| ; 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 <vscale x 1 x half> @llvm.vp.copysign.nxv1f16(<vscale x 1 x half>, <vscale x 1 x half>, <vscale x 1 x i1>, i32) |
| |
| define <vscale x 1 x half> @vfsgnj_vv_nxv1f16(<vscale x 1 x half> %va, <vscale x 1 x half> %vb, <vscale x 1 x i1> %m, i32 zeroext %evl) { |
| ; ZVFH-LABEL: vfsgnj_vv_nxv1f16: |
| ; ZVFH: # %bb.0: |
| ; ZVFH-NEXT: vsetvli zero, a0, e16, mf4, ta, ma |
| ; ZVFH-NEXT: vfsgnj.vv v8, v8, v9, v0.t |
| ; ZVFH-NEXT: ret |
| ; |
| ; ZVFHMIN-LABEL: vfsgnj_vv_nxv1f16: |
| ; ZVFHMIN: # %bb.0: |
| ; ZVFHMIN-NEXT: vsetvli a1, zero, e16, mf4, ta, ma |
| ; ZVFHMIN-NEXT: vfwcvt.f.f.v v10, v9 |
| ; ZVFHMIN-NEXT: vfwcvt.f.f.v v9, v8 |
| ; ZVFHMIN-NEXT: vsetvli zero, a0, e32, mf2, ta, ma |
| ; ZVFHMIN-NEXT: vfsgnj.vv v9, v9, v10, v0.t |
| ; ZVFHMIN-NEXT: vsetvli a0, zero, e16, mf4, ta, ma |
| ; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v9 |
| ; ZVFHMIN-NEXT: ret |
| %v = call <vscale x 1 x half> @llvm.vp.copysign.nxv1f16(<vscale x 1 x half> %va, <vscale x 1 x half> %vb, <vscale x 1 x i1> %m, i32 %evl) |
| ret <vscale x 1 x half> %v |
| } |
| |
| define <vscale x 1 x half> @vfsgnj_vv_nxv1f16_unmasked(<vscale x 1 x half> %va, <vscale x 1 x half> %vb, i32 zeroext %evl) { |
| ; ZVFH-LABEL: vfsgnj_vv_nxv1f16_unmasked: |
| ; ZVFH: # %bb.0: |
| ; ZVFH-NEXT: vsetvli zero, a0, e16, mf4, ta, ma |
| ; ZVFH-NEXT: vfsgnj.vv v8, v8, v9 |
| ; ZVFH-NEXT: ret |
| ; |
| ; ZVFHMIN-LABEL: vfsgnj_vv_nxv1f16_unmasked: |
| ; ZVFHMIN: # %bb.0: |
| ; ZVFHMIN-NEXT: vsetvli a1, zero, e16, mf4, ta, ma |
| ; ZVFHMIN-NEXT: vfwcvt.f.f.v v10, v9 |
| ; ZVFHMIN-NEXT: vfwcvt.f.f.v v9, v8 |
| ; ZVFHMIN-NEXT: vsetvli zero, a0, e32, mf2, ta, ma |
| ; ZVFHMIN-NEXT: vfsgnj.vv v9, v9, v10 |
| ; ZVFHMIN-NEXT: vsetvli a0, zero, e16, mf4, ta, ma |
| ; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v9 |
| ; ZVFHMIN-NEXT: ret |
| %v = call <vscale x 1 x half> @llvm.vp.copysign.nxv1f16(<vscale x 1 x half> %va, <vscale x 1 x half> %vb, <vscale x 1 x i1> splat (i1 true), i32 %evl) |
| ret <vscale x 1 x half> %v |
| } |
| |
| declare <vscale x 2 x half> @llvm.vp.copysign.nxv2f16(<vscale x 2 x half>, <vscale x 2 x half>, <vscale x 2 x i1>, i32) |
| |
| define <vscale x 2 x half> @vfsgnj_vv_nxv2f16(<vscale x 2 x half> %va, <vscale x 2 x half> %vb, <vscale x 2 x i1> %m, i32 zeroext %evl) { |
| ; ZVFH-LABEL: vfsgnj_vv_nxv2f16: |
| ; ZVFH: # %bb.0: |
| ; ZVFH-NEXT: vsetvli zero, a0, e16, mf2, ta, ma |
| ; ZVFH-NEXT: vfsgnj.vv v8, v8, v9, v0.t |
| ; ZVFH-NEXT: ret |
| ; |
| ; ZVFHMIN-LABEL: vfsgnj_vv_nxv2f16: |
| ; ZVFHMIN: # %bb.0: |
| ; ZVFHMIN-NEXT: vsetvli a1, zero, e16, mf2, ta, ma |
| ; ZVFHMIN-NEXT: vfwcvt.f.f.v v10, v9 |
| ; ZVFHMIN-NEXT: vfwcvt.f.f.v v9, v8 |
| ; ZVFHMIN-NEXT: vsetvli zero, a0, e32, m1, ta, ma |
| ; ZVFHMIN-NEXT: vfsgnj.vv v9, v9, v10, v0.t |
| ; ZVFHMIN-NEXT: vsetvli a0, zero, e16, mf2, ta, ma |
| ; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v9 |
