Skip to content

[Clang][AArch64] make bitperm intrinsics available in streaming mode #129700

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.

Sign up for GitHub

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
May 2, 2025
Merged

[Clang][AArch64] make bitperm intrinsics available in streaming mode #129700

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4b7b5a0
[Clang][AArch64] update bitperm intrinsics to be available in streami…
Lukacma Mar 4, 2025
d54644a
Merge branch 'main' into sme-bitperm
Lukacma Apr 30, 2025
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
14 changes: 7 additions & 7 deletions clang/include/clang/Basic/arm_sve.td
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1990,13 +1990,13 @@ def SVSM4E : SInst<"svsm4e[_{d}]", "ddd", "Ui", MergeNone, "aarch64_sve_sm
def SVSM4EKEY : SInst<"svsm4ekey[_{d}]", "ddd", "Ui", MergeNone, "aarch64_sve_sm4ekey", [IsOverloadNone]>;
}

let SVETargetGuard = "sve2,sve-bitperm", SMETargetGuard = InvalidMode in {
def SVBDEP : SInst<"svbdep[_{d}]", "ddd", "UcUsUiUl", MergeNone, "aarch64_sve_bdep_x">;
def SVBDEP_N : SInst<"svbdep[_n_{d}]", "dda", "UcUsUiUl", MergeNone, "aarch64_sve_bdep_x">;
def SVBEXT : SInst<"svbext[_{d}]", "ddd", "UcUsUiUl", MergeNone, "aarch64_sve_bext_x">;
def SVBEXT_N : SInst<"svbext[_n_{d}]", "dda", "UcUsUiUl", MergeNone, "aarch64_sve_bext_x">;
def SVBGRP : SInst<"svbgrp[_{d}]", "ddd", "UcUsUiUl", MergeNone, "aarch64_sve_bgrp_x">;
def SVBGRP_N : SInst<"svbgrp[_n_{d}]", "dda", "UcUsUiUl", MergeNone, "aarch64_sve_bgrp_x">;
let SVETargetGuard = "sve2,sve-bitperm", SMETargetGuard = "sme,ssve-bitperm" in {
def SVBDEP : SInst<"svbdep[_{d}]", "ddd", "UcUsUiUl", MergeNone, "aarch64_sve_bdep_x", [VerifyRuntimeMode]>;
def SVBDEP_N : SInst<"svbdep[_n_{d}]", "dda", "UcUsUiUl", MergeNone, "aarch64_sve_bdep_x", [VerifyRuntimeMode]>;
def SVBEXT : SInst<"svbext[_{d}]", "ddd", "UcUsUiUl", MergeNone, "aarch64_sve_bext_x", [VerifyRuntimeMode]>;
def SVBEXT_N : SInst<"svbext[_n_{d}]", "dda", "UcUsUiUl", MergeNone, "aarch64_sve_bext_x", [VerifyRuntimeMode]>;
def SVBGRP : SInst<"svbgrp[_{d}]", "ddd", "UcUsUiUl", MergeNone, "aarch64_sve_bgrp_x", [VerifyRuntimeMode]>;
def SVBGRP_N : SInst<"svbgrp[_n_{d}]", "dda", "UcUsUiUl", MergeNone, "aarch64_sve_bgrp_x", [VerifyRuntimeMode]>;
}

let SVETargetGuard = "sve2p1", SMETargetGuard = "sme" in {
Expand Down
24 changes: 16 additions & 8 deletions clang/test/CodeGen/AArch64/sve2-intrinsics/acle_sve2_bdep.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,8 @@
// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve-bitperm -O1 -Werror -Wall -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
// RUN: %clang_cc1 -fclang-abi-compat=latest -DSVE_OVERLOADED_FORMS -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve-bitperm -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
// RUN: %clang_cc1 -fclang-abi-compat=latest -DSVE_OVERLOADED_FORMS -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve-bitperm -O1 -Werror -Wall -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
// RUN: %clang_cc1 -triple aarch64 -target-feature +sme -target-feature +ssve-bitperm -S -disable-O0-optnone -Werror -Wall -o /dev/null %s
// RUN: not %clang_cc1 -triple aarch64 -target-feature +sme -S -disable-O0-optnone -Werror -Wall -o /dev/null %s

