llvm.org GIT mirror llvm / master test / CodeGen / AArch64 / sve-intrinsics-counting-bits.ll
master

Tree @master (Download .tar.gz)

sve-intrinsics-counting-bits.ll @masterraw · history · blame

; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve < %s | FileCheck %s

;
; CNT
;

define <vscale x 16 x i8> @cnt_i8(<vscale x 16 x i8> %a, <vscale x 16 x i1> %pg, <vscale x 16 x i8> %b) {
; CHECK-LABEL: cnt_i8:
; CHECK: cnt z0.b, p0/m, z1.b
; CHECK-NEXT: ret
  %out = call <vscale x 16 x i8> @llvm.aarch64.sve.cnt.nxv16i8(<vscale x 16 x i8> %a,
                                                               <vscale x 16 x i1> %pg,
                                                               <vscale x 16 x i8> %b)
  ret <vscale x 16 x i8> %out
}

define <vscale x 8 x i16> @cnt_i16(<vscale x 8 x i16> %a, <vscale x 8 x i1> %pg, <vscale x 8 x i16> %b) {
; CHECK-LABEL: cnt_i16:
; CHECK: cnt z0.h, p0/m, z1.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.cnt.nxv8i16(<vscale x 8 x i16> %a,
                                                               <vscale x 8 x i1> %pg,
                                                               <vscale x 8 x i16> %b)
  ret <vscale x 8 x i16> %out
}

define <vscale x 4 x i32> @cnt_i32(<vscale x 4 x i32> %a, <vscale x 4 x i1> %pg, <vscale x 4 x i32> %b) {
; CHECK-LABEL: cnt_i32:
; CHECK: cnt z0.s, p0/m, z1.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.cnt.nxv4i32(<vscale x 4 x i32> %a,
                                                               <vscale x 4 x i1> %pg,
                                                               <vscale x 4 x i32> %b)
  ret <vscale x 4 x i32> %out
}

define <vscale x 2 x i64> @cnt_i64(<vscale x 2 x i64> %a, <vscale x 2 x i1> %pg, <vscale x 2 x i64> %b) {
; CHECK-LABEL: cnt_i64:
; CHECK: cnt z0.d, p0/m, z1.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.cnt.nxv2i64(<vscale x 2 x i64> %a,
                                                               <vscale x 2 x i1> %pg,
                                                               <vscale x 2 x i64> %b)
  ret <vscale x 2 x i64> %out
}

define <vscale x 8 x i16> @cnt_f16(<vscale x 8 x i16> %a, <vscale x 8 x i1> %pg, <vscale x 8 x half> %b) {
; CHECK-LABEL: cnt_f16:
; CHECK: cnt z0.h, p0/m, z1.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.cnt.nxv8f16(<vscale x 8 x i16> %a,
                                                               <vscale x 8 x i1> %pg,
                                                               <vscale x 8 x half> %b)
  ret <vscale x 8 x i16> %out
}

define <vscale x 4 x i32> @cnt_f32(<vscale x 4 x i32> %a, <vscale x 4 x i1> %pg, <vscale x 4 x float> %b) {
; CHECK-LABEL: cnt_f32:
; CHECK: cnt z0.s, p0/m, z1.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.cnt.nxv4f32(<vscale x 4 x i32> %a,
                                                               <vscale x 4 x i1> %pg,
                                                               <vscale x 4 x float> %b)
  ret <vscale x 4 x i32> %out
}

define <vscale x 2 x i64> @cnt_f64(<vscale x 2 x i64> %a, <vscale x 2 x i1> %pg, <vscale x 2 x double> %b) {
; CHECK-LABEL: cnt_f64:
; CHECK: cnt z0.d, p0/m, z1.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.cnt.nxv2f64(<vscale x 2 x i64> %a,
                                                               <vscale x 2 x i1> %pg,
                                                               <vscale x 2 x double> %b)
  ret <vscale x 2 x i64> %out
}

declare <vscale x 16 x i8> @llvm.aarch64.sve.cnt.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i1>, <vscale x 16 x i8>)
declare <vscale x 8 x i16> @llvm.aarch64.sve.cnt.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i1>, <vscale x 8 x i16>)
declare <vscale x 4 x i32> @llvm.aarch64.sve.cnt.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i1>, <vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.cnt.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i1>, <vscale x 2 x i64>)
declare <vscale x 8 x i16> @llvm.aarch64.sve.cnt.nxv8f16(<vscale x 8 x i16>, <vscale x 8 x i1>, <vscale x 8 x half>)
declare <vscale x 4 x i32> @llvm.aarch64.sve.cnt.nxv4f32(<vscale x 4 x i32>, <vscale x 4 x i1>, <vscale x 4 x float>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.cnt.nxv2f64(<vscale x 2 x i64>, <vscale x 2 x i1>, <vscale x 2 x double>)