[clang] [Clang][AArch64] make bitperm intrinsics available in streaming mode (PR #129700)
via cfe-commits
cfe-commits at lists.llvm.org
Wed Apr 30 05:55:46 PDT 2025
https://github.com/Lukacma updated https://github.com/llvm/llvm-project/pull/129700
>From 4b7b5a05b918e644559319f10e6635643a2ee2e7 Mon Sep 17 00:00:00 2001
From: Marian Lukac <Marian.Lukac at arm.com>
Date: Tue, 4 Mar 2025 12:48:19 +0000
Subject: [PATCH] [Clang][AArch64] update bitperm intrinsics to be available in
streaming mode
---
clang/include/clang/Basic/arm_sve.td | 14 +--
.../AArch64/sve2-intrinsics/acle_sve2_bdep.c | 24 +++--
.../AArch64/sve2-intrinsics/acle_sve2_bext.c | 24 +++--
.../AArch64/sve2-intrinsics/acle_sve2_bgrp.c | 24 +++--
.../acle_sve2_aes_bitperm_sha3_sm4.cpp | 96 +++++++++----------
5 files changed, 103 insertions(+), 79 deletions(-)
diff --git a/clang/include/clang/Basic/arm_sve.td b/clang/include/clang/Basic/arm_sve.td
index b51106fa56759..03051362be4f9 100644
--- a/clang/include/clang/Basic/arm_sve.td
+++ b/clang/include/clang/Basic/arm_sve.td
@@ -1988,13 +1988,13 @@ 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 {
diff --git a/clang/test/CodeGen/AArch64/sve2-intrinsics/acle_sve2_bdep.c b/clang/test/CodeGen/AArch64/sve2-intrinsics/acle_sve2_bdep.c
index d4681394a0508..484a00af04cba 100644
--- a/clang/test/CodeGen/AArch64/sve2-intrinsics/acle_sve2_bdep.c
+++ b/clang/test/CodeGen/AArch64/sve2-intrinsics/acle_sve2_bdep.c
@@ -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>
@@ -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:%.*]])
@@ -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);
}
@@ -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);
}
@@ -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);
}
@@ -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);
}
@@ -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);
}
@@ -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);
}
@@ -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);
}
@@ -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);
}
diff --git a/clang/test/CodeGen/AArch64/sve2-intrinsics/acle_sve2_bext.c b/clang/test/CodeGen/AArch64/sve2-intrinsics/acle_sve2_bext.c
index 6d654b9353e7a..953ef4d203783 100644
--- a/clang/test/CodeGen/AArch64/sve2-intrinsics/acle_sve2_bext.c
+++ b/clang/test/CodeGen/AArch64/sve2-intrinsics/acle_sve2_bext.c
@@ -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>
@@ -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:%.*]])
@@ -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);
}
@@ -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);
}
@@ -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);
}
@@ -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);
}
@@ -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);
}
@@ -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);
}
@@ -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);
}
@@ -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);
}
diff --git a/clang/test/CodeGen/AArch64/sve2-intrinsics/acle_sve2_bgrp.c b/clang/test/CodeGen/AArch64/sve2-intrinsics/acle_sve2_bgrp.c
index a98d8e8a2b37c..62ea1c5278bb5 100644
--- a/clang/test/CodeGen/AArch64/sve2-intrinsics/acle_sve2_bgrp.c
+++ b/clang/test/CodeGen/AArch64/sve2-intrinsics/acle_sve2_bgrp.c
@@ -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>
@@ -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:%.*]])
@@ -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);
}
@@ -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);
}
@@ -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);
}
@@ -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);
}
@@ -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);
}