| ; ZVFHMIN-NEXT: ret |
| %v = call <vscale x 2 x half> @llvm.vp.copysign.nxv2f16(<vscale x 2 x half> %va, <vscale x 2 x half> %vb, <vscale x 2 x i1> %m, i32 %evl) |
| ret <vscale x 2 x half> %v |
| } |
| |
| define <vscale x 2 x half> @vfsgnj_vv_nxv2f16_unmasked(<vscale x 2 x half> %va, <vscale x 2 x half> %vb, i32 zeroext %evl) { |
| ; ZVFH-LABEL: vfsgnj_vv_nxv2f16_unmasked: |
| ; ZVFH: # %bb.0: |
| ; ZVFH-NEXT: vsetvli zero, a0, e16, mf2, ta, ma |
| ; ZVFH-NEXT: vfsgnj.vv v8, v8, v9 |
| ; ZVFH-NEXT: ret |
| ; |
| ; ZVFHMIN-LABEL: vfsgnj_vv_nxv2f16_unmasked: |
| ; ZVFHMIN: # %bb.0: |
| ; ZVFHMIN-NEXT: vsetvli a1, zero, e16, mf2, ta, ma |
| ; ZVFHMIN-NEXT: vfwcvt.f.f.v v10, v9 |
| ; ZVFHMIN-NEXT: vfwcvt.f.f.v v9, v8 |
| ; ZVFHMIN-NEXT: vsetvli zero, a0, e32, m1, ta, ma |
| ; ZVFHMIN-NEXT: vfsgnj.vv v9, v9, v10 |
| ; ZVFHMIN-NEXT: vsetvli a0, zero, e16, mf2, ta, ma |
| ; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v9 |
| ; ZVFHMIN-NEXT: ret |
| %v = call <vscale x 2 x half> @llvm.vp.copysign.nxv2f16(<vscale x 2 x half> %va, <vscale x 2 x half> %vb, <vscale x 2 x i1> splat (i1 true), i32 %evl) |
| ret <vscale x 2 x half> %v |
| } |
| |
| declare <vscale x 4 x half> @llvm.vp.copysign.nxv4f16(<vscale x 4 x half>, <vscale x 4 x half>, <vscale x 4 x i1>, i32) |
| |
| define <vscale x 4 x half> @vfsgnj_vv_nxv4f16(<vscale x 4 x half> %va, <vscale x 4 x half> %vb, <vscale x 4 x i1> %m, i32 zeroext %evl) { |
| ; ZVFH-LABEL: vfsgnj_vv_nxv4f16: |
| ; ZVFH: # %bb.0: |
| ; ZVFH-NEXT: vsetvli zero, a0, e16, m1, ta, ma |
| ; ZVFH-NEXT: vfsgnj.vv v8, v8, v9, v0.t |
| ; ZVFH-NEXT: ret |
| ; |
| ; ZVFHMIN-LABEL: vfsgnj_vv_nxv4f16: |
| ; ZVFHMIN: # %bb.0: |
| ; ZVFHMIN-NEXT: vsetvli a1, zero, e16, m1, ta, ma |
| ; ZVFHMIN-NEXT: vfwcvt.f.f.v v10, v9 |
| ; ZVFHMIN-NEXT: vfwcvt.f.f.v v12, v8 |
| ; ZVFHMIN-NEXT: vsetvli zero, a0, e32, m2, ta, ma |
| ; 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 <vscale x 4 x half> @llvm.vp.copysign.nxv4f16(<vscale x 4 x half> %va, <vscale x 4 x half> %vb, <vscale x 4 x i1> %m, i32 %evl) |
| ret <vscale x 4 x half> %v |
| } |
| |
| define <vscale x 4 x half> @vfsgnj_vv_nxv4f16_unmasked(<vscale x 4 x half> %va, <vscale x 4 x half> %vb, i32 zeroext %evl) { |
| ; ZVFH-LABEL: vfsgnj_vv_nxv4f16_unmasked: |
| ; ZVFH: # %bb.0: |
| ; ZVFH-NEXT: vsetvli zero, a0, e16, m1, ta, ma |
| ; ZVFH-NEXT: vfsgnj.vv v8, v8, v9 |
| ; ZVFH-NEXT: ret |
| ; |
| ; ZVFHMIN-LABEL: vfsgnj_vv_nxv4f16_unmasked: |
| ; ZVFHMIN: # %bb.0: |
| ; ZVFHMIN-NEXT: vsetvli a1, zero, e16, m1, ta, ma |
| ; ZVFHMIN-NEXT: vfwcvt.f.f.v v10, v9 |
| ; ZVFHMIN-NEXT: vfwcvt.f.f.v v12, v8 |
| ; ZVFHMIN-NEXT: vsetvli zero, a0, e32, m2, ta, ma |
| ; ZVFHMIN-NEXT: vfsgnj.vv v10, v12, v10 |
| ; ZVFHMIN-NEXT: vsetvli a0, zero, e16, m1, ta, ma |
| ; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v10 |
| ; ZVFHMIN-NEXT: ret |
| %v = call <vscale x 4 x half> @llvm.vp.copysign.nxv4f16(<vscale x 4 x half> %va, <vscale x 4 x half> %vb, <vscale x 4 x i1> splat (i1 true), i32 %evl) |
