[clang] 41def32 - [AArch64][SVE][NEON] Add NEON-SVE-Bridge intrinsics
Matt Devereau via cfe-commits
cfe-commits at lists.llvm.org
Mon Dec 13 03:32:13 PST 2021
Author: Matt Devereau
Date: 2021-12-13T11:31:57Z
New Revision: 41def32040787e917b52279cc30231b27f2f02f7
URL: https://github.com/llvm/llvm-project/commit/41def32040787e917b52279cc30231b27f2f02f7
DIFF: https://github.com/llvm/llvm-project/commit/41def32040787e917b52279cc30231b27f2f02f7.diff
LOG: [AArch64][SVE][NEON] Add NEON-SVE-Bridge intrinsics
Adds svset_neonq, svget_neonq, svdup_neonq AArch64 intrinsics.
These are described in the ACLE specification:
https://github.com/ARM-software/acle/pull/72
https://reviews.llvm.org/D114713
Added:
clang/include/clang/Basic/BuiltinsAArch64NeonSVEBridge.def
clang/include/clang/Basic/BuiltinsAArch64NeonSVEBridge_cg.def
clang/lib/Headers/arm_neon_sve_bridge.h
clang/test/CodeGen/aarch64_neon_sve_bridge_intrinsics/acle_neon_sve_bridge_dup_neonq.c
clang/test/CodeGen/aarch64_neon_sve_bridge_intrinsics/acle_neon_sve_bridge_get_neonq.c
clang/test/CodeGen/aarch64_neon_sve_bridge_intrinsics/acle_neon_sve_bridge_set_neonq.c
Modified:
clang/include/clang/Basic/BuiltinsSVE.def
clang/lib/Basic/Targets/AArch64.cpp
clang/lib/CodeGen/CGBuiltin.cpp
clang/lib/Headers/CMakeLists.txt
llvm/utils/gn/secondary/clang/lib/Headers/BUILD.gn
Removed:
################################################################################
diff --git a/clang/include/clang/Basic/BuiltinsAArch64NeonSVEBridge.def b/clang/include/clang/Basic/BuiltinsAArch64NeonSVEBridge.def
new file mode 100644
index 0000000000000..8e3229984d8b7
--- /dev/null
+++ b/clang/include/clang/Basic/BuiltinsAArch64NeonSVEBridge.def
@@ -0,0 +1,39 @@
+#ifdef GET_SVE_BUILTINS
+BUILTIN(__builtin_sve_svget_neonq_s8, "V16Scq16Sc", "n")
+BUILTIN(__builtin_sve_svget_neonq_s16, "V8sq8s", "n")
+BUILTIN(__builtin_sve_svget_neonq_s32, "V4iq4i", "n")
+BUILTIN(__builtin_sve_svget_neonq_s64, "V2Wiq2Wi", "n")
+BUILTIN(__builtin_sve_svget_neonq_u8, "V16Ucq16Uc", "n")
+BUILTIN(__builtin_sve_svget_neonq_u16, "V16Usq16Us", "n")
+BUILTIN(__builtin_sve_svget_neonq_u32, "V4Uiq4Ui", "n")
+BUILTIN(__builtin_sve_svget_neonq_u64, "V2UWiq2UWi", "n")
+BUILTIN(__builtin_sve_svget_neonq_f16, "V8hq8h", "n")
+BUILTIN(__builtin_sve_svget_neonq_f32, "V4fq4f", "n")
+BUILTIN(__builtin_sve_svget_neonq_f64, "V2dq2d", "n")
+BUILTIN(__builtin_sve_svget_neonq_bf16, "V8yq8y", "n")
+BUILTIN(__builtin_sve_svset_neonq_s8, "q16Scq16ScV16Sc", "n")
+BUILTIN(__builtin_sve_svset_neonq_s16, "q8sq8sV8s", "n")
+BUILTIN(__builtin_sve_svset_neonq_s32, "q4iq4iV4i", "n")
+BUILTIN(__builtin_sve_svset_neonq_s64, "q2Wiq2WiV2Wi", "n")
+BUILTIN(__builtin_sve_svset_neonq_u8, "q16Ucq16UcV16Uc", "n")
+BUILTIN(__builtin_sve_svset_neonq_u16, "q8Usq8UsV8s", "n")
+BUILTIN(__builtin_sve_svset_neonq_u32, "q4Uiq4UiV4Ui", "n")
+BUILTIN(__builtin_sve_svset_neonq_u64, "q2UWiq2UWiV2UWi", "n")
+BUILTIN(__builtin_sve_svset_neonq_f16, "q8hq8hV8h", "n")
+BUILTIN(__builtin_sve_svset_neonq_f32, "q4fq4fV4f", "n")
+BUILTIN(__builtin_sve_svset_neonq_f64, "q2dq2dV2d", "n")
+BUILTIN(__builtin_sve_svset_neonq_bf16, "q8yq8yV8y", "n")
+BUILTIN(__builtin_sve_svdup_neonq_s8, "q16ScV16Sc", "n")
+BUILTIN(__builtin_sve_svdup_neonq_s16, "q8sV8s", "n")
+BUILTIN(__builtin_sve_svdup_neonq_s32, "q4iV4i", "n")
+BUILTIN(__builtin_sve_svdup_neonq_s64, "q4iV4i", "n")
+BUILTIN(__builtin_sve_svdup_neonq_u8, "q16UcV16Uc", "n")
+BUILTIN(__builtin_sve_svdup_neonq_u16, "q8UsV8Us", "n")
+BUILTIN(__builtin_sve_svdup_neonq_u32, "q4UiV4Ui", "n")
+BUILTIN(__builtin_sve_svdup_neonq_u64, "q2UWiV2UWi", "n")
+BUILTIN(__builtin_sve_svdup_neonq_f16, "q8hV8h", "n")
+BUILTIN(__builtin_sve_svdup_neonq_f32, "q4fV4f", "n")
+BUILTIN(__builtin_sve_svdup_neonq_f64, "q2dV2d", "n")
+BUILTIN(__builtin_sve_svdup_neonq_bf16, "q8yV8y", "n")
+#endif
+
diff --git a/clang/include/clang/Basic/BuiltinsAArch64NeonSVEBridge_cg.def b/clang/include/clang/Basic/BuiltinsAArch64NeonSVEBridge_cg.def
new file mode 100644
index 0000000000000..7717ba67b4279
--- /dev/null
+++ b/clang/include/clang/Basic/BuiltinsAArch64NeonSVEBridge_cg.def
@@ -0,0 +1,39 @@
+#ifdef GET_SVE_LLVM_INTRINSIC_MAP
+SVEMAP2(svget_neonq_s8, SVETypeFlags::EltTyInt8),
+SVEMAP2(svget_neonq_s16, SVETypeFlags::EltTyInt16),
+SVEMAP2(svget_neonq_s32, SVETypeFlags::EltTyInt32),
+SVEMAP2(svget_neonq_s64, SVETypeFlags::EltTyInt64),
+SVEMAP2(svget_neonq_u8, SVETypeFlags::EltTyInt8),
+SVEMAP2(svget_neonq_u16, SVETypeFlags::EltTyInt16),
+SVEMAP2(svget_neonq_u32, SVETypeFlags::EltTyInt32),
+SVEMAP2(svget_neonq_u64, SVETypeFlags::EltTyInt64),
+SVEMAP2(svget_neonq_f16, SVETypeFlags::EltTyFloat16),
+SVEMAP2(svget_neonq_f32, SVETypeFlags::EltTyFloat32),
+SVEMAP2(svget_neonq_f64, SVETypeFlags::EltTyFloat64),
+SVEMAP2(svget_neonq_bf16, SVETypeFlags::EltTyBFloat16),
+SVEMAP2(svset_neonq_s8, SVETypeFlags::EltTyInt8),
+SVEMAP2(svset_neonq_s16, SVETypeFlags::EltTyInt16),
+SVEMAP2(svset_neonq_s32, SVETypeFlags::EltTyInt32),
+SVEMAP2(svset_neonq_s64, SVETypeFlags::EltTyInt64),
+SVEMAP2(svset_neonq_u8, SVETypeFlags::EltTyInt8),
+SVEMAP2(svset_neonq_u16, SVETypeFlags::EltTyInt16),
+SVEMAP2(svset_neonq_u32, SVETypeFlags::EltTyInt32),
+SVEMAP2(svset_neonq_u64, SVETypeFlags::EltTyInt64),
+SVEMAP2(svset_neonq_f16, SVETypeFlags::EltTyFloat16),
+SVEMAP2(svset_neonq_f32, SVETypeFlags::EltTyFloat32),
+SVEMAP2(svset_neonq_f64, SVETypeFlags::EltTyFloat64),
+SVEMAP2(svset_neonq_bf16, SVETypeFlags::EltTyBFloat16),
+SVEMAP2(svdup_neonq_s8, SVETypeFlags::EltTyInt8),
+SVEMAP2(svdup_neonq_s16, SVETypeFlags::EltTyInt16),
+SVEMAP2(svdup_neonq_s32, SVETypeFlags::EltTyInt32),
+SVEMAP2(svdup_neonq_s64, SVETypeFlags::EltTyInt64),
+SVEMAP2(svdup_neonq_u8, SVETypeFlags::EltTyInt8),
+SVEMAP2(svdup_neonq_u16, SVETypeFlags::EltTyInt16),
+SVEMAP2(svdup_neonq_u32, SVETypeFlags::EltTyInt32),
+SVEMAP2(svdup_neonq_u64, SVETypeFlags::EltTyInt64),
+SVEMAP2(svdup_neonq_f16, SVETypeFlags::EltTyFloat16),
+SVEMAP2(svdup_neonq_f32, SVETypeFlags::EltTyFloat32),
+SVEMAP2(svdup_neonq_f64, SVETypeFlags::EltTyFloat64),
+SVEMAP2(svdup_neonq_bf16, SVETypeFlags::EltTyBFloat16),
+#endif
+
diff --git a/clang/include/clang/Basic/BuiltinsSVE.def b/clang/include/clang/Basic/BuiltinsSVE.def
index 2839ca992d98c..c70525e967b17 100644
--- a/clang/include/clang/Basic/BuiltinsSVE.def
+++ b/clang/include/clang/Basic/BuiltinsSVE.def
@@ -15,6 +15,7 @@
#define GET_SVE_BUILTINS
