[AArch64] Always allow the __bf16 type

We would like to make the ACLE NEON and SVE intrinsics more useable by
gating them on the target, not by ifdef preprocessor macros. In order to
do this the types they use need to be available. This patches makes
__bf16 always available under AArch64 not just when the bf16
architecture feature is present. This bringing it in-line with GCC. In
subsequent patches the NEON bfloat16x8_t and SVE svbfloat16_t types
(along with bfloat16_t used in arm_sve.h) will be made unconditional
too.

The operations valid on the types are still very limited. They can be
used as a storage type, but the intrinsics used for convertions are
still behind an ifdef guard in arm_neon.h/arm_bf16.h.

Differential Revision: https://reviews.llvm.org/D130973

diff --git a/clang/docs/LanguageExtensions.rst b/clang/docs/LanguageExtensions.rst
index 1b82363..52931cc 100644 (file)
--- a/clang/docs/LanguageExtensions.rst
+++ b/clang/docs/LanguageExtensions.rst
@@ -757,8 +757,6 @@ performing the operation, and then truncating to ``_Float16``.
 * 32-bit ARM
 * 64-bit ARM (AArch64)
 
-The ``__bf16`` type is only available when supported in hardware.
-
 ``__fp16`` is a storage and interchange format only.  This means that values of
 ``__fp16`` are immediately promoted to (at least) ``float`` when used in arithmetic
 operations, so that e.g. the result of adding two ``__fp16`` values has type ``float``.

diff --git a/clang/lib/Basic/Targets/AArch64.cpp b/clang/lib/Basic/Targets/AArch64.cpp
index 60ef52a..8612138 100644 (file)
--- a/clang/lib/Basic/Targets/AArch64.cpp
+++ b/clang/lib/Basic/Targets/AArch64.cpp
@@ -670,6 +670,10 @@ bool AArch64TargetInfo::handleTargetFeatures(std::vector<std::string> &Features,
   return true;
 }
 
+bool AArch64TargetInfo::hasBFloat16Type() const {
+  return true;
+}
+
 TargetInfo::CallingConvCheckResult
 AArch64TargetInfo::checkCallingConvention(CallingConv CC) const {
   switch (CC) {

diff --git a/clang/lib/Basic/Targets/AArch64.h b/clang/lib/Basic/Targets/AArch64.h
index bd6812d..e28a4c5 100644 (file)
--- a/clang/lib/Basic/Targets/AArch64.h
+++ b/clang/lib/Basic/Targets/AArch64.h
@@ -116,6 +116,8 @@ public:
   bool handleTargetFeatures(std::vector<std::string> &Features,
                             DiagnosticsEngine &Diags) override;
 
+  bool hasBFloat16Type() const override;
+
   CallingConvCheckResult checkCallingConvention(CallingConv CC) const override;
 
   bool isCLZForZeroUndef() const override;

diff --git a/clang/test/CodeGen/arm-bf16-params-returns.c b/clang/test/CodeGen/arm-bf16-params-returns.c
index c9e1efb..d4d0e6c 100644 (file)
--- a/clang/test/CodeGen/arm-bf16-params-returns.c
+++ b/clang/test/CodeGen/arm-bf16-params-returns.c
@@ -1,6 +1,7 @@
 // RUN: %clang_cc1 -triple armv8.6a-arm-none-eabi -target-abi aapcs -mfloat-abi hard -target-feature +bf16 -target-feature +neon -emit-llvm -O2 -o - %s | opt -S -mem2reg -sroa | FileCheck %s --check-prefix=CHECK32-HARD
 // RUN: %clang_cc1 -triple armv8.6a-arm-none-eabi -target-abi aapcs -mfloat-abi softfp -target-feature +bf16 -target-feature +neon -emit-llvm -O2 -o - %s | opt -S -mem2reg -sroa | FileCheck %s --check-prefix=CHECK32-SOFTFP
-// RUN: %clang_cc1 -triple aarch64-arm-none-eabi -target-abi aapcs -target-feature +bf16 -target-feature +neon -emit-llvm -O2 -o - %s | opt -S -mem2reg -sroa | FileCheck %s --check-prefix=CHECK64
+// RUN: %clang_cc1 -triple aarch64-arm-none-eabi -target-abi aapcs -target-feature +bf16 -target-feature +neon -emit-llvm -O2 -o - %s | opt -S -mem2reg -sroa | FileCheck %s --check-prefixes=CHECK64,CHECK64NEON
+// RUN: %clang_cc1 -triple aarch64-arm-none-eabi -target-abi aapcs -target-feature -bf16 -target-feature +neon -DNONEON -emit-llvm -O2 -o - %s | opt -S -mem2reg -sroa | FileCheck %s --check-prefix=CHECK64
 
