maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

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.
This commit is contained in:
Zahira Ammarguellat 2021-11-17 11:53:36 -05:00
parent c2271926a4
commit 6623c02d70
9 changed files with 86 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
clang/docs/LanguageExtensions.rst
View File

@ -673,7 +673,7 @@ targets pending ABI standardization:
* 64-bit ARM (AArch64)
* AMDGPU
* SPIR
* X86 (Only available under feature AVX512-FP16)
* X86 (Available with feature SSE2 and up enabled)
``_Float16`` will be supported on more targets as they define ABIs for it.

1
clang/docs/ReleaseNotes.rst
View File

@ -187,6 +187,7 @@ X86 Support in Clang
--------------------
- Support for ``AVX512-FP16`` instructions has been added.
- Support for ``_Float16`` type has been added.
Arm and AArch64 Support in Clang
--------------------------------

4
clang/lib/Basic/Targets/X86.cpp
View File

@ -239,9 +239,9 @@ bool X86TargetInfo::handleTargetFeatures(std::vector<std::string> &Features,
HasAVX512ER = true;
} else if (Feature == "+avx512fp16") {
HasAVX512FP16 = true;
HasFloat16 = true;
} else if (Feature == "+avx512pf") {
HasAVX512PF = true;
HasLegalHalfType = true;
} else if (Feature == "+avx512dq") {
HasAVX512DQ = true;
} else if (Feature == "+avx512bitalg") {
@ -369,6 +369,8 @@ bool X86TargetInfo::handleTargetFeatures(std::vector<std::string> &Features,
.Default(NoXOP);
XOPLevel = std::max(XOPLevel, XLevel);
}
// Turn on _float16 for x86 (feature sse2)
HasFloat16 = SSELevel >= SSE2;
// LLVM doesn't have a separate switch for fpmath, so only accept it if it
// matches the selected sse level.

73
clang/test/CodeGen/X86/Float16-arithmetic.c Normal file
View File

@ -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{{.*}} 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;
}

2
clang/test/CodeGen/X86/avx512fp16-abi.c → clang/test/CodeGen/X86/fp16-abi.c
View File

@ -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;

1
clang/test/CodeGen/X86/avx512fp16-complex.c → clang/test/CodeGen/X86/fp16-complex.c
View File

@ -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(

3
clang/test/Sema/Float16.c
View File

@ -1,8 +1,9 @@
// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc %s
// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc %s -DHAVE
// 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 i386-pc-linux-gnu %s
#ifndef HAVE
// expected-error@+2{{_Float16 is not supported on this target}}

2
clang/test/Sema/conversion-target-dep.c
View File

@ -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'}}

3
clang/test/SemaCXX/Float16.cpp
View File

@ -1,7 +1,8 @@
// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc %s
// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc %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 i386-pc-linux-gnu %s
#ifdef HAVE
// expected-no-diagnostics