#include "clang/Basic/arm_sve_builtins.inc"
+#include "clang/Basic/BuiltinsAArch64NeonSVEBridge.def"
#undef GET_SVE_BUILTINS
#undef BUILTIN
diff --git a/clang/lib/Basic/Targets/AArch64.cpp b/clang/lib/Basic/Targets/AArch64.cpp
index 0212889811486..4089a393b7628 100644
--- a/clang/lib/Basic/Targets/AArch64.cpp
+++ b/clang/lib/Basic/Targets/AArch64.cpp
@@ -307,6 +307,9 @@ void AArch64TargetInfo::getTargetDefines(const LangOptions &Opts,
if (FPU & SveMode)
Builder.defineMacro("__ARM_FEATURE_SVE", "1");
+ if ((FPU & NeonMode) && (FPU & SveMode))
+ Builder.defineMacro("__ARM_NEON_SVE_BRIDGE", "1");
+
if (HasSVE2)
Builder.defineMacro("__ARM_FEATURE_SVE2", "1");
diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp
index 5a12231541562..714386bbe4e1d 100644
--- a/clang/lib/CodeGen/CGBuiltin.cpp
+++ b/clang/lib/CodeGen/CGBuiltin.cpp
@@ -6411,6 +6411,7 @@ static const ARMVectorIntrinsicInfo AArch64SISDIntrinsicMap[] = {
static const ARMVectorIntrinsicInfo AArch64SVEIntrinsicMap[] = {
#define GET_SVE_LLVM_INTRINSIC_MAP
#include "clang/Basic/arm_sve_builtin_cg.inc"
+#include "clang/Basic/BuiltinsAArch64NeonSVEBridge_cg.def"
#undef GET_SVE_LLVM_INTRINSIC_MAP
};
@@ -9334,6 +9335,54 @@ Value *CodeGenFunction::EmitAArch64SVEBuiltinExpr(unsigned BuiltinID,
Function *F = CGM.getIntrinsic(Intrinsic::aarch64_sve_tbl2, VTy);
return Builder.CreateCall(F, {V0, V1, Ops[1]});
}
+
+ case SVE::BI__builtin_sve_svset_neonq_s8:
+ case SVE::BI__builtin_sve_svset_neonq_s16:
+ case SVE::BI__builtin_sve_svset_neonq_s32:
+ case SVE::BI__builtin_sve_svset_neonq_s64:
+ case SVE::BI__builtin_sve_svset_neonq_u8:
+ case SVE::BI__builtin_sve_svset_neonq_u16:
+ case SVE::BI__builtin_sve_svset_neonq_u32:
+ case SVE::BI__builtin_sve_svset_neonq_u64:
+ case SVE::BI__builtin_sve_svset_neonq_f16:
+ case SVE::BI__builtin_sve_svset_neonq_f32:
+ case SVE::BI__builtin_sve_svset_neonq_f64:
+ case SVE::BI__builtin_sve_svset_neonq_bf16: {
+ return Builder.CreateInsertVector(Ty, Ops[0], Ops[1], Builder.getInt64(0));
+ }
+
+ case SVE::BI__builtin_sve_svget_neonq_s8:
+ case SVE::BI__builtin_sve_svget_neonq_s16:
+ case SVE::BI__builtin_sve_svget_neonq_s32:
+ case SVE::BI__builtin_sve_svget_neonq_s64:
+ case SVE::BI__builtin_sve_svget_neonq_u8:
+ case SVE::BI__builtin_sve_svget_neonq_u16:
+ case SVE::BI__builtin_sve_svget_neonq_u32:
+ case SVE::BI__builtin_sve_svget_neonq_u64:
+ case SVE::BI__builtin_sve_svget_neonq_f16:
+ case SVE::BI__builtin_sve_svget_neonq_f32:
+ case SVE::BI__builtin_sve_svget_neonq_f64:
+ case SVE::BI__builtin_sve_svget_neonq_bf16: {
+ return Builder.CreateExtractVector(Ty, Ops[0], Builder.getInt64(0));
+ }
+
+ case SVE::BI__builtin_sve_svdup_neonq_s8:
+ case SVE::BI__builtin_sve_svdup_neonq_s16:
+ case SVE::BI__builtin_sve_svdup_neonq_s32:
+ case SVE::BI__builtin_sve_svdup_neonq_s64:
+ case SVE::BI__builtin_sve_svdup_neonq_u8:
+ case SVE::BI__builtin_sve_svdup_neonq_u16:
+ case SVE::BI__builtin_sve_svdup_neonq_u32:
+ case SVE::BI__builtin_sve_svdup_neonq_u64:
+ case SVE::BI__builtin_sve_svdup_neonq_f16:
+ case SVE::BI__builtin_sve_svdup_neonq_f32:
+ case SVE::BI__builtin_sve_svdup_neonq_f64:
+ case SVE::BI__builtin_sve_svdup_neonq_bf16: {
+ Value *Insert = Builder.CreateInsertVector(Ty, UndefValue::get(Ty), Ops[0],
+ Builder.getInt64(0));
+ return Builder.CreateIntrinsic(Intrinsic::aarch64_sve_dupq_lane, {Ty},
+ {Insert, Builder.getInt64(0)});
+ }
}
/// Should not happen
diff --git a/clang/lib/Headers/CMakeLists.txt b/clang/lib/Headers/CMakeLists.txt
index cd3a1e133a06e..ca903da1fef31 100644
--- a/clang/lib/Headers/CMakeLists.txt
+++ b/clang/lib/Headers/CMakeLists.txt
@@ -219,6 +219,8 @@ if(ARM IN_LIST LLVM_TARGETS_TO_BUILD OR AArch64 IN_LIST LLVM_TARGETS_TO_BUILD)
clang_generate_header(-gen-arm-mve-header arm_mve.td arm_mve.h)
# Generate arm_cde.h
clang_generate_header(-gen-arm-cde-header arm_cde.td arm_cde.h)
+ # Copy arm_neon_sve_bridge.h
+ copy_header_to_output_dir(${CMAKE_CURRENT_SOURCE_DIR} arm_neon_sve_bridge.h)
endif()
if(RISCV IN_LIST LLVM_TARGETS_TO_BUILD)
# Generate riscv_vector.h
diff --git a/clang/lib/Headers/arm_neon_sve_bridge.h b/clang/lib/Headers/arm_neon_sve_bridge.h
new file mode 100644
index 0000000000000..17699d8d11dd8
--- /dev/null
+++ b/clang/lib/Headers/arm_neon_sve_bridge.h
@@ -0,0 +1,184 @@
+/*===---- arm_neon_sve_bridge.h - ARM NEON SVE Bridge intrinsics -----------===
+ *
+ *
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+ *
+ *===-----------------------------------------------------------------------===
+ */
+
+#ifndef __ARM_NEON_SVE_BRIDGE_H
+#define __ARM_NEON_SVE_BRIDGE_H
+
+#include <arm_neon.h>
+#include <arm_sve.h>
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* Function attributes */
+#define __ai static __inline__ __attribute__((__always_inline__, __nodebug__))
+#define __aio \
+ static __inline__ \
+ __attribute__((__always_inline__, __nodebug__, __overloadable__))
+
+__aio __attribute__((__clang_arm_builtin_alias(__builtin_sve_svset_neonq_s8)))
+svint8_t svset_neonq(svint8_t, int8x16_t);
+__aio __attribute__((__clang_arm_builtin_alias(__builtin_sve_svset_neonq_s16)))
+svint16_t svset_neonq(svint16_t, int16x8_t);
+__aio __attribute__((__clang_arm_builtin_alias(__builtin_sve_svset_neonq_s32)))
+svint32_t svset_neonq(svint32_t, int32x4_t);
+__aio __attribute__((__clang_arm_builtin_alias(__builtin_sve_svset_neonq_s64)))
+svint64_t svset_neonq(svint64_t, int64x2_t);
+__aio __attribute__((__clang_arm_builtin_alias(__builtin_sve_svset_neonq_u8)))
+svuint8_t svset_neonq(svuint8_t, uint8x16_t);
+__aio __attribute__((__clang_arm_builtin_alias(__builtin_sve_svset_neonq_u16)))
+svuint16_t svset_neonq(svuint16_t, uint16x8_t);
+__aio __attribute__((__clang_arm_builtin_alias(__builtin_sve_svset_neonq_u32)))
+svuint32_t svset_neonq(svuint32_t, uint32x4_t);
+__aio __attribute__((__clang_arm_builtin_alias(__builtin_sve_svset_neonq_u64)))
+svuint64_t svset_neonq(svuint64_t, uint64x2_t);
+__aio __attribute__((__clang_arm_builtin_alias(__builtin_sve_svset_neonq_f16)))
+svfloat16_t svset_neonq(svfloat16_t, float16x8_t);
+__aio __attribute__((__clang_arm_builtin_alias(__builtin_sve_svset_neonq_f32)))
+svfloat32_t svset_neonq(svfloat32_t, float32x4_t);
+__aio __attribute__((__clang_arm_builtin_alias(__builtin_sve_svset_neonq_f64)))
+svfloat64_t svset_neonq(svfloat64_t, float64x2_t);
+__ai __attribute__((__clang_arm_builtin_alias(__builtin_sve_svset_neonq_s8)))
