[clang] [Clang][AArch64] Use __clang_arm_builtin_alias for overloaded svreinterpret's (PR #92427)
via cfe-commits
cfe-commits at lists.llvm.org
Thu May 16 09:21:33 PDT 2024
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-clang
Author: Sander de Smalen (sdesmalen-arm)
<details>
<summary>Changes</summary>
The intrinsics are currently defined as:
__aio __attribute__((target("sve")))
svint8_t svreinterpret_s8(svuint8_t op) __arm_streaming_compatible {
return __builtin_sve_reinterpret_s8_u8(op);
}
which doesn't work when calling it from an __arm_streaming function when only +sme is available. By defining it in the same way as we've defined all the other intrinsics, we can leave it to the code in SemaChecking to verify that either +sve or +sme is available.
This PR also fixes the target guards for the svreinterpret_c and svreinterpret_b intrinsics, that convert between svcount_t and svbool_t, as these are available both in SME2 and SVE2p1.
---
Patch is 74.40 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/92427.diff
6 Files Affected:
- (modified) clang/include/clang/Basic/arm_sve.td (+3-3)
- (modified) clang/test/CodeGen/aarch64-sme2-intrinsics/acle_sme2_reinterpret_svcount_svbool.c (+4-2)
- (modified) clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_reinterpret-bfloat.c (+34-23)
- (modified) clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_reinterpret.c (+132-121)
- (removed) clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_reinterpret_from_streaming_mode.c (-35)
- (modified) clang/utils/TableGen/SveEmitter.cpp (+9-12)
``````````diff
diff --git a/clang/include/clang/Basic/arm_sve.td b/clang/include/clang/Basic/arm_sve.td
index 15340ebb62b36..6e5656b037d1d 100644
--- a/clang/include/clang/Basic/arm_sve.td
+++ b/clang/include/clang/Basic/arm_sve.td
@@ -2186,9 +2186,6 @@ let TargetGuard = "sme2" in {
def SVSQRSHRUN_X4 : SInst<"svqrshrun[_n]_{0}[_{d}_x4]", "b4i", "il", MergeNone, "aarch64_sve_sqrshrun_x4", [IsStreaming], [ImmCheck<1, ImmCheckShiftRight, 0>]>;
- def REINTERPRET_SVBOOL_TO_SVCOUNT : Inst<"svreinterpret[_c]", "}P", "Pc", MergeNone, "", [IsStreamingCompatible], []>;
- def REINTERPRET_SVCOUNT_TO_SVBOOL : Inst<"svreinterpret[_b]", "P}", "Pc", MergeNone, "", [IsStreamingCompatible], []>;
-
// SQDMULH
def SVSQDMULH_SINGLE_X2 : SInst<"svqdmulh[_single_{d}_x2]", "22d", "csil", MergeNone, "aarch64_sve_sqdmulh_single_vgx2", [IsStreaming], []>;
def SVSQDMULH_SINGLE_X4 : SInst<"svqdmulh[_single_{d}_x4]", "44d", "csil", MergeNone, "aarch64_sve_sqdmulh_single_vgx4", [IsStreaming], []>;
@@ -2197,6 +2194,9 @@ let TargetGuard = "sme2" in {
}
let TargetGuard = "sve2p1|sme2" in {
