llvm/test/Analysis/CostModel/AArch64/min-max.ll

; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
; RUN: opt < %s -mtriple=aarch64-unknown-linux-gnu -cost-model -cost-kind=throughput -analyze | FileCheck %s --check-prefixes=CHECK,CHECK-NOF16
; RUN: opt < %s -mtriple=aarch64-unknown-linux-gnu -mattr=+fullfp16 -cost-model -cost-kind=throughput -analyze | FileCheck %s --check-prefixes=CHECK,CHECK-F16

define void @reduce_umin() {
; CHECK-LABEL: 'reduce_umin'
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1i8 = call <1 x i8> @llvm.umin.v1i8(<1 x i8> undef, <1 x i8> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V3i8 = call <3 x i8> @llvm.umin.v3i8(<3 x i8> undef, <3 x i8> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4i8 = call <4 x i8> @llvm.umin.v4i8(<4 x i8> undef, <4 x i8> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8i8 = call <8 x i8> @llvm.umin.v8i8(<8 x i8> undef, <8 x i8> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16i8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32i8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64i8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2i16 = call <2 x i16> @llvm.umin.v2i16(<2 x i16> undef, <2 x i16> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4i16 = call <4 x i16> @llvm.umin.v4i16(<4 x i16> undef, <4 x i16> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8i16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16i16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2i32 = call <2 x i32> @llvm.umin.v2i32(<2 x i32> undef, <2 x i32> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4i32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8i32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
  %V1i8 = call <1 x i8> @llvm.umin.v1i8(<1 x i8> undef, <1 x i8> undef)
  %V3i8 = call <3 x i8> @llvm.umin.v3i8(<3 x i8> undef, <3 x i8> undef)
  %V4i8 = call <4 x i8> @llvm.umin.v4i8(<4 x i8> undef, <4 x i8> undef)
  %V8i8 = call <8 x i8> @llvm.umin.v8i8(<8 x i8> undef, <8 x i8> undef)
  %V16i8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
  %V32i8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
  %V64i8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
  %V2i16 = call <2 x i16> @llvm.umin.v2i16(<2 x i16> undef, <2 x i16> undef)
  %V4i16 = call <4 x i16> @llvm.umin.v4i16(<4 x i16> undef, <4 x i16> undef)
  %V8i16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
  %V16i16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
  %V2i32 = call <2 x i32> @llvm.umin.v2i32(<2 x i32> undef, <2 x i32> undef)
  %V4i32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
  %V8i32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
  %V2i64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
  %V4i64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
  ret void
}

define void @reduce_umax() {
; CHECK-LABEL: 'reduce_umax'
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1i8 = call <1 x i8> @llvm.umax.v1i8(<1 x i8> undef, <1 x i8> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V3i8 = call <3 x i8> @llvm.umax.v3i8(<3 x i8> undef, <3 x i8> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4i8 = call <4 x i8> @llvm.umax.v4i8(<4 x i8> undef, <4 x i8> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8i8 = call <8 x i8> @llvm.umax.v8i8(<8 x i8> undef, <8 x i8> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16i8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32i8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64i8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2i16 = call <2 x i16> @llvm.umax.v2i16(<2 x i16> undef, <2 x i16> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4i16 = call <4 x i16> @llvm.umax.v4i16(<4 x i16> undef, <4 x i16> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8i16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16i16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2i32 = call <2 x i32> @llvm.umax.v2i32(<2 x i32> undef, <2 x i32> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4i32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8i32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
  %V1i8 = call <1 x i8> @llvm.umax.v1i8(<1 x i8> undef, <1 x i8> undef)
  %V3i8 = call <3 x i8> @llvm.umax.v3i8(<3 x i8> undef, <3 x i8> undef)
  %V4i8 = call <4 x i8> @llvm.umax.v4i8(<4 x i8> undef, <4 x i8> undef)
  %V8i8 = call <8 x i8> @llvm.umax.v8i8(<8 x i8> undef, <8 x i8> undef)
  %V16i8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
  %V32i8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
  %V64i8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
  %V2i16 = call <2 x i16> @llvm.umax.v2i16(<2 x i16> undef, <2 x i16> undef)
  %V4i16 = call <4 x i16> @llvm.umax.v4i16(<4 x i16> undef, <4 x i16> undef)
  %V8i16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
  %V16i16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
  %V2i32 = call <2 x i32> @llvm.umax.v2i32(<2 x i32> undef, <2 x i32> undef)
  %V4i32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
  %V8i32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
  %V2i64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
  %V4i64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
  ret void
}

