; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv32 -mattr=+d,+zfh,+zvfh,+v -target-abi=ilp32d \
; RUN:   -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK,ZVFH
; RUN: llc -mtriple=riscv64 -mattr=+d,+zfh,+zvfh,+v -target-abi=lp64d \
; RUN:   -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK,ZVFH
; RUN: llc -mtriple=riscv32 -mattr=+d,+zfh,+zvfhmin,+v -target-abi=ilp32d \
; RUN:   -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK,ZVFHMIN
; RUN: llc -mtriple=riscv64 -mattr=+d,+zfh,+zvfhmin,+v -target-abi=lp64d \
; RUN:   -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK,ZVFHMIN

declare <2 x half> @llvm.maximum.v2f16(<2 x half>, <2 x half>)

define <2 x half> @vfmax_v2f16_vv(<2 x half> %a, <2 x half> %b) {
; ZVFH-LABEL: vfmax_v2f16_vv:
; ZVFH:       # %bb.0:
; ZVFH-NEXT:    vsetivli zero, 2, e16, mf4, ta, ma
; ZVFH-NEXT:    vmfeq.vv v0, v8, v8
; ZVFH-NEXT:    vmfeq.vv v10, v9, v9
; ZVFH-NEXT:    vmerge.vvm v11, v8, v9, v0
; ZVFH-NEXT:    vmv1r.v v0, v10
; ZVFH-NEXT:    vmerge.vvm v8, v9, v8, v0
; ZVFH-NEXT:    vfmax.vv v8, v8, v11
; ZVFH-NEXT:    ret
;
; ZVFHMIN-LABEL: vfmax_v2f16_vv:
; ZVFHMIN:       # %bb.0:
; ZVFHMIN-NEXT:    vsetivli zero, 2, e16, mf4, ta, ma
; ZVFHMIN-NEXT:    vfwcvt.f.f.v v10, v9
; ZVFHMIN-NEXT:    vfwcvt.f.f.v v9, v8
; ZVFHMIN-NEXT:    vsetvli zero, zero, e32, mf2, ta, ma
; ZVFHMIN-NEXT:    vmfeq.vv v0, v9, v9
; ZVFHMIN-NEXT:    vmfeq.vv v8, v10, v10
; ZVFHMIN-NEXT:    vmerge.vvm v11, v9, v10, v0
; ZVFHMIN-NEXT:    vmv1r.v v0, v8
; ZVFHMIN-NEXT:    vmerge.vvm v8, v10, v9, v0
; ZVFHMIN-NEXT:    vfmax.vv v9, v8, v11
; ZVFHMIN-NEXT:    vsetvli zero, zero, e16, mf4, ta, ma
; ZVFHMIN-NEXT:    vfncvt.f.f.w v8, v9
; ZVFHMIN-NEXT:    ret
  %v = call <2 x half> @llvm.maximum.v2f16(<2 x half> %a, <2 x half> %b)
  ret <2 x half> %v
}

declare <4 x half> @llvm.maximum.v4f16(<4 x half>, <4 x half>)