+svint8_t svset_neonq_s8(svint8_t, int8x16_t);
+__ai __attribute__((__clang_arm_builtin_alias(__builtin_sve_svset_neonq_s16)))
+svint16_t svset_neonq_s16(svint16_t, int16x8_t);
+__ai __attribute__((__clang_arm_builtin_alias(__builtin_sve_svset_neonq_s32)))
+svint32_t svset_neonq_s32(svint32_t, int32x4_t);
+__ai __attribute__((__clang_arm_builtin_alias(__builtin_sve_svset_neonq_s64)))
+svint64_t svset_neonq_s64(svint64_t, int64x2_t);
+__ai __attribute__((__clang_arm_builtin_alias(__builtin_sve_svset_neonq_u8)))
+svuint8_t svset_neonq_u8(svuint8_t, uint8x16_t);
+__ai __attribute__((__clang_arm_builtin_alias(__builtin_sve_svset_neonq_u16)))
+svuint16_t svset_neonq_u16(svuint16_t, uint16x8_t);
+__ai __attribute__((__clang_arm_builtin_alias(__builtin_sve_svset_neonq_u32)))
+svuint32_t svset_neonq_u32(svuint32_t, uint32x4_t);
+__ai __attribute__((__clang_arm_builtin_alias(__builtin_sve_svset_neonq_u64)))
+svuint64_t svset_neonq_u64(svuint64_t, uint64x2_t);
+__ai __attribute__((__clang_arm_builtin_alias(__builtin_sve_svset_neonq_f16)))
+svfloat16_t svset_neonq_f16(svfloat16_t, float16x8_t);
+__ai __attribute__((__clang_arm_builtin_alias(__builtin_sve_svset_neonq_f32)))
+svfloat32_t svset_neonq_f32(svfloat32_t, float32x4_t);
+__ai __attribute__((__clang_arm_builtin_alias(__builtin_sve_svset_neonq_f64)))
+svfloat64_t svset_neonq_f64(svfloat64_t, float64x2_t);
+
+__aio __attribute__((__clang_arm_builtin_alias(__builtin_sve_svget_neonq_s8)))
+int8x16_t svget_neonq(svint8_t);
+__aio __attribute__((__clang_arm_builtin_alias(__builtin_sve_svget_neonq_s16)))
+int16x8_t svget_neonq(svint16_t);
+__aio __attribute__((__clang_arm_builtin_alias(__builtin_sve_svget_neonq_s32)))
+int32x4_t svget_neonq(svint32_t);
+__aio __attribute__((__clang_arm_builtin_alias(__builtin_sve_svget_neonq_s64)))
+int64x2_t svget_neonq(svint64_t);
+__aio __attribute__((__clang_arm_builtin_alias(__builtin_sve_svget_neonq_u8)))
+uint8x16_t svget_neonq(svuint8_t);
+__aio __attribute__((__clang_arm_builtin_alias(__builtin_sve_svget_neonq_u16)))
+uint16x8_t svget_neonq(svuint16_t);
+__aio __attribute__((__clang_arm_builtin_alias(__builtin_sve_svget_neonq_u32)))
+uint32x4_t svget_neonq(svuint32_t);
+__aio __attribute__((__clang_arm_builtin_alias(__builtin_sve_svget_neonq_u64)))
+uint64x2_t svget_neonq(svuint64_t);
+__aio __attribute__((__clang_arm_builtin_alias(__builtin_sve_svget_neonq_f16)))
+float16x8_t svget_neonq(svfloat16_t);
+__aio __attribute__((__clang_arm_builtin_alias(__builtin_sve_svget_neonq_f32)))
+float32x4_t svget_neonq(svfloat32_t);
+__aio __attribute__((__clang_arm_builtin_alias(__builtin_sve_svget_neonq_f64)))
+float64x2_t svget_neonq(svfloat64_t);
+__aio __attribute__((__clang_arm_builtin_alias(__builtin_sve_svget_neonq_s8)))
+int8x16_t svget_neonq_s8(svint8_t);
+__ai __attribute__((__clang_arm_builtin_alias(__builtin_sve_svget_neonq_s16)))
+int16x8_t svget_neonq_s16(svint16_t);
+__ai __attribute__((__clang_arm_builtin_alias(__builtin_sve_svget_neonq_s32)))
+int32x4_t svget_neonq_s32(svint32_t);
+__ai __attribute__((__clang_arm_builtin_alias(__builtin_sve_svget_neonq_s64)))
+int64x2_t svget_neonq_s64(svint64_t);
+__ai __attribute__((__clang_arm_builtin_alias(__builtin_sve_svget_neonq_u8)))
+uint8x16_t svget_neonq_u8(svuint8_t);
+__ai __attribute__((__clang_arm_builtin_alias(__builtin_sve_svget_neonq_u16)))
+uint16x8_t svget_neonq_u16(svuint16_t);
+__ai __attribute__((__clang_arm_builtin_alias(__builtin_sve_svget_neonq_u32)))
+uint32x4_t svget_neonq_u32(svuint32_t);
+__ai __attribute__((__clang_arm_builtin_alias(__builtin_sve_svget_neonq_u64)))
+uint64x2_t svget_neonq_u64(svuint64_t);
+__ai __attribute__((__clang_arm_builtin_alias(__builtin_sve_svget_neonq_f16)))
+float16x8_t svget_neonq_f16(svfloat16_t);
+__ai __attribute__((__clang_arm_builtin_alias(__builtin_sve_svget_neonq_f32)))
+float32x4_t svget_neonq_f32(svfloat32_t);
+__ai __attribute__((__clang_arm_builtin_alias(__builtin_sve_svget_neonq_f64)))
+float64x2_t svget_neonq_f64(svfloat64_t);
+
+__aio __attribute__((__clang_arm_builtin_alias(__builtin_sve_svdup_neonq_s8)))
+svint8_t svdup_neonq(int8x16_t);
+__aio __attribute__((__clang_arm_builtin_alias(__builtin_sve_svdup_neonq_s16)))
+svint16_t svdup_neonq(int16x8_t);
+__aio __attribute__((__clang_arm_builtin_alias(__builtin_sve_svdup_neonq_s32)))
+svint32_t svdup_neonq(int32x4_t);
+__aio __attribute__((__clang_arm_builtin_alias(__builtin_sve_svdup_neonq_s64)))
+svint64_t svdup_neonq(int64x2_t);
+__aio __attribute__((__clang_arm_builtin_alias(__builtin_sve_svdup_neonq_u8)))
+svuint8_t svdup_neonq(uint8x16_t);
+__aio __attribute__((__clang_arm_builtin_alias(__builtin_sve_svdup_neonq_u16)))
+svuint16_t svdup_neonq(uint16x8_t);
+__aio __attribute__((__clang_arm_builtin_alias(__builtin_sve_svdup_neonq_u32)))
+svuint32_t svdup_neonq(uint32x4_t);
+__aio __attribute__((__clang_arm_builtin_alias(__builtin_sve_svdup_neonq_u64)))
+svuint64_t svdup_neonq(uint64x2_t);
+__aio __attribute__((__clang_arm_builtin_alias(__builtin_sve_svdup_neonq_f16)))
+svfloat16_t svdup_neonq(float16x8_t);
+__aio __attribute__((__clang_arm_builtin_alias(__builtin_sve_svdup_neonq_f32)))
+svfloat32_t svdup_neonq(float32x4_t);
+__aio __attribute__((__clang_arm_builtin_alias(__builtin_sve_svdup_neonq_f64)))
+svfloat64_t svdup_neonq(float64x2_t);
+__ai __attribute__((__clang_arm_builtin_alias(__builtin_sve_svdup_neonq_s8)))
+svint8_t svdup_neonq_s8(int8x16_t);
+__ai __attribute__((__clang_arm_builtin_alias(__builtin_sve_svdup_neonq_s16)))
+svint16_t svdup_neonq_s16(int16x8_t);
+__ai __attribute__((__clang_arm_builtin_alias(__builtin_sve_svdup_neonq_s32)))
+svint32_t svdup_neonq_s32(int32x4_t);
+__ai __attribute__((__clang_arm_builtin_alias(__builtin_sve_svdup_neonq_s64)))
+svint64_t svdup_neonq_s64(int64x2_t);
+__ai __attribute__((__clang_arm_builtin_alias(__builtin_sve_svdup_neonq_u8)))
+svuint8_t svdup_neonq_u8(uint8x16_t);
+__ai __attribute__((__clang_arm_builtin_alias(__builtin_sve_svdup_neonq_u16)))
+svuint16_t svdup_neonq_u16(uint16x8_t);
+__ai __attribute__((__clang_arm_builtin_alias(__builtin_sve_svdup_neonq_u32)))
+svuint32_t svdup_neonq_u32(uint32x4_t);
+__ai __attribute__((__clang_arm_builtin_alias(__builtin_sve_svdup_neonq_u64)))
+svuint64_t svdup_neonq_u64(uint64x2_t);
+__ai __attribute__((__clang_arm_builtin_alias(__builtin_sve_svdup_neonq_f16)))
+svfloat16_t svdup_neonq_f16(float16x8_t);