define void @reduce_smin() {
; CHECK-LABEL: 'reduce_smin'
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1i8 = call <1 x i8> @llvm.smin.v1i8(<1 x i8> undef, <1 x i8> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V3i8 = call <3 x i8> @llvm.smin.v3i8(<3 x i8> undef, <3 x i8> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4i8 = call <4 x i8> @llvm.smin.v4i8(<4 x i8> undef, <4 x i8> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8i8 = call <8 x i8> @llvm.smin.v8i8(<8 x i8> undef, <8 x i8> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16i8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32i8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64i8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2i16 = call <2 x i16> @llvm.smin.v2i16(<2 x i16> undef, <2 x i16> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4i16 = call <4 x i16> @llvm.smin.v4i16(<4 x i16> undef, <4 x i16> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8i16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16i16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2i32 = call <2 x i32> @llvm.smin.v2i32(<2 x i32> undef, <2 x i32> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4i32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8i32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
  %V1i8 = call <1 x i8> @llvm.smin.v1i8(<1 x i8> undef, <1 x i8> undef)
  %V3i8 = call <3 x i8> @llvm.smin.v3i8(<3 x i8> undef, <3 x i8> undef)
  %V4i8 = call <4 x i8> @llvm.smin.v4i8(<4 x i8> undef, <4 x i8> undef)
  %V8i8 = call <8 x i8> @llvm.smin.v8i8(<8 x i8> undef, <8 x i8> undef)
  %V16i8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
  %V32i8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
  %V64i8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
  %V2i16 = call <2 x i16> @llvm.smin.v2i16(<2 x i16> undef, <2 x i16> undef)
  %V4i16 = call <4 x i16> @llvm.smin.v4i16(<4 x i16> undef, <4 x i16> undef)
  %V8i16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
  %V16i16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
  %V2i32 = call <2 x i32> @llvm.smin.v2i32(<2 x i32> undef, <2 x i32> undef)
  %V4i32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
  %V8i32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
  %V2i64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
  %V4i64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
  ret void
}

define void @reduce_smax() {
; CHECK-LABEL: 'reduce_smax'
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1i8 = call <1 x i8> @llvm.smax.v1i8(<1 x i8> undef, <1 x i8> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V3i8 = call <3 x i8> @llvm.smax.v3i8(<3 x i8> undef, <3 x i8> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4i8 = call <4 x i8> @llvm.smax.v4i8(<4 x i8> undef, <4 x i8> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8i8 = call <8 x i8> @llvm.smax.v8i8(<8 x i8> undef, <8 x i8> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16i8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32i8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64i8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2i16 = call <2 x i16> @llvm.smax.v2i16(<2 x i16> undef, <2 x i16> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4i16 = call <4 x i16> @llvm.smax.v4i16(<4 x i16> undef, <4 x i16> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8i16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16i16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2i32 = call <2 x i32> @llvm.smax.v2i32(<2 x i32> undef, <2 x i32> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4i32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8i32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
  %V1i8 = call <1 x i8> @llvm.smax.v1i8(<1 x i8> undef, <1 x i8> undef)
  %V3i8 = call <3 x i8> @llvm.smax.v3i8(<3 x i8> undef, <3 x i8> undef)
  %V4i8 = call <4 x i8> @llvm.smax.v4i8(<4 x i8> undef, <4 x i8> undef)
  %V8i8 = call <8 x i8> @llvm.smax.v8i8(<8 x i8> undef, <8 x i8> undef)
  %V16i8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
  %V32i8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
  %V64i8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
  %V2i16 = call <2 x i16> @llvm.smax.v2i16(<2 x i16> undef, <2 x i16> undef)
  %V4i16 = call <4 x i16> @llvm.smax.v4i16(<4 x i16> undef, <4 x i16> undef)
  %V8i16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
  %V16i16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
  %V2i32 = call <2 x i32> @llvm.smax.v2i32(<2 x i32> undef, <2 x i32> undef)
  %V4i32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
  %V8i32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
  %V2i64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
  %V4i64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
  ret void
}