+ def REINTERPRET_SVBOOL_TO_SVCOUNT : Inst<"svreinterpret[_c]", "}P", "Pc", MergeNone, "", [IsStreamingCompatible], []>;
+ def REINTERPRET_SVCOUNT_TO_SVBOOL : Inst<"svreinterpret[_b]", "P}", "Pc", MergeNone, "", [IsStreamingCompatible], []>;
+
// SQRSHRN / UQRSHRN
def SVQRSHRN_X2 : SInst<"svqrshrn[_n]_{0}[_{d}_x2]", "h2i", "i", MergeNone, "aarch64_sve_sqrshrn_x2", [IsStreamingCompatible], [ImmCheck<1, ImmCheck1_16>]>;
def SVUQRSHRN_X2 : SInst<"svqrshrn[_n]_{0}[_{d}_x2]", "e2i", "Ui", MergeNone, "aarch64_sve_uqrshrn_x2", [IsStreamingCompatible], [ImmCheck<1, ImmCheck1_16>]>;
diff --git a/clang/test/CodeGen/aarch64-sme2-intrinsics/acle_sme2_reinterpret_svcount_svbool.c b/clang/test/CodeGen/aarch64-sme2-intrinsics/acle_sme2_reinterpret_svcount_svbool.c
index b3d5f4a4c4a53..e702d36ad3954 100644
--- a/clang/test/CodeGen/aarch64-sme2-intrinsics/acle_sme2_reinterpret_svcount_svbool.c
+++ b/clang/test/CodeGen/aarch64-sme2-intrinsics/acle_sme2_reinterpret_svcount_svbool.c
@@ -2,15 +2,17 @@
// REQUIRES: aarch64-registered-target
+// RUN: %clang_cc1 -triple aarch64 -target-feature +sve2p1 -disable-O0-optnone -Werror -Wall -emit-llvm -o - %s | opt -S -p mem2reg,instcombine,tailcallelim | FileCheck %s
+// RUN: %clang_cc1 -triple aarch64 -target-feature +sve2p1 -disable-O0-optnone -Werror -Wall -emit-llvm -o - -x c++ %s | opt -S -p mem2reg,instcombine,tailcallelim | FileCheck %s -check-prefix=CPP-CHECK
// RUN: %clang_cc1 -triple aarch64 -target-feature +sme2 -disable-O0-optnone -Werror -Wall -emit-llvm -o - %s | opt -S -p mem2reg,instcombine,tailcallelim | FileCheck %s
// RUN: %clang_cc1 -triple aarch64 -target-feature +sme2 -disable-O0-optnone -Werror -Wall -emit-llvm -o - -x c++ %s | opt -S -p mem2reg,instcombine,tailcallelim | FileCheck %s -check-prefix=CPP-CHECK
// RUN: %clang_cc1 -DSVE_OVERLOADED_FORMS -triple aarch64 -target-feature +sme2 -disable-O0-optnone -Werror -Wall -emit-llvm -o - %s | opt -S -p mem2reg,instcombine,tailcallelim | FileCheck %s
// RUN: %clang_cc1 -DSVE_OVERLOADED_FORMS -triple aarch64 -target-feature +sme2 -disable-O0-optnone -Werror -Wall -emit-llvm -o - -x c++ %s | opt -S -p mem2reg,instcombine,tailcallelim | FileCheck %s -check-prefix=CPP-CHECK
-#include <arm_sme.h>
+#include <arm_sve.h>
#ifdef SVE_OVERLOADED_FORMS
-// A simple used,unused... macro, long enough to represent any SVE builtin.ยง
+// 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
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_reinterpret-bfloat.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_reinterpret-bfloat.c
index bf2cd23e40802..41208bfb1f435 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_reinterpret-bfloat.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_reinterpret-bfloat.c
