maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/AArch64/sve-intrinsics-reversal.ll

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

167 lines
7.0 KiB
LLVM
Raw Normal View History

[AArch64][SVE] Implement reversal intrinsics Summary: Adds intrinsics for the following: * rbit * revb * revh * revw Patterns are also defined to map the 'llvm.bswap.*' intrinsic to the SVE revb instruction. Reviewers: sdesmalen, huntergr, dancgr, rengolin, efriedma, rovka Reviewed By: sdesmalen Subscribers: tschuett, kristof.beyls, hiraditya, rkruppe, psnobl, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D70960
2019-12-04 19:36:30 +08:00
; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve < %s | FileCheck %s
;
; RBIT
;
define <vscale x 16 x i8> @rbit_i8(<vscale x 16 x i8> %a, <vscale x 16 x i1> %pg, <vscale x 16 x i8> %b) {
; CHECK-LABEL: rbit_i8:
; CHECK: rbit z0.b, p0/m, z1.b
; CHECK-NEXT: ret
%out = call <vscale x 16 x i8> @llvm.aarch64.sve.rbit.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> @rbit_i16(<vscale x 8 x i16> %a, <vscale x 8 x i1> %pg, <vscale x 8 x i16> %b) {
; CHECK-LABEL: rbit_i16:
; CHECK: rbit z0.h, p0/m, z1.h
; CHECK-NEXT: ret
%out = call <vscale x 8 x i16> @llvm.aarch64.sve.rbit.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> @rbit_i32(<vscale x 4 x i32> %a, <vscale x 4 x i1> %pg, <vscale x 4 x i32> %b) {
; CHECK-LABEL: rbit_i32:
; CHECK: rbit z0.s, p0/m, z1.s
; CHECK-NEXT: ret
%out = call <vscale x 4 x i32> @llvm.aarch64.sve.rbit.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> @rbit_i64(<vscale x 2 x i64> %a, <vscale x 2 x i1> %pg, <vscale x 2 x i64> %b) {
; CHECK-LABEL: rbit_i64:
; CHECK: rbit z0.d, p0/m, z1.d
; CHECK-NEXT: ret
%out = call <vscale x 2 x i64> @llvm.aarch64.sve.rbit.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
}
;
; REVB
;
define <vscale x 8 x i16> @revb_i16(<vscale x 8 x i16> %a, <vscale x 8 x i1> %pg, <vscale x 8 x i16> %b) {
; CHECK-LABEL: revb_i16:
; CHECK: revb z0.h, p0/m, z1.h
; CHECK-NEXT: ret
%out = call <vscale x 8 x i16> @llvm.aarch64.sve.revb.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> @revb_i32(<vscale x 4 x i32> %a, <vscale x 4 x i1> %pg, <vscale x 4 x i32> %b) {
; CHECK-LABEL: revb_i32:
; CHECK: revb z0.s, p0/m, z1.s
; CHECK-NEXT: ret
%out = call <vscale x 4 x i32> @llvm.aarch64.sve.revb.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> @revb_i64(<vscale x 2 x i64> %a, <vscale x 2 x i1> %pg, <vscale x 2 x i64> %b) {
; CHECK-LABEL: revb_i64:
; CHECK: revb z0.d, p0/m, z1.d
; CHECK-NEXT: ret
%out = call <vscale x 2 x i64> @llvm.aarch64.sve.revb.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
}
;
; REVB (bswap)
;
define <vscale x 8 x i16> @revb_i16_bswap(<vscale x 8 x i16> %a) {
; CHECK-LABEL: revb_i16_bswap:
; CHECK: ptrue [[PG:p[0-9]+]].h
; CHECK-NEXT: revb z0.h, [[PG]]/m, z0.h
; CHECK-NEXT: ret
%res = call <vscale x 8 x i16> @llvm.bswap.nxv8i16(<vscale x 8 x i16> %a)
ret <vscale x 8 x i16> %res
}
define <vscale x 4 x i32> @revb_i32_bswap(<vscale x 4 x i32> %a) {
; CHECK-LABEL: revb_i32_bswap:
; CHECK: ptrue [[PG:p[0-9]+]].s
; CHECK-NEXT: revb z0.s, [[PG]]/m, z0.s
; CHECK-NEXT: ret
%res = call <vscale x 4 x i32> @llvm.bswap.nxv4i32(<vscale x 4 x i32> %a)
ret <vscale x 4 x i32> %res
}
define <vscale x 2 x i64> @revb_i64_bswap(<vscale x 2 x i64> %a) {
; CHECK-LABEL: revb_i64_bswap:
; CHECK: ptrue [[PG:p[0-9]+]].d
; CHECK-NEXT: revb z0.d, [[PG]]/m, z0.d
; CHECK-NEXT: ret
%res = call <vscale x 2 x i64> @llvm.bswap.nxv2i64(<vscale x 2 x i64> %a)
ret <vscale x 2 x i64> %res
}
;
; REVH
;
define <vscale x 4 x i32> @revh_i32(<vscale x 4 x i32> %a, <vscale x 4 x i1> %pg, <vscale x 4 x i32> %b) {
; CHECK-LABEL: revh_i32:
; CHECK: revh z0.s, p0/m, z1.s
; CHECK-NEXT: ret
%out = call <vscale x 4 x i32> @llvm.aarch64.sve.revh.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> @revh_i64(<vscale x 2 x i64> %a, <vscale x 2 x i1> %pg, <vscale x 2 x i64> %b) {
; CHECK-LABEL: revh_i64:
; CHECK: revh z0.d, p0/m, z1.d
; CHECK-NEXT: ret
%out = call <vscale x 2 x i64> @llvm.aarch64.sve.revh.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
}
;
; REVW
;
define <vscale x 2 x i64> @revw_i64(<vscale x 2 x i64> %a, <vscale x 2 x i1> %pg, <vscale x 2 x i64> %b) {
; CHECK-LABEL: revw_i64:
; CHECK: revw z0.d, p0/m, z1.d
; CHECK-NEXT: ret
%out = call <vscale x 2 x i64> @llvm.aarch64.sve.revw.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
}
declare <vscale x 16 x i8> @llvm.aarch64.sve.rbit.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.rbit.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.rbit.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.rbit.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.revb.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.revb.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.revb.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i1>, <vscale x 2 x i64>)
declare <vscale x 8 x i16> @llvm.bswap.nxv8i16(<vscale x 8 x i16>)
declare <vscale x 4 x i32> @llvm.bswap.nxv4i32(<vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.bswap.nxv2i64(<vscale x 2 x i64>)
declare <vscale x 4 x i32> @llvm.aarch64.sve.revh.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.revh.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i1>, <vscale x 2 x i64>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.revw.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i1>, <vscale x 2 x i64>)