; 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,RV32
; RUN: llc -mtriple=riscv64 -mattr=+d,+zfh,+zvfh,+v -target-abi=lp64d \
; RUN: -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK,RV64
define half @extractelt_nxv1f16_0(<vscale x 1 x half> %v) {
; CHECK-LABEL: extractelt_nxv1f16_0:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e16, m1, ta, ma
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 1 x half> %v, i32 0
ret half %r
}
define half @extractelt_nxv1f16_imm(<vscale x 1 x half> %v) {
; CHECK-LABEL: extractelt_nxv1f16_imm:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e16, mf4, ta, ma
; CHECK-NEXT: vslidedown.vi v8, v8, 2
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 1 x half> %v, i32 2
ret half %r
}
define half @extractelt_nxv1f16_idx(<vscale x 1 x half> %v, i32 zeroext %idx) {
; CHECK-LABEL: extractelt_nxv1f16_idx:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e16, mf4, ta, ma
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 1 x half> %v, i32 %idx
ret half %r
}
define half @extractelt_nxv2f16_0(<vscale x 2 x half> %v) {
; CHECK-LABEL: extractelt_nxv2f16_0:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e16, m1, ta, ma
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 2 x half> %v, i32 0
ret half %r
}
define half @extractelt_nxv2f16_imm(<vscale x 2 x half> %v) {
; CHECK-LABEL: extractelt_nxv2f16_imm:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e16, mf2, ta, ma
; CHECK-NEXT: vslidedown.vi v8, v8, 2
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 2 x half> %v, i32 2
ret half %r
}
define half @extractelt_nxv2f16_idx(<vscale x 2 x half> %v, i32 zeroext %idx) {
; CHECK-LABEL: extractelt_nxv2f16_idx:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e16, mf2, ta, ma
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 2 x half> %v, i32 %idx
ret half %r
}
define half @extractelt_nxv4f16_0(<vscale x 4 x half> %v) {
; CHECK-LABEL: extractelt_nxv4f16_0:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e16, m1, ta, ma
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 4 x half> %v, i32 0
ret half %r
}
define half @extractelt_nxv4f16_imm(<vscale x 4 x half> %v) {
; CHECK-LABEL: extractelt_nxv4f16_imm:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e16, m1, ta, ma
; CHECK-NEXT: vslidedown.vi v8, v8, 2
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 4 x half> %v, i32 2
ret half %r
}
define half @extractelt_nxv4f16_idx(<vscale x 4 x half> %v, i32 zeroext %idx) {
; CHECK-LABEL: extractelt_nxv4f16_idx:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e16, m1, ta, ma
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 4 x half> %v, i32 %idx
ret half %r
}
define half @extractelt_nxv8f16_0(<vscale x 8 x half> %v) {
; CHECK-LABEL: extractelt_nxv8f16_0:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e16, m1, ta, ma
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 8 x half> %v, i32 0
ret half %r
}
define half @extractelt_nxv8f16_imm(<vscale x 8 x half> %v) {
; CHECK-LABEL: extractelt_nxv8f16_imm:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e16, m1, ta, ma
; CHECK-NEXT: vslidedown.vi v8, v8, 2
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 8 x half> %v, i32 2
ret half %r
}
define half @extractelt_nxv8f16_idx(<vscale x 8 x half> %v, i32 zeroext %idx) {
; CHECK-LABEL: extractelt_nxv8f16_idx:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e16, m2, ta, ma