@@ -4,6 +4,10 @@
// RUN: %clang_cc1 -fclang-abi-compat=latest -DTUPLE=x2 -triple aarch64 -target-feature +sve -target-feature +bf16 -disable-O0-optnone -Werror -Wall -emit-llvm -o - %s | opt -S -passes=mem2reg,tailcallelim | FileCheck %s -check-prefix=TUPLE2
// RUN: %clang_cc1 -fclang-abi-compat=latest -DTUPLE=x3 -triple aarch64 -target-feature +sve -target-feature +bf16 -disable-O0-optnone -Werror -Wall -emit-llvm -o - %s | opt -S -passes=mem2reg,tailcallelim | FileCheck %s -check-prefix=TUPLE3
// RUN: %clang_cc1 -fclang-abi-compat=latest -DTUPLE=x4 -triple aarch64 -target-feature +sve -target-feature +bf16 -disable-O0-optnone -Werror -Wall -emit-llvm -o - %s | opt -S -passes=mem2reg,tailcallelim | FileCheck %s -check-prefix=TUPLE4
+// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64 -target-feature +sme -disable-O0-optnone -Werror -Wall -emit-llvm -o - %s | opt -S -passes=mem2reg,tailcallelim | FileCheck %s
+// RUN: %clang_cc1 -fclang-abi-compat=latest -DTUPLE=x2 -triple aarch64 -target-feature +sme -disable-O0-optnone -Werror -Wall -emit-llvm -o - %s | opt -S -passes=mem2reg,tailcallelim | FileCheck %s -check-prefix=TUPLE2
+// RUN: %clang_cc1 -fclang-abi-compat=latest -DTUPLE=x3 -triple aarch64 -target-feature +sme -disable-O0-optnone -Werror -Wall -emit-llvm -o - %s | opt -S -passes=mem2reg,tailcallelim | FileCheck %s -check-prefix=TUPLE3
+// RUN: %clang_cc1 -fclang-abi-compat=latest -DTUPLE=x4 -triple aarch64 -target-feature +sme -disable-O0-optnone -Werror -Wall -emit-llvm -o - %s | opt -S -passes=mem2reg,tailcallelim | FileCheck %s -check-prefix=TUPLE4
// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64 -target-feature +sve -target-feature +bf16 -disable-O0-optnone -Werror -Wall -emit-llvm -o - -x c++ %s | opt -S -passes=mem2reg,tailcallelim | FileCheck %s -check-prefix=CPP-CHECK
// RUN: %clang_cc1 -fclang-abi-compat=latest -DTUPLE=x2 -triple aarch64 -target-feature +sve -target-feature +bf16 -disable-O0-optnone -Werror -Wall -emit-llvm -o - -x c++ %s | opt -S -passes=mem2reg,tailcallelim | FileCheck %s -check-prefix=CPP-TUPLE2
// RUN: %clang_cc1 -fclang-abi-compat=latest -DTUPLE=x3 -triple aarch64 -target-feature +sve -target-feature +bf16 -disable-O0-optnone -Werror -Wall -emit-llvm -o - -x c++ %s | opt -S -passes=mem2reg,tailcallelim | FileCheck %s -check-prefix=CPP-TUPLE3
@@ -18,9 +22,16 @@
// RUN: %clang_cc1 -fclang-abi-compat=latest -DSVE_OVERLOADED_FORMS -DTUPLE=x4 -triple aarch64 -target-feature +sve -target-feature +bf16 -disable-O0-optnone -Werror -Wall -emit-llvm -o - -x c++ %s | opt -S -passes=mem2reg,tailcallelim | FileCheck %s -check-prefix=CPP-TUPLE4
// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64 -target-feature +sve -target-feature +bf16 -S -disable-O0-optnone -Werror -Wall -o /dev/null %s
+// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64 -target-feature +sme -S -disable-O0-optnone -Werror -Wall -o /dev/null %s
#include <arm_sve.h>
+#if defined __ARM_FEATURE_SME
+#define MODE_ATTR __arm_streaming
+#else
+#define MODE_ATTR
+#endif
+
#ifdef TUPLE
#define TYPE_1(base,tuple) base ## tuple ## _t
#define TYPE_0(base,tuple) TYPE_1(base,tuple)
@@ -81,7 +92,7 @@
// CPP-TUPLE4-NEXT: [[TMP0:%.*]] = bitcast <vscale x 32 x bfloat> [[OP:%.*]] to <vscale x 64 x i8>
// CPP-TUPLE4-NEXT: ret <vscale x 64 x i8> [[TMP0]]
//
-TYPE(svint8) test_svreinterpret_s8_bf16(TYPE(svbfloat16) op) {
+TYPE(svint8) test_svreinterpret_s8_bf16(TYPE(svbfloat16) op) MODE_ATTR {
return SVE_ACLE_FUNC(svreinterpret_s8, _bf16)(op);
}
@@ -125,7 +136,7 @@ TYPE(svint8) test_svreinterpret_s8_bf16(TYPE(svbfloat16) op) {
// CPP-TUPLE4-NEXT: [[TMP0:%.*]] = bitcast <vscale x 32 x bfloat> [[OP:%.*]] to <vscale x 32 x i16>
// CPP-TUPLE4-NEXT: ret <vscale x 32 x i16> [[TMP0]]
//
-TYPE(svint16) test_svreinterpret_s16_bf16(TYPE(svbfloat16) op) {
+TYPE(svint16) test_svreinterpret_s16_bf16(TYPE(svbfloat16) op) MODE_ATTR {
return SVE_ACLE_FUNC(svreinterpret_s16, _bf16)(op);
}
@@ -169,7 +180,7 @@ TYPE(svint16) test_svreinterpret_s16_bf16(TYPE(svbfloat16) op) {
// CPP-TUPLE4-NEXT: [[TMP0:%.*]] = bitcast <vscale x 32 x bfloat> [[OP:%.*]] to <vscale x 16 x i32>
// CPP-TUPLE4-NEXT: ret <vscale x 16 x i32> [[TMP0]]
//
-TYPE(svint32) test_svreinterpret_s32_bf16(TYPE(svbfloat16) op) {
+TYPE(svint32) test_svreinterpret_s32_bf16(TYPE(svbfloat16) op) MODE_ATTR {
return SVE_ACLE_FUNC(svreinterpret_s32, _bf16)(op);
}
// CHECK-LABEL: @test_svreinterpret_s64_bf16(
@@ -212,7 +223,7 @@ TYPE(svint32) test_svreinterpret_s32_bf16(TYPE(svbfloat16) op) {
// CPP-TUPLE4-NEXT: [[TMP0:%.*]] = bitcast <vscale x 32 x bfloat> [[OP:%.*]] to <vscale x 8 x i64>
// CPP-TUPLE4-NEXT: ret <vscale x 8 x i64> [[TMP0]]
//
-TYPE(svint64) test_svreinterpret_s64_bf16(TYPE(svbfloat16) op) {
+TYPE(svint64) test_svreinterpret_s64_bf16(TYPE(svbfloat16) op) MODE_ATTR {
return SVE_ACLE_FUNC(svreinterpret_s64, _bf16)(op);
}
@@ -256,7 +267,7 @@ TYPE(svint64) test_svreinterpret_s64_bf16(TYPE(svbfloat16) op) {
// CPP-TUPLE4-NEXT: [[TMP0:%.*]] = bitcast <vscale x 32 x bfloat> [[OP:%.*]] to <vscale x 64 x i8>
// CPP-TUPLE4-NEXT: ret <vscale x 64 x i8> [[TMP0]]
//
-TYPE(svuint8) test_svreinterpret_u8_bf16(TYPE(svbfloat16) op) {
+TYPE(svuint8) test_svreinterpret_u8_bf16(TYPE(svbfloat16) op) MODE_ATTR {
return SVE_ACLE_FUNC(svreinterpret_u8, _bf16)(op);
}
@@ -300,7 +311,7 @@ TYPE(svuint8) test_svreinterpret_u8_bf16(TYPE(svbfloat16) op) {