define <4 x half> @vfmax_v4f16_vv(<4 x half> %a, <4 x half> %b) {
; ZVFH-LABEL: vfmax_v4f16_vv:
; ZVFH:       # %bb.0:
; ZVFH-NEXT:    vsetivli zero, 4, e16, mf2, ta, ma
; ZVFH-NEXT:    vmfeq.vv v0, v8, v8
; ZVFH-NEXT:    vmfeq.vv v10, v9, v9
; ZVFH-NEXT:    vmerge.vvm v11, v8, v9, v0
; ZVFH-NEXT:    vmv1r.v v0, v10
; ZVFH-NEXT:    vmerge.vvm v8, v9, v8, v0
; ZVFH-NEXT:    vfmax.vv v8, v8, v11
; ZVFH-NEXT:    ret
;
; ZVFHMIN-LABEL: vfmax_v4f16_vv:
; ZVFHMIN:       # %bb.0:
; ZVFHMIN-NEXT:    vsetivli zero, 4, e16, mf2, ta, ma
; ZVFHMIN-NEXT:    vfwcvt.f.f.v v10, v9
; ZVFHMIN-NEXT:    vfwcvt.f.f.v v9, v8
; ZVFHMIN-NEXT:    vsetvli zero, zero, e32, m1, ta, ma
; ZVFHMIN-NEXT:    vmfeq.vv v0, v9, v9
; ZVFHMIN-NEXT:    vmfeq.vv v8, v10, v10
; ZVFHMIN-NEXT:    vmerge.vvm v11, v9, v10, v0
; ZVFHMIN-NEXT:    vmv.v.v v0, v8
; ZVFHMIN-NEXT:    vmerge.vvm v8, v10, v9, v0
; ZVFHMIN-NEXT:    vfmax.vv v9, v8, v11
; ZVFHMIN-NEXT:    vsetvli zero, zero, e16, mf2, ta, ma
; ZVFHMIN-NEXT:    vfncvt.f.f.w v8, v9
; ZVFHMIN-NEXT:    ret
  %v = call <4 x half> @llvm.maximum.v4f16(<4 x half> %a, <4 x half> %b)
  ret <4 x half> %v
}

declare <8 x half> @llvm.maximum.v8f16(<8 x half>, <8 x half>)

define <8 x half> @vfmax_v8f16_vv(<8 x half> %a, <8 x half> %b) {
; ZVFH-LABEL: vfmax_v8f16_vv:
; ZVFH:       # %bb.0:
; ZVFH-NEXT:    vsetivli zero, 8, e16, m1, ta, ma
; ZVFH-NEXT:    vmfeq.vv v0, v8, v8
; ZVFH-NEXT:    vmfeq.vv v10, v9, v9
; ZVFH-NEXT:    vmerge.vvm v11, v8, v9, v0
; ZVFH-NEXT:    vmv.v.v v0, v10
; ZVFH-NEXT:    vmerge.vvm v8, v9, v8, v0
; ZVFH-NEXT:    vfmax.vv v8, v8, v11
; ZVFH-NEXT:    ret
;
; ZVFHMIN-LABEL: vfmax_v8f16_vv:
; ZVFHMIN:       # %bb.0:
; ZVFHMIN-NEXT:    vsetivli zero, 8, e16, m1, ta, ma
; ZVFHMIN-NEXT:    vfwcvt.f.f.v v10, v9
; ZVFHMIN-NEXT:    vfwcvt.f.f.v v12, v8
; ZVFHMIN-NEXT:    vsetvli zero, zero, e32, m2, ta, ma
; ZVFHMIN-NEXT:    vmfeq.vv v0, v12, v12
; ZVFHMIN-NEXT:    vmfeq.vv v8, v10, v10
; ZVFHMIN-NEXT:    vmerge.vvm v14, v12, v10, v0
; ZVFHMIN-NEXT:    vmv1r.v v0, v8
; ZVFHMIN-NEXT:    vmerge.vvm v8, v10, v12, v0
; ZVFHMIN-NEXT:    vfmax.vv v10, v8, v14
; ZVFHMIN-NEXT:    vsetvli zero, zero, e16, m1, ta, ma
; ZVFHMIN-NEXT:    vfncvt.f.f.w v8, v10
; ZVFHMIN-NEXT:    ret
  %v = call <8 x half> @llvm.maximum.v8f16(<8 x half> %a, <8 x half> %b)
  ret <8 x half> %v
}

declare <16 x half> @llvm.maximum.v16f16(<16 x half>, <16 x half>)