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 8 x half> %v, i32 %idx
ret half %r
}
define half @extractelt_nxv16f16_0(<vscale x 16 x half> %v) {
; CHECK-LABEL: extractelt_nxv16f16_0:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e16, m1, ta, ma
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 16 x half> %v, i32 0
ret half %r
}
define half @extractelt_nxv16f16_imm(<vscale x 16 x half> %v) {
; CHECK-LABEL: extractelt_nxv16f16_imm:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e16, m1, ta, ma
; CHECK-NEXT: vslidedown.vi v8, v8, 2
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 16 x half> %v, i32 2
ret half %r
}
define half @extractelt_nxv16f16_idx(<vscale x 16 x half> %v, i32 zeroext %idx) {
; CHECK-LABEL: extractelt_nxv16f16_idx:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e16, m4, ta, ma
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 16 x half> %v, i32 %idx
ret half %r
}
define half @extractelt_nxv32f16_0(<vscale x 32 x half> %v) {
; CHECK-LABEL: extractelt_nxv32f16_0:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e16, m1, ta, ma
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 32 x half> %v, i32 0
ret half %r
}
define half @extractelt_nxv32f16_imm(<vscale x 32 x half> %v) {
; CHECK-LABEL: extractelt_nxv32f16_imm:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e16, m1, ta, ma
; CHECK-NEXT: vslidedown.vi v8, v8, 2
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 32 x half> %v, i32 2
ret half %r
}
define half @extractelt_nxv32f16_idx(<vscale x 32 x half> %v, i32 zeroext %idx) {
; CHECK-LABEL: extractelt_nxv32f16_idx:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e16, m8, ta, ma
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 32 x half> %v, i32 %idx
ret half %r
}
define float @extractelt_nxv1f32_0(<vscale x 1 x float> %v) {
; CHECK-LABEL: extractelt_nxv1f32_0:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e32, m1, ta, ma
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 1 x float> %v, i32 0
ret float %r
}
define float @extractelt_nxv1f32_imm(<vscale x 1 x float> %v) {
; CHECK-LABEL: extractelt_nxv1f32_imm:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e32, mf2, ta, ma
; CHECK-NEXT: vslidedown.vi v8, v8, 2
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 1 x float> %v, i32 2
ret float %r
}
define float @extractelt_nxv1f32_idx(<vscale x 1 x float> %v, i32 zeroext %idx) {
; CHECK-LABEL: extractelt_nxv1f32_idx:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e32, mf2, ta, ma
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 1 x float> %v, i32 %idx
ret float %r
}
define float @extractelt_nxv2f32_0(<vscale x 2 x float> %v) {
; CHECK-LABEL: extractelt_nxv2f32_0:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e32, m1, ta, ma
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 2 x float> %v, i32 0
ret float %r
}
define float @extractelt_nxv2f32_imm(<vscale x 2 x float> %v) {
; CHECK-LABEL: extractelt_nxv2f32_imm:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e32, m1, ta, ma
; CHECK-NEXT: vslidedown.vi v8, v8, 2
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 2 x float> %v, i32 2
ret float %r
}
define float @extractelt_nxv2f32_idx(<vscale x 2 x float> %v, i32 zeroext %idx) {
; CHECK-LABEL: extractelt_nxv2f32_idx:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e32, m1, ta, ma
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 2 x float> %v, i32 %idx
ret float %r
}