define void @reduce_minnum16() {
; CHECK-NOF16-LABEL: 'reduce_minnum16'
; CHECK-NOF16-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2f16 = call <2 x half> @llvm.minnum.v2f16(<2 x half> undef, <2 x half> undef)
; CHECK-NOF16-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V4f16 = call <4 x half> @llvm.minnum.v4f16(<4 x half> undef, <4 x half> undef)
; CHECK-NOF16-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V8f16 = call <8 x half> @llvm.minnum.v8f16(<8 x half> undef, <8 x half> undef)
; CHECK-NOF16-NEXT:  Cost Model: Found an estimated cost of 58 for instruction: %V16f16 = call <16 x half> @llvm.minnum.v16f16(<16 x half> undef, <16 x half> undef)
; CHECK-NOF16-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; CHECK-F16-LABEL: 'reduce_minnum16'
; CHECK-F16-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2f16 = call <2 x half> @llvm.minnum.v2f16(<2 x half> undef, <2 x half> undef)
; CHECK-F16-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4f16 = call <4 x half> @llvm.minnum.v4f16(<4 x half> undef, <4 x half> undef)
; CHECK-F16-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8f16 = call <8 x half> @llvm.minnum.v8f16(<8 x half> undef, <8 x half> undef)
; CHECK-F16-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16f16 = call <16 x half> @llvm.minnum.v16f16(<16 x half> undef, <16 x half> undef)
; CHECK-F16-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
  %V2f16 = call <2 x half> @llvm.minnum.v2f16(<2 x half> undef, <2 x half> undef)
  %V4f16 = call <4 x half> @llvm.minnum.v4f16(<4 x half> undef, <4 x half> undef)
  %V8f16 = call <8 x half> @llvm.minnum.v8f16(<8 x half> undef, <8 x half> undef)
  %V16f16 = call <16 x half> @llvm.minnum.v16f16(<16 x half> undef, <16 x half> undef)
  ret void
}

define void @reduce_maxnum16() {
; CHECK-NOF16-LABEL: 'reduce_maxnum16'
; CHECK-NOF16-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2f16 = call <2 x half> @llvm.maxnum.v2f16(<2 x half> undef, <2 x half> undef)
; CHECK-NOF16-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V4f16 = call <4 x half> @llvm.maxnum.v4f16(<4 x half> undef, <4 x half> undef)
; CHECK-NOF16-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V8f16 = call <8 x half> @llvm.maxnum.v8f16(<8 x half> undef, <8 x half> undef)
; CHECK-NOF16-NEXT:  Cost Model: Found an estimated cost of 58 for instruction: %V16f16 = call <16 x half> @llvm.maxnum.v16f16(<16 x half> undef, <16 x half> undef)
; CHECK-NOF16-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; CHECK-F16-LABEL: 'reduce_maxnum16'
; CHECK-F16-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2f16 = call <2 x half> @llvm.maxnum.v2f16(<2 x half> undef, <2 x half> undef)
; CHECK-F16-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4f16 = call <4 x half> @llvm.maxnum.v4f16(<4 x half> undef, <4 x half> undef)
; CHECK-F16-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8f16 = call <8 x half> @llvm.maxnum.v8f16(<8 x half> undef, <8 x half> undef)
; CHECK-F16-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16f16 = call <16 x half> @llvm.maxnum.v16f16(<16 x half> undef, <16 x half> undef)
; CHECK-F16-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
  %V2f16 = call <2 x half> @llvm.maxnum.v2f16(<2 x half> undef, <2 x half> undef)
  %V4f16 = call <4 x half> @llvm.maxnum.v4f16(<4 x half> undef, <4 x half> undef)
  %V8f16 = call <8 x half> @llvm.maxnum.v8f16(<8 x half> undef, <8 x half> undef)
  %V16f16 = call <16 x half> @llvm.maxnum.v16f16(<16 x half> undef, <16 x half> undef)
  ret void
}

