zahiraam created this revision.
zahiraam added reviewers: rjmccall, pengfei, andrew.w.kaylor.
zahiraam requested review of this revision.
Herald added a project: clang.
The _Float16 type is supported on x86 systems with SSE2 enabled. Operations are
emulated by software emulation and “float” instructions. This patch is allowing
the support of _Float16 type without the use of -max512fp16 flag. The final
goal being, perform _Float16 emulation for all arithmetic expressions.
Repository:
rG LLVM Github Monorepo
https://reviews.llvm.org/D114099
Files:
clang/docs/LanguageExtensions.rst
clang/docs/ReleaseNotes.rst
clang/lib/Basic/Targets/X86.cpp
clang/test/CodeGen/X86/Float16-arithmetic.c
clang/test/CodeGen/X86/avx512fp16-abi.c
clang/test/CodeGen/X86/avx512fp16-complex.c
clang/test/CodeGen/X86/fp16-abi.c
clang/test/Sema/Float16.c
clang/test/Sema/conversion-target-dep.c
clang/test/SemaCXX/Float16.cpp
Index: clang/test/SemaCXX/Float16.cpp
===================================================================
--- clang/test/SemaCXX/Float16.cpp
+++ clang/test/SemaCXX/Float16.cpp
@@ -1,18 +1,9 @@
// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc %s
-// RUN: %clang_cc1 -fsyntax-only -verify -triple spir-unknown-unknown %s -DHAVE
-// RUN: %clang_cc1 -fsyntax-only -verify -triple armv7a-linux-gnu %s -DHAVE
-// RUN: %clang_cc1 -fsyntax-only -verify -triple aarch64-linux-gnu %s -DHAVE
+// RUN: %clang_cc1 -fsyntax-only -verify -triple spir-unknown-unknown %s
+// RUN: %clang_cc1 -fsyntax-only -verify -triple armv7a-linux-gnu %s
+// RUN: %clang_cc1 -fsyntax-only -verify -triple aarch64-linux-gnu %s
-#ifdef HAVE
// expected-no-diagnostics
-#endif // HAVE
-#ifndef HAVE
-// expected-error@+2{{_Float16 is not supported on this target}}
-#endif // !HAVE
_Float16 f;
-
-#ifndef HAVE
-// expected-error@+2{{invalid suffix 'F16' on floating constant}}
-#endif // !HAVE
const auto g = 1.1F16;
Index: clang/test/Sema/conversion-target-dep.c
===================================================================
--- clang/test/Sema/conversion-target-dep.c
+++ clang/test/Sema/conversion-target-dep.c
@@ -6,7 +6,7 @@
long double ld;
double d;
-_Float16 f16; // x86-error {{_Float16 is not supported on this target}}
+_Float16 f16;
int main() {
ld = d; // x86-warning {{implicit conversion increases floating-point precision: 'double' to 'long double'}}
Index: clang/test/Sema/Float16.c
===================================================================
--- clang/test/Sema/Float16.c
+++ clang/test/Sema/Float16.c
@@ -1,18 +1,13 @@
// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc %s
-// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc -target-feature +avx512fp16 %s -DHAVE
-// RUN: %clang_cc1 -fsyntax-only -verify -triple spir-unknown-unknown %s -DHAVE
-// RUN: %clang_cc1 -fsyntax-only -verify -triple armv7a-linux-gnu %s -DHAVE
-// RUN: %clang_cc1 -fsyntax-only -verify -triple aarch64-linux-gnu %s -DHAVE
+// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc -target-feature +avx512fp16 %s
+// RUN: %clang_cc1 -fsyntax-only -verify -triple spir-unknown-unknown %s
+// RUN: %clang_cc1 -fsyntax-only -verify -triple armv7a-linux-gnu %s
+// RUN: %clang_cc1 -fsyntax-only -verify -triple aarch64-linux-gnu %s
-#ifndef HAVE
-// expected-error@+2{{_Float16 is not supported on this target}}
-#endif // HAVE
_Float16 f;
-#ifdef HAVE
_Complex _Float16 a;
void builtin_complex() {
_Float16 a = 0;
(void)__builtin_complex(a, a); // expected-error {{'_Complex _Float16' is invalid}}
}
-#endif