| ret <vscale x 4 x half> %v |
| } |
| |
| declare <vscale x 8 x half> @llvm.vp.copysign.nxv8f16(<vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x i1>, i32) |
| |
| define <vscale x 8 x half> @vfsgnj_vv_nxv8f16(<vscale x 8 x half> %va, <vscale x 8 x half> %vb, <vscale x 8 x i1> %m, i32 zeroext %evl) { |
| ; ZVFH-LABEL: vfsgnj_vv_nxv8f16: |
| ; ZVFH: # %bb.0: |
| ; ZVFH-NEXT: vsetvli zero, a0, e16, m2, ta, ma |
| ; ZVFH-NEXT: vfsgnj.vv v8, v8, v10, v0.t |
| ; ZVFH-NEXT: ret |
| ; |
| ; ZVFHMIN-LABEL: vfsgnj_vv_nxv8f16: |
| ; ZVFHMIN: # %bb.0: |
| ; ZVFHMIN-NEXT: vsetvli a1, zero, e16, m2, ta, ma |
| ; ZVFHMIN-NEXT: vfwcvt.f.f.v v12, v10 |
| ; ZVFHMIN-NEXT: vfwcvt.f.f.v v16, v8 |
| ; ZVFHMIN-NEXT: vsetvli zero, a0, e32, m4, ta, ma |
| ; 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 <vscale x 8 x half> @llvm.vp.copysign.nxv8f16(<vscale x 8 x half> %va, <vscale x 8 x half> %vb, <vscale x 8 x i1> %m, i32 %evl) |
| ret <vscale x 8 x half> %v |
| } |
| |
| define <vscale x 8 x half> @vfsgnj_vv_nxv8f16_unmasked(<vscale x 8 x half> %va, <vscale x 8 x half> %vb, i32 zeroext %evl) { |
| ; ZVFH-LABEL: vfsgnj_vv_nxv8f16_unmasked: |
| ; ZVFH: # %bb.0: |
| ; ZVFH-NEXT: vsetvli zero, a0, e16, m2, ta, ma |
| ; ZVFH-NEXT: vfsgnj.vv v8, v8, v10 |
| ; ZVFH-NEXT: ret |
| ; |
| ; ZVFHMIN-LABEL: vfsgnj_vv_nxv8f16_unmasked: |
| ; ZVFHMIN: # %bb.0: |
| ; ZVFHMIN-NEXT: vsetvli a1, zero, e16, m2, ta, ma |
| ; ZVFHMIN-NEXT: vfwcvt.f.f.v v12, v10 |
| ; ZVFHMIN-NEXT: vfwcvt.f.f.v v16, v8 |
| ; ZVFHMIN-NEXT: vsetvli zero, a0, e32, m4, ta, ma |
| ; ZVFHMIN-NEXT: vfsgnj.vv v12, v16, v12 |
| ; ZVFHMIN-NEXT: vsetvli a0, zero, e16, m2, ta, ma |
| ; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v12 |
| ; ZVFHMIN-NEXT: ret |
| %v = call <vscale x 8 x half> @llvm.vp.copysign.nxv8f16(<vscale x 8 x half> %va, <vscale x 8 x half> %vb, <vscale x 8 x i1> splat (i1 true), i32 %evl) |
| ret <vscale x 8 x half> %v |
| } |
| |
| declare <vscale x 16 x half> @llvm.vp.copysign.nxv16f16(<vscale x 16 x half>, <vscale x 16 x half>, <vscale x 16 x i1>, i32) |
| |
| define <vscale x 16 x half> @vfsgnj_vv_nxv16f16(<vscale x 16 x half> %va, <vscale x 16 x half> %vb, <vscale x 16 x i1> %m, i32 zeroext %evl) { |
| ; ZVFH-LABEL: vfsgnj_vv_nxv16f16: |
| ; ZVFH: # %bb.0: |
| ; ZVFH-NEXT: vsetvli zero, a0, e16, m4, ta, ma |
| ; ZVFH-NEXT: vfsgnj.vv v8, v8, v12, v0.t |
| ; ZVFH-NEXT: ret |
| ; |
| ; ZVFHMIN-LABEL: vfsgnj_vv_nxv16f16: |
| ; ZVFHMIN: # %bb.0: |
| ; ZVFHMIN-NEXT: vsetvli a1, zero, e16, m4, ta, ma |
| ; ZVFHMIN-NEXT: vfwcvt.f.f.v v16, v12 |
| ; ZVFHMIN-NEXT: vfwcvt.f.f.v v24, v8 |
| ; ZVFHMIN-NEXT: vsetvli zero, a0, e32, m8, ta, ma |
| ; 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 <vscale x 16 x half> @llvm.vp.copysign.nxv16f16(<vscale x 16 x half> %va, <vscale x 16 x half> %vb, <vscale x 16 x i1> %m, i32 %evl) |
| ret <vscale x 16 x half> %v |
