; 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,+zfhmin,+zvfhmin,+v -target-abi=ilp32d \ ; RUN: -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK,ZVFHMIN ; RUN: llc -mtriple=riscv64 -mattr=+d,+zfhmin,+zvfhmin,+v -target-abi=lp64d \ ; RUN: -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK,ZVFHMIN declare @llvm.vp.rint.nxv1f16(, , i32) define @vp_rint_nxv1f16( %va, %m, i32 zeroext %evl) { ; ZVFH-LABEL: vp_rint_nxv1f16: ; ZVFH: # %bb.0: ; ZVFH-NEXT: lui a1, %hi(.LCPI0_0) ; ZVFH-NEXT: flh fa5, %lo(.LCPI0_0)(a1) ; ZVFH-NEXT: vsetvli zero, a0, e16, mf4, ta, ma ; ZVFH-NEXT: vfabs.v v9, v8, v0.t ; ZVFH-NEXT: vsetvli zero, zero, e16, mf4, ta, mu ; ZVFH-NEXT: vmflt.vf v0, v9, fa5, v0.t ; ZVFH-NEXT: vsetvli zero, zero, e16, mf4, ta, ma ; ZVFH-NEXT: vfcvt.x.f.v v9, v8, v0.t ; ZVFH-NEXT: vfcvt.f.x.v v9, v9, v0.t ; ZVFH-NEXT: vsetvli zero, zero, e16, mf4, ta, mu ; ZVFH-NEXT: vfsgnj.vv v8, v9, v8, v0.t ; ZVFH-NEXT: ret ; ; ZVFHMIN-LABEL: vp_rint_nxv1f16: ; ZVFHMIN: # %bb.0: ; ZVFHMIN-NEXT: vsetvli a1, zero, e16, mf4, ta, ma ; ZVFHMIN-NEXT: vfwcvt.f.f.v v9, v8 ; ZVFHMIN-NEXT: vsetvli zero, a0, e32, mf2, ta, ma ; ZVFHMIN-NEXT: vfabs.v v8, v9, v0.t ; ZVFHMIN-NEXT: lui a0, 307200 ; ZVFHMIN-NEXT: fmv.w.x fa5, a0 ; ZVFHMIN-NEXT: vsetvli zero, zero, e32, mf2, ta, mu ; ZVFHMIN-NEXT: vmflt.vf v0, v8, fa5, v0.t ; ZVFHMIN-NEXT: vsetvli zero, zero, e32, mf2, ta, ma ; ZVFHMIN-NEXT: vfcvt.x.f.v v8, v9, v0.t ; ZVFHMIN-NEXT: vfcvt.f.x.v v8, v8, v0.t ; ZVFHMIN-NEXT: vsetvli zero, zero, e32, mf2, ta, mu ; ZVFHMIN-NEXT: vfsgnj.vv v9, v8, v9, v0.t ; ZVFHMIN-NEXT: vsetvli a0, zero, e16, mf4, ta, ma ; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v9 ; ZVFHMIN-NEXT: ret %v = call @llvm.vp.rint.nxv1f16( %va, %m, i32 %evl) ret %v } define @vp_rint_nxv1f16_unmasked( %va, i32 zeroext %evl) { ; ZVFH-LABEL: vp_rint_nxv1f16_unmasked: ; ZVFH: # %bb.0: ; ZVFH-NEXT: lui a1, %hi(.LCPI1_0) ; ZVFH-NEXT: flh fa5, %lo(.LCPI1_0)(a1) ; ZVFH-NEXT: vsetvli zero, a0, e16, mf4, ta, ma ; ZVFH-NEXT: vfabs.v v9, v8 ; ZVFH-NEXT: vmflt.vf v0, v9, fa5 ; ZVFH-NEXT: vfcvt.x.f.v v9, v8, v0.t ; ZVFH-NEXT: vfcvt.f.x.v v9, v9, v0.t ; ZVFH-NEXT: vsetvli zero, zero, e16, mf4, ta, mu ; ZVFH-NEXT: vfsgnj.vv v8, v9, v8, v0.t ; ZVFH-NEXT: ret ; ; ZVFHMIN-LABEL: vp_rint_nxv1f16_unmasked: ; ZVFHMIN: # %bb.0: ; ZVFHMIN-NEXT: vsetvli a1, zero, e16, mf4, ta, ma ; ZVFHMIN-NEXT: vfwcvt.f.f.v v9, v8 ; ZVFHMIN-NEXT: vsetvli zero, a0, e32, mf2, ta, ma ; ZVFHMIN-NEXT: vfabs.v v8, v9 ; ZVFHMIN-NEXT: lui a0, 307200 ; ZVFHMIN-NEXT: fmv.w.x fa5, a0 ; ZVFHMIN-NEXT: vmflt.vf v0, v8, fa5 ; ZVFHMIN-NEXT: vfcvt.x.f.v v8, v9, v0.t ; ZVFHMIN-NEXT: vfcvt.f.x.v v8, v8, v0.t ; ZVFHMIN-NEXT: vsetvli zero, zero, e32, mf2, ta, mu ; ZVFHMIN-NEXT: vfsgnj.vv v9, v8, v9, v0.t ; ZVFHMIN-NEXT: vsetvli a0, zero, e16, mf4, ta, ma ; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v9 ; ZVFHMIN-NEXT: ret %head = insertelement poison, i1 true, i32 0 %m = shufflevector %head, poison, zeroinitializer %v = call @llvm.vp.rint.nxv1f16( %va, %m, i32 %evl) ret %v } declare @llvm.vp.rint.nxv2f16(, , i32) define @vp_rint_nxv2f16( %va, %m, i32 zeroext %evl) { ; ZVFH-LABEL: vp_rint_nxv2f16: ; ZVFH: # %bb.0: ; ZVFH-NEXT: lui a1, %hi(.LCPI2_0) ; ZVFH-NEXT: flh fa5, %lo(.LCPI2_0)(a1) ; ZVFH-NEXT: vsetvli zero, a0, e16, mf2, ta, ma ; ZVFH-NEXT: vfabs.v v9, v8, v0.t ; ZVFH-NEXT: vsetvli zero, zero, e16, mf2, ta, mu ; ZVFH-NEXT: vmflt.vf v0, v9, fa5, v0.t ; ZVFH-NEXT: vsetvli zero, zero, e16, mf2, ta, ma ; ZVFH-NEXT: vfcvt.x.f.v v9, v8, v0.t ; ZVFH-NEXT: vfcvt.f.x.v v9, v9, v0.t ; ZVFH-NEXT: vsetvli zero, zero, e16, mf2, ta, mu ; ZVFH-NEXT: vfsgnj.vv v8, v9, v8, v0.t ; ZVFH-NEXT: ret ; ; ZVFHMIN-LABEL: vp_rint_nxv2f16: ; ZVFHMIN: # %bb.0: ; ZVFHMIN-NEXT: vsetvli a1, zero, e16, mf2, ta, ma ; ZVFHMIN-NEXT: vfwcvt.f.f.v v9, v8 ; ZVFHMIN-NEXT: vsetvli zero, a0, e32, m1, ta, ma ; ZVFHMIN-NEXT: vfabs.v v8, v9, v0.t ; ZVFHMIN-NEXT: lui a0, 307200 ; ZVFHMIN-NEXT: fmv.w.x fa5, a0 ; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m1, ta, mu ; ZVFHMIN-NEXT: vmflt.vf v0, v8, fa5, v0.t ; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m1, ta, ma ; ZVFHMIN-NEXT: vfcvt.x.f.v v8, v9, v0.t ; ZVFHMIN-NEXT: vfcvt.f.x.v v8, v8, v0.t ; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m1, ta, mu ; ZVFHMIN-NEXT: vfsgnj.vv v9, v8, v9, v0.t ; ZVFHMIN-NEXT: vsetvli a0, zero, e16, mf2, ta, ma ; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v9 ; ZVFHMIN-NEXT: ret %v = call @llvm.vp.rint.nxv2f16( %va, %m, i32 %evl) ret %v } define @vp_rint_nxv2f16_unmasked( %va, i32 zeroext %evl) { ; ZVFH-LABEL: vp_rint_nxv2f16_unmasked: ; ZVFH: # %bb.0: ; ZVFH-NEXT: lui a1, %hi(.LCPI3_0) ; ZVFH-NEXT: flh fa5, %lo(.LCPI3_0)(a1) ; ZVFH-NEXT: vsetvli zero, a0, e16, mf2, ta, ma ; ZVFH-NEXT: vfabs.v v9, v8 ; ZVFH-NEXT: vmflt.vf v0, v9, fa5 ; ZVFH-NEXT: vfcvt.x.f.v v9, v8, v0.t ; ZVFH-NEXT: vfcvt.f.x.v v9, v9, v0.t ; ZVFH-NEXT: vsetvli zero, zero, e16, mf2, ta, mu ; ZVFH-NEXT: vfsgnj.vv v8, v9, v8, v0.t ; ZVFH-NEXT: ret ; ; ZVFHMIN-LABEL: vp_rint_nxv2f16_unmasked: ; ZVFHMIN: # %bb.0: ; ZVFHMIN-NEXT: vsetvli a1, zero, e16, mf2, ta, ma ; ZVFHMIN-NEXT: vfwcvt.f.f.v v9, v8 ; ZVFHMIN-NEXT: vsetvli zero, a0, e32, m1, ta, ma ; ZVFHMIN-NEXT: vfabs.v v8, v9 ; ZVFHMIN-NEXT: lui a0, 307200 ; ZVFHMIN-NEXT: fmv.w.x fa5, a0 ; ZVFHMIN-NEXT: vmflt.vf v0, v8, fa5 ; ZVFHMIN-NEXT: vfcvt.x.f.v v8, v9, v0.t ; ZVFHMIN-NEXT: vfcvt.f.x.v v8, v8, v0.t ; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m1, ta, mu ; ZVFHMIN-NEXT: vfsgnj.vv v9, v8, v9, v0.t ; ZVFHMIN-NEXT: vsetvli a0, zero, e16, mf2, ta, ma ; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v9 ; ZVFHMIN-NEXT: ret %head = insertelement poison, i1 true, i32 0 %m = shufflevector %head, poison, zeroinitializer %v = call @llvm.vp.rint.nxv2f16( %va, %m, i32 %evl) ret %v } declare @llvm.vp.rint.nxv4f16(, , i32) define @vp_rint_nxv4f16( %va, %m, i32 zeroext %evl) { ; ZVFH-LABEL: vp_rint_nxv4f16: ; ZVFH: # %bb.0: ; ZVFH-NEXT: lui a1, %hi(.LCPI4_0) ; ZVFH-NEXT: flh fa5, %lo(.LCPI4_0)(a1) ; ZVFH-NEXT: vsetvli zero, a0, e16, m1, ta, ma ; ZVFH-NEXT: vfabs.v v9, v8, v0.t ; ZVFH-NEXT: vsetvli zero, zero, e16, m1, ta, mu ; ZVFH-NEXT: vmflt.vf v0, v9, fa5, v0.t ; ZVFH-NEXT: vsetvli zero, zero, e16, m1, ta, ma ; ZVFH-NEXT: vfcvt.x.f.v v9, v8, v0.t ; ZVFH-NEXT: vfcvt.f.x.v v9, v9, v0.t ; ZVFH-NEXT: vsetvli zero, zero, e16, m1, ta, mu ; ZVFH-NEXT: vfsgnj.vv v8, v9, v8, v0.t ; ZVFH-NEXT: ret ; ; ZVFHMIN-LABEL: vp_rint_nxv4f16: ; ZVFHMIN: # %bb.0: ; ZVFHMIN-NEXT: vmv1r.v v9, v0 ; ZVFHMIN-NEXT: vsetvli a1, zero, e16, m1, ta, ma ; ZVFHMIN-NEXT: vfwcvt.f.f.v v10, v8 ; ZVFHMIN-NEXT: vsetvli zero, a0, e32, m2, ta, ma ; ZVFHMIN-NEXT: vfabs.v v12, v10, v0.t ; ZVFHMIN-NEXT: lui a0, 307200 ; ZVFHMIN-NEXT: fmv.w.x fa5, a0 ; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m2, ta, mu ; ZVFHMIN-NEXT: vmflt.vf v9, v12, fa5, v0.t ; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m2, ta, ma ; ZVFHMIN-NEXT: vmv1r.v v0, v9 ; ZVFHMIN-NEXT: vfcvt.x.f.v v12, v10, v0.t ; ZVFHMIN-NEXT: vfcvt.f.x.v v12, v12, v0.t ; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m2, ta, mu ; ZVFHMIN-NEXT: vfsgnj.vv v10, v12, v10, v0.t ; ZVFHMIN-NEXT: vsetvli a0, zero, e16, m1, ta, ma ; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v10 ; ZVFHMIN-NEXT: ret %v = call @llvm.vp.rint.nxv4f16( %va, %m, i32 %evl) ret %v } define @vp_rint_nxv4f16_unmasked( %va, i32 zeroext %evl) { ; ZVFH-LABEL: vp_rint_nxv4f16_unmasked: ; ZVFH: # %bb.0: ; ZVFH-NEXT: lui a1, %hi(.LCPI5_0) ; ZVFH-NEXT: flh fa5, %lo(.LCPI5_0)(a1) ; ZVFH-NEXT: vsetvli zero, a0, e16, m1, ta, ma ; ZVFH-NEXT: vfabs.v v9, v8 ; ZVFH-NEXT: vmflt.vf v0, v9, fa5 ; ZVFH-NEXT: vfcvt.x.f.v v9, v8, v0.t ; ZVFH-NEXT: vfcvt.f.x.v v9, v9, v0.t ; ZVFH-NEXT: vsetvli zero, zero, e16, m1, ta, mu ; ZVFH-NEXT: vfsgnj.vv v8, v9, v8, v0.t ; ZVFH-NEXT: ret ; ; ZVFHMIN-LABEL: vp_rint_nxv4f16_unmasked: ; ZVFHMIN: # %bb.0: ; ZVFHMIN-NEXT: vsetvli a1, zero, e16, m1, ta, ma ; ZVFHMIN-NEXT: vfwcvt.f.f.v v10, v8 ; ZVFHMIN-NEXT: vsetvli zero, a0, e32, m2, ta, ma ; ZVFHMIN-NEXT: vfabs.v v8, v10 ; ZVFHMIN-NEXT: lui a0, 307200 ; ZVFHMIN-NEXT: fmv.w.x fa5, a0 ; ZVFHMIN-NEXT: vmflt.vf v0, v8, fa5 ; ZVFHMIN-NEXT: vfcvt.x.f.v v8, v10, v0.t ; ZVFHMIN-NEXT: vfcvt.f.x.v v8, v8, v0.t ; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m2, ta, mu ; ZVFHMIN-NEXT: vfsgnj.vv v10, v8, v10, v0.t ; ZVFHMIN-NEXT: vsetvli a0, zero, e16, m1, ta, ma ; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v10 ; ZVFHMIN-NEXT: ret %head = insertelement poison, i1 true, i32 0 %m = shufflevector %head, poison, zeroinitializer %v = call @llvm.vp.rint.nxv4f16( %va, %m, i32 %evl) ret %v } declare @llvm.vp.rint.nxv8f16(, , i32) define @vp_rint_nxv8f16( %va, %m, i32 zeroext %evl) { ; ZVFH-LABEL: vp_rint_nxv8f16: ; ZVFH: # %bb.0: ; ZVFH-NEXT: vmv1r.v v10, v0 ; ZVFH-NEXT: lui a1, %hi(.LCPI6_0) ; ZVFH-NEXT: flh fa5, %lo(.LCPI6_0)(a1) ; ZVFH-NEXT: vsetvli zero, a0, e16, m2, ta, ma ; ZVFH-NEXT: vfabs.v v12, v8, v0.t ; ZVFH-NEXT: vsetvli zero, zero, e16, m2, ta, mu ; ZVFH-NEXT: vmflt.vf v10, v12, fa5, v0.t ; ZVFH-NEXT: vsetvli zero, zero, e16, m2, ta, ma ; ZVFH-NEXT: vmv1r.v v0, v10 ; ZVFH-NEXT: vfcvt.x.f.v v12, v8, v0.t ; ZVFH-NEXT: vfcvt.f.x.v v12, v12, v0.t ; ZVFH-NEXT: vsetvli zero, zero, e16, m2, ta, mu ; ZVFH-NEXT: vfsgnj.vv v8, v12, v8, v0.t ; ZVFH-NEXT: ret ; ; ZVFHMIN-LABEL: vp_rint_nxv8f16: ; ZVFHMIN: # %bb.0: ; ZVFHMIN-NEXT: vmv1r.v v10, v0 ; ZVFHMIN-NEXT: vsetvli a1, zero, e16, m2, ta, ma ; ZVFHMIN-NEXT: vfwcvt.f.f.v v12, v8 ; ZVFHMIN-NEXT: vsetvli zero, a0, e32, m4, ta, ma ; ZVFHMIN-NEXT: vfabs.v v16, v12, v0.t ; ZVFHMIN-NEXT: lui a0, 