#include <arm_sve.h>

Expand All @@ -15,6 +17,12 @@
#define SVE_ACLE_FUNC(A1,A2,A3,A4) A1##A2##A3##A4
#endif

#ifdef __ARM_FEATURE_SME
#define STREAMING __arm_streaming
#else
#define STREAMING
#endif

// CHECK-LABEL: @test_svbdep_u8(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.bdep.x.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]])
Expand All @@ -25,7 +33,7 @@
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.bdep.x.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]])
// CPP-CHECK-NEXT: ret <vscale x 16 x i8> [[TMP0]]
//
svuint8_t test_svbdep_u8(svuint8_t op1, svuint8_t op2)
svuint8_t test_svbdep_u8(svuint8_t op1, svuint8_t op2) STREAMING
{
return SVE_ACLE_FUNC(svbdep,_u8,,)(op1, op2);
}
Expand All @@ -40,7 +48,7 @@ svuint8_t test_svbdep_u8(svuint8_t op1, svuint8_t op2)
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.bdep.x.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]])
// CPP-CHECK-NEXT: ret <vscale x 8 x i16> [[TMP0]]
//
svuint16_t test_svbdep_u16(svuint16_t op1, svuint16_t op2)
svuint16_t test_svbdep_u16(svuint16_t op1, svuint16_t op2) STREAMING
{
return SVE_ACLE_FUNC(svbdep,_u16,,)(op1, op2);
}
Expand All @@ -55,7 +63,7 @@ svuint16_t test_svbdep_u16(svuint16_t op1, svuint16_t op2)
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.bdep.x.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]])
// CPP-CHECK-NEXT: ret <vscale x 4 x i32> [[TMP0]]
//
svuint32_t test_svbdep_u32(svuint32_t op1, svuint32_t op2)
svuint32_t test_svbdep_u32(svuint32_t op1, svuint32_t op2) STREAMING
{
return SVE_ACLE_FUNC(svbdep,_u32,,)(op1, op2);
}
Expand All @@ -70,7 +78,7 @@ svuint32_t test_svbdep_u32(svuint32_t op1, svuint32_t op2)
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.bdep.x.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]])
// CPP-CHECK-NEXT: ret <vscale x 2 x i64> [[TMP0]]
//
svuint64_t test_svbdep_u64(svuint64_t op1, svuint64_t op2)
svuint64_t test_svbdep_u64(svuint64_t op1, svuint64_t op2) STREAMING
{
return SVE_ACLE_FUNC(svbdep,_u64,,)(op1, op2);
}
Expand All @@ -89,7 +97,7 @@ svuint64_t test_svbdep_u64(svuint64_t op1, svuint64_t op2)
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.bdep.x.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[DOTSPLAT]])
// CPP-CHECK-NEXT: ret <vscale x 16 x i8> [[TMP0]]
//
svuint8_t test_svbdep_n_u8(svuint8_t op1, uint8_t op2)
svuint8_t test_svbdep_n_u8(svuint8_t op1, uint8_t op2) STREAMING
{
return SVE_ACLE_FUNC(svbdep,_n_u8,,)(op1, op2);
}
Expand All @@ -108,7 +116,7 @@ svuint8_t test_svbdep_n_u8(svuint8_t op1, uint8_t op2)
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.bdep.x.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[DOTSPLAT]])
// CPP-CHECK-NEXT: ret <vscale x 8 x i16> [[TMP0]]
//
svuint16_t test_svbdep_n_u16(svuint16_t op1, uint16_t op2)
svuint16_t test_svbdep_n_u16(svuint16_t op1, uint16_t op2) STREAMING
{
return SVE_ACLE_FUNC(svbdep,_n_u16,,)(op1, op2);
}
Expand All @@ -127,7 +135,7 @@ svuint16_t test_svbdep_n_u16(svuint16_t op1, uint16_t op2)
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.bdep.x.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[DOTSPLAT]])
// CPP-CHECK-NEXT: ret <vscale x 4 x i32> [[TMP0]]
//
svuint32_t test_svbdep_n_u32(svuint32_t op1, uint32_t op2)
svuint32_t test_svbdep_n_u32(svuint32_t op1, uint32_t op2) STREAMING
{
return SVE_ACLE_FUNC(svbdep,_n_u32,,)(op1, op2);
}
Expand All @@ -146,7 +154,7 @@ svuint32_t test_svbdep_n_u32(svuint32_t op1, uint32_t op2)
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.bdep.x.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[DOTSPLAT]])
// CPP-CHECK-NEXT: ret <vscale x 2 x i64> [[TMP0]]
//
svuint64_t test_svbdep_n_u64(svuint64_t op1, uint64_t op2)
svuint64_t test_svbdep_n_u64(svuint64_t op1, uint64_t op2) STREAMING
{
return SVE_ACLE_FUNC(svbdep,_n_u64,,)(op1, op2);
}
24 changes: 16 additions & 8 deletions clang/test/CodeGen/AArch64/sve2-intrinsics/acle_sve2_bext.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,8 @@
// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve-bitperm -O1 -Werror -Wall -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
// RUN: %clang_cc1 -fclang-abi-compat=latest -DSVE_OVERLOADED_FORMS -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve-bitperm -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
// RUN: %clang_cc1 -fclang-abi-compat=latest -DSVE_OVERLOADED_FORMS -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve-bitperm -O1 -Werror -Wall -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
// RUN: %clang_cc1 -triple aarch64 -target-feature +sme -target-feature +ssve-bitperm -S -disable-O0-optnone -Werror -Wall -o /dev/null %s
// RUN: not %clang_cc1 -triple aarch64 -target-feature +sme -S -disable-O0-optnone -Werror -Wall -o /dev/null %s