@@ -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);
}
@@ -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);
}
@@ -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);
}
diff --git a/clang/test/Sema/aarch64-sve2-intrinsics/acle_sve2_aes_bitperm_sha3_sm4.cpp b/clang/test/Sema/aarch64-sve2-intrinsics/acle_sve2_aes_bitperm_sha3_sm4.cpp
index 985ea15ac2a4e..d165b92ffc8e4 100644
--- a/clang/test/Sema/aarch64-sve2-intrinsics/acle_sve2_aes_bitperm_sha3_sm4.cpp
+++ b/clang/test/Sema/aarch64-sve2-intrinsics/acle_sve2_aes_bitperm_sha3_sm4.cpp
@@ -26,61 +26,61 @@ void test(uint8_t u8, uint16_t u16, uint32_t u32, uint64_t u64)
// expected-error at +2 {{'svaesmc_u8' needs target feature sve,sve2,sve-aes}}
// overload-error at +1 {{'svaesmc' needs target feature sve,sve2,sve-aes}}
SVE_ACLE_FUNC(svaesmc,_u8,,)(svundef_u8());
- // expected-error at +2 {{'svbdep_u8' needs target feature sve,sve2,sve-bitperm}}
- // overload-error at +1 {{'svbdep' needs target feature sve,sve2,sve-bitperm}}
+ // expected-error at +2 {{'svbdep_u8' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
+ // overload-error at +1 {{'svbdep' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
SVE_ACLE_FUNC(svbdep,_u8,,)(svundef_u8(), svundef_u8());
- // expected-error at +2 {{'svbdep_n_u8' needs target feature sve,sve2,sve-bitperm}}
- // overload-error at +1 {{'svbdep' needs target feature sve,sve2,sve-bitperm}}
+ // expected-error at +2 {{'svbdep_n_u8' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
+ // overload-error at +1 {{'svbdep' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
SVE_ACLE_FUNC(svbdep,_n_u8,,)(svundef_u8(), u8);
- // expected-error at +2 {{'svbext_u8' needs target feature sve,sve2,sve-bitperm}}
- // overload-error at +1 {{'svbext' needs target feature sve,sve2,sve-bitperm}}
+ // expected-error at +2 {{'svbext_u8' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
+ // overload-error at +1 {{'svbext' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
SVE_ACLE_FUNC(svbext,_u8,,)(svundef_u8(), svundef_u8());
- // expected-error at +2 {{'svbext_n_u8' needs target feature sve,sve2,sve-bitperm}}
- // overload-error at +1 {{'svbext' needs target feature sve,sve2,sve-bitperm}}
+ // expected-error at +2 {{'svbext_n_u8' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
+ // overload-error at +1 {{'svbext' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
SVE_ACLE_FUNC(svbext,_n_u8,,)(svundef_u8(), u8);
- // expected-error at +2 {{'svbgrp_u8' needs target feature sve,sve2,sve-bitperm}}
- // overload-error at +1 {{'svbgrp' needs target feature sve,sve2,sve-bitperm}}
+ // expected-error at +2 {{'svbgrp_u8' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
+ // overload-error at +1 {{'svbgrp' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
SVE_ACLE_FUNC(svbgrp,_u8,,)(svundef_u8(), svundef_u8());
- // expected-error at +2 {{'svbgrp_n_u8' needs target feature sve,sve2,sve-bitperm}}
- // overload-error at +1 {{'svbgrp' needs target feature sve,sve2,sve-bitperm}}
+ // expected-error at +2 {{'svbgrp_n_u8' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
+ // overload-error at +1 {{'svbgrp' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
SVE_ACLE_FUNC(svbgrp,_n_u8,,)(svundef_u8(), u8);
- // expected-error at +2 {{'svbdep_u16' needs target feature sve,sve2,sve-bitperm}}
- // overload-error at +1 {{'svbdep' needs target feature sve,sve2,sve-bitperm}}
+ // expected-error at +2 {{'svbdep_u16' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
+ // overload-error at +1 {{'svbdep' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
SVE_ACLE_FUNC(svbdep,_u16,,)(svundef_u16(), svundef_u16());
- // expected-error at +2 {{'svbdep_n_u16' needs target feature sve,sve2,sve-bitperm}}
