make.inc.macos

#//////////////////////////////////////////////////////////////////////////////
#   -- MAGMA (version 2.0) --
#      Univ. of Tennessee, Knoxville
#      Univ. of California, Berkeley
#      Univ. of Colorado, Denver
#      @date
#//////////////////////////////////////////////////////////////////////////////

# --------------------
# programs
#
# Note: if clBLAS is compiled with Apple's cc,
# you must use Apple's cc here, too, not GNU gcc/g++. Else the stack alignment
# for float-complex seems to be different (clblasCgemm calls fails).

CC        = cc
CXX       = c++
FORT      = gfortran

ARCH      = ar
ARCHFLAGS = cr
RANLIB    = ranlib


# --------------------
# flags

# use -m32 to compile with 32-bit long & pointers.
# use -m64 to compile with 64-bit long & pointers (lp64). int is still 32-bit.
# add -DNDEBUG to disable asserts and certain error checks.
#
# MacOS veclib has a bug where some single precision functions return
# a double precision result, for instance slange.
# This is observed with -m64, but oddly not with -m32.
# The easiest fix is to replace those routines with correct ones from LAPACK.
# See BLAS_FIX below.
# Alternatively, don't link with the veclib/accelerate framework;
# use a different BLAS and LAPACK library.

# Use -fPIC to make shared (.so) and static (.a) library;
# can be commented out if making only static library.
FPIC      = -fPIC

# Apple's clang compiler doesn't have OpenMP
# gcc/g++/gfortran with OpenMP is available from http://hpc.sourceforge.net/
# Add -fopenmp to CFLAGS and LDFLAGS as in make.inc.mkl-gcc
CFLAGS    = -m64 -O3 $(FPIC) -DADD_ -Wall -Wshadow -DMAGMA_NOAFFINITY
FFLAGS    = -m64 -O3 $(FPIC) -DADD_ -Wall -Wno-unused-dummy-argument
F90FLAGS  = -m64 -O3 $(FPIC) -DADD_ -Wall -Wno-unused-dummy-argument -x f95-cpp-input
LDFLAGS   = -m64     $(FPIC)

# Options to do extra checks for non-standard things like variable length arrays;
# it is safe to disable all these
CFLAGS   += -pedantic -Wno-long-long
#CFLAGS   += -Werror  # uncomment to ensure all warnings are dealt with

# C++11 (gcc >= 4.7) is not required, but has benefits like atomic operations
CXXFLAGS := $(CFLAGS) -std=c++11
CFLAGS   += -std=c99

# MacOS likes the library's path to be set
INSTALL_NAME = -install_name @rpath/


# --------------------
# libraries

LIB       = -framework Accelerate -lstdc++ -lm

LIB      += -lclBLAS -framework OpenCL


# --------------------
# directories

# define library directories preferably in your environment, or here.
#clBLAS  ?= /opt/clBLAS
-include make.check-clblas

LIBDIR    = -L$(clBLAS)/lib

INC       = -I$(clBLAS)/include


# ========================================
# replace single & single-complex BLAS functions with reference versions.
# (i.e., functions that return float; subroutines do not need a fix.)
# Prepends -lblas_fix to LIB; see Makefile.
blas_fix = 1