#include <arm_sve.h>

Expand All @@ -15,6 +17,12 @@
#define SVE_ACLE_FUNC(A1,A2,A3,A4) A1##A2##A3##A4
#endif

#ifdef __ARM_FEATURE_SME
#define STREAMING __arm_streaming
#else
#define STREAMING
#endif

// CHECK-LABEL: @test_svbext_u8(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.bext.x.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]])
Expand All @@ -25,7 +33,7 @@
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.bext.x.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]])
// CPP-CHECK-NEXT: ret <vscale x 16 x i8> [[TMP0]]
//
svuint8_t test_svbext_u8(svuint8_t op1, svuint8_t op2)
svuint8_t test_svbext_u8(svuint8_t op1, svuint8_t op2) STREAMING
{
return SVE_ACLE_FUNC(svbext,_u8,,)(op1, op2);
}
Expand All @@ -40,7 +48,7 @@ svuint8_t test_svbext_u8(svuint8_t op1, svuint8_t op2)
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.bext.x.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]])
// CPP-CHECK-NEXT: ret <vscale x 8 x i16> [[TMP0]]
//
svuint16_t test_svbext_u16(svuint16_t op1, svuint16_t op2)
svuint16_t test_svbext_u16(svuint16_t op1, svuint16_t op2) STREAMING
{
return SVE_ACLE_FUNC(svbext,_u16,,)(op1, op2);
}
Expand All @@ -55,7 +63,7 @@ svuint16_t test_svbext_u16(svuint16_t op1, svuint16_t op2)
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.bext.x.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]])
// CPP-CHECK-NEXT: ret <vscale x 4 x i32> [[TMP0]]
//
svuint32_t test_svbext_u32(svuint32_t op1, svuint32_t op2)
svuint32_t test_svbext_u32(svuint32_t op1, svuint32_t op2) STREAMING
{
return SVE_ACLE_FUNC(svbext,_u32,,)(op1, op2);
}
Expand All @@ -70,7 +78,7 @@ svuint32_t test_svbext_u32(svuint32_t op1, svuint32_t op2)
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.bext.x.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]])
// CPP-CHECK-NEXT: ret <vscale x 2 x i64> [[TMP0]]
//
svuint64_t test_svbext_u64(svuint64_t op1, svuint64_t op2)
svuint64_t test_svbext_u64(svuint64_t op1, svuint64_t op2) STREAMING
{
return SVE_ACLE_FUNC(svbext,_u64,,)(op1, op2);
}
Expand All @@ -89,7 +97,7 @@ svuint64_t test_svbext_u64(svuint64_t op1, svuint64_t op2)
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.bext.x.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[DOTSPLAT]])
// CPP-CHECK-NEXT: ret <vscale x 16 x i8> [[TMP0]]
//
svuint8_t test_svbext_n_u8(svuint8_t op1, uint8_t op2)
svuint8_t test_svbext_n_u8(svuint8_t op1, uint8_t op2) STREAMING
{
return SVE_ACLE_FUNC(svbext,_n_u8,,)(op1, op2);
}