| } |
| |
| define <vscale x 16 x half> @vfsgnj_vv_nxv16f16_unmasked(<vscale x 16 x half> %va, <vscale x 16 x half> %vb, i32 zeroext %evl) { |
| ; ZVFH-LABEL: vfsgnj_vv_nxv16f16_unmasked: |
| ; ZVFH: # %bb.0: |
| ; ZVFH-NEXT: vsetvli zero, a0, e16, m4, ta, ma |
| ; ZVFH-NEXT: vfsgnj.vv v8, v8, v12 |
| ; ZVFH-NEXT: ret |
| ; |
| ; ZVFHMIN-LABEL: vfsgnj_vv_nxv16f16_unmasked: |
| ; ZVFHMIN: # %bb.0: |
| ; ZVFHMIN-NEXT: vsetvli a1, zero, e16, m4, ta, ma |
| ; ZVFHMIN-NEXT: vfwcvt.f.f.v v16, v12 |
| ; ZVFHMIN-NEXT: vfwcvt.f.f.v v24, v8 |
| ; ZVFHMIN-NEXT: vsetvli zero, a0, e32, m8, ta, ma |
| ; ZVFHMIN-NEXT: vfsgnj.vv v16, v24, v16 |
| ; ZVFHMIN-NEXT: vsetvli a0, zero, e16, m4, ta, ma |
| ; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v16 |
| ; ZVFHMIN-NEXT: ret |
| %v = call <vscale x 16 x half> @llvm.vp.copysign.nxv16f16(<vscale x 16 x half> %va, <vscale x 16 x half> %vb, <vscale x 16 x i1> splat (i1 true), i32 %evl) |
| ret <vscale x 16 x half> %v |
| } |
| |
| declare <vscale x 32 x half> @llvm.vp.copysign.nxv32f16(<vscale x 32 x half>, <vscale x 32 x half>, <vscale x 32 x i1>, i32) |
| |
| define <vscale x 32 x half> @vfsgnj_vv_nxv32f16(<vscale x 32 x half> %va, <vscale x 32 x half> %vb, <vscale x 32 x i1> %m, i32 zeroext %evl) { |
| ; ZVFH-LABEL: vfsgnj_vv_nxv32f16: |
| ; ZVFH: # %bb.0: |
| ; ZVFH-NEXT: vsetvli zero, a0, e16, m8, ta, ma |
| ; ZVFH-NEXT: vfsgnj.vv v8, v8, v16, v0.t |
| ; ZVFH-NEXT: ret |
| ; |
| ; ZVFHMIN-LABEL: vfsgnj_vv_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 v7, 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 v0, v0, a2 |
| ; ZVFHMIN-NEXT: vsetvli a2, zero, e16, m4, ta, ma |
| ; ZVFHMIN-NEXT: addi a2, sp, 16 |
| ; ZVFHMIN-NEXT: vs8r.v v16, (a2) # Unknown-size Folded Spill |
| ; ZVFHMIN-NEXT: vfwcvt.f.f.v v24, v20 |
| ; ZVFHMIN-NEXT: vfwcvt.f.f.v v16, v12 |
| ; ZVFHMIN-NEXT: vsetvli zero, a3, e32, m8, ta, ma |
| ; ZVFHMIN-NEXT: vfsgnj.vv v16, v16, v24, v0.t |
| ; ZVFHMIN-NEXT: vsetvli a2, zero, e16, m4, ta, ma |
| ; ZVFHMIN-NEXT: vfncvt.f.f.w v12, v16 |
| ; 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 v24, (a1) # Unknown-size Folded Reload |
| ; ZVFHMIN-NEXT: vfwcvt.f.f.v v16, v24 |
| ; ZVFHMIN-NEXT: vfwcvt.f.f.v v24, v8 |
| ; ZVFHMIN-NEXT: vsetvli zero, a0, e32, m8, ta, ma |
| ; ZVFHMIN-NEXT: vmv1r.v v0, v7 |
| ; 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 |
| %v = call <vscale x 32 x half> @llvm.vp.copysign.nxv32f16(<vscale x 32 x half> %va, <vscale x 32 x half> %vb, <vscale x 32 x i1> %m, i32 %evl) |
| ret <vscale x 32 x half> %v |
| } |
| |
| define <vscale x 32 x half> @vfsgnj_vv_nxv32f16_unmasked(<vscale x 32 x half> %va, <vscale x 32 x half> %vb, i32 zeroext %evl) { |
| ; ZVFH-LABEL: vfsgnj_vv_nxv32f16_unmasked: |
| ; ZVFH: # %bb.0: |
| ; ZVFH-NEXT: vsetvli zero, a0, e16, m8, ta, ma |
| ; ZVFH-NEXT: vfsgnj.vv v8, v8, v16 |
| ; ZVFH-NEXT: ret |
| ; |