Index: clang/test/CodeGen/X86/fp16-abi.c
===================================================================
--- /dev/null
+++ clang/test/CodeGen/X86/fp16-abi.c
@@ -0,0 +1,113 @@
+// RUN: %clang_cc1 -triple x86_64-linux -emit-llvm < %s | FileCheck %s
+
+struct half1 {
+ _Float16 a;
+};
+
+struct half1 h1(_Float16 a) {
+ // CHECK: define{{.*}}half @h1
+ struct half1 x;
+ x.a = a;
+ return x;
+}
+
+struct half2 {
+ _Float16 a;
+ _Float16 b;
+};
+
+struct half2 h2(_Float16 a, _Float16 b) {
+ // CHECK: define{{.*}}<2 x half> @h2
+ struct half2 x;
+ x.a = a;
+ x.b = b;
+ return x;
+}
+
+struct half3 {
+ _Float16 a;
+ _Float16 b;
+ _Float16 c;
+};
+
+struct half3 h3(_Float16 a, _Float16 b, _Float16 c) {
+ // CHECK: define{{.*}}<4 x half> @h3
+ struct half3 x;
+ x.a = a;
+ x.b = b;
+ x.c = c;
+ return x;
+}
+
+struct half4 {
+ _Float16 a;
+ _Float16 b;
+ _Float16 c;
+ _Float16 d;
+};
+
+struct half4 h4(_Float16 a, _Float16 b, _Float16 c, _Float16 d) {
+ // CHECK: define{{.*}}<4 x half> @h4
+ struct half4 x;
+ x.a = a;
+ x.b = b;
+ x.c = c;
+ x.d = d;
+ return x;
+}
+
+struct floathalf {
+ float a;
+ _Float16 b;
+};
+
+struct floathalf fh(float a, _Float16 b) {
+ // CHECK: define {{.*}} <4 x half> @fh
+ struct floathalf x;
+ x.a = a;
+ x.b = b;
+ return x;
+}
+
+struct floathalf2 {
+ float a;
+ _Float16 b;
+ _Float16 c;
+};
+
+struct floathalf2 fh2(float a, _Float16 b, _Float16 c) {
+ // CHECK: define {{.*}} <4 x half> @fh2
+ struct floathalf2 x;
+ x.a = a;
+ x.b = b;
+ x.c = c;
+ return x;
+}
+
+struct halffloat {
+ _Float16 a;
+ float b;
+};
+
+struct halffloat hf(_Float16 a, float b) {
+ // CHECK: define {{.*}} <4 x half> @hf
+ struct halffloat x;
+ x.a = a;
+ x.b = b;
+ return x;
+}
+
+struct half2float {
+ _Float16 a;
+ _Float16 b;
+ float c;
+};
+
+struct half2float h2f(_Float16 a, _Float16 b, float c) {
+ // CHECK: define {{.*}} <4 x half> @h2f
+ struct half2float x;
+ x.a = a;
+ x.b = b;
+ x.c = c;
+ return x;
+}
Index: clang/test/CodeGen/X86/avx512fp16-complex.c
===================================================================
--- clang/test/CodeGen/X86/avx512fp16-complex.c
+++ clang/test/CodeGen/X86/avx512fp16-complex.c
@@ -1,4 +1,5 @@
// RUN: %clang_cc1 %s -O0 -emit-llvm -triple x86_64-unknown-unknown -target-feature +avx512fp16 -o - | FileCheck %s --check-prefix=X86
+// RUN: %clang_cc1 %s -O0 -emit-llvm -triple x86_64-unknown-unknown -o - | FileCheck %s --check-prefix=X86
_Float16 _Complex add_half_rr(_Float16 a, _Float16 b) {
// X86-LABEL: @add_half_rr(
Index: clang/test/CodeGen/X86/avx512fp16-abi.c
===================================================================
--- clang/test/CodeGen/X86/avx512fp16-abi.c
+++ clang/test/CodeGen/X86/avx512fp16-abi.c
@@ -1,5 +1,7 @@
// RUN: %clang_cc1 -triple x86_64-linux -emit-llvm -target-feature +avx512fp16 < %s | FileCheck %s --check-prefixes=CHECK,CHECK-C
+// RUN: %clang_cc1 -triple x86_64-linux -emit-llvm < %s | FileCheck %s --check-prefixes=CHECK,CHECK-C
// RUN: %clang_cc1 -triple x86_64-linux -emit-llvm -target-feature +avx512fp16 -x c++ -std=c++11 < %s | FileCheck %s --check-prefixes=CHECK,CHECK-CPP
+// RUN: %clang_cc1 -triple x86_64-linux -emit-llvm -x c++ -std=c++11 < %s | FileCheck %s --check-prefixes=CHECK,CHECK-CPP
struct half1 {
_Float16 a;
Index: clang/test/CodeGen/X86/Float16-arithmetic.c
===================================================================
--- /dev/null
+++ clang/test/CodeGen/X86/Float16-arithmetic.c
@@ -0,0 +1,73 @@
+// RUN: %clang_cc1 -triple x86_64-unknown-unknown -emit-llvm \