define float @extractelt_nxv4f32_0(<vscale x 4 x float> %v) {
; CHECK-LABEL: extractelt_nxv4f32_0:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e32, m1, ta, ma
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 4 x float> %v, i32 0
ret float %r
}
define float @extractelt_nxv4f32_imm(<vscale x 4 x float> %v) {
; CHECK-LABEL: extractelt_nxv4f32_imm:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e32, m1, ta, ma
; CHECK-NEXT: vslidedown.vi v8, v8, 2
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 4 x float> %v, i32 2
ret float %r
}
define float @extractelt_nxv4f32_idx(<vscale x 4 x float> %v, i32 zeroext %idx) {
; CHECK-LABEL: extractelt_nxv4f32_idx:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e32, m2, ta, ma
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 4 x float> %v, i32 %idx
ret float %r
}
define float @extractelt_nxv8f32_0(<vscale x 8 x float> %v) {
; CHECK-LABEL: extractelt_nxv8f32_0:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e32, m1, ta, ma
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 8 x float> %v, i32 0
ret float %r
}
define float @extractelt_nxv8f32_imm(<vscale x 8 x float> %v) {
; CHECK-LABEL: extractelt_nxv8f32_imm:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e32, m1, ta, ma
; CHECK-NEXT: vslidedown.vi v8, v8, 2
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 8 x float> %v, i32 2
ret float %r
}
define float @extractelt_nxv8f32_idx(<vscale x 8 x float> %v, i32 zeroext %idx) {
; CHECK-LABEL: extractelt_nxv8f32_idx:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e32, m4, ta, ma
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 8 x float> %v, i32 %idx
ret float %r
}
define float @extractelt_nxv16f32_0(<vscale x 16 x float> %v) {
; CHECK-LABEL: extractelt_nxv16f32_0:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e32, m1, ta, ma
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 16 x float> %v, i32 0
ret float %r
}
define float @extractelt_nxv16f32_imm(<vscale x 16 x float> %v) {
; CHECK-LABEL: extractelt_nxv16f32_imm:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e32, m1, ta, ma
; CHECK-NEXT: vslidedown.vi v8, v8, 2
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 16 x float> %v, i32 2
ret float %r
}
define float @extractelt_nxv16f32_idx(<vscale x 16 x float> %v, i32 zeroext %idx) {
; CHECK-LABEL: extractelt_nxv16f32_idx:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e32, m8, ta, ma
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 16 x float> %v, i32 %idx
ret float %r
}
define double @extractelt_nxv1f64_0(<vscale x 1 x double> %v) {
; CHECK-LABEL: extractelt_nxv1f64_0:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e64, m1, ta, ma
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 1 x double> %v, i32 0
ret double %r
}
define double @extractelt_nxv1f64_imm(<vscale x 1 x double> %v) {
; CHECK-LABEL: extractelt_nxv1f64_imm:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e64, m1, ta, ma
; CHECK-NEXT: vslidedown.vi v8, v8, 2
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 1 x double> %v, i32 2
ret double %r
}
define double @extractelt_nxv1f64_idx(<vscale x 1 x double> %v, i32 zeroext %idx) {
; CHECK-LABEL: extractelt_nxv1f64_idx:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e64, m1, ta, ma
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 1 x double> %v, i32 %idx
ret double %r
}
define double @extractelt_nxv2f64_0(<vscale x 2 x double> %v) {