| ; ZVFHMIN-LABEL: vfsgnj_vv_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: 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, m4, ta, ma |
| ; ZVFHMIN-NEXT: vmset.m v24 |
| ; ZVFHMIN-NEXT: vsetvli a4, zero, e8, mf2, ta, ma |
| ; ZVFHMIN-NEXT: vslidedown.vx v0, v24, a2 |
| ; ZVFHMIN-NEXT: vsetvli a2, zero, e16, m4, ta, ma |
| ; ZVFHMIN-NEXT: addi a2, sp, 16 |
| ; ZVFHMIN-NEXT: vs8r.v v16, (a2) # Unknown-size Folded Spill |
| ; ZVFHMIN-NEXT: vfwcvt.f.f.v v24, v20 |
| ; ZVFHMIN-NEXT: vfwcvt.f.f.v v16, v12 |
| ; ZVFHMIN-NEXT: vsetvli zero, a3, e32, m8, ta, ma |
| ; ZVFHMIN-NEXT: vfsgnj.vv v16, v16, v24, v0.t |
| ; ZVFHMIN-NEXT: vsetvli a2, zero, e16, m4, ta, ma |
| ; ZVFHMIN-NEXT: vfncvt.f.f.w v12, v16 |
| ; 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: vfwcvt.f.f.v v24, v8 |
| ; ZVFHMIN-NEXT: vsetvli zero, a0, e32, m8, ta, ma |
| ; ZVFHMIN-NEXT: vfsgnj.vv v16, v24, v16 |
| ; 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 |
| %v = call <vscale x 32 x half> @llvm.vp.copysign.nxv32f16(<vscale x 32 x half> %va, <vscale x 32 x half> %vb, <vscale x 32 x i1> splat (i1 true), i32 %evl) |
| ret <vscale x 32 x half> %v |
| } |
| |
| declare <vscale x 1 x float> @llvm.vp.copysign.nxv1f32(<vscale x 1 x float>, <vscale x 1 x float>, <vscale x 1 x i1>, i32) |
| |
| define <vscale x 1 x float> @vfsgnj_vv_nxv1f32(<vscale x 1 x float> %va, <vscale x 1 x float> %vb, <vscale x 1 x i1> %m, i32 zeroext %evl) { |
| ; CHECK-LABEL: vfsgnj_vv_nxv1f32: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetvli zero, a0, e32, mf2, ta, ma |
| ; CHECK-NEXT: vfsgnj.vv v8, v8, v9, v0.t |
| ; CHECK-NEXT: ret |
| %v = call <vscale x 1 x float> @llvm.vp.copysign.nxv1f32(<vscale x 1 x float> %va, <vscale x 1 x float> %vb, <vscale x 1 x i1> %m, i32 %evl) |
| ret <vscale x 1 x float> %v |
| } |
| |
| define <vscale x 1 x float> @vfsgnj_vv_nxv1f32_unmasked(<vscale x 1 x float> %va, <vscale x 1 x float> %vb, i32 zeroext %evl) { |
| ; CHECK-LABEL: vfsgnj_vv_nxv1f32_unmasked: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetvli zero, a0, e32, mf2, ta, ma |
| ; CHECK-NEXT: vfsgnj.vv v8, v8, v9 |
| ; CHECK-NEXT: ret |
| %v = call <vscale x 1 x float> @llvm.vp.copysign.nxv1f32(<vscale x 1 x float> %va, <vscale x 1 x float> %vb, <vscale x 1 x i1> splat (i1 true), i32 %evl) |
| ret <vscale x 1 x float> %v |
| } |
| |
| declare <vscale x 2 x float> @llvm.vp.copysign.nxv2f32(<vscale x 2 x float>, <vscale x 2 x float>, <vscale x 2 x i1>, i32) |
| |
| define <vscale x 2 x float> @vfsgnj_vv_nxv2f32(<vscale x 2 x float> %va, <vscale x 2 x float> %vb, <vscale x 2 x i1> %m, i32 zeroext %evl) { |
| ; CHECK-LABEL: vfsgnj_vv_nxv2f32: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetvli zero, a0, e32, m1, ta, ma |
| ; CHECK-NEXT: vfsgnj.vv v8, v8, v9, v0.t |
| ; CHECK-NEXT: ret |
| %v = call <vscale x 2 x float> @llvm.vp.copysign.nxv2f32(<vscale x 2 x float> %va, <vscale x 2 x float> %vb, <vscale x 2 x i1> %m, i32 %evl) |
| ret <vscale x 2 x float> %v |
| } |
| |