 // REQUIRES: aarch64-registered-target || arm-registered-target
 
@@ -17,6 +18,8 @@ __bf16 test_ret_bf16(__bf16 v) {
 // CHECK64: define{{.*}} bfloat @test_ret_bf16(bfloat noundef returned %v) {{.*}} {
 // CHECK64: ret bfloat %v
 
+#ifndef NONEON
+
 bfloat16x4_t test_ret_bf16x4_t(bfloat16x4_t v) {
   return v;
 }
@@ -24,5 +27,7 @@ bfloat16x4_t test_ret_bf16x4_t(bfloat16x4_t v) {
 // CHECK32-HARD: ret <4 x bfloat> %v
 // CHECK32-SOFTFP: define{{.*}} <2 x i32> @test_ret_bf16x4_t(<2 x i32> [[V0:.*]]) {{.*}} {
 // CHECK32-SOFTFP: ret <2 x i32> %v
-// CHECK64: define{{.*}} <4 x bfloat> @test_ret_bf16x4_t(<4 x bfloat> noundef returned %v) {{.*}} {
-// CHECK64: ret <4 x bfloat> %v
+// CHECK64NEON: define{{.*}} <4 x bfloat> @test_ret_bf16x4_t(<4 x bfloat> noundef returned %v) {{.*}} {
+// CHECK64NEON: ret <4 x bfloat> %v
+
+#endif
\ No newline at end of file

diff --git a/clang/test/CodeGen/arm-mangle-bf16.cpp b/clang/test/CodeGen/arm-mangle-bf16.cpp
index c591217..6dd4a11 100644 (file)
--- a/clang/test/CodeGen/arm-mangle-bf16.cpp
+++ b/clang/test/CodeGen/arm-mangle-bf16.cpp
@@ -1,4 +1,5 @@
 // RUN: %clang_cc1 -triple aarch64-arm-none-eabi -target-feature +bf16 -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -triple aarch64-arm-none-eabi -target-feature -bf16 -emit-llvm -o - %s | FileCheck %s
 // RUN: %clang_cc1 -triple arm-arm-none-eabi -target-feature +bf16 -mfloat-abi hard -emit-llvm -o - %s | FileCheck %s
 // RUN: %clang_cc1 -triple arm-arm-none-eabi -target-feature +bf16 -mfloat-abi softfp -emit-llvm -o - %s | FileCheck %s
 

diff --git a/clang/test/Sema/arm-bf16-forbidden-ops.c b/clang/test/Sema/arm-bf16-forbidden-ops.c
index 22a7534..0311e7b 100644 (file)
--- a/clang/test/Sema/arm-bf16-forbidden-ops.c
+++ b/clang/test/Sema/arm-bf16-forbidden-ops.c
@@ -1,4 +1,5 @@
 // RUN: %clang_cc1 -fsyntax-only -verify -triple aarch64 -target-feature +bf16 %s
+// RUN: %clang_cc1 -fsyntax-only -verify -triple aarch64 -target-feature -bf16 %s
 
 __bf16 test_cast_from_float(float in) {
   return (__bf16)in; // expected-error {{cannot type-cast to __bf16}}

diff --git a/clang/test/Sema/arm-bf16-forbidden-ops.cpp b/clang/test/Sema/arm-bf16-forbidden-ops.cpp
index 0e1a6e0..2a10fd1 100644 (file)
--- a/clang/test/Sema/arm-bf16-forbidden-ops.cpp
+++ b/clang/test/Sema/arm-bf16-forbidden-ops.cpp
@@ -1,4 +1,5 @@
 // RUN: %clang_cc1 -fsyntax-only -verify -triple aarch64 -target-feature +bf16 %s
+// RUN: %clang_cc1 -fsyntax-only -verify -triple aarch64 -target-feature -bf16 %s
 
 __bf16 test_static_cast_from_float(float in) {
   return static_cast<__bf16>(in); // expected-error {{static_cast from 'float' to '__bf16' is not allowed}}