- // overload-error at +1 {{'svbdep' needs target feature sve,sve2,sve-bitperm}}
+ // expected-error at +2 {{'svbdep_n_u16' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
+ // overload-error at +1 {{'svbdep' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
SVE_ACLE_FUNC(svbdep,_n_u16,,)(svundef_u16(), u16);
- // expected-error at +2 {{'svbext_u16' needs target feature sve,sve2,sve-bitperm}}
- // overload-error at +1 {{'svbext' needs target feature sve,sve2,sve-bitperm}}
+ // expected-error at +2 {{'svbext_u16' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
+ // overload-error at +1 {{'svbext' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
SVE_ACLE_FUNC(svbext,_u16,,)(svundef_u16(), svundef_u16());
- // expected-error at +2 {{'svbext_n_u16' needs target feature sve,sve2,sve-bitperm}}
- // overload-error at +1 {{'svbext' needs target feature sve,sve2,sve-bitperm}}
+ // expected-error at +2 {{'svbext_n_u16' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
+ // overload-error at +1 {{'svbext' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
SVE_ACLE_FUNC(svbext,_n_u16,,)(svundef_u16(), u16);
- // expected-error at +2 {{'svbgrp_u16' needs target feature sve,sve2,sve-bitperm}}
- // overload-error at +1 {{'svbgrp' needs target feature sve,sve2,sve-bitperm}}
+ // expected-error at +2 {{'svbgrp_u16' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
+ // overload-error at +1 {{'svbgrp' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
SVE_ACLE_FUNC(svbgrp,_u16,,)(svundef_u16(), svundef_u16());
- // expected-error at +2 {{'svbgrp_n_u16' needs target feature sve,sve2,sve-bitperm}}
- // overload-error at +1 {{'svbgrp' needs target feature sve,sve2,sve-bitperm}}
+ // expected-error at +2 {{'svbgrp_n_u16' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
+ // overload-error at +1 {{'svbgrp' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
SVE_ACLE_FUNC(svbgrp,_n_u16,,)(svundef_u16(), u16);
- // expected-error at +2 {{'svbdep_u32' needs target feature sve,sve2,sve-bitperm}}
- // overload-error at +1 {{'svbdep' needs target feature sve,sve2,sve-bitperm}}
+ // expected-error at +2 {{'svbdep_u32' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
+ // overload-error at +1 {{'svbdep' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
SVE_ACLE_FUNC(svbdep,_u32,,)(svundef_u32(), svundef_u32());
- // expected-error at +2 {{'svbdep_n_u32' needs target feature sve,sve2,sve-bitperm}}
- // overload-error at +1 {{'svbdep' needs target feature sve,sve2,sve-bitperm}}
+ // expected-error at +2 {{'svbdep_n_u32' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
+ // overload-error at +1 {{'svbdep' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
SVE_ACLE_FUNC(svbdep,_n_u32,,)(svundef_u32(), u32);
- // expected-error at +2 {{'svbext_u32' needs target feature sve,sve2,sve-bitperm}}
- // overload-error at +1 {{'svbext' needs target feature sve,sve2,sve-bitperm}}
+ // expected-error at +2 {{'svbext_u32' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
+ // overload-error at +1 {{'svbext' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
SVE_ACLE_FUNC(svbext,_u32,,)(svundef_u32(), svundef_u32());
- // expected-error at +2 {{'svbext_n_u32' needs target feature sve,sve2,sve-bitperm}}
- // overload-error at +1 {{'svbext' needs target feature sve,sve2,sve-bitperm}}
+ // expected-error at +2 {{'svbext_n_u32' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
+ // overload-error at +1 {{'svbext' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
SVE_ACLE_FUNC(svbext,_n_u32,,)(svundef_u32(), u32);
- // expected-error at +2 {{'svbgrp_u32' needs target feature sve,sve2,sve-bitperm}}
- // overload-error at +1 {{'svbgrp' needs target feature sve,sve2,sve-bitperm}}