+// RUN: < %s | FileCheck %s --check-prefixes=CHECK
+
+_Float16 add1(_Float16 a, _Float16 b) {
+ // CHECK-LABEL: define {{.*}} half @add1
+ // CHECK: alloca half
+ // CHECK: alloca half
+ // CHECK: store half {{.*}}, half*
+ // CHECK: store half {{.*}}, half*
+ // CHECK: load half, half*
+ // CHECK: load half, half* {{.*}}
+ // CHECK: fadd half {{.*}}, {{.*}}
+ // CHECK: ret half
+ return a + b;
+}
+
+_Float16 add2(_Float16 a, _Float16 b, _Float16 c) {
+ // CHECK-LABEL: define dso_local half @add2
+ // CHECK: alloca half
+ // CHECK: alloca half
+ // CHECK: alloca half
+ // CHECK: store half {{.*}}, half*
+ // CHECK: store half {{.*}}, half*
+ // CHECK: store half {{.*}}, half*
+ // CHECK: load half, half* {{.*}}
+ // CHECK: load half, half* {{.*}}
+ // CHECK: fadd half {{.*}}, {{.*}}
+ // CHECK: load half, half* {{.*}}
+ // CHECK: fadd half {{.*}}, {{.*}}
+ // CHECK: ret half
+ return a + b + c;
+}
+
+_Float16 sub(_Float16 a, _Float16 b) {
+ // CHECK-LABEL: define {{.*}} half @sub
+ // CHECK: alloca half
+ // CHECK: alloca half
+ // CHECK: store half {{.*}}, half*
+ // CHECK: store half {{.*}}, half*
+ // CHECK: load half, half*
+ // CHECK: load half, half* {{.*}}
+ // CHECK: fsub half {{.*}}, {{.*}}
+ // CHECK: ret half
+ return a - b;
+}
+
+_Float16 div(_Float16 a, _Float16 b) {
+ // CHECK-LABEL: define {{.*}} half @div
+ // CHECK: alloca half
+ // CHECK: alloca half
+ // CHECK: store half {{.*}}, half*
+ // CHECK: store half {{.*}}, half*
+ // CHECK: load half, half* {{.*}}
+ // CHECK: load half, half* {{.*}}
+ // CHECK: fdiv half {{.*}}, {{.*}}
+ // CHECK: ret half
+ return a / b;
+}
+
+_Float16 mul(_Float16 a, _Float16 b) {
+ // CHECK-LABEL: define {{.*}} half @mul
+ // CHECK: alloca half
+ // CHECK: alloca half
+ // CHECK: store half {{.*}}, half*
+ // CHECK: store half {{.*}}, half*
+ // CHECK: load half, half* {{.*}}
+ // CHECK: load half, half* {{.*}}
+ // CHECK: fmul half {{.*}}, {{.*}}
+ // CHECK: ret half
+ return a * b;
+}
+
+
Index: clang/lib/Basic/Targets/X86.cpp
===================================================================
--- clang/lib/Basic/Targets/X86.cpp
+++ clang/lib/Basic/Targets/X86.cpp
@@ -239,7 +239,6 @@
HasAVX512ER = true;
} else if (Feature == "+avx512fp16") {
HasAVX512FP16 = true;
- HasFloat16 = true;
} else if (Feature == "+avx512pf") {
HasAVX512PF = true;
} else if (Feature == "+avx512dq") {
@@ -369,6 +368,8 @@
.Default(NoXOP);
XOPLevel = std::max(XOPLevel, XLevel);
}
+ // Turn on _float16 for x86 (feature sse+)
+ HasFloat16 = SSELevel >= SSE2;
// LLVM doesn't have a separate switch for fpmath, so only accept it if it
// matches the selected sse level.
Index: clang/docs/ReleaseNotes.rst
===================================================================
--- clang/docs/ReleaseNotes.rst
+++ clang/docs/ReleaseNotes.rst
@@ -187,6 +187,7 @@
--------------------
- Support for ``AVX512-FP16`` instructions has been added.
+- Support for ``_Float16`` type has been added.
Arm and AArch64 Support in Clang
--------------------------------
Index: clang/docs/LanguageExtensions.rst
===================================================================
--- clang/docs/LanguageExtensions.rst
+++ clang/docs/LanguageExtensions.rst
@@ -673,7 +673,7 @@
* 64-bit ARM (AArch64)
* AMDGPU
* SPIR
-* X86 (Only available under feature AVX512-FP16)
+* X86
``_Float16`` will be supported on more targets as they define ABIs for it.
_______________________________________________
cfe-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