define void @reduce_minnum() {
; CHECK-LABEL: 'reduce_minnum'
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2f32 = call <2 x float> @llvm.minnum.v2f32(<2 x float> undef, <2 x float> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4f32 = call <4 x float> @llvm.minnum.v4f32(<4 x float> undef, <4 x float> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8f32 = call <8 x float> @llvm.minnum.v8f32(<8 x float> undef, <8 x float> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2f64 = call <2 x double> @llvm.minnum.v2f64(<2 x double> undef, <2 x double> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4f64 = call <4 x double> @llvm.minnum.v4f64(<4 x double> undef, <4 x double> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
  %V2f32 = call <2 x float> @llvm.minnum.v2f32(<2 x float> undef, <2 x float> undef)
  %V4f32 = call <4 x float> @llvm.minnum.v4f32(<4 x float> undef, <4 x float> undef)
  %V8f32 = call <8 x float> @llvm.minnum.v8f32(<8 x float> undef, <8 x float> undef)
  %V2f64 = call <2 x double> @llvm.minnum.v2f64(<2 x double> undef, <2 x double> undef)
  %V4f64 = call <4 x double> @llvm.minnum.v4f64(<4 x double> undef, <4 x double> undef)
  ret void
}

define void @reduce_maxnum() {
; CHECK-LABEL: 'reduce_maxnum'
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2f32 = call <2 x float> @llvm.maxnum.v2f32(<2 x float> undef, <2 x float> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4f32 = call <4 x float> @llvm.maxnum.v4f32(<4 x float> undef, <4 x float> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8f32 = call <8 x float> @llvm.maxnum.v8f32(<8 x float> undef, <8 x float> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2f64 = call <2 x double> @llvm.maxnum.v2f64(<2 x double> undef, <2 x double> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4f64 = call <4 x double> @llvm.maxnum.v4f64(<4 x double> undef, <4 x double> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
  %V2f32 = call <2 x float> @llvm.maxnum.v2f32(<2 x float> undef, <2 x float> undef)
  %V4f32 = call <4 x float> @llvm.maxnum.v4f32(<4 x float> undef, <4 x float> undef)
  %V8f32 = call <8 x float> @llvm.maxnum.v8f32(<8 x float> undef, <8 x float> undef)
  %V2f64 = call <2 x double> @llvm.maxnum.v2f64(<2 x double> undef, <2 x double> undef)
  %V4f64 = call <4 x double> @llvm.maxnum.v4f64(<4 x double> undef, <4 x double> undef)
  ret void
}