| define <vscale x 2 x float> @vfsgnj_vv_nxv2f32_unmasked(<vscale x 2 x float> %va, <vscale x 2 x float> %vb, i32 zeroext %evl) { |
| ; CHECK-LABEL: vfsgnj_vv_nxv2f32_unmasked: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetvli zero, a0, e32, m1, ta, ma |
| ; CHECK-NEXT: vfsgnj.vv v8, v8, v9 |
| ; CHECK-NEXT: ret |
| %v = call <vscale x 2 x float> @llvm.vp.copysign.nxv2f32(<vscale x 2 x float> %va, <vscale x 2 x float> %vb, <vscale x 2 x i1> splat (i1 true), i32 %evl) |
| ret <vscale x 2 x float> %v |
| } |
| |
| declare <vscale x 4 x float> @llvm.vp.copysign.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x i1>, i32) |
| |
| define <vscale x 4 x float> @vfsgnj_vv_nxv4f32(<vscale x 4 x float> %va, <vscale x 4 x float> %vb, <vscale x 4 x i1> %m, i32 zeroext %evl) { |
| ; CHECK-LABEL: vfsgnj_vv_nxv4f32: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetvli zero, a0, e32, m2, ta, ma |
| ; CHECK-NEXT: vfsgnj.vv v8, v8, v10, v0.t |
| ; CHECK-NEXT: ret |
| %v = call <vscale x 4 x float> @llvm.vp.copysign.nxv4f32(<vscale x 4 x float> %va, <vscale x 4 x float> %vb, <vscale x 4 x i1> %m, i32 %evl) |
| ret <vscale x 4 x float> %v |
| } |
| |
| define <vscale x 4 x float> @vfsgnj_vv_nxv4f32_unmasked(<vscale x 4 x float> %va, <vscale x 4 x float> %vb, i32 zeroext %evl) { |
| ; CHECK-LABEL: vfsgnj_vv_nxv4f32_unmasked: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetvli zero, a0, e32, m2, ta, ma |
| ; CHECK-NEXT: vfsgnj.vv v8, v8, v10 |
| ; CHECK-NEXT: ret |
| %v = call <vscale x 4 x float> @llvm.vp.copysign.nxv4f32(<vscale x 4 x float> %va, <vscale x 4 x float> %vb, <vscale x 4 x i1> splat (i1 true), i32 %evl) |
| ret <vscale x 4 x float> %v |
| } |
| |
| declare <vscale x 8 x float> @llvm.vp.copysign.nxv8f32(<vscale x 8 x float>, <vscale x 8 x float>, <vscale x 8 x i1>, i32) |
| |
| define <vscale x 8 x float> @vfsgnj_vv_nxv8f32(<vscale x 8 x float> %va, <vscale x 8 x float> %vb, <vscale x 8 x i1> %m, i32 zeroext %evl) { |
| ; CHECK-LABEL: vfsgnj_vv_nxv8f32: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetvli zero, a0, e32, m4, ta, ma |
| ; CHECK-NEXT: vfsgnj.vv v8, v8, v12, v0.t |
| ; CHECK-NEXT: ret |
| %v = call <vscale x 8 x float> @llvm.vp.copysign.nxv8f32(<vscale x 8 x float> %va, <vscale x 8 x float> %vb, <vscale x 8 x i1> %m, i32 %evl) |
| ret <vscale x 8 x float> %v |
| } |
| |
| define <vscale x 8 x float> @vfsgnj_vv_nxv8f32_unmasked(<vscale x 8 x float> %va, <vscale x 8 x float> %vb, i32 zeroext %evl) { |
| ; CHECK-LABEL: vfsgnj_vv_nxv8f32_unmasked: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetvli zero, a0, e32, m4, ta, ma |
| ; CHECK-NEXT: vfsgnj.vv v8, v8, v12 |
| ; CHECK-NEXT: ret |
| %v = call <vscale x 8 x float> @llvm.vp.copysign.nxv8f32(<vscale x 8 x float> %va, <vscale x 8 x float> %vb, <vscale x 8 x i1> splat (i1 true), i32 %evl) |
| ret <vscale x 8 x float> %v |
| } |
| |
| declare <vscale x 16 x float> @llvm.vp.copysign.nxv16f32(<vscale x 16 x float>, <vscale x 16 x float>, <vscale x 16 x i1>, i32) |