// CPP-TUPLE4-NEXT: [[TMP0:%.*]] = bitcast <vscale x 32 x bfloat> [[OP:%.*]] to <vscale x 32 x i16>
// CPP-TUPLE4-NEXT: ret <vscale x 32 x i16> [[TMP0]]
//
-TYPE(svuint16) test_svreinterpret_u16_bf16(TYPE(svbfloat16) op) {
+TYPE(svuint16) test_svreinterpret_u16_bf16(TYPE(svbfloat16) op) MODE_ATTR {
return SVE_ACLE_FUNC(svreinterpret_u16, _bf16)(op);
}
@@ -344,7 +355,7 @@ TYPE(svuint16) test_svreinterpret_u16_bf16(TYPE(svbfloat16) op) {
// CPP-TUPLE4-NEXT: [[TMP0:%.*]] = bitcast <vscale x 32 x bfloat> [[OP:%.*]] to <vscale x 16 x i32>
// CPP-TUPLE4-NEXT: ret <vscale x 16 x i32> [[TMP0]]
//
-TYPE(svuint32) test_svreinterpret_u32_bf16(TYPE(svbfloat16) op) {
+TYPE(svuint32) test_svreinterpret_u32_bf16(TYPE(svbfloat16) op) MODE_ATTR {
return SVE_ACLE_FUNC(svreinterpret_u32, _bf16)(op);
}
@@ -388,7 +399,7 @@ TYPE(svuint32) test_svreinterpret_u32_bf16(TYPE(svbfloat16) op) {
// CPP-TUPLE4-NEXT: [[TMP0:%.*]] = bitcast <vscale x 32 x bfloat> [[OP:%.*]] to <vscale x 8 x i64>
// CPP-TUPLE4-NEXT: ret <vscale x 8 x i64> [[TMP0]]
//
-TYPE(svuint64) test_svreinterpret_u64_bf16(TYPE(svbfloat16) op) {
+TYPE(svuint64) test_svreinterpret_u64_bf16(TYPE(svbfloat16) op) MODE_ATTR {
return SVE_ACLE_FUNC(svreinterpret_u64, _bf16)(op);
}
@@ -432,7 +443,7 @@ TYPE(svuint64) test_svreinterpret_u64_bf16(TYPE(svbfloat16) op) {
// CPP-TUPLE4-NEXT: [[TMP0:%.*]] = bitcast <vscale x 64 x i8> [[OP:%.*]] to <vscale x 32 x bfloat>
// CPP-TUPLE4-NEXT: ret <vscale x 32 x bfloat> [[TMP0]]
//
-TYPE(svbfloat16) test_svreinterpret_bf16_s8(TYPE(svint8) op) {
+TYPE(svbfloat16) test_svreinterpret_bf16_s8(TYPE(svint8) op) MODE_ATTR {
return SVE_ACLE_FUNC(svreinterpret_bf16, _s8)(op);
}
@@ -476,7 +487,7 @@ TYPE(svbfloat16) test_svreinterpret_bf16_s8(TYPE(svint8) op) {
// CPP-TUPLE4-NEXT: [[TMP0:%.*]] = bitcast <vscale x 32 x i16> [[OP:%.*]] to <vscale x 32 x bfloat>
// CPP-TUPLE4-NEXT: ret <vscale x 32 x bfloat> [[TMP0]]
//
-TYPE(svbfloat16) test_svreinterpret_bf16_s16(TYPE(svint16) op) {
+TYPE(svbfloat16) test_svreinterpret_bf16_s16(TYPE(svint16) op) MODE_ATTR {
return SVE_ACLE_FUNC(svreinterpret_bf16, _s16)(op);
}
@@ -520,7 +531,7 @@ TYPE(svbfloat16) test_svreinterpret_bf16_s16(TYPE(svint16) op) {
// CPP-TUPLE4-NEXT: [[TMP0:%.*]] = bitcast <vscale x 16 x i32> [[OP:%.*]] to <vscale x 32 x bfloat>
// CPP-TUPLE4-NEXT: ret <vscale x 32 x bfloat> [[TMP0]]
//
-TYPE(svbfloat16) test_svreinterpret_bf16_s32(TYPE(svint32) op) {
+TYPE(svbfloat16) test_svreinterpret_bf16_s32(TYPE(svint32) op) MODE_ATTR {
return SVE_ACLE_FUNC(svreinterpret_bf16, _s32)(op);
}
@@ -564,7 +575,7 @@ TYPE(svbfloat16) test_svreinterpret_bf16_s32(TYPE(svint32) op) {
// CPP-TUPLE4-NEXT: [[TMP0:%.*]] = bitcast <vscale x 8 x i64> [[OP:%.*]] to <vscale x 32 x bfloat>