307200 ; ZVFHMIN-NEXT: fmv.w.x fa5, a0 ; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m4, ta, mu ; ZVFHMIN-NEXT: vmflt.vf v10, v16, fa5, v0.t ; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m4, ta, ma ; ZVFHMIN-NEXT: vmv1r.v v0, v10 ; ZVFHMIN-NEXT: vfcvt.x.f.v v16, v12, v0.t ; ZVFHMIN-NEXT: vfcvt.f.x.v v16, v16, v0.t ; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m4, ta, mu ; ZVFHMIN-NEXT: vfsgnj.vv v12, v16, v12, v0.t ; ZVFHMIN-NEXT: vsetvli a0, zero, e16, m2, ta, ma ; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v12 ; ZVFHMIN-NEXT: ret %v = call @llvm.vp.rint.nxv8f16( %va, %m, i32 %evl) ret %v } define @vp_rint_nxv8f16_unmasked( %va, i32 zeroext %evl) { ; ZVFH-LABEL: vp_rint_nxv8f16_unmasked: ; ZVFH: # %bb.0: ; ZVFH-NEXT: lui a1, %hi(.LCPI7_0) ; ZVFH-NEXT: flh fa5, %lo(.LCPI7_0)(a1) ; ZVFH-NEXT: vsetvli zero, a0, e16, m2, ta, ma ; ZVFH-NEXT: vfabs.v v10, v8 ; ZVFH-NEXT: vmflt.vf v0, v10, fa5 ; ZVFH-NEXT: vfcvt.x.f.v v10, v8, v0.t ; ZVFH-NEXT: vfcvt.f.x.v v10, v10, v0.t ; ZVFH-NEXT: vsetvli zero, zero, e16, m2, ta, mu ; ZVFH-NEXT: vfsgnj.vv v8, v10, v8, v0.t ; ZVFH-NEXT: ret ; ; ZVFHMIN-LABEL: vp_rint_nxv8f16_unmasked: ; ZVFHMIN: # %bb.0: ; ZVFHMIN-NEXT: vsetvli a1, zero, e16, m2, ta, ma ; ZVFHMIN-NEXT: vfwcvt.f.f.v v12, v8 ; ZVFHMIN-NEXT: vsetvli zero, a0, e32, m4, ta, ma ; ZVFHMIN-NEXT: vfabs.v v8, v12 ; ZVFHMIN-NEXT: lui a0, 307200 ; ZVFHMIN-NEXT: fmv.w.x fa5, a0 ; ZVFHMIN-NEXT: vmflt.vf v0, v8, fa5 ; ZVFHMIN-NEXT: vfcvt.x.f.v v8, v12, v0.t ; ZVFHMIN-NEXT: vfcvt.f.x.v v8, v8, v0.t ; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m4, ta, mu ; ZVFHMIN-NEXT: vfsgnj.vv v12, v8, v12, v0.t ; ZVFHMIN-NEXT: vsetvli a0, zero, e16, m2, ta, ma ; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v12 ; ZVFHMIN-NEXT: ret %head = insertelement poison, i1 true, i32 0 %m = shufflevector %head, poison, zeroinitializer %v = call @llvm.vp.rint.nxv8f16( %va, %m, i32 %evl) ret %v } declare @llvm.vp.rint.nxv16f16(, , i32) define @vp_rint_nxv16f16( %va, %m, i32 zeroext %evl) { ; ZVFH-LABEL: vp_rint_nxv16f16: ; ZVFH: # %bb.0: ; ZVFH-NEXT: vmv1r.v v12, v0 ; ZVFH-NEXT: lui a1, %hi(.LCPI8_0) ; ZVFH-NEXT: flh fa5, %lo(.LCPI8_0)(a1) ; ZVFH-NEXT: vsetvli zero, a0, e16, m4, ta, ma ; ZVFH-NEXT: vfabs.v v16, v8, v0.t ; ZVFH-NEXT: vsetvli zero, zero, e16, m4, ta, mu ; ZVFH-NEXT: vmflt.vf v12, v16, fa5, v0.t ; ZVFH-NEXT: vsetvli zero, zero, e16, m4, ta, ma ; ZVFH-NEXT: vmv1r.v v0, v12 ; ZVFH-NEXT: vfcvt.x.f.v v16, v8, v0.t ; ZVFH-NEXT: vfcvt.f.x.v v16, v16, v0.t ; ZVFH-NEXT: vsetvli zero, zero, e16, m4, ta, mu ; ZVFH-NEXT: vfsgnj.vv v8, v16, v8, v0.t ; ZVFH-NEXT: ret ; ; ZVFHMIN-LABEL: vp_rint_nxv16f16: ; ZVFHMIN: # %bb.0: ; ZVFHMIN-NEXT: vmv1r.v v12, v0 ; ZVFHMIN-NEXT: vsetvli a1, zero, e16, m4, ta, ma ; ZVFHMIN-NEXT: vfwcvt.f.f.v v16, v8 ; ZVFHMIN-NEXT: vsetvli zero, a0, e32, m8, ta, ma ; ZVFHMIN-NEXT: vfabs.v v24, v16, v0.t ; ZVFHMIN-NEXT: lui a0, 307200 ; ZVFHMIN-NEXT: fmv.w.x fa5, a0 ; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m8, ta, mu ; ZVFHMIN-NEXT: vmflt.vf v12, v24, fa5, v0.t ; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m8, ta, ma ; ZVFHMIN-NEXT: vmv1r.v v0, v12 ; ZVFHMIN-NEXT: vfcvt.x.f.v v24, v16, v0.t ; ZVFHMIN-NEXT: vfcvt.f.x.v v24, v24, v0.t ; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m8, ta, mu ; ZVFHMIN-NEXT: vfsgnj.vv v16, v24, v16, v0.t ; ZVFHMIN-NEXT: vsetvli a0, zero, e16, m4, ta, ma ; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v16 ; ZVFHMIN-NEXT: ret %v = call @llvm.vp.rint.nxv16f16( %va, %m, i32 %evl) ret %v } define @vp_rint_nxv16f16_unmasked( %va, i32 zeroext %evl) { ; ZVFH-LABEL: vp_rint_nxv16f16_unmasked: ; ZVFH: # %bb.0: ; ZVFH-NEXT: lui a1, %hi(.LCPI9_0) ; ZVFH-NEXT: flh fa5, %lo(.LCPI9_0)(a1) ; ZVFH-NEXT: vsetvli zero, a0, e16, m4, ta, ma ; ZVFH-NEXT: vfabs.v v12, v8 ; ZVFH-NEXT: vmflt.vf v0, v12, fa5 ; ZVFH-NEXT: vfcvt.x.f.v v12, v8, v0.t ; ZVFH-NEXT: vfcvt.f.x.v v12, v12, v0.t ; ZVFH-NEXT: vsetvli zero, zero, e16, m4, ta, mu ; ZVFH-NEXT: vfsgnj.vv v8, v12, v8, v0.t ; ZVFH-NEXT: ret ; ; ZVFHMIN-LABEL: vp_rint_nxv16f16_unmasked: ; ZVFHMIN: # %bb.0: ; ZVFHMIN-NEXT: vsetvli a1, zero, e16, m4, ta, ma ; ZVFHMIN-NEXT: vfwcvt.f.f.v v16, v8 ; ZVFHMIN-NEXT: vsetvli zero, a0, e32, m8, ta, ma ; ZVFHMIN-NEXT: vfabs.v v8, v16 ; ZVFHMIN-NEXT: lui a0, 307200 ; ZVFHMIN-NEXT: fmv.w.x fa5, a0 ; ZVFHMIN-NEXT: vmflt.vf v0, v8, fa5 ; ZVFHMIN-NEXT: vfcvt.x.f.v v8, v16, v0.t ; ZVFHMIN-NEXT: vfcvt.f.x.v v8, v8, v0.t ; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m8, ta, mu ; ZVFHMIN-NEXT: vfsgnj.vv v16, v8, v16, v0.t ; ZVFHMIN-NEXT: vsetvli a0, zero, e16, m4, ta, ma ; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v16 ; ZVFHMIN-NEXT: ret %head = insertelement poison, i1 true, i32 0 %m = shufflevector %head, poison, zeroinitializer %v = call @llvm.vp.rint.nxv16f16( %va, %m, i32 %evl) ret %v } declare @llvm.vp.rint.nxv32f16(, , i32) define @vp_rint_nxv32f16( %va, %m, i32 zeroext %evl) { ; ZVFH-LABEL: vp_rint_nxv32f16: ; ZVFH: # %bb.0: ; ZVFH-NEXT: vmv1r.v v16, v0 ; ZVFH-NEXT: lui a1, %hi(.LCPI10_0) ; ZVFH-NEXT: flh fa5, %lo(.LCPI10_0)(a1) ; ZVFH-NEXT: vsetvli zero, a0, e16, m8, ta, ma ; ZVFH-NEXT: vfabs.v v24, v8, v0.t ; ZVFH-NEXT: vsetvli zero, zero, e16, m8, ta, mu ; ZVFH-NEXT: vmflt.vf v16, v24, fa5, v0.t ; ZVFH-NEXT: vsetvli zero, zero, e16, m8, ta, ma ; ZVFH-NEXT: vmv1r.v v0, v16 ; ZVFH-NEXT: vfcvt.x.f.v v24, v8, v0.t ; ZVFH-NEXT: vfcvt.f.x.v v24, v24, v0.t ; ZVFH-NEXT: vsetvli zero, zero, e16, m8, ta, mu ; ZVFH-NEXT: vfsgnj.vv v8, v24, v8, v0.t ; ZVFH-NEXT: ret ; ; ZVFHMIN-LABEL: vp_rint_nxv32f16: ; ZVFHMIN: # %bb.0: ; ZVFHMIN-NEXT: addi sp, sp, -16 ; ZVFHMIN-NEXT: .cfi_def_cfa_offset 16 ; ZVFHMIN-NEXT: csrr a1, vlenb ; ZVFHMIN-NEXT: slli a1, a1, 3 ; ZVFHMIN-NEXT: sub sp, sp, a1 ; 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: vmv1r.v v16, v0 ; ZVFHMIN-NEXT: csrr a2, vlenb ; ZVFHMIN-NEXT: slli a1, a2, 1 ; ZVFHMIN-NEXT: sub a3, a0, a1 ; ZVFHMIN-NEXT: sltu a4, a0, a3 ; ZVFHMIN-NEXT: addi a4, a4, -1 ; ZVFHMIN-NEXT: and a3, a4, a3 ; ZVFHMIN-NEXT: srli a2, a2, 2 ; ZVFHMIN-NEXT: vsetvli a4, zero, e8, mf2, ta, ma ; ZVFHMIN-NEXT: vslidedown.vx v17, v0, a2 ; ZVFHMIN-NEXT: vsetvli a2, zero, e16, m4, ta, ma ; ZVFHMIN-NEXT: addi a2, sp, 16 ; ZVFHMIN-NEXT: vs8r.v v8, (a2) # Unknown-size Folded Spill ; ZVFHMIN-NEXT: vfwcvt.f.f.v v24, v12 ; ZVFHMIN-NEXT: vsetvli zero, a3, e32, m8, ta, ma ; ZVFHMIN-NEXT: vmv1r.v v0, v17 ; ZVFHMIN-NEXT: vfabs.v v8, v24, v0.t ; ZVFHMIN-NEXT: lui a2, 307200 ; ZVFHMIN-NEXT: fmv.w.x fa5, a2 ; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m8, ta, mu ; ZVFHMIN-NEXT: vmflt.vf v17, v8, fa5, v0.t ; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m8, ta, ma ; ZVFHMIN-NEXT: vmv1r.v v0, v17 ; ZVFHMIN-NEXT: vfcvt.x.f.v v8, v24, v0.t ; ZVFHMIN-NEXT: vfcvt.f.x.v v8, v8, v0.t ; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m8, ta, mu ; ZVFHMIN-NEXT: vfsgnj.vv v24, v8, v24, v0.t ; ZVFHMIN-NEXT: vsetvli a2, zero, e16, m4, ta, ma ; ZVFHMIN-NEXT: vfncvt.f.f.w v20, v24 ; ZVFHMIN-NEXT: bltu a0, a1, .LBB10_2 ; ZVFHMIN-NEXT: # %bb.1: ; ZVFHMIN-NEXT: mv a0, a1 ; ZVFHMIN-NEXT: .LBB10_2: ; ZVFHMIN-NEXT: addi a1, sp, 16 ; ZVFHMIN-NEXT: vl8r.v v8, (a1) # Unknown-size Folded Reload ; ZVFHMIN-NEXT: vfwcvt.f.f.v v24, v8 ; ZVFHMIN-NEXT: vsetvli zero, a0, e32, m8, ta, ma ; ZVFHMIN-NEXT: vmv1r.v v0, v16 ; ZVFHMIN-NEXT: vfabs.v v8, v24, v0.t ; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m8, ta, mu ; ZVFHMIN-NEXT: vmflt.vf v16, v8, fa5, v0.t ; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m8, ta, ma ; ZVFHMIN-NEXT: vmv1r.v v0, v16 ; ZVFHMIN-NEXT: vfcvt.x.f.v v8, v24, v0.t ; ZVFHMIN-NEXT: vfcvt.f.x.v v8, v8, v0.t ; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m8, ta, mu ; ZVFHMIN-NEXT: vfsgnj.vv v24, v8, v24, v0.t ; ZVFHMIN-NEXT: vsetvli a0, zero, e16, m4, ta, ma ; ZVFHMIN-NEXT: vfncvt.f.f.w v16, v24 ; ZVFHMIN-NEXT: vmv8r.v v8, v16 ; ZVFHMIN-NEXT: csrr a0, vlenb ; ZVFHMIN-NEXT: slli a0, a0, 3 ; ZVFHMIN-NEXT: add sp, sp, a0 ; ZVFHMIN-NEXT: addi sp, sp, 16 ; ZVFHMIN-NEXT: ret %v = call @llvm.vp.rint.nxv32f16( %va, %m, i32 %evl) ret %v } define @vp_rint_nxv32f16_unmasked( %va, i32 zeroext %evl) { ; ZVFH-LABEL: vp_rint_nxv32f16_unmasked: ; ZVFH: # %bb.0: ; ZVFH-NEXT: lui a1, %hi(.LCPI11_0) ; ZVFH-NEXT: flh fa5, %lo(.LCPI11_0)(a1) ; ZVFH-NEXT: vsetvli zero, a0, e16, m8, ta, ma ; ZVFH-NEXT: vfabs.v v16, v8 ; ZVFH-NEXT: vmflt.vf v0, v16, fa5 ; ZVFH-NEXT: vfcvt.x.f.v v16, v8, v0.t ; ZVFH-NEXT: vfcvt.f.x.v v16, v16, v0.t ; ZVFH-NEXT: vsetvli zero, zero, e16, m8, ta, mu ; ZVFH-NEXT: vfsgnj.vv v8, v16, v8, v0.t ; ZVFH-NEXT: ret ; ; ZVFHMIN-LABEL: vp_rint_nxv32f16_unmasked: ; ZVFHMIN: # %bb.0: ; ZVFHMIN-NEXT: addi sp, sp, -16 ; ZVFHMIN-NEXT: .cfi_def_cfa_offset 16 ; ZVFHMIN-NEXT: csrr a1, vlenb ; ZVFHMIN-NEXT: slli a1, a1, 3 ; ZVFHMIN-NEXT: sub sp, sp, a1 ; 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: vsetvli a1, zero, e8, m4, ta, ma ; ZVFHMIN-NEXT: vmset.m v16 ; ZVFHMIN-NEXT: csrr a2, vlenb ; ZVFHMIN-NEXT: slli a1, a2, 1 ; ZVFHMIN-NEXT: sub a3, a0, a1 ; ZVFHMIN-NEXT: sltu a4, a0, a3 ; ZVFHMIN-NEXT: addi a4, a4, -1 ; ZVFHMIN-NEXT: and a3, a4, a3 ; ZVFHMIN-NEXT: srli a2, a2, 2 ; ZVFHMIN-NEXT: vsetvli a4, zero, e8, mf2, ta, ma ; ZVFHMIN-NEXT: vslidedown.vx v16, v16, a2 ; ZVFHMIN-NEXT: vsetvli a2, zero, e16, m4, ta, ma ; ZVFHMIN-NEXT: addi a2, sp, 16 ; ZVFHMIN-NEXT: vs8r.v v8, (a2) # Unknown-size Folded Spill ; ZVFHMIN-NEXT: vfwcvt.f.f.v v24, v12 ; ZVFHMIN-NEXT: vsetvli zero, a3, e32, m8, ta, ma ; ZVFHMIN-NEXT: vmv1r.v v0, v16 ; ZVFHMIN-NEXT: vfabs.v v8, v24, v0.t ; ZVFHMIN-NEXT: lui a2, 307200 ; ZVFHMIN-NEXT: fmv.w.x