define void @reduce_minimum16() {
; CHECK-NOF16-LABEL: 'reduce_minimum16'
; CHECK-NOF16-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2f16 = call <2 x half> @llvm.minimum.v2f16(<2 x half> undef, <2 x half> undef)
; CHECK-NOF16-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V4f16 = call <4 x half> @llvm.minimum.v4f16(<4 x half> undef, <4 x half> undef)
; CHECK-NOF16-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V8f16 = call <8 x half> @llvm.minimum.v8f16(<8 x half> undef, <8 x half> undef)
; CHECK-NOF16-NEXT:  Cost Model: Found an estimated cost of 58 for instruction: %V16f16 = call <16 x half> @llvm.minimum.v16f16(<16 x half> undef, <16 x half> undef)
; CHECK-NOF16-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; CHECK-F16-LABEL: 'reduce_minimum16'
; CHECK-F16-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2f16 = call <2 x half> @llvm.minimum.v2f16(<2 x half> undef, <2 x half> undef)
; CHECK-F16-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4f16 = call <4 x half> @llvm.minimum.v4f16(<4 x half> undef, <4 x half> undef)
; CHECK-F16-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8f16 = call <8 x half> @llvm.minimum.v8f16(<8 x half> undef, <8 x half> undef)
; CHECK-F16-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16f16 = call <16 x half> @llvm.minimum.v16f16(<16 x half> undef, <16 x half> undef)
; CHECK-F16-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
  %V2f16 = call <2 x half> @llvm.minimum.v2f16(<2 x half> undef, <2 x half> undef)
  %V4f16 = call <4 x half> @llvm.minimum.v4f16(<4 x half> undef, <4 x half> undef)
  %V8f16 = call <8 x half> @llvm.minimum.v8f16(<8 x half> undef, <8 x half> undef)
  %V16f16 = call <16 x half> @llvm.minimum.v16f16(<16 x half> undef, <16 x half> undef)
  ret void
}

define void @reduce_maximum16() {
; CHECK-NOF16-LABEL: 'reduce_maximum16'
; CHECK-NOF16-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2f16 = call <2 x half> @llvm.maximum.v2f16(<2 x half> undef, <2 x half> undef)
; CHECK-NOF16-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V4f16 = call <4 x half> @llvm.maximum.v4f16(<4 x half> undef, <4 x half> undef)
; CHECK-NOF16-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V8f16 = call <8 x half> @llvm.maximum.v8f16(<8 x half> undef, <8 x half> undef)
; CHECK-NOF16-NEXT:  Cost Model: Found an estimated cost of 58 for instruction: %V16f16 = call <16 x half> @llvm.maximum.v16f16(<16 x half> undef, <16 x half> undef)
; CHECK-NOF16-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; CHECK-F16-LABEL: 'reduce_maximum16'
; CHECK-F16-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2f16 = call <2 x half> @llvm.maximum.v2f16(<2 x half> undef, <2 x half> undef)
; CHECK-F16-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4f16 = call <4 x half> @llvm.maximum.v4f16(<4 x half> undef, <4 x half> undef)
; CHECK-F16-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8f16 = call <8 x half> @llvm.maximum.v8f16(<8 x half> undef, <8 x half> undef)
; CHECK-F16-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16f16 = call <16 x half> @llvm.maximum.v16f16(<16 x half> undef, <16 x half> undef)
; CHECK-F16-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
  %V2f16 = call <2 x half> @llvm.maximum.v2f16(<2 x half> undef, <2 x half> undef)
  %V4f16 = call <4 x half> @llvm.maximum.v4f16(<4 x half> undef, <4 x half> undef)
  %V8f16 = call <8 x half> @llvm.maximum.v8f16(<8 x half> undef, <8 x half> undef)
  %V16f16 = call <16 x half> @llvm.maximum.v16f16(<16 x half> undef, <16 x half> undef)
  ret void
}