; CHECK-LABEL: extractelt_nxv2f64_0:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e64, m1, ta, ma
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 2 x double> %v, i32 0
ret double %r
}
define double @extractelt_nxv2f64_imm(<vscale x 2 x double> %v) {
; CHECK-LABEL: extractelt_nxv2f64_imm:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e64, m2, ta, ma
; CHECK-NEXT: vslidedown.vi v8, v8, 2
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 2 x double> %v, i32 2
ret double %r
}
define double @extractelt_nxv2f64_idx(<vscale x 2 x double> %v, i32 zeroext %idx) {
; CHECK-LABEL: extractelt_nxv2f64_idx:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e64, m2, ta, ma
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 2 x double> %v, i32 %idx
ret double %r
}
define double @extractelt_nxv4f64_0(<vscale x 4 x double> %v) {
; CHECK-LABEL: extractelt_nxv4f64_0:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e64, m1, ta, ma
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 4 x double> %v, i32 0
ret double %r
}
define double @extractelt_nxv4f64_imm(<vscale x 4 x double> %v) {
; CHECK-LABEL: extractelt_nxv4f64_imm:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e64, m2, ta, ma
; CHECK-NEXT: vslidedown.vi v8, v8, 2
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 4 x double> %v, i32 2
ret double %r
}
define double @extractelt_nxv4f64_idx(<vscale x 4 x double> %v, i32 zeroext %idx) {
; CHECK-LABEL: extractelt_nxv4f64_idx:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e64, m4, ta, ma
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 4 x double> %v, i32 %idx
ret double %r
}
define double @extractelt_nxv8f64_0(<vscale x 8 x double> %v) {
; CHECK-LABEL: extractelt_nxv8f64_0:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e64, m1, ta, ma
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 8 x double> %v, i32 0
ret double %r
}
define double @extractelt_nxv8f64_imm(<vscale x 8 x double> %v) {
; CHECK-LABEL: extractelt_nxv8f64_imm:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e64, m2, ta, ma
; CHECK-NEXT: vslidedown.vi v8, v8, 2
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 8 x double> %v, i32 2
ret double %r
}
define double @extractelt_nxv8f64_idx(<vscale x 8 x double> %v, i32 zeroext %idx) {
; CHECK-LABEL: extractelt_nxv8f64_idx:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e64, m8, ta, ma
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 8 x double> %v, i32 %idx
ret double %r
}
define void @store_extractelt_nxv8f64(ptr %x, ptr %p) {
; CHECK-LABEL: store_extractelt_nxv8f64:
; CHECK: # %bb.0:
; CHECK-NEXT: vl8re64.v v8, (a0)
; CHECK-NEXT: vsetivli zero, 1, e64, m1, ta, ma
; CHECK-NEXT: vslidedown.vi v8, v8, 1
; CHECK-NEXT: vse64.v v8, (a1)
; CHECK-NEXT: ret
%a = load <vscale x 8 x double>, ptr %x
%b = extractelement <vscale x 8 x double> %a, i64 1
store double %b, ptr %p
ret void
}
define void @store_vfmv_f_s_nxv8f64(ptr %x, ptr %p) {
; CHECK-LABEL: store_vfmv_f_s_nxv8f64:
; CHECK: # %bb.0:
; CHECK-NEXT: vl8re64.v v8, (a0)
; CHECK-NEXT: vsetivli zero, 1, e64, m1, ta, ma
; CHECK-NEXT: vse64.v v8, (a1)
; CHECK-NEXT: ret
%a = load <vscale x 8 x double>, ptr %x
%b = call double @llvm.riscv.vfmv.f.s.nxv8f64(<vscale x 8 x double> %a)
store double %b, ptr %p
ret void
}
declare double @llvm.riscv.vfmv.f.s.nxv8f64(<vscale x 8 x double>)
define float @extractelt_fadd_nxv4f32_splat(<vscale x 4 x float> %x) {