+ // expected-error at +2 {{'svbgrp_u32' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
+ // overload-error at +1 {{'svbgrp' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
SVE_ACLE_FUNC(svbgrp,_u32,,)(svundef_u32(), svundef_u32());
- // expected-error at +2 {{'svbgrp_n_u32' needs target feature sve,sve2,sve-bitperm}}
- // overload-error at +1 {{'svbgrp' needs target feature sve,sve2,sve-bitperm}}
+ // expected-error at +2 {{'svbgrp_n_u32' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
+ // overload-error at +1 {{'svbgrp' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
SVE_ACLE_FUNC(svbgrp,_n_u32,,)(svundef_u32(), u32);
// expected-error at +2 {{'svsm4e_u32' needs target feature sve,sve2-sm4}}
// overload-error at +1 {{'svsm4e' needs target feature sve,sve2-sm4}}
@@ -89,23 +89,23 @@ void test(uint8_t u8, uint16_t u16, uint32_t u32, uint64_t u64)
// overload-error at +1 {{'svsm4ekey' needs target feature sve,sve2-sm4}}
SVE_ACLE_FUNC(svsm4ekey,_u32,,)(svundef_u32(), svundef_u32());
- // expected-error at +2 {{'svbdep_u64' needs target feature sve,sve2,sve-bitperm}}
- // overload-error at +1 {{'svbdep' needs target feature sve,sve2,sve-bitperm}}
+ // expected-error at +2 {{'svbdep_u64' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
+ // overload-error at +1 {{'svbdep' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
SVE_ACLE_FUNC(svbdep,_u64,,)(svundef_u64(), svundef_u64());
- // expected-error at +2 {{'svbdep_n_u64' needs target feature sve,sve2,sve-bitperm}}
- // overload-error at +1 {{'svbdep' needs target feature sve,sve2,sve-bitperm}}
+ // expected-error at +2 {{'svbdep_n_u64' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
+ // overload-error at +1 {{'svbdep' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
SVE_ACLE_FUNC(svbdep,_n_u64,,)(svundef_u64(), u64);
- // expected-error at +2 {{'svbext_u64' needs target feature sve,sve2,sve-bitperm}}
- // overload-error at +1 {{'svbext' needs target feature sve,sve2,sve-bitperm}}
+ // expected-error at +2 {{'svbext_u64' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
+ // overload-error at +1 {{'svbext' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
SVE_ACLE_FUNC(svbext,_u64,,)(svundef_u64(), svundef_u64());
- // expected-error at +2 {{'svbext_n_u64' needs target feature sve,sve2,sve-bitperm}}
- // overload-error at +1 {{'svbext' needs target feature sve,sve2,sve-bitperm}}
+ // expected-error at +2 {{'svbext_n_u64' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
+ // overload-error at +1 {{'svbext' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
SVE_ACLE_FUNC(svbext,_n_u64,,)(svundef_u64(), u64);
- // expected-error at +2 {{'svbgrp_u64' needs target feature sve,sve2,sve-bitperm}}
- // overload-error at +1 {{'svbgrp' needs target feature sve,sve2,sve-bitperm}}
+ // expected-error at +2 {{'svbgrp_u64' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
+ // overload-error at +1 {{'svbgrp' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
SVE_ACLE_FUNC(svbgrp,_u64,,)(svundef_u64(), svundef_u64());
- // expected-error at +2 {{'svbgrp_n_u64' needs target feature sve,sve2,sve-bitperm}}
- // overload-error at +1 {{'svbgrp' needs target feature sve,sve2,sve-bitperm}}
+ // expected-error at +2 {{'svbgrp_n_u64' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
+ // overload-error at +1 {{'svbgrp' needs target feature (sve,sve2,sve-bitperm)|(sme,ssve-bitperm)}}
SVE_ACLE_FUNC(svbgrp,_n_u64,,)(svundef_u64(), u64);
// expected-error at +2 {{'svpmullb_pair_u64' needs target feature sve,sve2,sve-aes}}
// overload-error at +1 {{'svpmullb_pair' needs target feature sve,sve2,sve-aes}}
More information about the cfe-commits
mailing list