diff --git a/clang/test/Sema/arm-bfloat.cpp b/clang/test/Sema/arm-bfloat.cpp
index b24c320..df3cb8a 100644 (file)
--- a/clang/test/Sema/arm-bfloat.cpp
+++ b/clang/test/Sema/arm-bfloat.cpp
@@ -1,49 +1,57 @@
-// RUN: %clang_cc1 -fsyntax-only -verify -std=c++11 \
-// RUN: -triple aarch64-arm-none-eabi -target-cpu cortex-a75 \
-// RUN: -target-feature +bf16 -target-feature +neon %s
-// RUN: %clang_cc1 -fsyntax-only -verify -std=c++11 \
-// RUN: -triple arm-arm-none-eabi -target-cpu cortex-a53 \
-// RUN: -target-feature +bf16 -target-feature +neon %s
+// RUN: %clang_cc1 -fsyntax-only -verify=scalar,neon -std=c++11 \
+// RUN:   -triple aarch64-arm-none-eabi -target-cpu cortex-a75 \
+// RUN:   -target-feature +bf16 -target-feature +neon %s
+// RUN: %clang_cc1 -fsyntax-only -verify=scalar,neon -std=c++11 \
+// RUN:   -triple arm-arm-none-eabi -target-cpu cortex-a53 \
+// RUN:   -target-feature +bf16 -target-feature +neon %s
+
+// The types should be available under AArch64 even without the bf16 feature
+// RUN: %clang_cc1 -fsyntax-only -verify=scalar -DNONEON -std=c++11 \
+// RUN:   -triple aarch64-arm-none-eabi -target-cpu cortex-a75 \
+// RUN:   -target-feature -bf16 -target-feature +neon %s
 
 // REQUIRES: aarch64-registered-target || arm-registered-target
 
 void test(bool b) {
   __bf16 bf16;
 
-  bf16 + bf16; // expected-error {{invalid operands to binary expression ('__bf16' and '__bf16')}}
-  bf16 - bf16; // expected-error {{invalid operands to binary expression ('__bf16' and '__bf16')}}
-  bf16 * bf16; // expected-error {{invalid operands to binary expression ('__bf16' and '__bf16')}}
-  bf16 / bf16; // expected-error {{invalid operands to binary expression ('__bf16' and '__bf16')}}
+  bf16 + bf16; // scalar-error {{invalid operands to binary expression ('__bf16' and '__bf16')}}
+  bf16 - bf16; // scalar-error {{invalid operands to binary expression ('__bf16' and '__bf16')}}
+  bf16 * bf16; // scalar-error {{invalid operands to binary expression ('__bf16' and '__bf16')}}
+  bf16 / bf16; // scalar-error {{invalid operands to binary expression ('__bf16' and '__bf16')}}
 
   __fp16 fp16;
 
-  bf16 + fp16; // expected-error {{invalid operands to binary expression ('__bf16' and '__fp16')}}
-  fp16 + bf16; // expected-error {{invalid operands to binary expression ('__fp16' and '__bf16')}}
-  bf16 - fp16; // expected-error {{invalid operands to binary expression ('__bf16' and '__fp16')}}
-  fp16 - bf16; // expected-error {{invalid operands to binary expression ('__fp16' and '__bf16')}}
-  bf16 * fp16; // expected-error {{invalid operands to binary expression ('__bf16' and '__fp16')}}
-  fp16 * bf16; // expected-error {{invalid operands to binary expression ('__fp16' and '__bf16')}}
-  bf16 / fp16; // expected-error {{invalid operands to binary expression ('__bf16' and '__fp16')}}
-  fp16 / bf16; // expected-error {{invalid operands to binary expression ('__fp16' and '__bf16')}}
-  bf16 = fp16; // expected-error {{assigning to '__bf16' from incompatible type '__fp16'}}
-  fp16 = bf16; // expected-error {{assigning to '__fp16' from incompatible type '__bf16'}}
-  bf16 + (b ? fp16 : bf16); // expected-error {{incompatible operand types ('__fp16' and '__bf16')}}
+  bf16 + fp16; // scalar-error {{invalid operands to binary expression ('__bf16' and '__fp16')}}
+  fp16 + bf16; // scalar-error {{invalid operands to binary expression ('__fp16' and '__bf16')}}
+  bf16 - fp16; // scalar-error {{invalid operands to binary expression ('__bf16' and '__fp16')}}
+  fp16 - bf16; // scalar-error {{invalid operands to binary expression ('__fp16' and '__bf16')}}
+  bf16 * fp16; // scalar-error {{invalid operands to binary expression ('__bf16' and '__fp16')}}
+  fp16 * bf16; // scalar-error {{invalid operands to binary expression ('__fp16' and '__bf16')}}
+  bf16 / fp16; // scalar-error {{invalid operands to binary expression ('__bf16' and '__fp16')}}
+  fp16 / bf16; // scalar-error {{invalid operands to binary expression ('__fp16' and '__bf16')}}
+  bf16 = fp16; // scalar-error {{assigning to '__bf16' from incompatible type '__fp16'}}
+  fp16 = bf16; // scalar-error {{assigning to '__fp16' from incompatible type '__bf16'}}
+  bf16 + (b ? fp16 : bf16); // scalar-error {{incompatible operand types ('__fp16' and '__bf16')}}
 }
 
+#ifndef NONEON
+
 #include <arm_neon.h>
 
 void test_vector(bfloat16x4_t a, bfloat16x4_t b, float16x4_t c) {
-  a + b; // expected-error {{invalid operands to binary expression ('bfloat16x4_t' (vector of 4 'bfloat16_t' values) and 'bfloat16x4_t')}}
-  a - b; // expected-error {{invalid operands to binary expression ('bfloat16x4_t' (vector of 4 'bfloat16_t' values) and 'bfloat16x4_t')}}
-  a * b; // expected-error {{invalid operands to binary expression ('bfloat16x4_t' (vector of 4 'bfloat16_t' values) and 'bfloat16x4_t')}}
-  a / b; // expected-error {{invalid operands to binary expression ('bfloat16x4_t' (vector of 4 'bfloat16_t' values) and 'bfloat16x4_t')}}
-
-  a + c; // expected-error {{invalid operands to binary expression ('bfloat16x4_t' (vector of 4 'bfloat16_t' values) and 'float16x4_t' (vector of 4 'float16_t' values))}}
-  a - c; // expected-error {{invalid operands to binary expression ('bfloat16x4_t' (vector of 4 'bfloat16_t' values) and 'float16x4_t' (vector of 4 'float16_t' values))}}
-  a * c; // expected-error {{invalid operands to binary expression ('bfloat16x4_t' (vector of 4 'bfloat16_t' values) and 'float16x4_t' (vector of 4 'float16_t' values))}}
-  a / c; // expected-error {{invalid operands to binary expression ('bfloat16x4_t' (vector of 4 'bfloat16_t' values) and 'float16x4_t' (vector of 4 'float16_t' values))}}
-  c + b; // expected-error {{invalid operands to binary expression ('float16x4_t' (vector of 4 'float16_t' values) and 'bfloat16x4_t' (vector of 4 'bfloat16_t' values))}}
-  c - b; // expected-error {{invalid operands to binary expression ('float16x4_t' (vector of 4 'float16_t' values) and 'bfloat16x4_t' (vector of 4 'bfloat16_t' values))}}
-  c * b; // expected-error {{invalid operands to binary expression ('float16x4_t' (vector of 4 'float16_t' values) and 'bfloat16x4_t' (vector of 4 'bfloat16_t' values))}}
-  c / b; // expected-error {{invalid operands to binary expression ('float16x4_t' (vector of 4 'float16_t' values) and 'bfloat16x4_t' (vector of 4 'bfloat16_t' values))}}
+  a + b; // neon-error {{invalid operands to binary expression ('bfloat16x4_t' (vector of 4 'bfloat16_t' values) and 'bfloat16x4_t')}}
+  a - b; // neon-error {{invalid operands to binary expression ('bfloat16x4_t' (vector of 4 'bfloat16_t' values) and 'bfloat16x4_t')}}
+  a * b; // neon-error {{invalid operands to binary expression ('bfloat16x4_t' (vector of 4 'bfloat16_t' values) and 'bfloat16x4_t')}}
+  a / b; // neon-error {{invalid operands to binary expression ('bfloat16x4_t' (vector of 4 'bfloat16_t' values) and 'bfloat16x4_t')}}
+
+  a + c; // neon-error {{invalid operands to binary expression ('bfloat16x4_t' (vector of 4 'bfloat16_t' values) and 'float16x4_t' (vector of 4 'float16_t' values))}}
+  a - c; // neon-error {{invalid operands to binary expression ('bfloat16x4_t' (vector of 4 'bfloat16_t' values) and 'float16x4_t' (vector of 4 'float16_t' values))}}
+  a * c; // neon-error {{invalid operands to binary expression ('bfloat16x4_t' (vector of 4 'bfloat16_t' values) and 'float16x4_t' (vector of 4 'float16_t' values))}}
+  a / c; // neon-error {{invalid operands to binary expression ('bfloat16x4_t' (vector of 4 'bfloat16_t' values) and 'float16x4_t' (vector of 4 'float16_t' values))}}
+  c + b; // neon-error {{invalid operands to binary expression ('float16x4_t' (vector of 4 'float16_t' values) and 'bfloat16x4_t' (vector of 4 'bfloat16_t' values))}}
+  c - b; // neon-error {{invalid operands to binary expression ('float16x4_t' (vector of 4 'float16_t' values) and 'bfloat16x4_t' (vector of 4 'bfloat16_t' values))}}
+  c * b; // neon-error {{invalid operands to binary expression ('float16x4_t' (vector of 4 'float16_t' values) and 'bfloat16x4_t' (vector of 4 'bfloat16_t' values))}}
+  c / b; // neon-error {{invalid operands to binary expression ('float16x4_t' (vector of 4 'float16_t' values) and 'bfloat16x4_t' (vector of 4 'bfloat16_t' values))}}
 }
+#endif
\ No newline at end of file