+__ai __attribute__((__clang_arm_builtin_alias(__builtin_sve_svdup_neonq_f32)))
+svfloat32_t svdup_neonq_f32(float32x4_t);
+__ai __attribute__((__clang_arm_builtin_alias(__builtin_sve_svdup_neonq_f64)))
+svfloat64_t svdup_neonq_f64(float64x2_t);
+
+#if defined(__ARM_FEATURE_SVE_BF16)
+__aio __attribute__((__clang_arm_builtin_alias(__builtin_sve_svset_neonq_bf16)))
+svbfloat16_t svset_neonq(svbfloat16_t, bfloat16x8_t);
+__ai __attribute__((__clang_arm_builtin_alias(__builtin_sve_svset_neonq_bf16)))
+svbfloat16_t svset_neonq_bf16(svbfloat16_t, bfloat16x8_t);
+__aio __attribute__((__clang_arm_builtin_alias(__builtin_sve_svget_neonq_bf16)))
+bfloat16x8_t svget_neonq(svbfloat16_t);
+__ai __attribute__((__clang_arm_builtin_alias(__builtin_sve_svget_neonq_bf16)))
+bfloat16x8_t svget_neonq_bf16(svbfloat16_t);
+__aio __attribute__((__clang_arm_builtin_alias(__builtin_sve_svdup_neonq_bf16)))
+svbfloat16_t svdup_neonq(bfloat16x8_t);
+__ai __attribute__((__clang_arm_builtin_alias(__builtin_sve_svdup_neonq_bf16)))
+svbfloat16_t svdup_neonq_bf16(bfloat16x8_t);
+#endif // defined(__ARM_FEATURE_SVE_BF16)
+
+#undef __ai
+#undef __aio
+
+#ifdef __cplusplus
+} // extern "C"
+#endif
+
+#endif //__ARM_NEON_SVE_BRIDGE_H
diff --git a/clang/test/CodeGen/aarch64_neon_sve_bridge_intrinsics/acle_neon_sve_bridge_dup_neonq.c b/clang/test/CodeGen/aarch64_neon_sve_bridge_intrinsics/acle_neon_sve_bridge_dup_neonq.c
new file mode 100644
index 0000000000000..8d7b811b4cfa2
--- /dev/null
+++ b/clang/test/CodeGen/aarch64_neon_sve_bridge_intrinsics/acle_neon_sve_bridge_dup_neonq.c
@@ -0,0 +1,210 @@
+// 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 +neon -target-feature +sve -target-feature +bf16 -fallow-half-arguments-and-returns -S -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +neon -target-feature +sve -target-feature +bf16 -fallow-half-arguments-and-returns -S -O1 -Werror -Wall -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
+// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +neon -target-feature +sve -target-feature +bf16 -fallow-half-arguments-and-returns -S -O1 -Werror -Wall -o /dev/null %s
+// RUN: %clang_cc1 -DSVE_OVERLOADED_FORMS -triple aarch64-none-linux-gnu -target-feature +neon -target-feature +sve -target-feature +bf16 -fallow-half-arguments-and-returns -S -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -DSVE_OVERLOADED_FORMS -triple aarch64-none-linux-gnu -target-feature +neon -target-feature +sve -target-feature +bf16 -fallow-half-arguments-and-returns -S -O1 -Werror -Wall -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
+#include <arm_neon_sve_bridge.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_svdup_neonq_s8(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.experimental.vector.insert.nxv16i8.v16i8(<vscale x 16 x i8> undef, <16 x i8> [[N:%.*]], i64 0)
+// CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dupq.lane.nxv16i8(<vscale x 16 x i8> [[TMP0]], i64 0)
+// CHECK-NEXT: ret <vscale x 16 x i8> [[TMP1]]
+//
+// CPP-CHECK-LABEL: @_Z19test_svdup_neonq_s811__Int8x16_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.experimental.vector.insert.nxv16i8.v16i8(<vscale x 16 x i8> undef, <16 x i8> [[N:%.*]], i64 0)
+// CPP-CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dupq.lane.nxv16i8(<vscale x 16 x i8> [[TMP0]], i64 0)
+// CPP-CHECK-NEXT: ret <vscale x 16 x i8> [[TMP1]]
+//
+svint8_t test_svdup_neonq_s8(int8x16_t n) {
+ return SVE_ACLE_FUNC(svdup_neonq, _s8, , )(n);
+}
+
+// CHECK-LABEL: @test_svdup_neonq_s16(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.experimental.vector.insert.nxv8i16.v8i16(<vscale x 8 x i16> undef, <8 x i16> [[N:%.*]], i64 0)
+// CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dupq.lane.nxv8i16(<vscale x 8 x i16> [[TMP0]], i64 0)
+// CHECK-NEXT: ret <vscale x 8 x i16> [[TMP1]]
+//
+// CPP-CHECK-LABEL: @_Z20test_svdup_neonq_s1611__Int16x8_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.experimental.vector.insert.nxv8i16.v8i16(<vscale x 8 x i16> undef, <8 x i16> [[N:%.*]], i64 0)
+// CPP-CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dupq.lane.nxv8i16(<vscale x 8 x i16> [[TMP0]], i64 0)
+// CPP-CHECK-NEXT: ret <vscale x 8 x i16> [[TMP1]]
+//
+svint16_t test_svdup_neonq_s16(int16x8_t n) {
+ return SVE_ACLE_FUNC(svdup_neonq, _s16, , )(n);
+}
+
+// CHECK-LABEL: @test_svdup_neonq_s32(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.experimental.vector.insert.nxv4i32.v4i32(<vscale x 4 x i32> undef, <4 x i32> [[N:%.*]], i64 0)
+// CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dupq.lane.nxv4i32(<vscale x 4 x i32> [[TMP0]], i64 0)
+// CHECK-NEXT: ret <vscale x 4 x i32> [[TMP1]]
+//
+// CPP-CHECK-LABEL: @_Z20test_svdup_neonq_s3211__Int32x4_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.experimental.vector.insert.nxv4i32.v4i32(<vscale x 4 x i32> undef, <4 x i32> [[N:%.*]], i64 0)
+// CPP-CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dupq.lane.nxv4i32(<vscale x 4 x i32> [[TMP0]], i64 0)
+// CPP-CHECK-NEXT: ret <vscale x 4 x i32> [[TMP1]]
+//
+svint32_t test_svdup_neonq_s32(int32x4_t n) {
+ return SVE_ACLE_FUNC(svdup_neonq, _s32, , )(n);
+}
+
+// CHECK-LABEL: @test_svdup_neonq_s64(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.experimental.vector.insert.nxv2i64.v2i64(<vscale x 2 x i64> undef, <2 x i64> [[N:%.*]], i64 0)
+// CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dupq.lane.nxv2i64(<vscale x 2 x i64> [[TMP0]], i64 0)
+// CHECK-NEXT: ret <vscale x 2 x i64> [[TMP1]]
+//
+// CPP-CHECK-LABEL: @_Z20test_svdup_neonq_s6411__Int64x2_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.experimental.vector.insert.nxv2i64.v2i64(<vscale x 2 x i64> undef, <2 x i64> [[N:%.*]], i64 0)
+// CPP-CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dupq.lane.nxv2i64(<vscale x 2 x i64> [[TMP0]], i64 0)
+// CPP-CHECK-NEXT: ret <vscale x 2 x i64> [[TMP1]]
+//
+svint64_t test_svdup_neonq_s64(int64x2_t n) {
+ return SVE_ACLE_FUNC(svdup_neonq, _s64, , )(n);
+}
+
+// CHECK-LABEL: @test_svdup_neonq_u8(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.experimental.vector.insert.nxv16i8.v16i8(<vscale x 16 x i8> undef, <16 x i8> [[N:%.*]], i64 0)
+// CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dupq.lane.nxv16i8(<vscale x 16 x i8> [[TMP0]], i64 0)
+// CHECK-NEXT: ret <vscale x 16 x i8> [[TMP1]]
+//
