Magic-Mirror/llvm-capstone
1
0
Fork 0
mirror of https://github.com/capstone-engine/llvm-capstone.git synced 2025-02-18 08:49:55 +00:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[AArch64][SVE] Add the @llvm.aarch64.sve.sel intrinsic

Browse Source 
Reviewers: sdesmalen, efriedma

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

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D75928
This commit is contained in:
Andrzej Warzynski 2020-03-10 15:40:40 +00:00
parent e671641844
commit a9f1583228
3 changed files with 98 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
llvm/include/llvm/IR/IntrinsicsAArch64.td
View File

@ -1498,6 +1498,7 @@ def int_aarch64_sve_clastb_n : AdvSIMD_SVE_ReduceWithInit_Intrinsic;
def int_aarch64_sve_compact : AdvSIMD_Pred1VectorArg_Intrinsic;
def int_aarch64_sve_dupq_lane : AdvSIMD_SVE_DUPQ_Intrinsic;
def int_aarch64_sve_ext : AdvSIMD_2VectorArgIndexed_Intrinsic;
def int_aarch64_sve_sel : AdvSIMD_Pred2VectorArg_Intrinsic;
def int_aarch64_sve_lasta : AdvSIMD_SVE_Reduce_Intrinsic;
def int_aarch64_sve_lastb : AdvSIMD_SVE_Reduce_Intrinsic;
def int_aarch64_sve_rev : AdvSIMD_1VectorArg_Intrinsic;

3
llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
View File

@ -11296,6 +11296,9 @@ static SDValue performIntrinsicCombine(SDNode *N,
return LowerSVEIntrinsicDUP(N, DAG);
case Intrinsic::aarch64_sve_ext:
return LowerSVEIntrinsicEXT(N, DAG);
case Intrinsic::aarch64_sve_sel:
return DAG.getNode(ISD::VSELECT, SDLoc(N), N->getValueType(0),
N->getOperand(1), N->getOperand(2), N->getOperand(3));
case Intrinsic::aarch64_sve_cmpeq_wide:
return tryConvertSVEWideCompare(N, Intrinsic::aarch64_sve_cmpeq,
false, DCI, DAG);

94
llvm/test/CodeGen/AArch64/sve-intrinsics-sel.ll Normal file
View File

@ -0,0 +1,94 @@
; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve < %s | FileCheck %s
;
; SEL (Vectors)
;
define <vscale x 16 x i1> @sel_i1(<vscale x 16 x i1> %pg, <vscale x 16 x i1> %a, <vscale x 16 x i1> %b) {
; CHECK-LABEL: sel_i1:
; CHECK: sel p0.b, p0, p1.b, p2.b
; CHECK-NEXT: ret
%out = call <vscale x 16 x i1> @llvm.aarch64.sve.sel.nxv16i1(<vscale x 16 x i1> %pg,
<vscale x 16 x i1> %a,
<vscale x 16 x i1> %b)
ret <vscale x 16 x i1> %out
}
define <vscale x 16 x i8> @sel_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
; CHECK-LABEL: sel_i8:
; CHECK: sel z0.b, p0, z0.b, z1.b
; CHECK-NEXT: ret
%out = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> %pg,
<vscale x 16 x i8> %a,
<vscale x 16 x i8> %b)
ret <vscale x 16 x i8> %out
}
define <vscale x 8 x i16> @sel_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
; CHECK-LABEL: sel_i16:
; CHECK: sel z0.h, p0, z0.h, z1.h
; CHECK-NEXT: ret
%out = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> %pg,
<vscale x 8 x i16> %a,
<vscale x 8 x i16> %b)
ret <vscale x 8 x i16> %out
}
define <vscale x 4 x i32> @sel_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
; CHECK-LABEL: sel_i32:
; CHECK: sel z0.s, p0, z0.s, z1.s
; CHECK-NEXT: ret
%out = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> %pg,
<vscale x 4 x i32> %a,
<vscale x 4 x i32> %b)
ret <vscale x 4 x i32> %out
}
define <vscale x 2 x i64> @sel_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
; CHECK-LABEL: sel_i64:
; CHECK: sel z0.d, p0, z0.d, z1.d
; CHECK-NEXT: ret
%out = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> %pg,
<vscale x 2 x i64> %a,
<vscale x 2 x i64> %b)
ret <vscale x 2 x i64> %out
}
define <vscale x 8 x half> @sel_f16(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b) {
; CHECK-LABEL: sel_f16:
; CHECK: sel z0.h, p0, z0.h, z1.h
; CHECK-NEXT: ret
%out = call <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1> %pg,
<vscale x 8 x half> %a,
<vscale x 8 x half> %b)
ret <vscale x 8 x half> %out
}
define <vscale x 4 x float> @sel_f32(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b) {
; CHECK-LABEL: sel_f32:
; CHECK: sel z0.s, p0, z0.s, z1.s
; CHECK-NEXT: ret
%out = call <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1> %pg,
<vscale x 4 x float> %a,
<vscale x 4 x float> %b)
ret <vscale x 4 x float> %out
}
define <vscale x 2 x double> @sel_f64(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b) {
; CHECK-LABEL: sel_f64:
; CHECK: sel z0.d, p0, z0.d, z1.d
; CHECK-NEXT: ret
%out = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> %pg,
<vscale x 2 x double> %a,
<vscale x 2 x double> %b)
ret <vscale x 2 x double> %out
}
declare <vscale x 16 x i1> @llvm.aarch64.sve.sel.nxv16i1(<vscale x 16 x i1>, <vscale x 16 x i1>, <vscale x 16 x i1>)
declare <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 16 x i8>)
declare <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>)
declare <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, <vscale x 2 x i64>)
declare <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)