fa5, a2 ; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m8, ta, mu ; ZVFHMIN-NEXT: vmflt.vf v16, v8, fa5, v0.t ; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m8, ta, ma ; ZVFHMIN-NEXT: vmv1r.v v0, v16 ; ZVFHMIN-NEXT: vfcvt.x.f.v v8, v24, v0.t ; ZVFHMIN-NEXT: vfcvt.f.x.v v8, v8, v0.t ; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m8, ta, mu ; ZVFHMIN-NEXT: vfsgnj.vv v24, v8, v24, v0.t ; ZVFHMIN-NEXT: vsetvli a2, zero, e16, m4, ta, ma ; ZVFHMIN-NEXT: vfncvt.f.f.w v12, v24 ; ZVFHMIN-NEXT: bltu a0, a1, .LBB11_2 ; ZVFHMIN-NEXT: # %bb.1: ; ZVFHMIN-NEXT: mv a0, a1 ; ZVFHMIN-NEXT: .LBB11_2: ; ZVFHMIN-NEXT: addi a1, sp, 16 ; ZVFHMIN-NEXT: vl8r.v v24, (a1) # Unknown-size Folded Reload ; ZVFHMIN-NEXT: vfwcvt.f.f.v v16, v24 ; ZVFHMIN-NEXT: vsetvli zero, a0, e32, m8, ta, ma ; ZVFHMIN-NEXT: vfabs.v v24, v16 ; ZVFHMIN-NEXT: vmflt.vf v0, v24, fa5 ; ZVFHMIN-NEXT: vfcvt.x.f.v v24, v16, v0.t ; ZVFHMIN-NEXT: vfcvt.f.x.v v24, v24, v0.t ; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m8, ta, mu ; ZVFHMIN-NEXT: vfsgnj.vv v16, v24, v16, v0.t ; ZVFHMIN-NEXT: vsetvli a0, zero, e16, m4, ta, ma ; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v16 ; ZVFHMIN-NEXT: csrr a0, vlenb ; ZVFHMIN-NEXT: slli a0, a0, 3 ; ZVFHMIN-NEXT: add sp, sp, a0 ; ZVFHMIN-NEXT: addi sp, sp, 16 ; ZVFHMIN-NEXT: ret %head = insertelement poison, i1 true, i32 0 %m = shufflevector %head, poison, zeroinitializer %v = call @llvm.vp.rint.nxv32f16( %va, %m, i32 %evl) ret %v } declare @llvm.vp.rint.nxv1f32(, , i32) define @vp_rint_nxv1f32( %va, %m, i32 zeroext %evl) { ; CHECK-LABEL: vp_rint_nxv1f32: ; CHECK: # %bb.0: ; CHECK-NEXT: vsetvli zero, a0, e32, mf2, ta, ma ; CHECK-NEXT: vfabs.v v9, v8, v0.t ; CHECK-NEXT: lui a0, 307200 ; CHECK-NEXT: fmv.w.x fa5, a0 ; CHECK-NEXT: vsetvli zero, zero, e32, mf2, ta, mu ; CHECK-NEXT: vmflt.vf v0, v9, fa5, v0.t ; CHECK-NEXT: vsetvli zero, zero, e32, mf2, ta, ma ; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t ; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t ; CHECK-NEXT: vsetvli zero, zero, e32, mf2, ta, mu ; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t ; CHECK-NEXT: ret %v = call @llvm.vp.rint.nxv1f32( %va, %m, i32 %evl) ret %v } define @vp_rint_nxv1f32_unmasked( %va, i32 zeroext %evl) { ; CHECK-LABEL: vp_rint_nxv1f32_unmasked: ; CHECK: # %bb.0: ; CHECK-NEXT: vsetvli zero, a0, e32, mf2, ta, ma ; CHECK-NEXT: vfabs.v v9, v8 ; CHECK-NEXT: lui a0, 307200 ; CHECK-NEXT: fmv.w.x fa5, a0 ; CHECK-NEXT: vmflt.vf v0, v9, fa5 ; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t ; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t ; CHECK-NEXT: vsetvli zero, zero, e32, mf2, ta, mu ; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t ; CHECK-NEXT: ret %head = insertelement poison, i1 true, i32 0 %m = shufflevector %head, poison, zeroinitializer %v = call @llvm.vp.rint.nxv1f32( %va, %m, i32 %evl) ret %v } declare @llvm.vp.rint.nxv2f32(, , i32) define @vp_rint_nxv2f32( %va, %m, i32 zeroext %evl) { ; CHECK-LABEL: vp_rint_nxv2f32: ; CHECK: # %bb.0: ; CHECK-NEXT: vsetvli zero, a0, e32, m1, ta, ma ; CHECK-NEXT: vfabs.v v9, v8, v0.t ; CHECK-NEXT: lui a0, 307200 ; CHECK-NEXT: fmv.w.x fa5, a0 ; CHECK-NEXT: vsetvli zero, zero, e32, m1, ta, mu ; CHECK-NEXT: vmflt.vf v0, v9, fa5, v0.t ; CHECK-NEXT: vsetvli zero, zero, e32, m1, ta, ma ; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t ; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t ; CHECK-NEXT: vsetvli zero, zero, e32, m1, ta, mu ; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t ; CHECK-NEXT: ret %v = call @llvm.vp.rint.nxv2f32( %va, %m, i32 %evl) ret %v } define @vp_rint_nxv2f32_unmasked( %va, i32 zeroext %evl) { ; CHECK-LABEL: vp_rint_nxv2f32_unmasked: ; CHECK: # %bb.0: ; CHECK-NEXT: vsetvli zero, a0, e32, m1, ta, ma ; CHECK-NEXT: vfabs.v v9, v8 ; CHECK-NEXT: lui a0, 307200 ; CHECK-NEXT: fmv.w.x fa5, a0 ; CHECK-NEXT: vmflt.vf v0, v9, fa5 ; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t ; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t ; CHECK-NEXT: vsetvli zero, zero, e32, m1, ta, mu ; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t ; CHECK-NEXT: ret %head = insertelement poison, i1 true, i32 0 %m = shufflevector %head, poison, zeroinitializer %v = call @llvm.vp.rint.nxv2f32( %va, %m, i32 %evl) ret %v } declare @llvm.vp.rint.nxv4f32(, , i32) define @vp_rint_nxv4f32( %va, %m, i32 zeroext %evl) { ; CHECK-LABEL: vp_rint_nxv4f32: ; CHECK: # %bb.0: ; CHECK-NEXT: vmv1r.v v10, v0 ; CHECK-NEXT: vsetvli zero, a0, e32, m2, ta, ma ; CHECK-NEXT: vfabs.v v12, v8, v0.t ; CHECK-NEXT: lui a0, 307200 ; CHECK-NEXT: fmv.w.x fa5, a0 ; CHECK-NEXT: vsetvli zero, zero, e32, m2, ta, mu ; CHECK-NEXT: vmflt.vf v10, v12, fa5, v0.t ; CHECK-NEXT: vsetvli zero, zero, e32, m2, ta, ma ; CHECK-NEXT: vmv1r.v v0, v10 ; CHECK-NEXT: vfcvt.x.f.v v12, v8, v0.t ; CHECK-NEXT: vfcvt.f.x.v v12, v12, v0.t ; CHECK-NEXT: vsetvli zero, zero, e32, m2, ta, mu ; CHECK-NEXT: vfsgnj.vv v8, v12, v8, v0.t ; CHECK-NEXT: ret %v = call @llvm.vp.rint.nxv4f32( %va, %m, i32 %evl) ret %v } define @vp_rint_nxv4f32_unmasked( %va, i32 zeroext %evl) { ; CHECK-LABEL: vp_rint_nxv4f32_unmasked: ; CHECK: # %bb.0: ; CHECK-NEXT: vsetvli zero, a0, e32, m2, ta, ma ; CHECK-NEXT: vfabs.v v10, v8 ; CHECK-NEXT: lui a0, 307200 ; CHECK-NEXT: fmv.w.x fa5, a0 ; CHECK-NEXT: vmflt.vf v0, v10, fa5 ; CHECK-NEXT: vfcvt.x.f.v v10, v8, v0.t ; CHECK-NEXT: vfcvt.f.x.v v10, v10, v0.t ; CHECK-NEXT: vsetvli zero, zero, e32, m2, ta, mu ; CHECK-NEXT: vfsgnj.vv v8, v10, v8, v0.t ; CHECK-NEXT: ret %head = insertelement poison, i1 true, i32 0 %m = shufflevector %head, poison, zeroinitializer %v = call @llvm.vp.rint.nxv4f32( %va, %m, i32 %evl) ret %v } declare @llvm.vp.rint.nxv8f32(, , i32) define @vp_rint_nxv8f32( %va, %m, i32 zeroext %evl) { ; CHECK-LABEL: vp_rint_nxv8f32: ; CHECK: # %bb.0: ; CHECK-NEXT: vmv1r.v v12, v0 ; CHECK-NEXT: vsetvli zero, a0, e32, m4, ta, ma ; CHECK-NEXT: vfabs.v v16, v8, v0.t ; CHECK-NEXT: lui a0, 307200 ; CHECK-NEXT: fmv.w.x fa5, a0 ; CHECK-NEXT: vsetvli zero, zero, e32, m4, ta, mu ; CHECK-NEXT: vmflt.vf v12, v16, fa5, v0.t ; CHECK-NEXT: vsetvli zero, zero, e32, m4, ta, ma ; CHECK-NEXT: vmv1r.v v0, v12 ; CHECK-NEXT: vfcvt.x.f.v v16, v8, v0.t ; CHECK-NEXT: vfcvt.f.x.v v16, v16, v0.t ; CHECK-NEXT: vsetvli zero, zero, e32, m4, ta, mu ; CHECK-NEXT: vfsgnj.vv v8, v16, v8, v0.t ; CHECK-NEXT: ret %v = call @llvm.vp.rint.nxv8f32( %va, %m, i32 %evl) ret %v } define @vp_rint_nxv8f32_unmasked( %va, i32 zeroext %evl) { ; CHECK-LABEL: vp_rint_nxv8f32_unmasked: ; CHECK: # %bb.0: ; CHECK-NEXT: vsetvli zero, a0, e32, m4, ta, ma ; CHECK-NEXT: vfabs.v v12, v8 ; CHECK-NEXT: lui a0, 307200 ; CHECK-NEXT: fmv.w.x fa5, a0 ; CHECK-NEXT: vmflt.vf v0, v12, fa5 ; CHECK-NEXT: vfcvt.x.f.v v12, v8, v0.t ; CHECK-NEXT: vfcvt.f.x.v v12, v12, v0.t ; CHECK-NEXT: vsetvli zero, zero, e32, m4, ta, mu ; CHECK-NEXT: vfsgnj.vv v8, v12, v8, v0.t ; CHECK-NEXT: ret %head = insertelement poison, i1 true, i32 0 %m = shufflevector %head, poison, zeroinitializer %v = call @llvm.vp.rint.nxv8f32( %va, %m, i32 %evl) ret %v } declare @llvm.vp.rint.nxv16f32(, , i32) define @vp_rint_nxv16f32( %va, %m, i32 zeroext %evl) { ; CHECK-LABEL: vp_rint_nxv16f32: ; CHECK: # %bb.0: ; CHECK-NEXT: vmv1r.v v16, v0 ; CHECK-NEXT: vsetvli zero, a0, e32, m8, ta, ma ; CHECK-NEXT: vfabs.v v24, v8, v0.t ; CHECK-NEXT: lui a0, 307200 ; CHECK-NEXT: fmv.w.x fa5, a0 ; CHECK-NEXT: vsetvli zero, zero, e32, m8, ta, mu ; CHECK-NEXT: vmflt.vf v16, v24, fa5, v0.t ; CHECK-NEXT: vsetvli zero, zero, e32, m8, ta, ma ; CHECK-NEXT: vmv1r.v v0, v16 ; CHECK-NEXT: vfcvt.x.f.v v24, v8, v0.t ; CHECK-NEXT: vfcvt.f.x.v v24, v24, v0.t ; CHECK-NEXT: vsetvli zero, zero, e32, m8, ta, mu ; CHECK-NEXT: vfsgnj.vv v8, v24, v8, v0.t ; CHECK-NEXT: ret %v = call @llvm.vp.rint.nxv16f32( %va, %m, i32 %evl) ret %v } define @vp_rint_nxv16f32_unmasked( %va, i32 zeroext %evl) { ; CHECK-LABEL: vp_rint_nxv16f32_unmasked: ; CHECK: # %bb.0: ; CHECK-NEXT: vsetvli zero, a0, e32, m8, ta, ma ; CHECK-NEXT: vfabs.v v16, v8 ; CHECK-NEXT: lui a0, 307200 ; CHECK-NEXT: fmv.w.x fa5, a0 ; CHECK-NEXT: vmflt.vf v0, v16, fa5 ; CHECK-NEXT: vfcvt.x.f.v v16, v8, v0.t ; CHECK-NEXT: vfcvt.f.x.v v16, v16, v0.t ; CHECK-NEXT: vsetvli zero, zero, e32, m8, ta, mu ; CHECK-NEXT: vfsgnj.vv v8, v16, v8, v0.t ; CHECK-NEXT: ret %head = insertelement poison, i1 true, i32 0 %m = shufflevector %head, poison, zeroinitializer %v = call @llvm.vp.rint.nxv16f32( %va, %m, i32 %evl) ret %v } declare @llvm.vp.rint.nxv1f64(, , i32) define @vp_rint_nxv1f64( %va, %m, i32 zeroext %evl) { ; CHECK-LABEL: vp_rint_nxv1f64: ; CHECK: # %bb.0: ; CHECK-NEXT: lui a1, %hi(.LCPI22_0) ; CHECK-NEXT: fld fa5, %lo(.LCPI22_0)(a1) ; CHECK-NEXT: vsetvli zero, a0, e64, m1, ta, ma ; CHECK-NEXT: vfabs.v v9, v8, v0.t ; CHECK-NEXT: vsetvli zero, zero, e64, m1, ta, mu ; CHECK-NEXT: vmflt.vf v0, v9, fa5, v0.t ; CHECK-NEXT: vsetvli zero, zero, e64, m1, ta, ma ; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t ; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t ; CHECK-NEXT: vsetvli zero, zero, e64, m1, ta, mu ; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t ; CHECK-NEXT: ret %v = call @llvm.vp.rint.nxv1f64( %va, %m, i32 %evl) ret %v } define @vp_rint_nxv1f64_unmasked( %va, i32 zeroext %evl) { ; CHECK-LABEL: vp_rint_nxv1f64_unmasked: ; CHECK: # %bb.0: ; CHECK-NEXT: lui a1, %hi(.LCPI23_0) ; CHECK-NEXT: fld fa5, %lo(.LCPI23_0)(a1) ; CHECK-NEXT: vsetvli zero, a0, e64, m1, ta, ma ; CHECK-NEXT: vfabs.v v9, v8 ; CHECK-NEXT: vmflt.vf v0, v9, fa5 ; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t ; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t ; CHECK-NEXT: vsetvli zero, zero, e64, m1, ta, mu ; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t ; CHECK-NEXT: ret %head = insertelement poison, i1 true, i32 0 %m = shufflevector %head, poison, zeroinitializer %v = call @llvm.vp.rint.nxv1f64( %va, %m, i32 %evl) ret %v } declare @llvm.vp.rint.nxv2f64(, , i32) define @vp_rint_nxv2f64( %va, %m, i32 zeroext %evl) { ; CHECK-LABEL: vp_rint_nxv2f64: ; CHECK: # %bb.0: ; CHECK-NEXT: vmv1r.v v10, v0 ; CHECK-NEXT: lui a1, %hi(.LCPI24_0) ; CHECK-NEXT: fld fa5, %lo(.LCPI24_0)(a1) ; CHECK-NEXT: vsetvli zero, a0, e64, m2, ta, ma ; CHECK-NEXT: vfabs.v v12, v8, v0.t ; CHECK-NEXT: vsetvli zero, zero, e64, m2, ta, mu ; CHECK-NEXT: vmflt.vf v10, v12, fa5, v0.t ; CHECK-NEXT: vsetvli zero, zero, e64, m2, ta, ma ; CHECK-NEXT: vmv1r.v v0, v10 ; CHECK-NEXT: vfcvt.x.f.v v12, v8, v0.t ; CHECK-NEXT: vfcvt.f.x.v v12, v12, v0.t ; CHECK-NEXT: vsetvli zero, zero, e64, m2, ta, mu ; CHECK-NEXT: vfsgnj.vv v8, v12, v8, v0.t ; CHECK-NEXT: ret %v = call @llvm.vp.rint.nxv2f64( %va, %m, i32 %evl) ret %v } define @vp_rint_nxv2f64_unmasked( %va, i32 zeroext %evl) { ; CHECK-LABEL: vp_rint_nxv2f64_unmasked: ; CHECK: # %bb.0: ; CHECK-NEXT: lui a1, %hi(.LCPI25_0) ; CHECK-NEXT: fld fa5, %lo(.LCPI25_0)(a1) ; CHECK-NEXT: vsetvli zero, a0, e64, m2, ta, ma ; CHECK-NEXT: vfabs.v v10, v8 ; CHECK-NEXT: vmflt.vf v0, v10, fa5 ; CHECK-NEXT: vfcvt.x.f.v v10, v8, v0.t ; CHECK-NEXT: vfcvt.f.x.v v10, v10, v0.t ; CHECK-NEXT: vsetvli zero, zero, e64, m2, ta, mu ; CHECK-NEXT: vfsgnj.vv v8, v10, v8, v0.t ; CHECK-NEXT: ret %head = insertelement poison, i1 true, i32 0 %m = shufflevector %head, poison, zeroinitializer %v = call @llvm.vp.rint.nxv2f64( %va, %m, i32 %evl) ret %v } declare @llvm.vp.rint.nxv4f64(, , i32) define @vp_rint_nxv4f64( %va, %m, i32 zeroext %evl) { ; CHECK-LABEL: vp_rint_nxv4f64: ; CHECK: # %bb.0: ; CHECK-NEXT: vmv1r.v v12, v0 ; CHECK-NEXT: lui a1, %hi(.LCPI26_0) ; CHECK-NEXT: fld fa5, %lo(.LCPI26_0)(a1) ; CHECK-NEXT: vsetvli zero, a0, e64, m4, ta, ma ; CHECK-NEXT: vfabs.v v16, v8, v0.t ; CHECK-NEXT: vsetvli zero, zero, e64, m4, ta, mu ; CHECK-NEXT: vmflt.vf v12, v16, fa5, v0.t ; CHECK-NEXT: vsetvli zero, zero, e64, m4, ta, ma ; CHECK-NEXT: vmv1r.v v0, v12 ; CHECK-NEXT: vfcvt.x.f.v v16, v8, v0.t ; CHECK-NEXT: vfcvt.f.x.v v16, v16, v0.t ; CHECK-NEXT: vsetvli zero, zero, e64, m4, ta, mu ; CHECK-NEXT: vfsgnj.vv v8, v16, v8, v0.t ; CHECK-NEXT: ret %v = call @llvm.vp.rint.nxv4f64( %va, %m, i32 %evl) ret %v } define @vp_rint_nxv4f64_unmasked( %va, i32 zeroext %evl) { ; CHECK-LABEL: vp_rint_nxv4f64_unmasked: ; CHECK: # %bb.0: ; CHECK-NEXT: lui a1, %hi(.LCPI27_0) ; CHECK-NEXT: fld fa5, %lo(.LCPI27_0)(a1) ; CHECK-NEXT: vsetvli zero, a0, e64, m4, ta, ma ; CHECK-NEXT: vfabs.v v12, v8 ; CHECK-NEXT: vmflt.vf v0, v12, fa5 ; CHECK-NEXT: vfcvt.x.f.v v12, v8, v0.t ; CHECK-NEXT: vfcvt.f.x.v v12, v12, v0.t ; CHECK-NEXT: vsetvli zero, zero, e64, m4, ta, mu ; CHECK-NEXT: vfsgnj.vv v8, v12, v8, v0.t ; CHECK-NEXT: ret %head = insertelement poison, i1 true, i32 0 %m = shufflevector %head, poison, zeroinitializer %v = call @llvm.vp.rint.nxv4f64( %va, %m, i32 %evl) ret %v } declare @llvm.vp.rint.nxv7f64(, , i32) define @vp_rint_nxv7f64( %va, %m, i32 zeroext %evl) { ; CHECK-LABEL: vp_rint_nxv7f64: ; CHECK: # %bb.0: ; CHECK-NEXT: vmv1r.v v16, v0 ; CHECK-NEXT: lui a1, %hi(.LCPI28_0) ; CHECK-NEXT: fld fa5, %lo(.LCPI28_0)(a1) ; CHECK-NEXT: vsetvli zero, a0, e64, m8, ta, ma ; CHECK-NEXT: vfabs.v v24, v8, v0.t ; CHECK-NEXT: vsetvli zero, zero, e64, m8, ta, mu ; CHECK-NEXT: vmflt.vf v16, v24, fa5, v0.t ; CHECK-NEXT: vsetvli zero, zero, e64, m8, ta, ma ; CHECK-NEXT: vmv1r.v v0, v16 ; CHECK-NEXT: vfcvt.x.f.v v24, v8, v0.t ; CHECK-NEXT: vfcvt.f.x.v v24, v24, v0.t ; CHECK-NEXT: vsetvli zero, zero, e64, m8, ta, mu ; CHECK-NEXT: vfsgnj.vv v8, v24, v8, v0.t ; CHECK-NEXT: ret %v = call @llvm.vp.rint.nxv7f64( %va, %m, i32 %evl) ret %v } define @vp_rint_nxv7f64_unmasked( %va, i32 zeroext %evl) { ; CHECK-LABEL: vp_rint_nxv7f64_unmasked: ; CHECK: # %bb.0: ; CHECK-NEXT: lui a1, %hi(.LCPI29_0) ; CHECK-NEXT: fld fa5, %lo(.LCPI29_0)(a1) ; CHECK-NEXT: vsetvli zero, a0, e64, m8, ta, ma ; CHECK-NEXT: vfabs.v v16, v8 ; CHECK-NEXT: vmflt.vf v0, v16, fa5 ; CHECK-NEXT: vfcvt.x.f.v v16, v8, v0.t ; CHECK-NEXT: vfcvt.f.x.v v16, v16, v0.t ; CHECK-NEXT: vsetvli zero, zero, e64, m8, ta, mu ; CHECK-NEXT: vfsgnj.vv v8, v16, v8, v0.t ; CHECK-NEXT: ret %head = insertelement poison, i1 true, i32 0 %m = shufflevector %head, poison, zeroinitializer %v = call @llvm.vp.rint.nxv7f64( %va, %m, i32 %evl) ret %v } declare @llvm.vp.rint.nxv8f64(, , i32) define @vp_rint_nxv8f64( %va, %m, i32 zeroext %evl) { ; CHECK-LABEL: vp_rint_nxv8f64: ; CHECK: # %bb.0: ; CHECK-NEXT: vmv1r.v v16, v0 ; CHECK-NEXT: lui a1, %hi(.LCPI30_0) ; CHECK-NEXT: fld