Expand All @@ -108,7 +116,7 @@ svuint8_t test_svbext_n_u8(svuint8_t op1, uint8_t op2)
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.bext.x.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[DOTSPLAT]])
// CPP-CHECK-NEXT: ret <vscale x 8 x i16> [[TMP0]]
//
svuint16_t test_svbext_n_u16(svuint16_t op1, uint16_t op2)
svuint16_t test_svbext_n_u16(svuint16_t op1, uint16_t op2) STREAMING
{
return SVE_ACLE_FUNC(svbext,_n_u16,,)(op1, op2);
}
Expand All @@ -127,7 +135,7 @@ svuint16_t test_svbext_n_u16(svuint16_t op1, uint16_t op2)
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.bext.x.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[DOTSPLAT]])
// CPP-CHECK-NEXT: ret <vscale x 4 x i32> [[TMP0]]
//
svuint32_t test_svbext_n_u32(svuint32_t op1, uint32_t op2)
svuint32_t test_svbext_n_u32(svuint32_t op1, uint32_t op2) STREAMING
{
return SVE_ACLE_FUNC(svbext,_n_u32,,)(op1, op2);
}
Expand All @@ -146,7 +154,7 @@ svuint32_t test_svbext_n_u32(svuint32_t op1, uint32_t op2)
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.bext.x.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[DOTSPLAT]])
// CPP-CHECK-NEXT: ret <vscale x 2 x i64> [[TMP0]]
//
svuint64_t test_svbext_n_u64(svuint64_t op1, uint64_t op2)
svuint64_t test_svbext_n_u64(svuint64_t op1, uint64_t op2) STREAMING
{
return SVE_ACLE_FUNC(svbext,_n_u64,,)(op1, op2);
}
24 changes: 16 additions & 8 deletions clang/test/CodeGen/AArch64/sve2-intrinsics/acle_sve2_bgrp.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,8 @@
// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve-bitperm -O1 -Werror -Wall -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
// RUN: %clang_cc1 -fclang-abi-compat=latest -DSVE_OVERLOADED_FORMS -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve-bitperm -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
// RUN: %clang_cc1 -fclang-abi-compat=latest -DSVE_OVERLOADED_FORMS -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve-bitperm -O1 -Werror -Wall -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
// RUN: %clang_cc1 -triple aarch64 -target-feature +sme -target-feature +ssve-bitperm -S -disable-O0-optnone -Werror -Wall -o /dev/null %s
// RUN: not %clang_cc1 -triple aarch64 -target-feature +sme -S -disable-O0-optnone -Werror -Wall -o /dev/null %s

#include <arm_sve.h>

Expand All @@ -15,6 +17,12 @@
#define SVE_ACLE_FUNC(A1,A2,A3,A4) A1##A2##A3##A4
#endif

#ifdef __ARM_FEATURE_SME
#define STREAMING __arm_streaming
#else
#define STREAMING
#endif

