Author: Zahira Ammarguellat Date: 2021-11-19T08:59:50-05:00 New Revision: 6623c02d70c3732dbea59c6d79c69501baf9627b
URL: https://github.com/llvm/llvm-project/commit/6623c02d70c3732dbea59c6d79c69501baf9627b DIFF: https://github.com/llvm/llvm-project/commit/6623c02d70c3732dbea59c6d79c69501baf9627b.diff LOG: 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. Added: clang/test/CodeGen/X86/Float16-arithmetic.c clang/test/CodeGen/X86/fp16-abi.c clang/test/CodeGen/X86/fp16-complex.c Modified: clang/docs/LanguageExtensions.rst clang/docs/ReleaseNotes.rst clang/lib/Basic/Targets/X86.cpp clang/test/Sema/Float16.c clang/test/Sema/conversion-target-dep.c clang/test/SemaCXX/Float16.cpp Removed: clang/test/CodeGen/X86/avx512fp16-abi.c clang/test/CodeGen/X86/avx512fp16-complex.c ################################################################################ diff --git a/clang/docs/LanguageExtensions.rst b/clang/docs/LanguageExtensions.rst index 60b1ed383a1ff..dfdb01b8ff542 100644 --- a/clang/docs/LanguageExtensions.rst +++ b/clang/docs/LanguageExtensions.rst @@ -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. diff --git a/clang/docs/ReleaseNotes.rst b/clang/docs/ReleaseNotes.rst index 104d2e908d809..d2fa7ff05a160 100644 --- a/clang/docs/ReleaseNotes.rst +++ b/clang/docs/ReleaseNotes.rst @@ -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 -------------------------------- diff --git a/clang/lib/Basic/Targets/X86.cpp b/clang/lib/Basic/Targets/X86.cpp index 454a7743dded3..5e36868937194 100644 --- a/clang/lib/Basic/Targets/X86.cpp +++ b/clang/lib/Basic/Targets/X86.cpp @@ -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. diff --git a/clang/test/CodeGen/X86/Float16-arithmetic.c b/clang/test/CodeGen/X86/Float16-arithmetic.c new file mode 100644 index 0000000000000..7f7b3ff594424 --- /dev/null +++ b/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{{.*}} 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; +} + + diff --git a/clang/test/CodeGen/X86/avx512fp16-abi.c b/clang/test/CodeGen/X86/fp16-abi.c similarity index 94% rename from clang/test/CodeGen/X86/avx512fp16-abi.c rename to clang/test/CodeGen/X86/fp16-abi.c index 1144274280557..62a914f878c7b 100644 --- a/clang/test/CodeGen/X86/avx512fp16-abi.c +++ b/clang/test/CodeGen/X86/fp16-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; diff --git a/clang/test/CodeGen/X86/avx512fp16-complex.c b/clang/test/CodeGen/X86/fp16-complex.c similarity index 96% rename from clang/test/CodeGen/X86/avx512fp16-complex.c rename to clang/test/CodeGen/X86/fp16-complex.c index 8a6b50eb0056b..ebb290c976e7d 100644 --- a/clang/test/CodeGen/X86/avx512fp16-complex.c +++ b/clang/test/CodeGen/X86/fp16-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( diff --git a/clang/test/Sema/Float16.c b/clang/test/Sema/Float16.c index ff0bf9043a675..34f0af71c7919 100644 --- a/clang/test/Sema/Float16.c +++ b/clang/test/Sema/Float16.c @@ -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}} diff --git a/clang/test/Sema/conversion-target-dep.c b/clang/test/Sema/conversion-target-dep.c index e16685fa0674d..6c14750c4d209 100644 --- a/clang/test/Sema/conversion-target-dep.c +++ b/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'}} diff --git a/clang/test/SemaCXX/Float16.cpp b/clang/test/SemaCXX/Float16.cpp index f27c3839854e1..c5fdc7af58a3f 100644 --- a/clang/test/SemaCXX/Float16.cpp +++ b/clang/test/SemaCXX/Float16.cpp @@ -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 _______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits