[ARM][AArch64] Add feature +fp16fml

Armv8.4-A adds a few FP16 instructions that can optionally be implemented
in CPUs of Armv8.2-A and above.

This patch adds a feature to clang to permit selection of these
instructions. This interacts with the +fp16 option as follows:

Prior to Armv8.4-A:
*) +fp16fml implies +fp16
*) +nofp16 implies +nofp16fml

From Armv8.4-A:
*) The above conditions apply, additionally: +fp16 implies +fp16fml

Patch by Bernard Ogden.

Differential Revision: https://reviews.llvm.org/D50229

llvm-svn: 342862

2 files changed, 72 insertions, 5 deletions

diff --git a/clang/test/Preprocessor/aarch64-target-features.c b/clang/test/Preprocessor/aarch64-target-features.c
index 92df0004e90..58bc7192d7f 100644
--- a/clang/test/Preprocessor/aarch64-target-features.c
+++ b/clang/test/Preprocessor/aarch64-target-features.c
@@ -93,18 +93,45 @@
 // RUN: %clang -target aarch64-none-linux-gnu -march=armv8.2a+dotprod -x c -E -dM %s -o - | FileCheck --check-prefix=CHECK-DOTPROD %s
 // CHECK-DOTPROD: __ARM_FEATURE_DOTPROD 1
 
-// RUN: %clang -target aarch64-none-linux-gnueabi -march=armv8.2a+fp16 -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-VECTOR-SCALAR %s
+// RUN: %clang -target aarch64-none-linux-gnueabi -march=armv8.2-a+nofp16fml+fp16 -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-VECTOR-SCALAR %s
+// RUN: %clang -target aarch64-none-linux-gnueabi -march=armv8.2-a+nofp16+fp16fml -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-VECTOR-SCALAR %s
+// RUN: %clang -target aarch64-none-linux-gnueabi -march=armv8.2-a+fp16+nofp16fml -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-VECTOR-SCALAR %s
+// RUN: %clang -target aarch64-none-linux-gnueabi -march=armv8-a+fp16fml -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-VECTOR-SCALAR %s
+// RUN: %clang -target aarch64-none-linux-gnueabi -march=armv8-a+fp16 -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-VECTOR-SCALAR %s
+// RUN: %clang -target aarch64-none-linux-gnueabi -march=armv8.4-a+nofp16fml+fp16 -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-VECTOR-SCALAR %s
+// RUN: %clang -target aarch64-none-linux-gnueabi -march=armv8.4-a+nofp16+fp16fml -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-VECTOR-SCALAR %s
+// RUN: %clang -target aarch64-none-linux-gnueabi -march=armv8.4-a+fp16+nofp16fml -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-VECTOR-SCALAR %s
+// RUN: %clang -target aarch64-none-linux-gnueabi -march=armv8.4-a+fp16fml -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-VECTOR-SCALAR %s
+// RUN: %clang -target aarch64-none-linux-gnueabi -march=armv8.4-a+fp16 -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-VECTOR-SCALAR %s
 // CHECK-FULLFP16-VECTOR-SCALAR: #define __ARM_FEATURE_FP16_SCALAR_ARITHMETIC 1
 // CHECK-FULLFP16-VECTOR-SCALAR: #define __ARM_FEATURE_FP16_VECTOR_ARITHMETIC 1
 // CHECK-FULLFP16-VECTOR-SCALAR: #define __ARM_FP 0xE
 // CHECK-FULLFP16-VECTOR-SCALAR: #define __ARM_FP16_FORMAT_IEEE 1
 
-// RUN: %clang -target aarch64-none-linux-gnueabi -march=armv8.2a+fp16+nosimd -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-SCALAR %s
+// +fp16fml+nosimd doesn't make sense as the fp16fml instructions all require SIMD.
+// However, as +fp16fml implies +fp16 there is a set of defines that we would expect.
+// RUN: %clang -target aarch64-none-linux-gnueabi -march=armv8-a+fp16fml+nosimd -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-SCALAR %s
+// RUN: %clang -target aarch64-none-linux-gnueabi -march=armv8-a+fp16+nosimd -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-SCALAR %s
+// RUN: %clang -target aarch64-none-linux-gnueabi -march=armv8.4-a+fp16fml+nosimd -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-SCALAR %s
+// RUN: %clang -target aarch64-none-linux-gnueabi -march=armv8.4-a+fp16+nosimd -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-SCALAR %s
 // CHECK-FULLFP16-SCALAR:       #define __ARM_FEATURE_FP16_SCALAR_ARITHMETIC 1
 // CHECK-FULLFP16-SCALAR-NOT:   #define __ARM_FEATURE_FP16_VECTOR_ARITHMETIC 1
 // CHECK-FULLFP16-SCALAR:       #define __ARM_FP 0xE
 // CHECK-FULLFP16-SCALAR:       #define __ARM_FP16_FORMAT_IEEE 1
 
+// RUN: %clang -target aarch64-none-linux-gnueabi -march=armv8.2-a -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-NOFML-VECTOR-SCALAR %s
+// RUN: %clang -target aarch64-none-linux-gnueabi -march=armv8.2-a+nofp16 -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-NOFML-VECTOR-SCALAR %s
+// RUN: %clang -target aarch64-none-linux-gnueabi -march=armv8.2-a+nofp16fml -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-NOFML-VECTOR-SCALAR %s
+// RUN: %clang -target aarch64-none-linux-gnueabi -march=armv8.2-a+fp16fml+nofp16 -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-NOFML-VECTOR-SCALAR %s
+// RUN: %clang -target aarch64-none-linux-gnueabi -march=armv8.4-a -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-NOFML-VECTOR-SCALAR %s
+// RUN: %clang -target aarch64-none-linux-gnueabi -march=armv8.4-a+nofp16 -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-NOFML-VECTOR-SCALAR %s
+// RUN: %clang -target aarch64-none-linux-gnueabi -march=armv8.4-a+nofp16fml -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-NOFML-VECTOR-SCALAR %s
+// RUN: %clang -target aarch64-none-linux-gnueabi -march=armv8.4-a+fp16fml+nofp16 -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-NOFML-VECTOR-SCALAR %s
+// CHECK-FULLFP16-NOFML-VECTOR-SCALAR-NOT: #define __ARM_FEATURE_FP16_SCALAR_ARITHMETIC 1
+// CHECK-FULLFP16-NOFML-VECTOR-SCALAR-NOT: #define __ARM_FEATURE_FP16_VECTOR_ARITHMETIC 1
+// CHECK-FULLFP16-NOFML-VECTOR-SCALAR: #define __ARM_FP 0xE
+// CHECK-FULLFP16-NOFML-VECTOR-SCALAR: #define __ARM_FP16_FORMAT_IEEE 1
+
 // ================== Check whether -mtune accepts mixed-case features.
 // RUN: %clang -target aarch64 -mtune=CYCLONE -### -c %s 2>&1 | FileCheck -check-prefix=CHECK-MTUNE-CYCLONE %s
 // CHECK-MTUNE-CYCLONE: "-cc1"{{.*}} "-triple" "aarch64{{.*}}" "-target-feature" "+neon" "-target-feature" "+zcm" "-target-feature" "+zcz"
diff --git a/clang/test/Preprocessor/arm-target-features.c b/clang/test/Preprocessor/arm-target-features.c
index a982d808502..3affb54d75f 100644
--- a/clang/test/Preprocessor/arm-target-features.c
+++ b/clang/test/Preprocessor/arm-target-features.c
@@ -21,18 +21,58 @@
 // CHECK-V8A-ALLOW-FP-INSTR: #define __ARM_FP16_FORMAT_IEEE 1
 // CHECK-V8A-ALLOW-FP-INSTR-V8A-NOT: #define __ARM_FEATURE_DOTPROD
 
-// RUN: %clang -target arm-none-linux-gnueabi -march=armv8.2a+fp16 -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-VECTOR-SCALAR %s
+// RUN: %clang -target arm-none-linux-gnueabi -march=armv8.2-a+nofp16fml+fp16 -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-VECTOR-SCALAR %s
+// RUN: %clang -target arm-none-linux-gnueabi -march=armv8.2-a+nofp16+fp16fml -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-VECTOR-SCALAR %s
+// RUN: %clang -target arm-none-linux-gnueabi -march=armv8.2-a+fp16+nofp16fml -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-VECTOR-SCALAR %s
+// RUN: %clang -target arm-none-linux-gnueabi -march=armv8-a+fp16fml -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-VECTOR-SCALAR %s
+// RUN: %clang -target arm-none-linux-gnueabi -march=armv8-a+fp16 -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-VECTOR-SCALAR %s
+// RUN: %clang -target arm-none-linux-gnueabi -march=armv8.4-a+nofp16fml+fp16 -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-VECTOR-SCALAR %s
+// RUN: %clang -target arm-none-linux-gnueabi -march=armv8.4-a+nofp16+fp16fml -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-VECTOR-SCALAR %s
+// RUN: %clang -target arm-none-linux-gnueabi -march=armv8.4-a+fp16+nofp16fml -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-VECTOR-SCALAR %s
+// RUN: %clang -target arm-none-linux-gnueabi -march=armv8.4-a+fp16fml -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-VECTOR-SCALAR %s
+// RUN: %clang -target arm-none-linux-gnueabi -march=armv8.4-a+fp16 -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-VECTOR-SCALAR %s
 // CHECK-FULLFP16-VECTOR-SCALAR: #define __ARM_FEATURE_FP16_SCALAR_ARITHMETIC 1
 // CHECK-FULLFP16-VECTOR-SCALAR: #define __ARM_FEATURE_FP16_VECTOR_ARITHMETIC 1
 // CHECK-FULLFP16-VECTOR-SCALAR: #define __ARM_FP 0xe
 // CHECK-FULLFP16-VECTOR-SCALAR: #define __ARM_FP16_FORMAT_IEEE 1
 