// CHECK-LABEL: @test_svbgrp_u8(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.bgrp.x.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]])
Expand All @@ -25,7 +33,7 @@
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.bgrp.x.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]])
// CPP-CHECK-NEXT: ret <vscale x 16 x i8> [[TMP0]]
//
svuint8_t test_svbgrp_u8(svuint8_t op1, svuint8_t op2)
svuint8_t test_svbgrp_u8(svuint8_t op1, svuint8_t op2) STREAMING
{
return SVE_ACLE_FUNC(svbgrp,_u8,,)(op1, op2);
}
Expand All @@ -40,7 +48,7 @@ svuint8_t test_svbgrp_u8(svuint8_t op1, svuint8_t op2)
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.bgrp.x.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]])
// CPP-CHECK-NEXT: ret <vscale x 8 x i16> [[TMP0]]
//
svuint16_t test_svbgrp_u16(svuint16_t op1, svuint16_t op2)
svuint16_t test_svbgrp_u16(svuint16_t op1, svuint16_t op2) STREAMING
{
return SVE_ACLE_FUNC(svbgrp,_u16,,)(op1, op2);
}
Expand All @@ -55,7 +63,7 @@ svuint16_t test_svbgrp_u16(svuint16_t op1, svuint16_t op2)
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.bgrp.x.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]])
// CPP-CHECK-NEXT: ret <vscale x 4 x i32> [[TMP0]]
//
svuint32_t test_svbgrp_u32(svuint32_t op1, svuint32_t op2)
svuint32_t test_svbgrp_u32(svuint32_t op1, svuint32_t op2) STREAMING
{
return SVE_ACLE_FUNC(svbgrp,_u32,,)(op1, op2);
}
Expand All @@ -70,7 +78,7 @@ svuint32_t test_svbgrp_u32(svuint32_t op1, svuint32_t op2)
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.bgrp.x.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]])
// CPP-CHECK-NEXT: ret <vscale x 2 x i64> [[TMP0]]
//
svuint64_t test_svbgrp_u64(svuint64_t op1, svuint64_t op2)
svuint64_t test_svbgrp_u64(svuint64_t op1, svuint64_t op2) STREAMING
{
return SVE_ACLE_FUNC(svbgrp,_u64,,)(op1, op2);
}
Expand All @@ -89,7 +97,7 @@ svuint64_t test_svbgrp_u64(svuint64_t op1, svuint64_t op2)
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.bgrp.x.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[DOTSPLAT]])
// CPP-CHECK-NEXT: ret <vscale x 16 x i8> [[TMP0]]
//
svuint8_t test_svbgrp_n_u8(svuint8_t op1, uint8_t op2)
svuint8_t test_svbgrp_n_u8(svuint8_t op1, uint8_t op2) STREAMING
{
return SVE_ACLE_FUNC(svbgrp,_n_u8,,)(op1, op2);
}
Expand All @@ -108,7 +116,7 @@ svuint8_t test_svbgrp_n_u8(svuint8_t op1, uint8_t op2)
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.bgrp.x.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[DOTSPLAT]])
// CPP-CHECK-NEXT: ret <vscale x 8 x i16> [[TMP0]]
//
svuint16_t test_svbgrp_n_u16(svuint16_t op1, uint16_t op2)
svuint16_t test_svbgrp_n_u16(svuint16_t op1, uint16_t op2) STREAMING
{
return SVE_ACLE_FUNC(svbgrp,_n_u16,,)(op1, op2);
}
Expand All @@ -127,7 +135,7 @@ svuint16_t test_svbgrp_n_u16(svuint16_t op1, uint16_t op2)
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.bgrp.x.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[DOTSPLAT]])
// CPP-CHECK-NEXT: ret <vscale x 4 x i32> [[TMP0]]
//
svuint32_t test_svbgrp_n_u32(svuint32_t op1, uint32_t op2)
svuint32_t test_svbgrp_n_u32(svuint32_t op1, uint32_t op2) STREAMING
{
return SVE_ACLE_FUNC(svbgrp,_n_u32,,)(op1, op2);
}
Expand All @@ -146,7 +154,7 @@ svuint32_t test_svbgrp_n_u32(svuint32_t op1, uint32_t op2)
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.bgrp.x.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[DOTSPLAT]])
// CPP-CHECK-NEXT: ret <vscale x 2 x i64> [[TMP0]]
//
svuint64_t test_svbgrp_n_u64(svuint64_t op1, uint64_t op2)
svuint64_t test_svbgrp_n_u64(svuint64_t op1, uint64_t op2) STREAMING
{
return SVE_ACLE_FUNC(svbgrp,_n_u64,,)(op1, op2);
}
Loading