Skip to content

[AArch64][SME2] Add builtins to cast svbool from/to svcount. #74720

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Dec 8, 2023
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions clang/include/clang/Basic/arm_sve.td
Original file line number Diff line number Diff line change
Expand Up @@ -2161,6 +2161,9 @@ let TargetGuard = "sme2" in {
def SVSQRSHRU_X4 : SInst<"svqrshru[_n]_{0}[_{d}_x4]", "b4i", "il", MergeNone, "aarch64_sve_sqrshru_x4", [IsStreaming], [ImmCheck<1, ImmCheckShiftRight, 0>]>;

def SVSQRSHRUN_X4 : SInst<"svqrshrun[_n]_{0}[_{d}_x4]", "b4i", "il", MergeNone, "aarch64_sve_sqrshrun_x4", [IsStreaming], [ImmCheck<1, ImmCheckShiftRight, 0>]>;

def REINTERPRET_SVBOOL_TO_SVCOUNT : Inst<"svreinterpret[_c]", "}P", "Pc", MergeNone, "", [IsStreamingCompatible], []>;
def REINTERPRET_SVCOUNT_TO_SVBOOL : Inst<"svreinterpret[_b]", "P}", "Pc", MergeNone, "", [IsStreamingCompatible], []>;
}

let TargetGuard = "sve2p1" in {
Expand Down
16 changes: 16 additions & 0 deletions clang/lib/CodeGen/CGBuiltin.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -10211,6 +10211,22 @@ Value *CodeGenFunction::EmitAArch64SVEBuiltinExpr(unsigned BuiltinID,
switch (BuiltinID) {
default:
return nullptr;

case SVE::BI__builtin_sve_svreinterpret_b: {
auto SVCountTy =
llvm::TargetExtType::get(getLLVMContext(), "aarch64.svcount");
Function *CastFromSVCountF =
CGM.getIntrinsic(Intrinsic::aarch64_sve_convert_to_svbool, SVCountTy);
return Builder.CreateCall(CastFromSVCountF, Ops[0]);
}
case SVE::BI__builtin_sve_svreinterpret_c: {
auto SVCountTy =
llvm::TargetExtType::get(getLLVMContext(), "aarch64.svcount");
Function *CastToSVCountF =
CGM.getIntrinsic(Intrinsic::aarch64_sve_convert_from_svbool, SVCountTy);
return Builder.CreateCall(CastToSVCountF, Ops[0]);
}

case SVE::BI__builtin_sve_svpsel_lane_b8:
case SVE::BI__builtin_sve_svpsel_lane_b16:
case SVE::BI__builtin_sve_svpsel_lane_b32:
Expand Down
Original file line number Diff line number Diff line change
@@ -0,0 +1,47 @@
// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py

// REQUIRES: aarch64-registered-target

// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +sve -target-feature +sme2 -S -disable-O0-optnone -Werror -Wall -emit-llvm -o - %s | opt -S -p mem2reg,instcombine,tailcallelim | FileCheck %s
// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +sve -target-feature +sme2 -S -disable-O0-optnone -Werror -Wall -emit-llvm -o - -x c++ %s | opt -S -p mem2reg,instcombine,tailcallelim | FileCheck %s -check-prefix=CPP-CHECK
// RUN: %clang_cc1 -DSVE_OVERLOADED_FORMS -triple aarch64-none-linux-gnu -target-feature +sve -target-feature +sme2 -S -disable-O0-optnone -Werror -Wall -emit-llvm -o - %s | opt -S -p mem2reg,instcombine,tailcallelim | FileCheck %s
// RUN: %clang_cc1 -DSVE_OVERLOADED_FORMS -triple aarch64-none-linux-gnu -target-feature +sve -target-feature +sme2 -S -disable-O0-optnone -Werror -Wall -emit-llvm -o - -x c++ %s | opt -S -p mem2reg,instcombine,tailcallelim | FileCheck %s -check-prefix=CPP-CHECK

#include <arm_sme_draft_spec_subject_to_change.h>

#ifdef SVE_OVERLOADED_FORMS
// A simple used,unused... macro, long enough to represent any SVE builtin.§
#define SVE_ACLE_FUNC(A1,A2_UNUSED,A3,A4_UNUSED) A1##A3
#else
#define SVE_ACLE_FUNC(A1,A2,A3,A4) A1##A2##A3##A4
#endif

// CHECK-LABEL: @test_svreinterpret_svbool_svcnt(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.taarch64.svcountt(target("aarch64.svcount") [[CNT:%.*]])
// CHECK-NEXT: ret <vscale x 16 x i1> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z31test_svreinterpret_svbool_svcntu11__SVCount_t(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.taarch64.svcountt(target("aarch64.svcount") [[CNT:%.*]])
// CPP-CHECK-NEXT: ret <vscale x 16 x i1> [[TMP0]]
//
svbool_t test_svreinterpret_svbool_svcnt(svcount_t cnt) __arm_streaming_compatible
{
return SVE_ACLE_FUNC(svreinterpret,_b,,)(cnt);
}

// CHECK-LABEL: @test_svreinterpret_svcnt_svbool(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call target("aarch64.svcount") @llvm.aarch64.sve.convert.from.svbool.taarch64.svcountt(<vscale x 16 x i1> [[PG:%.*]])
// CHECK-NEXT: ret target("aarch64.svcount") [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z31test_svreinterpret_svcnt_svboolu10__SVBool_t(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call target("aarch64.svcount") @llvm.aarch64.sve.convert.from.svbool.taarch64.svcountt(<vscale x 16 x i1> [[PG:%.*]])
// CPP-CHECK-NEXT: ret target("aarch64.svcount") [[TMP0]]
//
svcount_t test_svreinterpret_svcnt_svbool(svbool_t pg) __arm_streaming_compatible
{
return SVE_ACLE_FUNC(svreinterpret,_c,,)(pg);
}