[AArch64][SVE] Guard svbfloat16_t with feature macro in ACLE

Summary:
svbfloat16_t should only be defined if the __ARM_FEATURE_SVE_BF16
feature macro is enabled, similar to the scalar bfloat16_t type. Also,
arm_bf16.h should be included in arm_sve.h when
__ARM_FEATURE_BF16_SCALAR_ARITHMETIC is defined.

Patch also contains a fix for ld1ro intrinsic which should be guarded on
__ARM_FEATURE_SVE_BF16 rather than __ARM_FEATURE_BF16_SCALAR_ARITHMETIC,
and a fix for bfmmla test which was missing
__ARM_FEATURE_BF16_SCALAR_ARITHMETIC and -target-feature +bf16 in the
RUN line.

Reviewed By: fpetrogalli

Differential Revision: https://reviews.llvm.org/D82178

diff --git a/clang/include/clang/Basic/arm_sve.td b/clang/include/clang/Basic/arm_sve.td
index 818d167..ba42943 100644 (file)
--- a/clang/include/clang/Basic/arm_sve.td
+++ b/clang/include/clang/Basic/arm_sve.td
@@ -494,8 +494,8 @@ def SVLD4_VNUM : SInst<"svld4_vnum[_{2}]", "4Pcl", "csilUcUsUiUlhfd", MergeNone,
 let ArchGuard = "defined(__ARM_FEATURE_SVE_MATMUL_FP64)" in {
   def SVLD1RO : SInst<"svld1ro[_{2}]", "dPc", "csilUcUsUiUlhfd", MergeNone, "aarch64_sve_ld1ro">;
 }
-let ArchGuard = "defined(__ARM_FEATURE_SVE_MATMUL_FP64) && defined(__ARM_FEATURE_BF16_SCALAR_ARITHMETIC)" in {
-  def SVLD1RO_BF : SInst<"svld1ro[_{2}]", "dPc", "b", MergeNone, "aarch64_sve_ld1ro">;
+let ArchGuard = "defined(__ARM_FEATURE_SVE_MATMUL_FP64) && defined(__ARM_FEATURE_SVE_BF16)" in {
+  def SVLD1RO_BF16 : SInst<"svld1ro[_{2}]", "dPc", "b", MergeNone, "aarch64_sve_ld1ro">;
 }
 
 let ArchGuard = "defined(__ARM_FEATURE_SVE_BF16)" in {

diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_bfmmla.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_bfmmla.c
index 654876b..0b9483d 100644 (file)
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_bfmmla.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_bfmmla.c
@@ -1,5 +1,5 @@
-// RUN: %clang_cc1 -D__ARM_FEATURE_SVE -D__ARM_FEATURE_SVE_BF16 -triple aarch64-none-linux-gnu -target-feature +sve -fallow-half-arguments-and-returns -S -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
-// RUN: %clang_cc1 -D__ARM_FEATURE_SVE -D__ARM_FEATURE_SVE_BF16 -DSVE_OVERLOADED_FORMS -triple aarch64-none-linux-gnu -target-feature +sve -fallow-half-arguments-and-returns -S -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -D__ARM_FEATURE_SVE -D__ARM_FEATURE_BF16_SCALAR_ARITHMETIC -D__ARM_FEATURE_SVE_BF16 -triple aarch64-none-linux-gnu -target-feature +sve -target-feature +bf16 -fallow-half-arguments-and-returns -S -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -D__ARM_FEATURE_SVE -D__ARM_FEATURE_BF16_SCALAR_ARITHMETIC -D__ARM_FEATURE_SVE_BF16 -DSVE_OVERLOADED_FORMS -triple aarch64-none-linux-gnu -target-feature +sve -target-feature +bf16 -fallow-half-arguments-and-returns -S -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
 
 #include <arm_sve.h>
 

diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_ld1ro-bfloat.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_ld1ro-bfloat.c
index 56137bd..852cf27 100644 (file)
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_ld1ro-bfloat.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_ld1ro-bfloat.c
@@ -1,5 +1,5 @@
-// RUN: %clang_cc1 -D__ARM_FEATURE_SVE_MATMUL_FP64 -D__ARM_FEATURE_BF16_SCALAR_ARITHMETIC -D__ARM_FEATURE_SVE -triple aarch64-none-linux-gnu -target-feature +sve -target-feature +bf16 -fallow-half-arguments-and-returns -S -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
-// RUN: %clang_cc1 -D__ARM_FEATURE_SVE_MATMUL_FP64 -D__ARM_FEATURE_BF16_SCALAR_ARITHMETIC -D__ARM_FEATURE_SVE -DSVE_OVERLOADED_FORMS -triple aarch64-none-linux-gnu -target-feature +sve -target-feature +bf16 -fallow-half-arguments-and-returns -S -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -D__ARM_FEATURE_SVE_MATMUL_FP64 -D__ARM_FEATURE_SVE_BF16 -D__ARM_FEATURE_BF16_SCALAR_ARITHMETIC -D__ARM_FEATURE_SVE -triple aarch64-none-linux-gnu -target-feature +sve -target-feature +bf16 -fallow-half-arguments-and-returns -S -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -D__ARM_FEATURE_SVE_MATMUL_FP64 -D__ARM_FEATURE_SVE_BF16 -D__ARM_FEATURE_BF16_SCALAR_ARITHMETIC -D__ARM_FEATURE_SVE -DSVE_OVERLOADED_FORMS -triple aarch64-none-linux-gnu -target-feature +sve -target-feature +bf16 -fallow-half-arguments-and-returns -S -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
 
 #include <arm_sve.h>
 

diff --git a/clang/utils/TableGen/SveEmitter.cpp b/clang/utils/TableGen/SveEmitter.cpp
index b5eed2c..a3cf384 100644 (file)
--- a/clang/utils/TableGen/SveEmitter.cpp
+++ b/clang/utils/TableGen/SveEmitter.cpp
@@ -1088,10 +1088,20 @@ void SVEEmitter::createHeader(raw_ostream &OS) {
   OS << "typedef __SVUint16_t svuint16_t;\n";
   OS << "typedef __SVUint32_t svuint32_t;\n";
   OS << "typedef __SVUint64_t svuint64_t;\n";
-  OS << "typedef __SVFloat16_t svfloat16_t;\n";
-  OS << "typedef __SVBFloat16_t svbfloat16_t;\n\n";
+  OS << "typedef __SVFloat16_t svfloat16_t;\n\n";
 
-  OS << "#ifdef __ARM_FEATURE_BF16_SCALAR_ARITHMETIC\n";
+  OS << "#if defined(__ARM_FEATURE_SVE_BF16) && "
+        "!defined(__ARM_FEATURE_BF16_SCALAR_ARITHMETIC)\n";
+  OS << "#error \"__ARM_FEATURE_BF16_SCALAR_ARITHMETIC must be defined when "
+        "__ARM_FEATURE_SVE_BF16 is defined\"\n";
+  OS << "#endif\n\n";
+
+  OS << "#if defined(__ARM_FEATURE_SVE_BF16)\n";
+  OS << "typedef __SVBFloat16_t svbfloat16_t;\n";
+  OS << "#endif\n\n";
+
+  OS << "#if defined(__ARM_FEATURE_BF16_SCALAR_ARITHMETIC)\n";
+  OS << "#include <arm_bf16.h>\n";
   OS << "typedef __bf16 bfloat16_t;\n";
   OS << "#endif\n\n";