| |
| define <vscale x 16 x float> @vfsgnj_vv_nxv16f32(<vscale x 16 x float> %va, <vscale x 16 x float> %vb, <vscale x 16 x i1> %m, i32 zeroext %evl) { |
| ; CHECK-LABEL: vfsgnj_vv_nxv16f32: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetvli zero, a0, e32, m8, ta, ma |
| ; CHECK-NEXT: vfsgnj.vv v8, v8, v16, v0.t |
| ; CHECK-NEXT: ret |
| %v = call <vscale x 16 x float> @llvm.vp.copysign.nxv16f32(<vscale x 16 x float> %va, <vscale x 16 x float> %vb, <vscale x 16 x i1> %m, i32 %evl) |
| ret <vscale x 16 x float> %v |
| } |
| |
| define <vscale x 16 x float> @vfsgnj_vv_nxv16f32_unmasked(<vscale x 16 x float> %va, <vscale x 16 x float> %vb, i32 zeroext %evl) { |
| ; CHECK-LABEL: vfsgnj_vv_nxv16f32_unmasked: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetvli zero, a0, e32, m8, ta, ma |
| ; CHECK-NEXT: vfsgnj.vv v8, v8, v16 |
| ; CHECK-NEXT: ret |
| %v = call <vscale x 16 x float> @llvm.vp.copysign.nxv16f32(<vscale x 16 x float> %va, <vscale x 16 x float> %vb, <vscale x 16 x i1> splat (i1 true), i32 %evl) |
| ret <vscale x 16 x float> %v |
| } |
| |
| declare <vscale x 1 x double> @llvm.vp.copysign.nxv1f64(<vscale x 1 x double>, <vscale x 1 x double>, <vscale x 1 x i1>, i32) |
| |
| define <vscale x 1 x double> @vfsgnj_vv_nxv1f64(<vscale x 1 x double> %va, <vscale x 1 x double> %vb, <vscale x 1 x i1> %m, i32 zeroext %evl) { |
| ; CHECK-LABEL: vfsgnj_vv_nxv1f64: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetvli zero, a0, e64, m1, ta, ma |
| ; CHECK-NEXT: vfsgnj.vv v8, v8, v9, v0.t |
| ; CHECK-NEXT: ret |
| %v = call <vscale x 1 x double> @llvm.vp.copysign.nxv1f64(<vscale x 1 x double> %va, <vscale x 1 x double> %vb, <vscale x 1 x i1> %m, i32 %evl) |
| ret <vscale x 1 x double> %v |
| } |
| |
| define <vscale x 1 x double> @vfsgnj_vv_nxv1f64_unmasked(<vscale x 1 x double> %va, <vscale x 1 x double> %vb, i32 zeroext %evl) { |
| ; CHECK-LABEL: vfsgnj_vv_nxv1f64_unmasked: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetvli zero, a0, e64, m1, ta, ma |
| ; CHECK-NEXT: vfsgnj.vv v8, v8, v9 |
| ; CHECK-NEXT: ret |
| %v = call <vscale x 1 x double> @llvm.vp.copysign.nxv1f64(<vscale x 1 x double> %va, <vscale x 1 x double> %vb, <vscale x 1 x i1> splat (i1 true), i32 %evl) |
| ret <vscale x 1 x double> %v |
| } |
| |
| declare <vscale x 2 x double> @llvm.vp.copysign.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x i1>, i32) |
| |
| define <vscale x 2 x double> @vfsgnj_vv_nxv2f64(<vscale x 2 x double> %va, <vscale x 2 x double> %vb, <vscale x 2 x i1> %m, i32 zeroext %evl) { |
| ; CHECK-LABEL: vfsgnj_vv_nxv2f64: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetvli zero, a0, e64, m2, ta, ma |
| ; CHECK-NEXT: vfsgnj.vv v8, v8, v10, v0.t |
| ; CHECK-NEXT: ret |
| %v = call <vscale x 2 x double> @llvm.vp.copysign.nxv2f64(<vscale x 2 x double> %va, <vscale x 2 x double> %vb, <vscale x 2 x i1> %m, i32 %evl) |
| ret <vscale x 2 x double> %v |