-// RUN: %clang -target arm-none-linux-gnueabi -march=armv8.2a+fp16 -mfpu=vfp4 -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-SCALAR %s
+// +fp16fml without neon doesn't make sense as the fp16fml instructions all require SIMD.
+// However, as +fp16fml implies +fp16 there is a set of defines that we would expect.
+// RUN: %clang -target arm-none-linux-gnueabi -march=armv8-a+fp16fml -mfpu=vfp4 -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-SCALAR %s
+// RUN: %clang -target arm-none-linux-gnueabi -march=armv8-a+fp16 -mfpu=vfp4 -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-SCALAR %s
+// RUN: %clang -target arm-none-linux-gnueabi -march=armv8.4-a+fp16fml -mfpu=vfp4 -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-SCALAR %s
+// RUN: %clang -target arm-none-linux-gnueabi -march=armv8.4-a+fp16 -mfpu=vfp4 -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-SCALAR %s
 // CHECK-FULLFP16-SCALAR:       #define __ARM_FEATURE_FP16_SCALAR_ARITHMETIC 1
 // CHECK-FULLFP16-SCALAR-NOT:   #define __ARM_FEATURE_FP16_VECTOR_ARITHMETIC 1
 // CHECK-FULLFP16-SCALAR:       #define __ARM_FP 0xe
 // CHECK-FULLFP16-SCALAR:       #define __ARM_FP16_FORMAT_IEEE 1
-//
+
+// RUN: %clang -target arm-none-linux-gnueabi -march=armv8.2-a -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-NOFML-VECTOR-SCALAR %s
+// RUN: %clang -target arm-none-linux-gnueabi -march=armv8.2-a+nofp16 -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-NOFML-VECTOR-SCALAR %s
+// RUN: %clang -target arm-none-linux-gnueabi -march=armv8.2-a+nofp16fml -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-NOFML-VECTOR-SCALAR %s
+// RUN: %clang -target arm-none-linux-gnueabi -march=armv8.2-a+fp16fml+nofp16 -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-NOFML-VECTOR-SCALAR %s
+// RUN: %clang -target arm-none-linux-gnueabi -march=armv8.4-a -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-NOFML-VECTOR-SCALAR %s
+// RUN: %clang -target arm-none-linux-gnueabi -march=armv8.4-a+nofp16 -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-NOFML-VECTOR-SCALAR %s
+// RUN: %clang -target arm-none-linux-gnueabi -march=armv8.4-a+nofp16fml -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-NOFML-VECTOR-SCALAR %s
+// RUN: %clang -target arm-none-linux-gnueabi -march=armv8.4-a+fp16fml+nofp16 -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-NOFML-VECTOR-SCALAR %s
+// CHECK-FULLFP16-NOFML-VECTOR-SCALAR-NOT: #define __ARM_FEATURE_FP16_SCALAR_ARITHMETIC 1
+// CHECK-FULLFP16-NOFML-VECTOR-SCALAR-NOT: #define __ARM_FEATURE_FP16_VECTOR_ARITHMETIC 1
+// CHECK-FULLFP16-NOFML-VECTOR-SCALAR: #define __ARM_FP 0xe
+// CHECK-FULLFP16-NOFML-VECTOR-SCALAR: #define __ARM_FP16_FORMAT_IEEE 1
+
+// RUN: %clang -target arm -march=armv8-a+fp16 -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-SOFT %s
+// RUN: %clang -target arm -march=armv8-a+fp16fml -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-SOFT %s
+// RUN: %clang -target arm -march=armv8-a+fp16+fp16fml -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-SOFT %s
+// RUN: %clang -target arm -march=armv8-a+fp16fml+fp16 -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-SOFT %s
+// RUN: %clang -target arm -march=armv8.4-a+fp16 -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-SOFT %s
+// RUN: %clang -target arm -march=armv8.4-a+fp16fml -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-SOFT %s
+// RUN: %clang -target arm -march=armv8.4-a+fp16+fp16fml -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-SOFT %s
+// RUN: %clang -target arm -march=armv8.4-a+fp16fml+fp16 -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-SOFT %s
+// CHECK-FULLFP16-SOFT-NOT: #define __ARM_FEATURE_FP16_SCALAR_ARITHMETIC
+// CHECK-FULLFP16-SOFT-NOT: #define __ARM_FEATURE_FP16_VECTOR_ARITHMETIC
+// CHECK-FULLFP16-SOFT-NOT: #define __ARM_FEATURE_FP16_SCALAR_ARITHMETIC
+// CHECK-FULLFP16-SOFT-NOT: #define __ARM_FEATURE_FP16_VECTOR_ARITHMETIC
+
 // RUN: %clang -target arm-none-linux-gnueabi -march=armv8.2a+dotprod -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-DOTPROD %s
 // CHECK-DOTPROD: #define __ARM_FEATURE_DOTPROD 1