vfwcvt.f.f.v v24, v12
 ; ZVFHMIN-NEXT:    vsetvli a1, zero, e16, m8, ta, ma
 ; ZVFHMIN-NEXT:    vmv.v.x v8, a0
 ; ZVFHMIN-NEXT:    vsetvli a0, zero, e16, m4, ta, ma
 ; ZVFHMIN-NEXT:    vfwcvt.f.f.v v0, v8
-; ZVFHMIN-NEXT:    vfwcvt.f.f.v v16, v12
-; ZVFHMIN-NEXT:    addi a0, sp, 16
-; ZVFHMIN-NEXT:    vl8r.v v8, (a0) # Unknown-size Folded Reload
 ; ZVFHMIN-NEXT:    vsetvli zero, zero, e32, m8, ta, ma
-; ZVFHMIN-NEXT:    vfdiv.vv v0, v8, v0
+; ZVFHMIN-NEXT:    vfdiv.vv v16, v16, v0
 ; ZVFHMIN-NEXT:    vsetvli zero, zero, e16, m4, ta, ma
-; ZVFHMIN-NEXT:    vfncvt.f.f.w v8, v0
+; ZVFHMIN-NEXT:    vfwcvt.f.f.v v0, v12
 ; ZVFHMIN-NEXT:    vsetvli zero, zero, e32, m8, ta, ma
-; ZVFHMIN-NEXT:    vfdiv.vv v16, v24, v16
+; ZVFHMIN-NEXT:    vfdiv.vv v24, v24, v0
 ; ZVFHMIN-NEXT:    vsetvli zero, zero, e16, m4, ta, ma
-; ZVFHMIN-NEXT:    vfncvt.f.f.w v12, v16
-; ZVFHMIN-NEXT:    csrr a0, vlenb
-; ZVFHMIN-NEXT:    slli a0, a0, 3
-; ZVFHMIN-NEXT:    add sp, sp, a0
-; ZVFHMIN-NEXT:    .cfi_def_cfa sp, 16
-; ZVFHMIN-NEXT:    addi sp, sp, 16
-; ZVFHMIN-NEXT:    .cfi_def_cfa_offset 0
+; ZVFHMIN-NEXT:    vfncvt.f.f.w v8, v16
+; ZVFHMIN-NEXT:    vfncvt.f.f.w v12, v24
 ; ZVFHMIN-NEXT:    ret
   %head = insertelement <vscale x 32 x half> poison, half %b, i32 0
   %splat = shufflevector <vscale x 32 x half> %head, <vscale x 32 x half> poison, <vscale x 32 x i32> zeroinitializer