define <16 x half> @vfmax_v16f16_vv(<16 x half> %a, <16 x half> %b) {
; ZVFH-LABEL: vfmax_v16f16_vv:
; ZVFH:       # %bb.0:
; ZVFH-NEXT:    vsetivli zero, 16, e16, m2, ta, ma
; ZVFH-NEXT:    vmfeq.vv v0, v8, v8
; ZVFH-NEXT:    vmfeq.vv v12, v10, v10
; ZVFH-NEXT:    vmerge.vvm v14, v8, v10, v0
; ZVFH-NEXT:    vmv1r.v v0, v12
; ZVFH-NEXT:    vmerge.vvm v8, v10, v8, v0
; ZVFH-NEXT:    vfmax.vv v8, v8, v14
; ZVFH-NEXT:    ret
;
; ZVFHMIN-LABEL: vfmax_v16f16_vv:
; ZVFHMIN:       # %bb.0:
; ZVFHMIN-NEXT:    vsetivli zero, 16, e16, m2, ta, ma
; ZVFHMIN-NEXT:    vfwcvt.f.f.v v12, v10
; ZVFHMIN-NEXT:    vfwcvt.f.f.v v16, v8
; ZVFHMIN-NEXT:    vsetvli zero, zero, e32, m4, ta, ma
; ZVFHMIN-NEXT:    vmfeq.vv v0, v16, v16
; ZVFHMIN-NEXT:    vmfeq.vv v8, v12, v12
; ZVFHMIN-NEXT:    vmerge.vvm v20, v16, v12, v0
; ZVFHMIN-NEXT:    vmv1r.v v0, v8
; ZVFHMIN-NEXT:    vmerge.vvm v8, v12, v16, v0
; ZVFHMIN-NEXT:    vfmax.vv v12, v8, v20
; ZVFHMIN-NEXT:    vsetvli zero, zero, e16, m2, ta, ma
; ZVFHMIN-NEXT:    vfncvt.f.f.w v8, v12
; ZVFHMIN-NEXT:    ret
  %v = call <16 x half> @llvm.maximum.v16f16(<16 x half> %a, <16 x half> %b)
  ret <16 x half> %v
}

declare <2 x float> @llvm.maximum.v2f32(<2 x float>, <2 x float>)

define <2 x float> @vfmax_v2f32_vv(<2 x float> %a, <2 x float> %b) {
; CHECK-LABEL: vfmax_v2f32_vv:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetivli zero, 2, e32, mf2, ta, ma
; CHECK-NEXT:    vmfeq.vv v0, v8, v8
; CHECK-NEXT:    vmfeq.vv v10, v9, v9
; CHECK-NEXT:    vmerge.vvm v11, v8, v9, v0
; CHECK-NEXT:    vmv1r.v v0, v10
; CHECK-NEXT:    vmerge.vvm v8, v9, v8, v0
; CHECK-NEXT:    vfmax.vv v8, v8, v11
; CHECK-NEXT:    ret
  %v = call <2 x float> @llvm.maximum.v2f32(<2 x float> %a, <2 x float> %b)
  ret <2 x float> %v
}

declare <4 x float> @llvm.maximum.v4f32(<4 x float>, <4 x float>)

define <4 x float> @vfmax_v4f32_vv(<4 x float> %a, <4 x float> %b) {
; CHECK-LABEL: vfmax_v4f32_vv:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
; CHECK-NEXT:    vmfeq.vv v0, v8, v8
; CHECK-NEXT:    vmfeq.vv v10, v9, v9
; CHECK-NEXT:    vmerge.vvm v11, v8, v9, v0
; CHECK-NEXT:    vmv.v.v v0, v10
; CHECK-NEXT:    vmerge.vvm v8, v9, v8, v0
; CHECK-NEXT:    vfmax.vv v8, v8, v11
; CHECK-NEXT:    ret
  %v = call <4 x float> @llvm.maximum.v4f32(<4 x float> %a, <4 x float> %b)
  ret <4 x float> %v
}

declare <8 x float> @llvm.maximum.v8f32(<8 x float>, <8 x float>)

define <8 x float> @vfmax_v8f32_vv(<8 x float> %a, <8 x float> %b) {
; CHECK-LABEL: vfmax_v8f32_vv:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetivli zero, 8, e32, m2, ta, ma
; CHECK-NEXT:    vmfeq.vv v0, v8, v8
; CHECK-NEXT:    vmfeq.vv v12, v10, v10
; CHECK-NEXT:    vmerge.vvm v14, v8, v10, v0
; CHECK-NEXT:    vmv1r.v v0, v12
; CHECK-NEXT:    vmerge.vvm v8, v10, v8, v0
; CHECK-NEXT:    vfmax.vv v8, v8, v14
; CHECK-NEXT:    ret
  %v = call <8 x float> @llvm.maximum.v8f32(<8 x float> %a, <8 x float> %b)
  ret <8 x float> %v
}