define void @reduce_minimum() {
; CHECK-LABEL: 'reduce_minimum'
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2f32 = call <2 x float> @llvm.minimum.v2f32(<2 x float> undef, <2 x float> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4f32 = call <4 x float> @llvm.minimum.v4f32(<4 x float> undef, <4 x float> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8f32 = call <8 x float> @llvm.minimum.v8f32(<8 x float> undef, <8 x float> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2f64 = call <2 x double> @llvm.minimum.v2f64(<2 x double> undef, <2 x double> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4f64 = call <4 x double> @llvm.minimum.v4f64(<4 x double> undef, <4 x double> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
  %V2f32 = call <2 x float> @llvm.minimum.v2f32(<2 x float> undef, <2 x float> undef)
  %V4f32 = call <4 x float> @llvm.minimum.v4f32(<4 x float> undef, <4 x float> undef)
  %V8f32 = call <8 x float> @llvm.minimum.v8f32(<8 x float> undef, <8 x float> undef)
  %V2f64 = call <2 x double> @llvm.minimum.v2f64(<2 x double> undef, <2 x double> undef)
  %V4f64 = call <4 x double> @llvm.minimum.v4f64(<4 x double> undef, <4 x double> undef)
  ret void
}

define void @reduce_maximum() {
; CHECK-LABEL: 'reduce_maximum'
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2f32 = call <2 x float> @llvm.maximum.v2f32(<2 x float> undef, <2 x float> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4f32 = call <4 x float> @llvm.maximum.v4f32(<4 x float> undef, <4 x float> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8f32 = call <8 x float> @llvm.maximum.v8f32(<8 x float> undef, <8 x float> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2f64 = call <2 x double> @llvm.maximum.v2f64(<2 x double> undef, <2 x double> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4f64 = call <4 x double> @llvm.maximum.v4f64(<4 x double> undef, <4 x double> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
  %V2f32 = call <2 x float> @llvm.maximum.v2f32(<2 x float> undef, <2 x float> undef)
  %V4f32 = call <4 x float> @llvm.maximum.v4f32(<4 x float> undef, <4 x float> undef)
  %V8f32 = call <8 x float> @llvm.maximum.v8f32(<8 x float> undef, <8 x float> undef)
  %V2f64 = call <2 x double> @llvm.maximum.v2f64(<2 x double> undef, <2 x double> undef)
  %V4f64 = call <4 x double> @llvm.maximum.v4f64(<4 x double> undef, <4 x double> undef)
  ret void
}

declare <1 x i8> @llvm.umin.v1i8(<1 x i8>, <1 x i8>)
declare <3 x i8> @llvm.umin.v3i8(<3 x i8>, <3 x i8>)
declare <4 x i8> @llvm.umin.v4i8(<4 x i8>, <4 x i8>)
declare <8 x i8> @llvm.umin.v8i8(<8 x i8>, <8 x i8>)
declare <16 x i8> @llvm.umin.v16i8(<16 x i8>, <16 x i8>)
declare <32 x i8> @llvm.umin.v32i8(<32 x i8>, <32 x i8>)
declare <64 x i8> @llvm.umin.v64i8(<64 x i8>, <64 x i8>)
declare <2 x i16> @llvm.umin.v2i16(<2 x i16>, <2 x i16>)
declare <4 x i16> @llvm.umin.v4i16(<4 x i16>, <4 x i16>)
declare <8 x i16> @llvm.umin.v8i16(<8 x i16>, <8 x i16>)
declare <16 x i16> @llvm.umin.v16i16(<16 x i16>, <16 x i16>)
declare <2 x i32> @llvm.umin.v2i32(<2 x i32>, <2 x i32>)
declare <4 x i32> @llvm.umin.v4i32(<4 x i32>, <4 x i32>)
declare <8 x i32> @llvm.umin.v8i32(<8 x i32>, <8 x i32>)
declare <2 x i64> @llvm.umin.v2i64(<2 x i64>, <2 x i64>)
declare <4 x i64> @llvm.umin.v4i64(<4 x i64>, <4 x i64>)