+// CPP-CHECK-LABEL: @_Z19test_svdup_neonq_u812__Uint8x16_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.experimental.vector.insert.nxv16i8.v16i8(<vscale x 16 x i8> undef, <16 x i8> [[N:%.*]], i64 0)
+// CPP-CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dupq.lane.nxv16i8(<vscale x 16 x i8> [[TMP0]], i64 0)
+// CPP-CHECK-NEXT: ret <vscale x 16 x i8> [[TMP1]]
+//
+svuint8_t test_svdup_neonq_u8(uint8x16_t n) {
+ return SVE_ACLE_FUNC(svdup_neonq, _u8, , )(n);
+}
+
+// CHECK-LABEL: @test_svdup_neonq_u16(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.experimental.vector.insert.nxv8i16.v8i16(<vscale x 8 x i16> undef, <8 x i16> [[N:%.*]], i64 0)
+// CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dupq.lane.nxv8i16(<vscale x 8 x i16> [[TMP0]], i64 0)
+// CHECK-NEXT: ret <vscale x 8 x i16> [[TMP1]]
+//
+// CPP-CHECK-LABEL: @_Z20test_svdup_neonq_u1612__Uint16x8_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.experimental.vector.insert.nxv8i16.v8i16(<vscale x 8 x i16> undef, <8 x i16> [[N:%.*]], i64 0)
+// CPP-CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dupq.lane.nxv8i16(<vscale x 8 x i16> [[TMP0]], i64 0)
+// CPP-CHECK-NEXT: ret <vscale x 8 x i16> [[TMP1]]
+//
+svuint16_t test_svdup_neonq_u16(uint16x8_t n) {
+ return SVE_ACLE_FUNC(svdup_neonq, _u16, , )(n);
+}
+
+// CHECK-LABEL: @test_svdup_neonq_u32(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.experimental.vector.insert.nxv4i32.v4i32(<vscale x 4 x i32> undef, <4 x i32> [[N:%.*]], i64 0)
+// CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dupq.lane.nxv4i32(<vscale x 4 x i32> [[TMP0]], i64 0)
+// CHECK-NEXT: ret <vscale x 4 x i32> [[TMP1]]
+//
+// CPP-CHECK-LABEL: @_Z20test_svdup_neonq_u3212__Uint32x4_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.experimental.vector.insert.nxv4i32.v4i32(<vscale x 4 x i32> undef, <4 x i32> [[N:%.*]], i64 0)
+// CPP-CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dupq.lane.nxv4i32(<vscale x 4 x i32> [[TMP0]], i64 0)
+// CPP-CHECK-NEXT: ret <vscale x 4 x i32> [[TMP1]]
+//
+svuint32_t test_svdup_neonq_u32(uint32x4_t n) {
+ return SVE_ACLE_FUNC(svdup_neonq, _u32, , )(n);
+}
+
+// CHECK-LABEL: @test_svdup_neonq_u64(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.experimental.vector.insert.nxv2i64.v2i64(<vscale x 2 x i64> undef, <2 x i64> [[N:%.*]], i64 0)
+// CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dupq.lane.nxv2i64(<vscale x 2 x i64> [[TMP0]], i64 0)
+// CHECK-NEXT: ret <vscale x 2 x i64> [[TMP1]]
+//
+// CPP-CHECK-LABEL: @_Z20test_svdup_neonq_u6412__Uint64x2_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.experimental.vector.insert.nxv2i64.v2i64(<vscale x 2 x i64> undef, <2 x i64> [[N:%.*]], i64 0)
+// CPP-CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dupq.lane.nxv2i64(<vscale x 2 x i64> [[TMP0]], i64 0)
+// CPP-CHECK-NEXT: ret <vscale x 2 x i64> [[TMP1]]
+//
+svuint64_t test_svdup_neonq_u64(uint64x2_t n) {
+ return SVE_ACLE_FUNC(svdup_neonq, _u64, , )(n);
+}
+
+// CHECK-LABEL: @test_svdup_neonq_f16(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 8 x half> @llvm.experimental.vector.insert.nxv8f16.v8f16(<vscale x 8 x half> undef, <8 x half> [[N:%.*]], i64 0)
+// CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dupq.lane.nxv8f16(<vscale x 8 x half> [[TMP0]], i64 0)
+// CHECK-NEXT: ret <vscale x 8 x half> [[TMP1]]
+//
+// CPP-CHECK-LABEL: @_Z20test_svdup_neonq_f1613__Float16x8_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 8 x half> @llvm.experimental.vector.insert.nxv8f16.v8f16(<vscale x 8 x half> undef, <8 x half> [[N:%.*]], i64 0)
+// CPP-CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dupq.lane.nxv8f16(<vscale x 8 x half> [[TMP0]], i64 0)
+// CPP-CHECK-NEXT: ret <vscale x 8 x half> [[TMP1]]
+//
+svfloat16_t test_svdup_neonq_f16(float16x8_t n) {
+ return SVE_ACLE_FUNC(svdup_neonq, _f16, , )(n);
+}
+
+// CHECK-NEXT %0 = call <vscale x 4 x float> @llvm.experimental.vector.insert.nxv4f32.v4f32(<vscale x 4 x float> undef, <4 x float> %n, i64 0)
+// CHECK-NEXT %1 = call <vscale x 4 x float> @llvm.aarch64.sve.dupq.lane.nxv4f32(<vscale x 4 x float> %0, i64 0)
+// CHECK-NEXT ret <vscale x 4 x float> %1
+// CHECK-LABEL: @test_svdup_neonq_f32(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 4 x float> @llvm.experimental.vector.insert.nxv4f32.v4f32(<vscale x 4 x float> undef, <4 x float> [[N:%.*]], i64 0)
+// CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dupq.lane.nxv4f32(<vscale x 4 x float> [[TMP0]], i64 0)
+// CHECK-NEXT: ret <vscale x 4 x float> [[TMP1]]
+//
+// CPP-CHECK-LABEL: @_Z20test_svdup_neonq_f3213__Float32x4_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 4 x float> @llvm.experimental.vector.insert.nxv4f32.v4f32(<vscale x 4 x float> undef, <4 x float> [[N:%.*]], i64 0)
+// CPP-CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dupq.lane.nxv4f32(<vscale x 4 x float> [[TMP0]], i64 0)
+// CPP-CHECK-NEXT: ret <vscale x 4 x float> [[TMP1]]
+//
+svfloat32_t test_svdup_neonq_f32(float32x4_t n) {
+ return SVE_ACLE_FUNC(svdup_neonq, _f32, , )(n);
+}
+
+// CHECK-LABEL: @test_svdup_neonq_f64(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 2 x double> @llvm.experimental.vector.insert.nxv2f64.v2f64(<vscale x 2 x double> undef, <2 x double> [[N:%.*]], i64 0)
+// CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dupq.lane.nxv2f64(<vscale x 2 x double> [[TMP0]], i64 0)
+// CHECK-NEXT: ret <vscale x 2 x double> [[TMP1]]
+//
+// CPP-CHECK-LABEL: @_Z20test_svdup_neonq_f6413__Float64x2_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 2 x double> @llvm.experimental.vector.insert.nxv2f64.v2f64(<vscale x 2 x double> undef, <2 x double> [[N:%.*]], i64 0)
+// CPP-CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dupq.lane.nxv2f64(<vscale x 2 x double> [[TMP0]], i64 0)
+// CPP-CHECK-NEXT: ret <vscale x 2 x double> [[TMP1]]
+//
+svfloat64_t test_svdup_neonq_f64(float64x2_t n) {
+ return SVE_ACLE_FUNC(svdup_neonq, _f64, , )(n);
+}
+
+// CHECK-LABEL: @test_svdup_neonq_bf16(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 8 x bfloat> @llvm.experimental.vector.insert.nxv8bf16.v8bf16(<vscale x 8 x bfloat> undef, <8 x bfloat> [[N:%.*]], i64 0)
+// CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 8 x bfloat> @llvm.aarch64.sve.dupq.lane.nxv8bf16(<vscale x 8 x bfloat> [[TMP0]], i64 0)
+// CHECK-NEXT: ret <vscale x 8 x bfloat> [[TMP1]]
+//