// CPP-TUPLE4-NEXT: ret <vscale x 32 x bfloat> [[TMP0]]
//
-TYPE(svbfloat16) test_svreinterpret_bf16_s64(TYPE(svint64) op) {
+TYPE(svbfloat16) test_svreinterpret_bf16_s64(TYPE(svint64) op) MODE_ATTR {
return SVE_ACLE_FUNC(svreinterpret_bf16, _s64)(op);
}
@@ -608,7 +619,7 @@ TYPE(svbfloat16) test_svreinterpret_bf16_s64(TYPE(svint64) op) {
// CPP-TUPLE4-NEXT: [[TMP0:%.*]] = bitcast <vscale x 64 x i8> [[OP:%.*]] to <vscale x 32 x bfloat>
// CPP-TUPLE4-NEXT: ret <vscale x 32 x bfloat> [[TMP0]]
//
-TYPE(svbfloat16) test_svreinterpret_bf16_u8(TYPE(svuint8) op) {
+TYPE(svbfloat16) test_svreinterpret_bf16_u8(TYPE(svuint8) op) MODE_ATTR {
return SVE_ACLE_FUNC(svreinterpret_bf16, _u8)(op);
}
@@ -652,7 +663,7 @@ TYPE(svbfloat16) test_svreinterpret_bf16_u8(TYPE(svuint8) op) {
// CPP-TUPLE4-NEXT: [[TMP0:%.*]] = bitcast <vscale x 32 x i16> [[OP:%.*]] to <vscale x 32 x bfloat>
// CPP-TUPLE4-NEXT: ret <vscale x 32 x bfloat> [[TMP0]]
//
-TYPE(svbfloat16) test_svreinterpret_bf16_u16(TYPE(svuint16) op) {
+TYPE(svbfloat16) test_svreinterpret_bf16_u16(TYPE(svuint16) op) MODE_ATTR {
return SVE_ACLE_FUNC(svreinterpret_bf16, _u16)(op);
}
@@ -696,7 +707,7 @@ TYPE(svbfloat16) test_svreinterpret_bf16_u16(TYPE(svuint16) op) {
// CPP-TUPLE4-NEXT: [[TMP0:%.*]] = bitcast <vscale x 16 x i32> [[OP:%.*]] to <vscale x 32 x bfloat>
// CPP-TUPLE4-NEXT: ret <vscale x 32 x bfloat> [[TMP0]]
//
-TYPE(svbfloat16) test_svreinterpret_bf16_u32(TYPE(svuint32) op) {
+TYPE(svbfloat16) test_svreinterpret_bf16_u32(TYPE(svuint32) op) MODE_ATTR {
return SVE_ACLE_FUNC(svreinterpret_bf16, _u32)(op);
}
@@ -740,7 +751,7 @@ TYPE(svbfloat16) test_svreinterpret_bf16_u32(TYPE(svuint32) op) {
// CPP-TUPLE4-NEXT: [[TMP0:%.*]] = bitcast <vscale x 8 x i64> [[OP:%.*]] to <vscale x 32 x bfloat>
// CPP-TUPLE4-NEXT: ret <vscale x 32 x bfloat> [[TMP0]]
//
-TYPE(svbfloat16) test_svreinterpret_bf16_u64(TYPE(svuint64) op) {
+TYPE(svbfloat16) test_svreinterpret_bf16_u64(TYPE(svuint64) op) MODE_ATTR {
return SVE_ACLE_FUNC(svreinterpret_bf16, _u64)(op);
}
@@ -776,7 +787,7 @@ TYPE(svbfloat16) test_svreinterpret_bf16_u64(TYPE(svuint64) op) {
// CPP-TUPLE4-NEXT: entry:
// CPP-TUPLE4-NEXT: ret <vscale x 32 x bfloat> [[OP:%.*]]
//
-TYPE(svbfloat16) test_svreinterpret_bf16_bf16(TYPE(svbfloat16) op) {
+TYPE(svbfloat16) test_svreinterpret_bf16_bf16(TYPE(svbfloat16) op) MODE_ATTR {
return SVE_ACLE_FUNC(svreinterpret_bf16, _bf16)(op);
}
@@ -820,7 +831,7 @@ TYPE(svbfloat16) test_svreinterpret_bf16_bf16(TYPE(svbfloat16) op) {
// CPP-TUPLE4-NEXT: [[TMP0:%.*]] = bitcast <vscale x 32 x half> [[OP:%.*]] to <vscale x 32 x bfloat>
// CPP-TUPLE4-NEXT: ret <vscale x 32 x bfloat> [[TMP0]]
//