declare <1 x i8> @llvm.umax.v1i8(<1 x i8>, <1 x i8>)
declare <3 x i8> @llvm.umax.v3i8(<3 x i8>, <3 x i8>)
declare <4 x i8> @llvm.umax.v4i8(<4 x i8>, <4 x i8>)
declare <8 x i8> @llvm.umax.v8i8(<8 x i8>, <8 x i8>)
declare <16 x i8> @llvm.umax.v16i8(<16 x i8>, <16 x i8>)
declare <32 x i8> @llvm.umax.v32i8(<32 x i8>, <32 x i8>)
declare <64 x i8> @llvm.umax.v64i8(<64 x i8>, <64 x i8>)
declare <2 x i16> @llvm.umax.v2i16(<2 x i16>, <2 x i16>)
declare <4 x i16> @llvm.umax.v4i16(<4 x i16>, <4 x i16>)
declare <8 x i16> @llvm.umax.v8i16(<8 x i16>, <8 x i16>)
declare <16 x i16> @llvm.umax.v16i16(<16 x i16>, <16 x i16>)
declare <2 x i32> @llvm.umax.v2i32(<2 x i32>, <2 x i32>)
declare <4 x i32> @llvm.umax.v4i32(<4 x i32>, <4 x i32>)
declare <8 x i32> @llvm.umax.v8i32(<8 x i32>, <8 x i32>)
declare <2 x i64> @llvm.umax.v2i64(<2 x i64>, <2 x i64>)
declare <4 x i64> @llvm.umax.v4i64(<4 x i64>, <4 x i64>)

declare <1 x i8> @llvm.smin.v1i8(<1 x i8>, <1 x i8>)
declare <3 x i8> @llvm.smin.v3i8(<3 x i8>, <3 x i8>)
declare <4 x i8> @llvm.smin.v4i8(<4 x i8>, <4 x i8>)
declare <8 x i8> @llvm.smin.v8i8(<8 x i8>, <8 x i8>)
declare <16 x i8> @llvm.smin.v16i8(<16 x i8>, <16 x i8>)
declare <32 x i8> @llvm.smin.v32i8(<32 x i8>, <32 x i8>)
declare <64 x i8> @llvm.smin.v64i8(<64 x i8>, <64 x i8>)
declare <2 x i16> @llvm.smin.v2i16(<2 x i16>, <2 x i16>)
declare <4 x i16> @llvm.smin.v4i16(<4 x i16>, <4 x i16>)
declare <8 x i16> @llvm.smin.v8i16(<8 x i16>, <8 x i16>)
declare <16 x i16> @llvm.smin.v16i16(<16 x i16>, <16 x i16>)
declare <2 x i32> @llvm.smin.v2i32(<2 x i32>, <2 x i32>)
declare <4 x i32> @llvm.smin.v4i32(<4 x i32>, <4 x i32>)
declare <8 x i32> @llvm.smin.v8i32(<8 x i32>, <8 x i32>)
declare <2 x i64> @llvm.smin.v2i64(<2 x i64>, <2 x i64>)
declare <4 x i64> @llvm.smin.v4i64(<4 x i64>, <4 x i64>)

declare <1 x i8> @llvm.smax.v1i8(<1 x i8>, <1 x i8>)
declare <3 x i8> @llvm.smax.v3i8(<3 x i8>, <3 x i8>)
declare <4 x i8> @llvm.smax.v4i8(<4 x i8>, <4 x i8>)
declare <8 x i8> @llvm.smax.v8i8(<8 x i8>, <8 x i8>)
declare <16 x i8> @llvm.smax.v16i8(<16 x i8>, <16 x i8>)
declare <32 x i8> @llvm.smax.v32i8(<32 x i8>, <32 x i8>)
declare <64 x i8> @llvm.smax.v64i8(<64 x i8>, <64 x i8>)
declare <2 x i16> @llvm.smax.v2i16(<2 x i16>, <2 x i16>)
declare <4 x i16> @llvm.smax.v4i16(<4 x i16>, <4 x i16>)
declare <8 x i16> @llvm.smax.v8i16(<8 x i16>, <8 x i16>)
declare <16 x i16> @llvm.smax.v16i16(<16 x i16>, <16 x i16>)
declare <2 x i32> @llvm.smax.v2i32(<2 x i32>, <2 x i32>)
declare <4 x i32> @llvm.smax.v4i32(<4 x i32>, <4 x i32>)
declare <8 x i32> @llvm.smax.v8i32(<8 x i32>, <8 x i32>)
declare <2 x i64> @llvm.smax.v2i64(<2 x i64>, <2 x i64>)
declare <4 x i64> @llvm.smax.v4i64(<4 x i64>, <4 x i64>)