+// CPP-CHECK-LABEL: @_Z21test_svdup_neonq_bf1614__Bfloat16x8_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 8 x bfloat> @llvm.experimental.vector.insert.nxv8bf16.v8bf16(<vscale x 8 x bfloat> undef, <8 x bfloat> [[N:%.*]], i64 0)
+// CPP-CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 8 x bfloat> @llvm.aarch64.sve.dupq.lane.nxv8bf16(<vscale x 8 x bfloat> [[TMP0]], i64 0)
+// CPP-CHECK-NEXT: ret <vscale x 8 x bfloat> [[TMP1]]
+//
+svbfloat16_t test_svdup_neonq_bf16(bfloat16x8_t n) {
+ return SVE_ACLE_FUNC(svdup_neonq, _bf16, , )(n);
+}
diff --git a/clang/test/CodeGen/aarch64_neon_sve_bridge_intrinsics/acle_neon_sve_bridge_get_neonq.c b/clang/test/CodeGen/aarch64_neon_sve_bridge_intrinsics/acle_neon_sve_bridge_get_neonq.c
new file mode 100644
index 0000000000000..ac33477fccc1f
--- /dev/null
+++ b/clang/test/CodeGen/aarch64_neon_sve_bridge_intrinsics/acle_neon_sve_bridge_get_neonq.c
@@ -0,0 +1,184 @@
+// 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 +neon -target-feature +sve -target-feature +bf16 -fallow-half-arguments-and-returns -S -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +neon -target-feature +sve -target-feature +bf16 -fallow-half-arguments-and-returns -S -O1 -Werror -Wall -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
+// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +neon -target-feature +sve -target-feature +bf16 -fallow-half-arguments-and-returns -S -O1 -Werror -Wall -o /dev/null %s
+// RUN: %clang_cc1 -DSVE_OVERLOADED_FORMS -triple aarch64-none-linux-gnu -target-feature +neon -target-feature +sve -target-feature +bf16 -fallow-half-arguments-and-returns -S -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -DSVE_OVERLOADED_FORMS -triple aarch64-none-linux-gnu -target-feature +neon -target-feature +sve -target-feature +bf16 -fallow-half-arguments-and-returns -S -O1 -Werror -Wall -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
+#include <arm_neon_sve_bridge.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_svget_neonq_s8(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = call <16 x i8> @llvm.experimental.vector.extract.v16i8.nxv16i8(<vscale x 16 x i8> [[N:%.*]], i64 0)
+// CHECK-NEXT: ret <16 x i8> [[TMP0]]
+//
+// CPP-CHECK-LABEL: @_Z19test_svget_neonq_s8u10__SVInt8_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = call <16 x i8> @llvm.experimental.vector.extract.v16i8.nxv16i8(<vscale x 16 x i8> [[N:%.*]], i64 0)
+// CPP-CHECK-NEXT: ret <16 x i8> [[TMP0]]
+//
+int8x16_t test_svget_neonq_s8(svint8_t n) {
+ return SVE_ACLE_FUNC(svget_neonq, _s8, , )(n);
+}
+
+//
+// CHECK-LABEL: @test_svget_neonq_s16(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = call <8 x i16> @llvm.experimental.vector.extract.v8i16.nxv8i16(<vscale x 8 x i16> [[N:%.*]], i64 0)
+// CHECK-NEXT: ret <8 x i16> [[TMP0]]
+//
+// CPP-CHECK-LABEL: @_Z20test_svget_neonq_s16u11__SVInt16_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = call <8 x i16> @llvm.experimental.vector.extract.v8i16.nxv8i16(<vscale x 8 x i16> [[N:%.*]], i64 0)
+// CPP-CHECK-NEXT: ret <8 x i16> [[TMP0]]
+//
+int16x8_t test_svget_neonq_s16(svint16_t n) {
+ return SVE_ACLE_FUNC(svget_neonq, _s16, , )(n);
+}
+
+// CHECK-LABEL: @test_svget_neonq_s32(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = call <4 x i32> @llvm.experimental.vector.extract.v4i32.nxv4i32(<vscale x 4 x i32> [[N:%.*]], i64 0)
+// CHECK-NEXT: ret <4 x i32> [[TMP0]]
+//
+// CPP-CHECK-LABEL: @_Z20test_svget_neonq_s32u11__SVInt32_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = call <4 x i32> @llvm.experimental.vector.extract.v4i32.nxv4i32(<vscale x 4 x i32> [[N:%.*]], i64 0)
+// CPP-CHECK-NEXT: ret <4 x i32> [[TMP0]]
+//
+int32x4_t test_svget_neonq_s32(svint32_t n) {
+ return SVE_ACLE_FUNC(svget_neonq, _s32, , )(n);
+}
+
+// CHECK-LABEL: @test_svget_neonq_s64(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = call <2 x i64> @llvm.experimental.vector.extract.v2i64.nxv2i64(<vscale x 2 x i64> [[N:%.*]], i64 0)
+// CHECK-NEXT: ret <2 x i64> [[TMP0]]
+//
+// CPP-CHECK-LABEL: @_Z20test_svget_neonq_s64u11__SVInt64_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = call <2 x i64> @llvm.experimental.vector.extract.v2i64.nxv2i64(<vscale x 2 x i64> [[N:%.*]], i64 0)
+// CPP-CHECK-NEXT: ret <2 x i64> [[TMP0]]
+//
+int64x2_t test_svget_neonq_s64(svint64_t n) {
+ return SVE_ACLE_FUNC(svget_neonq, _s64, , )(n);
+}
+
+// CHECK-LABEL: @test_svget_neonq_u8(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = call <16 x i8> @llvm.experimental.vector.extract.v16i8.nxv16i8(<vscale x 16 x i8> [[N:%.*]], i64 0)
+// CHECK-NEXT: ret <16 x i8> [[TMP0]]
+//
+// CPP-CHECK-LABEL: @_Z19test_svget_neonq_u8u11__SVUint8_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = call <16 x i8> @llvm.experimental.vector.extract.v16i8.nxv16i8(<vscale x 16 x i8> [[N:%.*]], i64 0)
+// CPP-CHECK-NEXT: ret <16 x i8> [[TMP0]]
+//
+uint8x16_t test_svget_neonq_u8(svuint8_t n) {
+ return SVE_ACLE_FUNC(svget_neonq, _u8, , )(n);
+}
+
+// CHECK-LABEL: @test_svget_neonq_u16(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = call <8 x i16> @llvm.experimental.vector.extract.v8i16.nxv8i16(<vscale x 8 x i16> [[N:%.*]], i64 0)
+// CHECK-NEXT: ret <8 x i16> [[TMP0]]
+//
+// CPP-CHECK-LABEL: @_Z20test_svget_neonq_u16u12__SVUint16_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = call <8 x i16> @llvm.experimental.vector.extract.v8i16.nxv8i16(<vscale x 8 x i16> [[N:%.*]], i64 0)
+// CPP-CHECK-NEXT: ret <8 x i16> [[TMP0]]
+//
+uint16x8_t test_svget_neonq_u16(svuint16_t n) {
+ return SVE_ACLE_FUNC(svget_neonq, _u16, , )(n);
+}
+
+// CHECK-LABEL: @test_svget_neonq_u32(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = call <4 x i32> @llvm.experimental.vector.extract.v4i32.nxv4i32(<vscale x 4 x i32> [[N:%.*]], i64 0)
+// CHECK-NEXT: ret <4 x i32> [[TMP0]]
+//
+// CPP-CHECK-LABEL: @_Z20test_svget_neonq_u32u12__SVUint32_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = call <4 x i32> @llvm.experimental.vector.extract.v4i32.nxv4i32(<vscale x 4 x i32> [[N:%.*]], i64 0)
+// CPP-CHECK-NEXT: ret <4 x i32> [[TMP0]]
+//
+uint32x4_t test_svget_neonq_u32(svuint32_t n) {
+ return SVE_ACLE_FUNC(svget_neonq, _u32, , )(n);
+}
+
+// CHECK-LABEL: @test_svget_neonq_u64(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = call <2 x i64> @llvm.experimental.vector.extract.v2i64.nxv2i64(<vscale x 2 x i64> [[N:%.*]], i64 0)
+// CHECK-NEXT: ret <2 x i64> [[TMP0]]
+//
