1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-23 11:13:28 +01:00
llvm-mirror/test/CodeGen/AArch64/sve2-intrinsics-widening-pairwise-arith.ll
Kerry McLaughlin 163db16495 [AArch64][SVE] Add SVE2 intrinsics for pairwise arithmetic
Summary:
Implements the following intrinsics:
 - addp
 - smaxp, sminp, umaxp & uminp
 - sadalp & uadalp

Reviewers: dancgr, efriedma, sdesmalen, c-rhodes

Reviewed By: c-rhodes

Subscribers: tschuett, kristof.beyls, hiraditya, rkruppe, psnobl, cameron.mcinally, cfe-commits, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D73347
2020-01-29 10:31:31 +00:00

78 lines
3.6 KiB
LLVM

; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve2 < %s | FileCheck %s
;
; SADALP
;
define <vscale x 8 x i16> @sadalp_i8(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 16 x i8> %b) {
; CHECK-LABEL: sadalp_i8:
; CHECK: sadalp z0.h, p0/m, z1.b
; CHECK-NEXT: ret
%out = call <vscale x 8 x i16> @llvm.aarch64.sve.sadalp.nxv8i16(<vscale x 8 x i1> %pg,
<vscale x 8 x i16> %a,
<vscale x 16 x i8> %b)
ret <vscale x 8 x i16> %out
}
define <vscale x 4 x i32> @sadalp_i16(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 8 x i16> %b) {
; CHECK-LABEL: sadalp_i16:
; CHECK: sadalp z0.s, p0/m, z1.h
; CHECK-NEXT: ret
%out = call <vscale x 4 x i32> @llvm.aarch64.sve.sadalp.nxv4i32(<vscale x 4 x i1> %pg,
<vscale x 4 x i32> %a,
<vscale x 8 x i16> %b)
ret <vscale x 4 x i32> %out
}
define <vscale x 2 x i64> @sadalp_i32(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 4 x i32> %b) {
; CHECK-LABEL: sadalp_i32:
; CHECK: sadalp z0.d, p0/m, z1.s
; CHECK-NEXT: ret
%out = call <vscale x 2 x i64> @llvm.aarch64.sve.sadalp.nxv2i64(<vscale x 2 x i1> %pg,
<vscale x 2 x i64> %a,
<vscale x 4 x i32> %b)
ret <vscale x 2 x i64> %out
}
;
; UADALP
;
define <vscale x 8 x i16> @uadalp_i8(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 16 x i8> %b) {
; CHECK-LABEL: uadalp_i8:
; CHECK: uadalp z0.h, p0/m, z1.b
; CHECK-NEXT: ret
%out = call <vscale x 8 x i16> @llvm.aarch64.sve.uadalp.nxv8i16(<vscale x 8 x i1> %pg,
<vscale x 8 x i16> %a,
<vscale x 16 x i8> %b)
ret <vscale x 8 x i16> %out
}
define <vscale x 4 x i32> @uadalp_i16(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 8 x i16> %b) {
; CHECK-LABEL: uadalp_i16:
; CHECK: uadalp z0.s, p0/m, z1.h
; CHECK-NEXT: ret
%out = call <vscale x 4 x i32> @llvm.aarch64.sve.uadalp.nxv4i32(<vscale x 4 x i1> %pg,
<vscale x 4 x i32> %a,
<vscale x 8 x i16> %b)
ret <vscale x 4 x i32> %out
}
define <vscale x 2 x i64> @uadalp_i32(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 4 x i32> %b) {
; CHECK-LABEL: uadalp_i32:
; CHECK: uadalp z0.d, p0/m, z1.s
; CHECK-NEXT: ret
%out = call <vscale x 2 x i64> @llvm.aarch64.sve.uadalp.nxv2i64(<vscale x 2 x i1> %pg,
<vscale x 2 x i64> %a,
<vscale x 4 x i32> %b)
ret <vscale x 2 x i64> %out
}
declare <vscale x 8 x i16> @llvm.aarch64.sve.sadalp.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 16 x i8>)
declare <vscale x 4 x i32> @llvm.aarch64.sve.sadalp.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 8 x i16>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.sadalp.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, <vscale x 4 x i32>)
declare <vscale x 8 x i16> @llvm.aarch64.sve.uadalp.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 16 x i8>)
declare <vscale x 4 x i32> @llvm.aarch64.sve.uadalp.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 8 x i16>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.uadalp.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, <vscale x 4 x i32>)