declare <2 x half> @llvm.minnum.v2f16(<2 x half>, <2 x half>)
declare <4 x half> @llvm.minnum.v4f16(<4 x half>, <4 x half>)
declare <8 x half> @llvm.minnum.v8f16(<8 x half>, <8 x half>)
declare <16 x half> @llvm.minnum.v16f16(<16 x half>, <16 x half>)
declare <2 x float> @llvm.minnum.v2f32(<2 x float>, <2 x float>)
declare <4 x float> @llvm.minnum.v4f32(<4 x float>, <4 x float>)
declare <8 x float> @llvm.minnum.v8f32(<8 x float>, <8 x float>)
declare <2 x double> @llvm.minnum.v2f64(<2 x double>, <2 x double>)
declare <4 x double> @llvm.minnum.v4f64(<4 x double>, <4 x double>)

declare <2 x half> @llvm.maxnum.v2f16(<2 x half>, <2 x half>)
declare <4 x half> @llvm.maxnum.v4f16(<4 x half>, <4 x half>)
declare <8 x half> @llvm.maxnum.v8f16(<8 x half>, <8 x half>)
declare <16 x half> @llvm.maxnum.v16f16(<16 x half>, <16 x half>)
declare <2 x float> @llvm.maxnum.v2f32(<2 x float>, <2 x float>)
declare <4 x float> @llvm.maxnum.v4f32(<4 x float>, <4 x float>)
declare <8 x float> @llvm.maxnum.v8f32(<8 x float>, <8 x float>)
declare <2 x double> @llvm.maxnum.v2f64(<2 x double>, <2 x double>)
declare <4 x double> @llvm.maxnum.v4f64(<4 x double>, <4 x double>)

declare <2 x half> @llvm.minimum.v2f16(<2 x half>, <2 x half>)
declare <4 x half> @llvm.minimum.v4f16(<4 x half>, <4 x half>)
declare <8 x half> @llvm.minimum.v8f16(<8 x half>, <8 x half>)
declare <16 x half> @llvm.minimum.v16f16(<16 x half>, <16 x half>)
declare <2 x float> @llvm.minimum.v2f32(<2 x float>, <2 x float>)
declare <4 x float> @llvm.minimum.v4f32(<4 x float>, <4 x float>)
declare <8 x float> @llvm.minimum.v8f32(<8 x float>, <8 x float>)
declare <2 x double> @llvm.minimum.v2f64(<2 x double>, <2 x double>)
declare <4 x double> @llvm.minimum.v4f64(<4 x double>, <4 x double>)

declare <2 x half> @llvm.maximum.v2f16(<2 x half>, <2 x half>)
declare <4 x half> @llvm.maximum.v4f16(<4 x half>, <4 x half>)
declare <8 x half> @llvm.maximum.v8f16(<8 x half>, <8 x half>)
declare <16 x half> @llvm.maximum.v16f16(<16 x half>, <16 x half>)
declare <2 x float> @llvm.maximum.v2f32(<2 x float>, <2 x float>)
declare <4 x float> @llvm.maximum.v4f32(<4 x float>, <4 x float>)
declare <8 x float> @llvm.maximum.v8f32(<8 x float>, <8 x float>)
declare <2 x double> @llvm.maximum.v2f64(<2 x double>, <2 x double>)
declare <4 x double> @llvm.maximum.v4f64(<4 x double>, <4 x double>)