+// CPP-CHECK-LABEL: @_Z20test_svget_neonq_u64u12__SVUint64_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = call <2 x i64> @llvm.experimental.vector.extract.v2i64.nxv2i64(<vscale x 2 x i64> [[N:%.*]], i64 0)
+// CPP-CHECK-NEXT: ret <2 x i64> [[TMP0]]
+//
+uint64x2_t test_svget_neonq_u64(svuint64_t n) {
+ return SVE_ACLE_FUNC(svget_neonq, _u64, , )(n);
+}
+
+// CHECK-LABEL: @test_svget_neonq_f16(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = call <8 x half> @llvm.experimental.vector.extract.v8f16.nxv8f16(<vscale x 8 x half> [[N:%.*]], i64 0)
+// CHECK-NEXT: ret <8 x half> [[TMP0]]
+//
+// CPP-CHECK-LABEL: @_Z20test_svget_neonq_f16u13__SVFloat16_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = call <8 x half> @llvm.experimental.vector.extract.v8f16.nxv8f16(<vscale x 8 x half> [[N:%.*]], i64 0)
+// CPP-CHECK-NEXT: ret <8 x half> [[TMP0]]
+//
+float16x8_t test_svget_neonq_f16(svfloat16_t n) {
+ return SVE_ACLE_FUNC(svget_neonq, _f16, , )(n);
+}
+
+// CHECK-LABEL: @test_svget_neonq_f32(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = call <4 x float> @llvm.experimental.vector.extract.v4f32.nxv4f32(<vscale x 4 x float> [[N:%.*]], i64 0)
+// CHECK-NEXT: ret <4 x float> [[TMP0]]
+//
+// CPP-CHECK-LABEL: @_Z20test_svget_neonq_f32u13__SVFloat32_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = call <4 x float> @llvm.experimental.vector.extract.v4f32.nxv4f32(<vscale x 4 x float> [[N:%.*]], i64 0)
+// CPP-CHECK-NEXT: ret <4 x float> [[TMP0]]
+//
+float32x4_t test_svget_neonq_f32(svfloat32_t n) {
+ return SVE_ACLE_FUNC(svget_neonq, _f32, , )(n);
+}
+
+// CHECK-LABEL: @test_svget_neonq_f64(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = call <2 x double> @llvm.experimental.vector.extract.v2f64.nxv2f64(<vscale x 2 x double> [[N:%.*]], i64 0)
+// CHECK-NEXT: ret <2 x double> [[TMP0]]
+//
+// CPP-CHECK-LABEL: @_Z20test_svget_neonq_f64u13__SVFloat64_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = call <2 x double> @llvm.experimental.vector.extract.v2f64.nxv2f64(<vscale x 2 x double> [[N:%.*]], i64 0)
+// CPP-CHECK-NEXT: ret <2 x double> [[TMP0]]
+//
+float64x2_t test_svget_neonq_f64(svfloat64_t n) {
+ return SVE_ACLE_FUNC(svget_neonq, _f64, , )(n);
+}
+
+// CHECK-LABEL: @test_svget_neonq_bf16(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = call <8 x bfloat> @llvm.experimental.vector.extract.v8bf16.nxv8bf16(<vscale x 8 x bfloat> [[N:%.*]], i64 0)
+// CHECK-NEXT: ret <8 x bfloat> [[TMP0]]
+//
+// CPP-CHECK-LABEL: @_Z21test_svget_neonq_bf16u14__SVBFloat16_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = call <8 x bfloat> @llvm.experimental.vector.extract.v8bf16.nxv8bf16(<vscale x 8 x bfloat> [[N:%.*]], i64 0)
+// CPP-CHECK-NEXT: ret <8 x bfloat> [[TMP0]]
+//
+bfloat16x8_t test_svget_neonq_bf16(svbfloat16_t n) {
+ return SVE_ACLE_FUNC(svget_neonq, _bf16, , )(n);
+}
diff --git a/clang/test/CodeGen/aarch64_neon_sve_bridge_intrinsics/acle_neon_sve_bridge_set_neonq.c b/clang/test/CodeGen/aarch64_neon_sve_bridge_intrinsics/acle_neon_sve_bridge_set_neonq.c
new file mode 100644
index 0000000000000..d6ceb8218ea27
--- /dev/null
+++ b/clang/test/CodeGen/aarch64_neon_sve_bridge_intrinsics/acle_neon_sve_bridge_set_neonq.c
@@ -0,0 +1,183 @@
+// 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 +neon -target-feature +sve -target-feature +bf16 -fallow-half-arguments-and-returns -S -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +neon -target-feature +sve -target-feature +bf16 -fallow-half-arguments-and-returns -S -O1 -Werror -Wall -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
+// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +neon -target-feature +sve -target-feature +bf16 -fallow-half-arguments-and-returns -S -O1 -Werror -Wall -o /dev/null %s
+// RUN: %clang_cc1 -DSVE_OVERLOADED_FORMS -triple aarch64-none-linux-gnu -target-feature +neon -target-feature +sve -target-feature +bf16 -fallow-half-arguments-and-returns -S -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -DSVE_OVERLOADED_FORMS -triple aarch64-none-linux-gnu -target-feature +neon -target-feature +sve -target-feature +bf16 -fallow-half-arguments-and-returns -S -O1 -Werror -Wall -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
+#include <arm_neon_sve_bridge.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_svset_neonq_s8(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.experimental.vector.insert.nxv16i8.v16i8(<vscale x 16 x i8> [[S:%.*]], <16 x i8> [[N:%.*]], i64 0)
+// CHECK-NEXT: ret <vscale x 16 x i8> [[TMP0]]
+//
+// CPP-CHECK-LABEL: @_Z19test_svset_neonq_s8u10__SVInt8_t11__Int8x16_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.experimental.vector.insert.nxv16i8.v16i8(<vscale x 16 x i8> [[S:%.*]], <16 x i8> [[N:%.*]], i64 0)
+// CPP-CHECK-NEXT: ret <vscale x 16 x i8> [[TMP0]]
+//
+svint8_t test_svset_neonq_s8(svint8_t s, int8x16_t n) {
+ return SVE_ACLE_FUNC(svset_neonq, _s8, , )(s, n);
+}
+
+// CHECK-LABEL: @test_svset_neonq_s16(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.experimental.vector.insert.nxv8i16.v8i16(<vscale x 8 x i16> [[S:%.*]], <8 x i16> [[N:%.*]], i64 0)
+// CHECK-NEXT: ret <vscale x 8 x i16> [[TMP0]]
+//
+// CPP-CHECK-LABEL: @_Z20test_svset_neonq_s16u11__SVInt16_t11__Int16x8_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.experimental.vector.insert.nxv8i16.v8i16(<vscale x 8 x i16> [[S:%.*]], <8 x i16> [[N:%.*]], i64 0)
+// CPP-CHECK-NEXT: ret <vscale x 8 x i16> [[TMP0]]
+//
+svint16_t test_svset_neonq_s16(svint16_t s, int16x8_t n) {
+ return SVE_ACLE_FUNC(svset_neonq, _s16, , )(s, n);
+}
+
+// CHECK-LABEL: @test_svset_neonq_s32(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.experimental.vector.insert.nxv4i32.v4i32(<vscale x 4 x i32> [[S:%.*]], <4 x i32> [[N:%.*]], i64 0)
+// CHECK-NEXT: ret <vscale x 4 x i32> [[TMP0]]
+//
+// CPP-CHECK-LABEL: @_Z20test_svset_neonq_s32u11__SVInt32_t11__Int32x4_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.experimental.vector.insert.nxv4i32.v4i32(<vscale x 4 x i32> [[S:%.*]], <4 x i32> [[N:%.*]], i64 0)
+// CPP-CHECK-NEXT: ret <vscale x 4 x i32> [[TMP0]]
+//
+svint32_t test_svset_neonq_s32(svint32_t s, int32x4_t n) {
+ return SVE_ACLE_FUNC(svset_neonq, _s32, , )(s, n);
+}
+
+// CHECK-LABEL: @test_svset_neonq_s64(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.experimental.vector.insert.nxv2i64.v2i64(<vscale x 2 x i64> [[S:%.*]], <2 x i64> [[N:%.*]], i64 0)