declare <16 x float> @llvm.maximum.v16f32(<16 x float>, <16 x float>)

define <16 x float> @vfmax_v16f32_vv(<16 x float> %a, <16 x float> %b) {
; CHECK-LABEL: vfmax_v16f32_vv:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetivli zero, 16, e32, m4, ta, ma
; CHECK-NEXT:    vmfeq.vv v0, v8, v8
; CHECK-NEXT:    vmfeq.vv v16, v12, v12
; CHECK-NEXT:    vmerge.vvm v20, v8, v12, v0
; CHECK-NEXT:    vmv1r.v v0, v16
; CHECK-NEXT:    vmerge.vvm v8, v12, v8, v0
; CHECK-NEXT:    vfmax.vv v8, v8, v20
; CHECK-NEXT:    ret
  %v = call <16 x float> @llvm.maximum.v16f32(<16 x float> %a, <16 x float> %b)
  ret <16 x float> %v
}

declare <2 x double> @llvm.maximum.v2f64(<2 x double>, <2 x double>)

define <2 x double> @vfmax_v2f64_vv(<2 x double> %a, <2 x double> %b) {
; CHECK-LABEL: vfmax_v2f64_vv:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetivli zero, 2, e64, m1, ta, ma
; CHECK-NEXT:    vmfeq.vv v0, v8, v8
; CHECK-NEXT:    vmfeq.vv v10, v9, v9
; CHECK-NEXT:    vmerge.vvm v11, v8, v9, v0
; CHECK-NEXT:    vmv.v.v v0, v10
; CHECK-NEXT:    vmerge.vvm v8, v9, v8, v0
; CHECK-NEXT:    vfmax.vv v8, v8, v11
; CHECK-NEXT:    ret
  %v = call <2 x double> @llvm.maximum.v2f64(<2 x double> %a, <2 x double> %b)
  ret <2 x double> %v
}

declare <4 x double> @llvm.maximum.v4f64(<4 x double>, <4 x double>)

define <4 x double> @vfmax_v4f64_vv(<4 x double> %a, <4 x double> %b) {
; CHECK-LABEL: vfmax_v4f64_vv:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetivli zero, 4, e64, m2, ta, ma
; CHECK-NEXT:    vmfeq.vv v0, v8, v8
; CHECK-NEXT:    vmfeq.vv v12, v10, v10
; CHECK-NEXT:    vmerge.vvm v14, v8, v10, v0
; CHECK-NEXT:    vmv1r.v v0, v12
; CHECK-NEXT:    vmerge.vvm v8, v10, v8, v0
; CHECK-NEXT:    vfmax.vv v8, v8, v14
; CHECK-NEXT:    ret
  %v = call <4 x double> @llvm.maximum.v4f64(<4 x double> %a, <4 x double> %b)
  ret <4 x double> %v
}

declare <8 x double> @llvm.maximum.v8f64(<8 x double>, <8 x double>)

define <8 x double> @vfmax_v8f64_vv(<8 x double> %a, <8 x double> %b) {
; CHECK-LABEL: vfmax_v8f64_vv:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetivli zero, 8, e64, m4, ta, ma
; CHECK-NEXT:    vmfeq.vv v0, v8, v8
; CHECK-NEXT:    vmfeq.vv v16, v12, v12
; CHECK-NEXT:    vmerge.vvm v20, v8, v12, v0
; CHECK-NEXT:    vmv1r.v v0, v16
; CHECK-NEXT:    vmerge.vvm v8, v12, v8, v0
; CHECK-NEXT:    vfmax.vv v8, v8, v20
; CHECK-NEXT:    ret
  %v = call <8 x double> @llvm.maximum.v8f64(<8 x double> %a, <8 x double> %b)
  ret <8 x double> %v
}

declare <16 x double> @llvm.maximum.v16f64(<16 x double>, <16 x double>)

