8aa64edb34
This patch adds direct code-gen support for a faster MOD intrinsic for REAL types. Flang has maintained and keeps maintaining a high-precision implementation of the MOD intrinsic as part of the Fortran runtime. With the -ffast-real-mod flag, users can opt to avoid calling into the Fortran runtime, but instead trigger code-gen that produces faster code by avoiding the runtime call, at the expense of potentially risking bit cancelation by having the compiler use the MOD formula a specified by ISO Fortran.
70 lines
2.8 KiB
Modula-2
70 lines
2.8 KiB
Modula-2
//===------ LangOptions.def - Code generation option database ----- C++ -*-===//
|
|
//
|
|
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
|
|
// See https://llvm.org/LICENSE.txt for license information.
|
|
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// This file defines the language dialect options. Users of this file
|
|
// must define the LANGOPT macro to make use of this information.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
#ifndef LANGOPT
|
|
# error Define the LANGOPT macro to handle language options
|
|
#endif
|
|
|
|
#ifndef ENUM_LANGOPT
|
|
# define ENUM_LANGOPT(Name, Type, Bits, Default) \
|
|
LANGOPT(Name, Bits, Default)
|
|
#endif
|
|
|
|
ENUM_LANGOPT(FPContractMode, FPModeKind, 2, FPM_Fast) ///< FP Contract Mode (off/fast)
|
|
/// signed integer overflow handling
|
|
ENUM_LANGOPT(SignedOverflowBehavior, SignedOverflowBehaviorTy, 1, SOB_Undefined)
|
|
|
|
/// Indicate a build without the standard GPU libraries.
|
|
LANGOPT(NoGPULib , 1, false)
|
|
/// Permit floating point optimization without regard to infinities
|
|
LANGOPT(NoHonorInfs, 1, false)
|
|
/// Permit floating point optimization without regard to NaN
|
|
LANGOPT(NoHonorNaNs, 1, false)
|
|
/// Allow math functions to be replaced with an approximately equivalent
|
|
/// calculation
|
|
LANGOPT(ApproxFunc, 1, false)
|
|
/// Allow optimizations that ignore the sign of floating point zeros
|
|
LANGOPT(NoSignedZeros, 1, false)
|
|
/// Allow reassociation transformations for floating-point instructions
|
|
LANGOPT(AssociativeMath, 1, false)
|
|
/// Allow division operations to be reassociated
|
|
LANGOPT(ReciprocalMath, 1, false)
|
|
/// Specify version of OpenMP standard
|
|
LANGOPT(OpenMPVersion, 31, 0)
|
|
/// Generate code only for OpenMP target device
|
|
LANGOPT(OpenMPIsTargetDevice, 1, false)
|
|
/// Generate OpenMP target code only for GPUs
|
|
LANGOPT(OpenMPIsGPU, 1, false)
|
|
/// Generate OpenMP target code only for GPUs
|
|
LANGOPT(OpenMPForceUSM, 1, false)
|
|
/// Enable debugging in the OpenMP offloading device RTL
|
|
LANGOPT(OpenMPTargetDebug, 32, 0)
|
|
/// Assume work-shared loops do not have more iterations than participating
|
|
/// threads.
|
|
LANGOPT(OpenMPThreadSubscription, 1, 0)
|
|
/// Assume distributed loops do not have more iterations than participating
|
|
/// teams.
|
|
LANGOPT(OpenMPTeamSubscription, 1, 0)
|
|
/// Assume that no thread in a parallel region will modify an ICV.
|
|
LANGOPT(OpenMPNoThreadState, 1, 0)
|
|
/// Assume that no thread in a parallel region will encounter a parallel region
|
|
LANGOPT(OpenMPNoNestedParallelism, 1, 0)
|
|
/// Use SIMD only OpenMP support.
|
|
LANGOPT(OpenMPSimd, 1, false)
|
|
/// Enable fast MOD operations for REAL
|
|
LANGOPT(NoFastRealMod, 1, false)
|
|
LANGOPT(VScaleMin, 32, 0) ///< Minimum vscale range value
|
|
LANGOPT(VScaleMax, 32, 0) ///< Maximum vscale range value
|
|
|
|
#undef LANGOPT
|
|
#undef ENUM_LANGOPT
|