; CHECK-LABEL: extractelt_fadd_nxv4f32_splat:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e32, m1, ta, ma
; CHECK-NEXT: vslidedown.vi v8, v8, 2
; CHECK-NEXT: vfmv.f.s fa5, v8
; CHECK-NEXT: lui a0, 263168
; CHECK-NEXT: fmv.w.x fa4, a0
; CHECK-NEXT: fadd.s fa0, fa5, fa4
; CHECK-NEXT: ret
%bo = fadd <vscale x 4 x float> %x, splat (float 3.0)
%ext = extractelement <vscale x 4 x float> %bo, i32 2
ret float %ext
}
define float @extractelt_fsub_nxv4f32_splat(<vscale x 4 x float> %x) {
; CHECK-LABEL: extractelt_fsub_nxv4f32_splat:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e32, m1, ta, ma
; CHECK-NEXT: vslidedown.vi v8, v8, 1
; CHECK-NEXT: vfmv.f.s fa5, v8
; CHECK-NEXT: lui a0, 263168
; CHECK-NEXT: fmv.w.x fa4, a0
; CHECK-NEXT: fsub.s fa0, fa4, fa5
; CHECK-NEXT: ret
%bo = fsub <vscale x 4 x float> splat (float 3.0), %x
%ext = extractelement <vscale x 4 x float> %bo, i32 1
ret float %ext
}
define float @extractelt_fmul_nxv4f32_splat(<vscale x 4 x float> %x) {
; CHECK-LABEL: extractelt_fmul_nxv4f32_splat:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e32, m1, ta, ma
; CHECK-NEXT: vslidedown.vi v8, v8, 3
; CHECK-NEXT: vfmv.f.s fa5, v8
; CHECK-NEXT: lui a0, 263168
; CHECK-NEXT: fmv.w.x fa4, a0
; CHECK-NEXT: fmul.s fa0, fa5, fa4
; CHECK-NEXT: ret
%bo = fmul <vscale x 4 x float> %x, splat (float 3.0)
%ext = extractelement <vscale x 4 x float> %bo, i32 3
ret float %ext
}
define float @extractelt_fdiv_nxv4f32_splat(<vscale x 4 x float> %x) {
; CHECK-LABEL: extractelt_fdiv_nxv4f32_splat:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e32, m1, ta, ma
; CHECK-NEXT: vfmv.f.s fa5, v8
; CHECK-NEXT: lui a0, 263168
; CHECK-NEXT: fmv.w.x fa4, a0
; CHECK-NEXT: fdiv.s fa0, fa5, fa4
; CHECK-NEXT: ret
%bo = fdiv <vscale x 4 x float> %x, splat (float 3.0)
%ext = extractelement <vscale x 4 x float> %bo, i32 0
ret float %ext
}
define double @extractelt_nxv16f64_0(<vscale x 16 x double> %v) {
; CHECK-LABEL: extractelt_nxv16f64_0:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e64, m1, ta, ma
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 16 x double> %v, i32 0
ret double %r
}
define double @extractelt_nxv16f64_neg1(<vscale x 16 x double> %v) {
; RV32-LABEL: extractelt_nxv16f64_neg1:
; RV32: # %bb.0:
; RV32-NEXT: addi sp, sp, -80
; RV32-NEXT: .cfi_def_cfa_offset 80
; RV32-NEXT: sw ra, 76(sp) # 4-byte Folded Spill
; RV32-NEXT: sw s0, 72(sp) # 4-byte Folded Spill
; RV32-NEXT: .cfi_offset ra, -4
; RV32-NEXT: .cfi_offset s0, -8
; RV32-NEXT: addi s0, sp, 80
; RV32-NEXT: .cfi_def_cfa s0, 0
; RV32-NEXT: csrr a0, vlenb
; RV32-NEXT: slli a0, a0, 4
; RV32-NEXT: sub sp, sp, a0
; RV32-NEXT: andi sp, sp, -64
; RV32-NEXT: addi a0, sp, 64
; RV32-NEXT: vs8r.v v8, (a0)
; RV32-NEXT: csrr a1, vlenb
; RV32-NEXT: slli a2, a1, 3
; RV32-NEXT: add a2, a0, a2
; RV32-NEXT: vs8r.v v16, (a2)
; RV32-NEXT: slli a1, a1, 4
; RV32-NEXT: add a0, a1, a0
; RV32-NEXT: fld fa0, -8(a0)
; RV32-NEXT: addi sp, s0, -80
; RV32-NEXT: lw ra, 76(sp) # 4-byte Folded Reload
; RV32-NEXT: lw s0, 72(sp) # 4-byte Folded Reload
; RV32-NEXT: addi sp, sp, 80
; RV32-NEXT: ret
;
; RV64-LABEL: extractelt_nxv16f64_neg1:
; RV64: # %bb.0:
; RV64-NEXT: addi sp, sp, -80
; RV64-NEXT: .cfi_def_cfa_offset 80
; RV64-NEXT: sd ra, 72(sp) # 8-byte Folded Spill
; RV64-NEXT: sd s0, 64(sp) # 8-byte Folded Spill
; RV64-NEXT: .cfi_offset ra, -8
; RV64-NEXT: .cfi_offset s0, -16
; RV64-NEXT: addi s0, sp, 80
; RV64-NEXT: .cfi_def_cfa s0, 0