| } |
| |
| define <vscale x 2 x double> @vfsgnj_vv_nxv2f64_unmasked(<vscale x 2 x double> %va, <vscale x 2 x double> %vb, i32 zeroext %evl) { |
| ; CHECK-LABEL: vfsgnj_vv_nxv2f64_unmasked: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetvli zero, a0, e64, m2, ta, ma |
| ; CHECK-NEXT: vfsgnj.vv v8, v8, v10 |
| ; CHECK-NEXT: ret |
| %v = call <vscale x 2 x double> @llvm.vp.copysign.nxv2f64(<vscale x 2 x double> %va, <vscale x 2 x double> %vb, <vscale x 2 x i1> splat (i1 true), i32 %evl) |
| ret <vscale x 2 x double> %v |
| } |
| |
| declare <vscale x 4 x double> @llvm.vp.copysign.nxv4f64(<vscale x 4 x double>, <vscale x 4 x double>, <vscale x 4 x i1>, i32) |
| |
| define <vscale x 4 x double> @vfsgnj_vv_nxv4f64(<vscale x 4 x double> %va, <vscale x 4 x double> %vb, <vscale x 4 x i1> %m, i32 zeroext %evl) { |
| ; CHECK-LABEL: vfsgnj_vv_nxv4f64: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetvli zero, a0, e64, m4, ta, ma |
| ; CHECK-NEXT: vfsgnj.vv v8, v8, v12, v0.t |
| ; CHECK-NEXT: ret |
| %v = call <vscale x 4 x double> @llvm.vp.copysign.nxv4f64(<vscale x 4 x double> %va, <vscale x 4 x double> %vb, <vscale x 4 x i1> %m, i32 %evl) |
| ret <vscale x 4 x double> %v |
| } |
| |
| define <vscale x 4 x double> @vfsgnj_vv_nxv4f64_unmasked(<vscale x 4 x double> %va, <vscale x 4 x double> %vb, i32 zeroext %evl) { |
| ; CHECK-LABEL: vfsgnj_vv_nxv4f64_unmasked: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetvli zero, a0, e64, m4, ta, ma |
| ; CHECK-NEXT: vfsgnj.vv v8, v8, v12 |
| ; CHECK-NEXT: ret |
| %v = call <vscale x 4 x double> @llvm.vp.copysign.nxv4f64(<vscale x 4 x double> %va, <vscale x 4 x double> %vb, <vscale x 4 x i1> splat (i1 true), i32 %evl) |
| ret <vscale x 4 x double> %v |
| } |
| |
| declare <vscale x 8 x double> @llvm.vp.copysign.nxv8f64(<vscale x 8 x double>, <vscale x 8 x double>, <vscale x 8 x i1>, i32) |
| |
| define <vscale x 8 x double> @vfsgnj_vv_nxv8f64(<vscale x 8 x double> %va, <vscale x 8 x double> %vb, <vscale x 8 x i1> %m, i32 zeroext %evl) { |
| ; CHECK-LABEL: vfsgnj_vv_nxv8f64: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetvli zero, a0, e64, m8, ta, ma |
| ; CHECK-NEXT: vfsgnj.vv v8, v8, v16, v0.t |
| ; CHECK-NEXT: ret |
| %v = call <vscale x 8 x double> @llvm.vp.copysign.nxv8f64(<vscale x 8 x double> %va, <vscale x 8 x double> %vb, <vscale x 8 x i1> %m, i32 %evl) |
| ret <vscale x 8 x double> %v |
| } |
| |
| define <vscale x 8 x double> @vfsgnj_vv_nxv8f64_unmasked(<vscale x 8 x double> %va, <vscale x 8 x double> %vb, i32 zeroext %evl) { |
| ; CHECK-LABEL: vfsgnj_vv_nxv8f64_unmasked: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetvli zero, a0, e64, m8, ta, ma |
| ; CHECK-NEXT: vfsgnj.vv v8, v8, v16 |
| ; CHECK-NEXT: ret |
| %v = call <vscale x 8 x double> @llvm.vp.copysign.nxv8f64(<vscale x 8 x double> %va, <vscale x 8 x double> %vb, <vscale x 8 x i1> splat (i1 true), i32 %evl) |
| ret <vscale x 8 x double> %v |
| } |