define <16 x double> @vfmax_v16f64_vv(<16 x double> %a, <16 x double> %b) nounwind {
; CHECK-LABEL: vfmax_v16f64_vv:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetivli zero, 16, e64, m8, ta, ma
; CHECK-NEXT:    vmfeq.vv v0, v8, v8
; CHECK-NEXT:    vmfeq.vv v1, v16, v16
; CHECK-NEXT:    vmerge.vvm v24, v8, v16, v0
; CHECK-NEXT:    vmv1r.v v0, v1
; CHECK-NEXT:    vmerge.vvm v8, v16, v8, v0
; CHECK-NEXT:    vfmax.vv v8, v8, v24
; CHECK-NEXT:    ret
  %v = call <16 x double> @llvm.maximum.v16f64(<16 x double> %a, <16 x double> %b)
  ret <16 x double> %v
}

define <2 x half> @vfmax_v2f16_vv_nnan(<2 x half> %a, <2 x half> %b) {
; ZVFH-LABEL: vfmax_v2f16_vv_nnan:
; ZVFH:       # %bb.0:
; ZVFH-NEXT:    vsetivli zero, 2, e16, mf4, ta, ma
; ZVFH-NEXT:    vfmax.vv v8, v8, v9
; ZVFH-NEXT:    ret
;
; ZVFHMIN-LABEL: vfmax_v2f16_vv_nnan:
; ZVFHMIN:       # %bb.0:
; ZVFHMIN-NEXT:    vsetivli zero, 2, e16, mf4, ta, ma
; ZVFHMIN-NEXT:    vfwcvt.f.f.v v10, v9
; ZVFHMIN-NEXT:    vfwcvt.f.f.v v9, v8
; ZVFHMIN-NEXT:    vsetvli zero, zero, e32, mf2, ta, ma
; ZVFHMIN-NEXT:    vfmax.vv v9, v9, v10
; ZVFHMIN-NEXT:    vsetvli zero, zero, e16, mf4, ta, ma
; ZVFHMIN-NEXT:    vfncvt.f.f.w v8, v9
; ZVFHMIN-NEXT:    ret
  %v = call nnan <2 x half> @llvm.maximum.v2f16(<2 x half> %a, <2 x half> %b)
  ret <2 x half> %v
}

; FIXME: The nnan from fadd isn't propagating.
define <2 x half> @vfmax_v2f16_vv_nnana(<2 x half> %a, <2 x half> %b) {
; ZVFH-LABEL: vfmax_v2f16_vv_nnana:
; ZVFH:       # %bb.0:
; ZVFH-NEXT:    vsetivli zero, 2, e16, mf4, ta, ma
; ZVFH-NEXT:    vfadd.vv v10, v8, v8
; ZVFH-NEXT:    vmfeq.vv v0, v9, v9
; ZVFH-NEXT:    vmfeq.vv v8, v10, v10
; ZVFH-NEXT:    vmerge.vvm v11, v9, v10, v0
; ZVFH-NEXT:    vmv1r.v v0, v8
; ZVFH-NEXT:    vmerge.vvm v8, v10, v9, v0
; ZVFH-NEXT:    vfmax.vv v8, v11, v8
; ZVFH-NEXT:    ret
;
; ZVFHMIN-LABEL: vfmax_v2f16_vv_nnana:
; ZVFHMIN:       # %bb.0:
; ZVFHMIN-NEXT:    vsetivli zero, 2, e16, mf4, ta, ma
; ZVFHMIN-NEXT:    vfwcvt.f.f.v v10, v8
; ZVFHMIN-NEXT:    vsetvli zero, zero, e32, mf2, ta, ma
; ZVFHMIN-NEXT:    vfadd.vv v8, v10, v10
; ZVFHMIN-NEXT:    vsetvli zero, zero, e16, mf4, ta, ma
; ZVFHMIN-NEXT:    vfncvt.f.f.w v10, v8
; ZVFHMIN-NEXT:    vfwcvt.f.f.v v11, v9
; ZVFHMIN-NEXT:    vsetvli zero, zero, e32, mf2, ta, ma
; ZVFHMIN-NEXT:    vmfeq.vv v0, v11, v11
; ZVFHMIN-NEXT:    vsetvli zero, zero, e16, mf4, ta, ma
; ZVFHMIN-NEXT:    vfwcvt.f.f.v v9, v10
; ZVFHMIN-NEXT:    vsetvli zero, zero, e32, mf2, ta, ma
; ZVFHMIN-NEXT:    vmfeq.vv v8, v9, v9
; ZVFHMIN-NEXT:    vmerge.vvm v10, v11, v9, v0
; ZVFHMIN-NEXT:    vmv1r.v v0, v8
; ZVFHMIN-NEXT:    vmerge.vvm v8, v9, v11, v0
; ZVFHMIN-NEXT:    vfmax.vv v9, v10, v8
; ZVFHMIN-NEXT:    vsetvli zero, zero, e16, mf4, ta, ma
; ZVFHMIN-NEXT:    vfncvt.f.f.w v8, v9
; ZVFHMIN-NEXT:    ret
  %c = fadd nnan <2 x half> %a, %a
  %v = call <2 x half> @llvm.maximum.v2f16(<2 x half> %c, <2 x half> %b)
  ret <2 x half> %v
}