fa5, %lo(.LCPI30_0)(a1) ; CHECK-NEXT: vsetvli zero, a0, e64, m8, ta, ma ; CHECK-NEXT: vfabs.v v24, v8, v0.t ; CHECK-NEXT: vsetvli zero, zero, e64, m8, ta, mu ; CHECK-NEXT: vmflt.vf v16, v24, fa5, v0.t ; CHECK-NEXT: vsetvli zero, zero, e64, m8, ta, ma ; CHECK-NEXT: vmv1r.v v0, v16 ; CHECK-NEXT: vfcvt.x.f.v v24, v8, v0.t ; CHECK-NEXT: vfcvt.f.x.v v24, v24, v0.t ; CHECK-NEXT: vsetvli zero, zero, e64, m8, ta, mu ; CHECK-NEXT: vfsgnj.vv v8, v24, v8, v0.t ; CHECK-NEXT: ret %v = call @llvm.vp.rint.nxv8f64( %va, %m, i32 %evl) ret %v } define @vp_rint_nxv8f64_unmasked( %va, i32 zeroext %evl) { ; CHECK-LABEL: vp_rint_nxv8f64_unmasked: ; CHECK: # %bb.0: ; CHECK-NEXT: lui a1, %hi(.LCPI31_0) ; CHECK-NEXT: fld fa5, %lo(.LCPI31_0)(a1) ; CHECK-NEXT: vsetvli zero, a0, e64, m8, ta, ma ; CHECK-NEXT: vfabs.v v16, v8 ; CHECK-NEXT: vmflt.vf v0, v16, fa5 ; CHECK-NEXT: vfcvt.x.f.v v16, v8, v0.t ; CHECK-NEXT: vfcvt.f.x.v v16, v16, v0.t ; CHECK-NEXT: vsetvli zero, zero, e64, m8, ta, mu ; CHECK-NEXT: vfsgnj.vv v8, v16, v8, v0.t ; CHECK-NEXT: ret %head = insertelement poison, i1 true, i32 0 %m = shufflevector %head, poison, zeroinitializer %v = call @llvm.vp.rint.nxv8f64( %va, %m, i32 %evl) ret %v } ; Test splitting. declare @llvm.vp.rint.nxv16f64(, , i32) define @vp_rint_nxv16f64( %va, %m, i32 zeroext %evl) { ; CHECK-LABEL: vp_rint_nxv16f64: ; CHECK: # %bb.0: ; CHECK-NEXT: addi sp, sp, -16 ; CHECK-NEXT: .cfi_def_cfa_offset 16 ; CHECK-NEXT: csrr a1, vlenb ; CHECK-NEXT: slli a1, a1, 4 ; CHECK-NEXT: sub sp, sp, a1 ; 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: vmv1r.v v24, v0 ; CHECK-NEXT: addi a1, sp, 16 ; CHECK-NEXT: vs8r.v v8, (a1) # Unknown-size Folded Spill ; CHECK-NEXT: csrr a1, vlenb ; CHECK-NEXT: srli a2, a1, 3 ; CHECK-NEXT: vsetvli a3, zero, e8, mf4, ta, ma ; CHECK-NEXT: vslidedown.vx v25, v0, a2 ; CHECK-NEXT: sub a2, a0, a1 ; CHECK-NEXT: sltu a3, a0, a2 ; CHECK-NEXT: addi a3, a3, -1 ; CHECK-NEXT: and a2, a3, a2 ; CHECK-NEXT: lui a3, %hi(.LCPI32_0) ; CHECK-NEXT: fld fa5, %lo(.LCPI32_0)(a3) ; CHECK-NEXT: vsetvli zero, a2, e64, m8, ta, ma ; CHECK-NEXT: vmv1r.v v0, v25 ; CHECK-NEXT: vfabs.v v8, v16, v0.t ; CHECK-NEXT: vsetvli zero, zero, e64, m8, ta, mu ; CHECK-NEXT: vmflt.vf v25, v8, fa5, v0.t ; CHECK-NEXT: vsetvli zero, zero, e64, m8, ta, ma ; CHECK-NEXT: vmv1r.v v0, v25 ; CHECK-NEXT: vfcvt.x.f.v v8, v16, v0.t ; CHECK-NEXT: vfcvt.f.x.v v8, v8, v0.t ; CHECK-NEXT: vsetvli zero, zero, e64, m8, ta, mu ; CHECK-NEXT: vfsgnj.vv v16, v8, v16, v0.t ; CHECK-NEXT: csrr a2, vlenb ; CHECK-NEXT: slli a2, a2, 3 ; CHECK-NEXT: add a2, sp, a2 ; CHECK-NEXT: addi a2, a2, 16 ; CHECK-NEXT: vs8r.v v16, (a2) # Unknown-size Folded Spill ; CHECK-NEXT: bltu a0, a1, .LBB32_2 ; CHECK-NEXT: # %bb.1: ; CHECK-NEXT: mv a0, a1 ; CHECK-NEXT: .LBB32_2: ; CHECK-NEXT: vsetvli zero, a0, e64, m8, ta, ma ; CHECK-NEXT: vmv1r.v v0, v24 ; CHECK-NEXT: addi a0, sp, 16 ; CHECK-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload ; CHECK-NEXT: vfabs.v v16, v8, v0.t ; CHECK-NEXT: vsetvli zero, zero, e64, m8, ta, mu ; CHECK-NEXT: vmflt.vf v24, v16, fa5, v0.t ; CHECK-NEXT: vsetvli zero, zero, e64, m8, ta, ma ; CHECK-NEXT: vmv1r.v v0, v24 ; CHECK-NEXT: vfcvt.x.f.v v16, v8, v0.t ; CHECK-NEXT: vfcvt.f.x.v v16, v16, v0.t ; CHECK-NEXT: vsetvli zero, zero, e64, m8, ta, mu ; CHECK-NEXT: vfsgnj.vv v8, v16, v8, v0.t ; 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 v16, (a0) # Unknown-size Folded Reload ; CHECK-NEXT: csrr a0, vlenb ; CHECK-NEXT: slli a0, a0, 4 ; CHECK-NEXT: add sp, sp, a0 ; CHECK-NEXT: addi sp, sp, 16 ; CHECK-NEXT: ret %v = call @llvm.vp.rint.nxv16f64( %va, %m, i32 %evl) ret %v } define @vp_rint_nxv16f64_unmasked( %va, i32 zeroext %evl) { ; CHECK-LABEL: vp_rint_nxv16f64_unmasked: ; CHECK: # %bb.0: ; CHECK-NEXT: csrr a1, vlenb ; CHECK-NEXT: sub a2, a0, a1 ; CHECK-NEXT: lui a3, %hi(.LCPI33_0) ; CHECK-NEXT: fld fa5, %lo(.LCPI33_0)(a3) ; CHECK-NEXT: sltu a3, a0, a2 ; CHECK-NEXT: addi a3, a3, -1 ; CHECK-NEXT: and a2, a3, a2 ; CHECK-NEXT: vsetvli zero, a2, e64, m8, ta, ma ; CHECK-NEXT: vfabs.v v24, v16 ; CHECK-NEXT: vmflt.vf v0, v24, fa5 ; CHECK-NEXT: vfcvt.x.f.v v24, v16, v0.t ; CHECK-NEXT: vfcvt.f.x.v v24, v24, v0.t ; CHECK-NEXT: vsetvli zero, zero, e64, m8, ta, mu ; CHECK-NEXT: vfsgnj.vv v16, v24, v16, v0.t ; CHECK-NEXT: bltu a0, a1, .LBB33_2 ; CHECK-NEXT: # %bb.1: ; CHECK-NEXT: mv a0, a1 ; CHECK-NEXT: .LBB33_2: ; CHECK-NEXT: vsetvli zero, a0, e64, m8, ta, ma ; CHECK-NEXT: vfabs.v v24, v8 ; CHECK-NEXT: vmflt.vf v0, v24, fa5 ; CHECK-NEXT: vfcvt.x.f.v v24, v8, v0.t ; CHECK-NEXT: vfcvt.f.x.v v24, v24, v0.t ; CHECK-NEXT: vsetvli zero, zero, e64, m8, ta, mu ; CHECK-NEXT: vfsgnj.vv v8, v24, v8, v0.t ; CHECK-NEXT: ret %head = insertelement poison, i1 true, i32 0 %m = shufflevector %head, poison, zeroinitializer %v = call @llvm.vp.rint.nxv16f64( %va, %m, i32 %evl) ret %v }