; RV64-NEXT: csrr a0, vlenb
; RV64-NEXT: slli a0, a0, 4
; RV64-NEXT: sub sp, sp, a0
; RV64-NEXT: andi sp, sp, -64
; RV64-NEXT: addi a0, sp, 64
; RV64-NEXT: vs8r.v v8, (a0)
; RV64-NEXT: csrr a2, vlenb
; RV64-NEXT: slli a1, a2, 3
; RV64-NEXT: add a3, a0, a1
; RV64-NEXT: li a1, -1
; RV64-NEXT: srli a1, a1, 32
; RV64-NEXT: slli a2, a2, 1
; RV64-NEXT: addi a2, a2, -1
; RV64-NEXT: vs8r.v v16, (a3)
; RV64-NEXT: bltu a2, a1, .LBB52_2
; RV64-NEXT: # %bb.1:
; RV64-NEXT: mv a2, a1
; RV64-NEXT: .LBB52_2:
; RV64-NEXT: slli a2, a2, 3
; RV64-NEXT: add a0, a0, a2
; RV64-NEXT: fld fa0, 0(a0)
; RV64-NEXT: addi sp, s0, -80
; RV64-NEXT: ld ra, 72(sp) # 8-byte Folded Reload
; RV64-NEXT: ld s0, 64(sp) # 8-byte Folded Reload
; RV64-NEXT: addi sp, sp, 80
; RV64-NEXT: ret
%r = extractelement <vscale x 16 x double> %v, i32 -1
ret double %r
}
define double @extractelt_nxv16f64_imm(<vscale x 16 x double> %v) {
; CHECK-LABEL: extractelt_nxv16f64_imm:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e64, m2, ta, ma
; CHECK-NEXT: vslidedown.vi v8, v8, 2
; CHECK-NEXT: vfmv.f.s fa0, v8
; CHECK-NEXT: ret
%r = extractelement <vscale x 16 x double> %v, i32 2
ret double %r
}
define double @extractelt_nxv16f64_idx(<vscale x 16 x double> %v, i32 zeroext %idx) {
; RV32-LABEL: extractelt_nxv16f64_idx:
; RV32: # %bb.0:
; RV32-NEXT: csrr a1, vlenb
; RV32-NEXT: slli a2, a1, 1
; RV32-NEXT: addi a2, a2, -1
; RV32-NEXT: bltu a0, a2, .LBB54_2
; RV32-NEXT: # %bb.1:
; RV32-NEXT: mv a0, a2
; RV32-NEXT: .LBB54_2:
; RV32-NEXT: addi sp, sp, -80
; RV32-NEXT: .cfi_def_cfa_offset 80
; RV32-NEXT: sw ra, 76(sp) # 4-byte Folded Spill
; RV32-NEXT: sw s0, 72(sp) # 4-byte Folded Spill
; RV32-NEXT: .cfi_offset ra, -4
; RV32-NEXT: .cfi_offset s0, -8
; RV32-NEXT: addi s0, sp, 80
; RV32-NEXT: .cfi_def_cfa s0, 0
; RV32-NEXT: csrr a2, vlenb
; RV32-NEXT: slli a2, a2, 4
; RV32-NEXT: sub sp, sp, a2
; RV32-NEXT: andi sp, sp, -64
; RV32-NEXT: slli a0, a0, 3
; RV32-NEXT: addi a2, sp, 64
; RV32-NEXT: add a0, a2, a0
; RV32-NEXT: vs8r.v v8, (a2)
; RV32-NEXT: slli a1, a1, 3
; RV32-NEXT: add a1, a2, a1
; RV32-NEXT: vs8r.v v16, (a1)
; RV32-NEXT: fld fa0, 0(a0)
; RV32-NEXT: addi sp, s0, -80
; RV32-NEXT: lw ra, 76(sp) # 4-byte Folded Reload
; RV32-NEXT: lw s0, 72(sp) # 4-byte Folded Reload
; RV32-NEXT: addi sp, sp, 80
; RV32-NEXT: ret
;
; RV64-LABEL: extractelt_nxv16f64_idx:
; RV64: # %bb.0:
; RV64-NEXT: csrr a1, vlenb
; RV64-NEXT: slli a2, a1, 1
; RV64-NEXT: addi a2, a2, -1
; RV64-NEXT: bltu a0, a2, .LBB54_2
; RV64-NEXT: # %bb.1:
; RV64-NEXT: mv a0, a2
; RV64-NEXT: .LBB54_2:
; RV64-NEXT: addi sp, sp, -80
; RV64-NEXT: .cfi_def_cfa_offset 80
; RV64-NEXT: sd ra, 72(sp) # 8-byte Folded Spill
; RV64-NEXT: sd s0, 64(sp) # 8-byte Folded Spill
; RV64-NEXT: .cfi_offset ra, -8
; RV64-NEXT: .cfi_offset s0, -16
; RV64-NEXT: addi s0, sp, 80
; RV64-NEXT: .cfi_def_cfa s0, 0
; RV64-NEXT: csrr a2, vlenb
; RV64-NEXT: slli a2, a2, 4
; RV64-NEXT: sub sp, sp, a2
; RV64-NEXT: andi sp, sp, -64
; RV64-NEXT: slli a0, a0, 3
; RV64-NEXT: addi a2, sp, 64
; RV64-NEXT: add a0, a2, a0
; RV64-NEXT: vs8r.v v8, (a2)
; RV64-NEXT: slli a1, a1, 3
; RV64-NEXT: add a1, a2, a1
; RV64-NEXT: vs8r.v v16, (a1)
; RV64-NEXT: fld fa0, 0(a0)
; RV64-NEXT: addi sp, s0, -80
; RV64-NEXT: ld ra, 72(sp) # 8-byte Folded Reload
; RV64-NEXT: ld s0, 64(sp) # 8-byte Folded Reload
; RV64-NEXT: addi sp, sp, 80
; RV64-NEXT: ret
%r = extractelement <vscale x 16 x double> %v, i32 %idx
ret double %r
}
Codebase Browser
llvm