+// CHECK-NEXT: ret <vscale x 2 x i64> [[TMP0]]
+//
+// CPP-CHECK-LABEL: @_Z20test_svset_neonq_s64u11__SVInt64_t11__Int64x2_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.experimental.vector.insert.nxv2i64.v2i64(<vscale x 2 x i64> [[S:%.*]], <2 x i64> [[N:%.*]], i64 0)
+// CPP-CHECK-NEXT: ret <vscale x 2 x i64> [[TMP0]]
+//
+svint64_t test_svset_neonq_s64(svint64_t s, int64x2_t n) {
+ return SVE_ACLE_FUNC(svset_neonq, _s64, , )(s, n);
+}
+
+// CHECK-LABEL: @test_svset_neonq_u8(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.experimental.vector.insert.nxv16i8.v16i8(<vscale x 16 x i8> [[S:%.*]], <16 x i8> [[N:%.*]], i64 0)
+// CHECK-NEXT: ret <vscale x 16 x i8> [[TMP0]]
+//
+// CPP-CHECK-LABEL: @_Z19test_svset_neonq_u8u11__SVUint8_t12__Uint8x16_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.experimental.vector.insert.nxv16i8.v16i8(<vscale x 16 x i8> [[S:%.*]], <16 x i8> [[N:%.*]], i64 0)
+// CPP-CHECK-NEXT: ret <vscale x 16 x i8> [[TMP0]]
+//
+svuint8_t test_svset_neonq_u8(svuint8_t s, uint8x16_t n) {
+ return SVE_ACLE_FUNC(svset_neonq, _u8, , )(s, n);
+}
+
+// CHECK-LABEL: @test_svset_neonq_u16(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.experimental.vector.insert.nxv8i16.v8i16(<vscale x 8 x i16> [[S:%.*]], <8 x i16> [[N:%.*]], i64 0)
+// CHECK-NEXT: ret <vscale x 8 x i16> [[TMP0]]
+//
+// CPP-CHECK-LABEL: @_Z20test_svset_neonq_u16u12__SVUint16_t12__Uint16x8_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.experimental.vector.insert.nxv8i16.v8i16(<vscale x 8 x i16> [[S:%.*]], <8 x i16> [[N:%.*]], i64 0)
+// CPP-CHECK-NEXT: ret <vscale x 8 x i16> [[TMP0]]
+//
+svuint16_t test_svset_neonq_u16(svuint16_t s, uint16x8_t n) {
+ return SVE_ACLE_FUNC(svset_neonq, _u16, , )(s, n);
+}
+
+// CHECK-LABEL: @test_svset_neonq_u32(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.experimental.vector.insert.nxv4i32.v4i32(<vscale x 4 x i32> [[S:%.*]], <4 x i32> [[N:%.*]], i64 0)
+// CHECK-NEXT: ret <vscale x 4 x i32> [[TMP0]]
+//
+// CPP-CHECK-LABEL: @_Z20test_svset_neonq_u32u12__SVUint32_t12__Uint32x4_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.experimental.vector.insert.nxv4i32.v4i32(<vscale x 4 x i32> [[S:%.*]], <4 x i32> [[N:%.*]], i64 0)
+// CPP-CHECK-NEXT: ret <vscale x 4 x i32> [[TMP0]]
+//
+svuint32_t test_svset_neonq_u32(svuint32_t s, uint32x4_t n) {
+ return SVE_ACLE_FUNC(svset_neonq, _u32, , )(s, n);
+}
+
+// CHECK-LABEL: @test_svset_neonq_u64(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.experimental.vector.insert.nxv2i64.v2i64(<vscale x 2 x i64> [[S:%.*]], <2 x i64> [[N:%.*]], i64 0)
+// CHECK-NEXT: ret <vscale x 2 x i64> [[TMP0]]
+//
+// CPP-CHECK-LABEL: @_Z20test_svset_neonq_u64u12__SVUint64_t12__Uint64x2_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.experimental.vector.insert.nxv2i64.v2i64(<vscale x 2 x i64> [[S:%.*]], <2 x i64> [[N:%.*]], i64 0)
+// CPP-CHECK-NEXT: ret <vscale x 2 x i64> [[TMP0]]
+//
+svuint64_t test_svset_neonq_u64(svuint64_t s, uint64x2_t n) {
+ return SVE_ACLE_FUNC(svset_neonq, _u64, , )(s, n);
+}
+
+// CHECK-LABEL: @test_svset_neonq_f16(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 8 x half> @llvm.experimental.vector.insert.nxv8f16.v8f16(<vscale x 8 x half> [[S:%.*]], <8 x half> [[N:%.*]], i64 0)
+// CHECK-NEXT: ret <vscale x 8 x half> [[TMP0]]
+//
+// CPP-CHECK-LABEL: @_Z20test_svset_neonq_f16u13__SVFloat16_t13__Float16x8_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 8 x half> @llvm.experimental.vector.insert.nxv8f16.v8f16(<vscale x 8 x half> [[S:%.*]], <8 x half> [[N:%.*]], i64 0)
+// CPP-CHECK-NEXT: ret <vscale x 8 x half> [[TMP0]]
+//
+svfloat16_t test_svset_neonq_f16(svfloat16_t s, float16x8_t n) {
+ return SVE_ACLE_FUNC(svset_neonq, _f16, , )(s, n);
+}
+
+// CHECK-LABEL: @test_svset_neonq_f32(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 4 x float> @llvm.experimental.vector.insert.nxv4f32.v4f32(<vscale x 4 x float> [[S:%.*]], <4 x float> [[N:%.*]], i64 0)
+// CHECK-NEXT: ret <vscale x 4 x float> [[TMP0]]
+//
+// CPP-CHECK-LABEL: @_Z20test_svset_neonq_f32u13__SVFloat32_t13__Float32x4_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 4 x float> @llvm.experimental.vector.insert.nxv4f32.v4f32(<vscale x 4 x float> [[S:%.*]], <4 x float> [[N:%.*]], i64 0)
+// CPP-CHECK-NEXT: ret <vscale x 4 x float> [[TMP0]]
+//
+svfloat32_t test_svset_neonq_f32(svfloat32_t s, float32x4_t n) {
+ return SVE_ACLE_FUNC(svset_neonq, _f32, , )(s, n);
+}
+
+// CHECK-LABEL: @test_svset_neonq_f64(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 2 x double> @llvm.experimental.vector.insert.nxv2f64.v2f64(<vscale x 2 x double> [[S:%.*]], <2 x double> [[N:%.*]], i64 0)
+// CHECK-NEXT: ret <vscale x 2 x double> [[TMP0]]
+//
+// CPP-CHECK-LABEL: @_Z20test_svset_neonq_f64u13__SVFloat64_t13__Float64x2_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 2 x double> @llvm.experimental.vector.insert.nxv2f64.v2f64(<vscale x 2 x double> [[S:%.*]], <2 x double> [[N:%.*]], i64 0)
+// CPP-CHECK-NEXT: ret <vscale x 2 x double> [[TMP0]]
+//
+svfloat64_t test_svset_neonq_f64(svfloat64_t s, float64x2_t n) {
+ return SVE_ACLE_FUNC(svset_neonq, _f64, , )(s, n);
+}
+
+// CHECK-LABEL: @test_svset_neonq_bf16(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 8 x bfloat> @llvm.experimental.vector.insert.nxv8bf16.v8bf16(<vscale x 8 x bfloat> [[S:%.*]], <8 x bfloat> [[N:%.*]], i64 0)
+// CHECK-NEXT: ret <vscale x 8 x bfloat> [[TMP0]]
+//
+// CPP-CHECK-LABEL: @_Z21test_svset_neonq_bf16u14__SVBFloat16_t14__Bfloat16x8_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = call <vscale x 8 x bfloat> @llvm.experimental.vector.insert.nxv8bf16.v8bf16(<vscale x 8 x bfloat> [[S:%.*]], <8 x bfloat> [[N:%.*]], i64 0)
+// CPP-CHECK-NEXT: ret <vscale x 8 x bfloat> [[TMP0]]
+//
+svbfloat16_t test_svset_neonq_bf16(svbfloat16_t s, bfloat16x8_t n) {
+ return SVE_ACLE_FUNC(svset_neonq, _bf16, , )(s, n);
+}
diff --git a/llvm/utils/gn/secondary/clang/lib/Headers/BUILD.gn b/llvm/utils/gn/secondary/clang/lib/Headers/BUILD.gn
index 7e459e3ecae94..7ce6daa5df2d2 100644
--- a/llvm/utils/gn/secondary/clang/lib/Headers/BUILD.gn
+++ b/llvm/utils/gn/secondary/clang/lib/Headers/BUILD.gn
@@ -96,6 +96,7 @@ copy("Headers") {
"arm64intr.h",
"arm_acle.h",
"arm_cmse.h",
+ "arm_neon_sve_bridge.h",
"armintr.h",
"avx2intrin.h",
"avx512bf16intrin.h",
More information about the cfe-commits
mailing list