; FIXME: The nnan from fadd isn't propagating.
define <2 x half> @vfmax_v2f16_vv_nnanb(<2 x half> %a, <2 x half> %b) {
; ZVFH-LABEL: vfmax_v2f16_vv_nnanb:
; ZVFH:       # %bb.0:
; ZVFH-NEXT:    vsetivli zero, 2, e16, mf4, ta, ma
; ZVFH-NEXT:    vfadd.vv v10, v9, v9
; ZVFH-NEXT:    vmfeq.vv v0, v8, v8
; ZVFH-NEXT:    vmfeq.vv v9, v10, v10
; ZVFH-NEXT:    vmerge.vvm v11, v8, v10, v0
; ZVFH-NEXT:    vmv1r.v v0, v9
; ZVFH-NEXT:    vmerge.vvm v8, v10, v8, v0
; ZVFH-NEXT:    vfmax.vv v8, v8, v11
; ZVFH-NEXT:    ret
;
; ZVFHMIN-LABEL: vfmax_v2f16_vv_nnanb:
; ZVFHMIN:       # %bb.0:
; ZVFHMIN-NEXT:    vsetivli zero, 2, e16, mf4, ta, ma
; ZVFHMIN-NEXT:    vfwcvt.f.f.v v10, v9
; ZVFHMIN-NEXT:    vsetvli zero, zero, e32, mf2, ta, ma
; ZVFHMIN-NEXT:    vfadd.vv v9, v10, v10
; ZVFHMIN-NEXT:    vsetvli zero, zero, e16, mf4, ta, ma
; ZVFHMIN-NEXT:    vfncvt.f.f.w v10, v9
; ZVFHMIN-NEXT:    vfwcvt.f.f.v v9, v8
; ZVFHMIN-NEXT:    vsetvli zero, zero, e32, mf2, ta, ma
; ZVFHMIN-NEXT:    vmfeq.vv v0, v9, v9
; ZVFHMIN-NEXT:    vsetvli zero, zero, e16, mf4, ta, ma
; ZVFHMIN-NEXT:    vfwcvt.f.f.v v11, v10
; ZVFHMIN-NEXT:    vsetvli zero, zero, e32, mf2, ta, ma
; ZVFHMIN-NEXT:    vmfeq.vv v8, v11, v11
; ZVFHMIN-NEXT:    vmerge.vvm v10, v9, v11, v0
; ZVFHMIN-NEXT:    vmv1r.v v0, v8
; ZVFHMIN-NEXT:    vmerge.vvm v8, v11, v9, v0
; ZVFHMIN-NEXT:    vfmax.vv v9, v8, v10
; ZVFHMIN-NEXT:    vsetvli zero, zero, e16, mf4, ta, ma
; ZVFHMIN-NEXT:    vfncvt.f.f.w v8, v9
; ZVFHMIN-NEXT:    ret
  %c = fadd nnan <2 x half> %b, %b
  %v = call <2 x half> @llvm.maximum.v2f16(<2 x half> %a, <2 x half> %c)
  ret <2 x half> %v
}