-TYPE(svbfloat16) test_svreinterpret_bf16_f16(TYPE(svfloat16) op) {
+TYPE(svbfloat16) test_svreinterpret_bf16_f16(TYPE(svfloat16) op) MODE_ATTR {
return SVE_ACLE_FUNC(svreinterpret_bf16, _f16)(op);
}
@@ -864,7 +875,7 @@ TYPE(svbfloat16) test_svreinterpret_bf16_f16(TYPE(svfloat16) op) {
// CPP-TUPLE4-NEXT: [[TMP0:%.*]] = bitcast <vscale x 16 x float> [[OP:%.*]] to <vscale x 32 x bfloat>
// CPP-TUPLE4-NEXT: ret <vscale x 32 x bfloat> [[TMP0]]
//
-TYPE(svbfloat16) test_svreinterpret_bf16_f32(TYPE(svfloat32) op) {
+TYPE(svbfloat16) test_svreinterpret_bf16_f32(TYPE(svfloat32) op) MODE_ATTR {
return SVE_ACLE_FUNC(svreinterpret_bf16, _f32)(op);
}
@@ -908,7 +919,7 @@ TYPE(svbfloat16) test_svreinterpret_bf16_f32(TYPE(svfloat32) op) {
// CPP-TUPLE4-NEXT: [[TMP0:%.*]] = bitcast <vscale x 8 x double> [[OP:%.*]] to <vscale x 32 x bfloat>
// CPP-TUPLE4-NEXT: ret <vscale x 32 x bfloat> [[TMP0]]
//
-TYPE(svbfloat16) test_svreinterpret_bf16_f64(TYPE(svfloat64) op) {
+TYPE(svbfloat16) test_svreinterpret_bf16_f64(TYPE(svfloat64) op) MODE_ATTR {
return SVE_ACLE_FUNC(svreinterpret_bf16, _f64)(op);
}
@@ -952,7 +963,7 @@ TYPE(svbfloat16) test_svreinterpret_bf16_f64(TYPE(svfloat64) op) {
// CPP-TUPLE4-NEXT: [[TMP0:%.*]] = bitcast <vscale x 32 x bfloat> [[OP:%.*]] to <vscale x 16 x float>
// CPP-TUPLE4-NEXT: ret <vscale x 16 x float> [[TMP0]]
//
-TYPE(svfloat32) test_svreinterpret_f32_bf16(TYPE(svbfloat16) op) {
+TYPE(svfloat32) test_svreinterpret_f32_bf16(TYPE(svbfloat16) op) MODE_ATTR {
return SVE_ACLE_FUNC(svreinterpret_f32, _bf16)(op);
}
@@ -996,7 +1007,7 @@ TYPE(svfloat32) test_svreinterpret_f32_bf16(TYPE(svbfloat16) op) {
// CPP-TUPLE4-NEXT: [[TMP0:%.*]] = bitcast <vscale x 32 x bfloat> [[OP:%.*]] to <vscale x 32 x half>
// CPP-TUPLE4-NEXT: ret <vscale x 32 x half> [[TMP0]]
//
-TYPE(svfloat16) test_svreinterpret_f16_bf16(TYPE(svbfloat16) op) {
+TYPE(svfloat16) test_svreinterpret_f16_bf16(TYPE(svbfloat16) op) MODE_ATTR {
return SVE_ACLE_FUNC(svreinterpret_f16, _bf16)(op);
}
@@ -1040,6 +1051,6 @@ TYPE(svfloat16) test_svreinterpret_f16_bf16(TYPE(svbfloat16) op) {
// CPP-TUPLE4-NEXT: [[TMP0:%.*]] = bitcast <vscale x 32 x bfloat> [[OP:%.*]] to <vscale x 8 x double>
// CPP-TUPLE4-NEXT: ret <vscale x 8 x double> [[TMP0]]
//
-TYPE(svfloat64) test_svreinterpret_f64_bf16(TYPE(svbfloat16) op) {
+TYPE(svfloat64) test_svreinterpret_f64_bf16(TYPE(svbfloat16) op) MODE_ATTR {
return SVE_ACLE_FUNC(svreinterpret_f64, _bf16)(op);
}
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_reinterpret.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_reinterpret.c
index 3d9d5c3ce45ae..e61bbf3e03d7e 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_reinterpret.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_reinterpret.c
