maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[AArch64][SVE] Implement int_aarch64_sve_cnt intrinsic 

Summary: This patch includes tests for the VecOfBitcastsToInt type added by D68021

Reviewers: c-rhodes, sdesmalen, rovka

Reviewed By: c-rhodes

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

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D68023

llvm-svn: 373468
This commit is contained in:
Kerry McLaughlin 2019-10-02 13:09:54 +00:00
parent b635964abc
commit 822b298958
4 changed files with 112 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
llvm/include/llvm/IR/IntrinsicsAArch64.td
View File

@ -768,6 +768,13 @@ let TargetPrefix = "aarch64" in { // All intrinsics start with "llvm.aarch64.".
LLVMMatchType<0>],
[IntrNoMem]>;
class AdvSIMD_SVE_CNT_Intrinsic
: Intrinsic<[LLVMVectorOfBitcastsToInt<0>],
[LLVMVectorOfBitcastsToInt<0>,
LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
llvm_anyvector_ty],
[IntrNoMem]>;
class AdvSIMD_SVE_PUNPKHI_Intrinsic
: Intrinsic<[LLVMHalfElementsVectorType<0>],
[llvm_anyvector_ty],
@ -792,6 +799,12 @@ let TargetPrefix = "aarch64" in { // All intrinsics start with "llvm.aarch64.".
def int_aarch64_sve_abs : AdvSIMD_Merged1VectorArg_Intrinsic;
def int_aarch64_sve_neg : AdvSIMD_Merged1VectorArg_Intrinsic;
//
// Counting bits
//
def int_aarch64_sve_cnt : AdvSIMD_SVE_CNT_Intrinsic;
//
// Floating-point comparisons
//

10
llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td
View File

@ -97,11 +97,11 @@ let Predicates = [HasSVE] in {
defm ABS_ZPmZ : sve_int_un_pred_arit_0< 0b110, "abs", int_aarch64_sve_abs>;
defm NEG_ZPmZ : sve_int_un_pred_arit_0< 0b111, "neg", int_aarch64_sve_neg>;
defm CLS_ZPmZ : sve_int_un_pred_arit_1< 0b000, "cls">;
defm CLZ_ZPmZ : sve_int_un_pred_arit_1< 0b001, "clz">;
defm CNT_ZPmZ : sve_int_un_pred_arit_1< 0b010, "cnt">;
defm CNOT_ZPmZ : sve_int_un_pred_arit_1< 0b011, "cnot">;
defm NOT_ZPmZ : sve_int_un_pred_arit_1< 0b110, "not">;
defm CLS_ZPmZ : sve_int_un_pred_arit_1< 0b000, "cls", null_frag>;
defm CLZ_ZPmZ : sve_int_un_pred_arit_1< 0b001, "clz", null_frag>;
defm CNT_ZPmZ : sve_int_un_pred_arit_1< 0b010, "cnt", int_aarch64_sve_cnt>;
defm CNOT_ZPmZ : sve_int_un_pred_arit_1< 0b011, "cnot", null_frag>;
defm NOT_ZPmZ : sve_int_un_pred_arit_1< 0b110, "not", null_frag>;
defm FABS_ZPmZ : sve_int_un_pred_arit_1_fp<0b100, "fabs">;
defm FNEG_ZPmZ : sve_int_un_pred_arit_1_fp<0b101, "fneg">;

12
llvm/lib/Target/AArch64/SVEInstrFormats.td
View File

@ -2876,11 +2876,21 @@ multiclass sve_int_un_pred_arit_0_d<bits<3> opc, string asm> {
def _D : sve_int_un_pred_arit<0b11, { opc, 0b0 }, asm, ZPR64>;
}
multiclass sve_int_un_pred_arit_1<bits<3> opc, string asm> {
multiclass sve_int_un_pred_arit_1<bits<3> opc, string asm,
SDPatternOperator op> {
def _B : sve_int_un_pred_arit<0b00, { opc, 0b1 }, asm, ZPR8>;
def _H : sve_int_un_pred_arit<0b01, { opc, 0b1 }, asm, ZPR16>;
def _S : sve_int_un_pred_arit<0b10, { opc, 0b1 }, asm, ZPR32>;
def _D : sve_int_un_pred_arit<0b11, { opc, 0b1 }, asm, ZPR64>;
def : SVE_3_Op_Pat<nxv16i8, op, nxv16i8, nxv16i1, nxv16i8, !cast<Instruction>(NAME # _B)>;
def : SVE_3_Op_Pat<nxv8i16, op, nxv8i16, nxv8i1, nxv8i16, !cast<Instruction>(NAME # _H)>;
def : SVE_3_Op_Pat<nxv4i32, op, nxv4i32, nxv4i1, nxv4i32, !cast<Instruction>(NAME # _S)>;
def : SVE_3_Op_Pat<nxv2i64, op, nxv2i64, nxv2i1, nxv2i64, !cast<Instruction>(NAME # _D)>;
def : SVE_3_Op_Pat<nxv8i16, op, nxv8i16, nxv8i1, nxv8f16, !cast<Instruction>(NAME # _H)>;
def : SVE_3_Op_Pat<nxv4i32, op, nxv4i32, nxv4i1, nxv4f32, !cast<Instruction>(NAME # _S)>;
def : SVE_3_Op_Pat<nxv2i64, op, nxv2i64, nxv2i1, nxv2f64, !cast<Instruction>(NAME # _D)>;
}
multiclass sve_int_un_pred_arit_1_fp<bits<3> opc, string asm> {

83
llvm/test/CodeGen/AArch64/sve-intrinsics-counting-bits.ll Normal file
View File

@ -0,0 +1,83 @@
; 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>)