@@ -4,6 +4,10 @@
// RUN: %clang_cc1 -DTUPLE=x2 -triple aarch64 -target-feature +sve -disable-O0-optnone -Werror -Wall -emit-llvm -o - %s | opt -S -passes=mem2reg,tailcallelim | FileCheck %s -check-prefix=TUPLE2
// RUN: %clang_cc1 -DTUPLE=x3 -triple aarch64 -target-feature +sve -disable-O0-optnone -Werror -Wall -emit-llvm -o - %s | opt -S -passes=mem2reg,tailcallelim | FileCheck %s -check-prefix=TUPLE3
// RUN: %clang_cc1 -DTUPLE=x4 -triple aarch64 -target-feature +sve -disable-O0-optnone -Werror -Wall -emit-llvm -o - %s | opt -S -passes=mem2reg,tailcallelim | FileCheck %s -check-prefix=TUPLE4
+// RUN: %clang_cc1 -triple aarch64 -target-feature +sme -disable-O0-optnone -Werror -Wall -emit-llvm -o - %s | opt -S -passes=mem2reg,tailcallelim | FileCheck %s
+// RUN: %clang_cc1 -DTUPLE=x2 -triple aarch64 -target-feature +sme -disable-O0-optnone -Werror -Wall -emit-llvm -o - %s | opt -S -passes=mem2reg,tailcallelim | FileCheck %s -check-prefix=TUPLE2
+// RUN: %clang_cc1 -DTUPLE=x3 -triple aarch64 -target-feature +sme -disable-O0-optnone -Werror -Wall -emit-llvm -o - %s | opt -S -passes=mem2reg,tailcallelim | FileCheck %s -check-prefix=TUPLE3
+// RUN: %clang_cc1 -DTUPLE=x4 -triple aarch64 -target-feature +sme -disable-O0-optnone -Werror -Wall -emit-llvm -o - %s | opt -S -passes=mem2reg,tailcallelim | FileCheck %s -check-prefix=TUPLE4
// RUN: %clang_cc1 -triple aarch64 -target-feature +sve -disable-O0-optnone -Werror -Wall -emit-llvm -o - -x c++ %s | opt -S -passes=mem2reg,tailcallelim | FileCheck %s -check-prefix=CPP-CHECK
// RUN: %clang_cc1 -DTUPLE=x2 -triple aarch64 -target-feature +sve -disable-O0-optnone -Werror -Wall -emit-llvm -o - -x c++ %s | opt -S -passes=mem2reg,tailcallelim | FileCheck %s -check-prefix=CPP-TUPLE2
// RUN: %clang_cc1 -DTUPLE=x3 -triple aarch64 -target-feature +sve -disable-O0-optnone -Werror -Wall -emit-llvm -o - -x c++ %s | opt -S -passes=mem2reg,tailcallelim | FileCheck %s -check-prefix=CPP-TUPLE3
@@ -17,9 +21,16 @@
// RUN: %clang_cc1 -DSVE_OVERLOADED_FORMS -DTUPLE=x3 -triple aarch64 -target-feature +sve -disable-O0-optnone -Werror -Wall -emit-llvm -o - -x c++ %s | opt -S -passes=mem2reg,tailcallelim | FileCheck %s -check-prefix=CPP-TUPLE3
// RUN: %clang_cc1 -DSVE_OVERLOADED_FORMS -DTUPLE=x4 -triple aarch64 -target-feature +sve -disable-O0-optnone -Werror -Wall -emit-llvm -o - -x c++ %s | opt -S -passes=mem2reg,tailcallelim | FileCheck %s -check-prefix=CPP-TUPLE4
// RUN: %clang_cc1 -triple aarch64 -target-feature +sve -S -disable-O0-optnone -Werror -Wall -o /dev/null %s
+// RUN: %clang_cc1 -triple aarch64...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/92427
More information about the cfe-commits
mailing list