Centre Blaise Pascal » HPL sur GPU

#

#  -- High Performance Computing Linpack Benchmark (HPL)

#     HPL - 2.0 - September 10, 2008

#     Antoine P. Petitet

#     University of Tennessee, Knoxville

#     Innovative Computing Laboratory

#     (C) Copyright 2000-2008 All Rights Reserved

#

#  -- Copyright notice and Licensing terms:

#

#  Redistribution  and  use in  source and binary forms, with or without

#  modification, are  permitted provided  that the following  conditions

#  are met:

#

#  1. Redistributions  of  source  code  must retain the above copyright

#  notice, this list of conditions and the following disclaimer.

#

#  2. Redistributions in binary form must reproduce  the above copyright

#  notice, this list of conditions,  and the following disclaimer in the

#  documentation and/or other materials provided with the distribution.

#

#  3. All  advertising  materials  mentioning  features  or  use of this

#  software must display the following acknowledgement:

#  This  product  includes  software  developed  at  the  University  of

#  Tennessee, Knoxville, Innovative Computing Laboratory.

#

#  4. The name of the  University,  the name of the  Laboratory,  or the

#  names  of  its  contributors  may  not  be used to endorse or promote

#  products  derived   from   this  software  without  specific  written

#  permission.

#

#  -- Disclaimer:

#

#  THIS  SOFTWARE  IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS

#  ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES,  INCLUDING,  BUT NOT

#  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR

#  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE UNIVERSITY

#  OR  CONTRIBUTORS  BE  LIABLE FOR ANY  DIRECT,  INDIRECT,  INCIDENTAL,

#  SPECIAL,  EXEMPLARY,  OR  CONSEQUENTIAL DAMAGES  (INCLUDING,  BUT NOT

#  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,

#  DATA OR PROFITS; OR BUSINESS INTERRUPTION)  HOWEVER CAUSED AND ON ANY

#  THEORY OF LIABILITY, WHETHER IN CONTRACT,  STRICT LIABILITY,  OR TORT

#  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE

#  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

# ######################################################################

#

# ----------------------------------------------------------------------

# - shell --------------------------------------------------------------

# ----------------------------------------------------------------------

#

SHELL        = /bin/sh

#

CD           = cd

CP           = cp

LN_S         = ln -s

MKDIR        = mkdir

RM           = /bin/rm -f

TOUCH        = touch

#

# ----------------------------------------------------------------------

# - Platform identifier ------------------------------------------------

# ----------------------------------------------------------------------

#

ARCH         = T3E_FBLAS

#

# ----------------------------------------------------------------------

# - HPL Directory Structure / HPL library ------------------------------

# ----------------------------------------------------------------------

#

TOPdir       = $(HOME)/hpl

INCdir       = $(TOPdir)/include

BINdir       = $(TOPdir)/bin/$(ARCH)

LIBdir       = $(TOPdir)/lib/$(ARCH)

#

HPLlib       = $(LIBdir)/libhpl.a

#

# ----------------------------------------------------------------------

# - Message Passing library (MPI) --------------------------------------

# ----------------------------------------------------------------------

# MPinc tells the  C  compiler where to find the Message Passing library

# header files,  MPlib  is defined  to be the name of  the library to be

# used. The variable MPdir is only used for defining MPinc and MPlib.

#

MPdir        =

MPinc        =

MPlib        =

#

# ----------------------------------------------------------------------

# - Linear Algebra library (BLAS or VSIPL) -----------------------------

# ----------------------------------------------------------------------

# LAinc tells the  C  compiler where to find the Linear Algebra  library

# header files,  LAlib  is defined  to be the name of  the library to be

# used. The variable LAdir is only used for defining LAinc and LAlib.

#

LAdir        =

LAinc        =

LAlib        =

#

# ----------------------------------------------------------------------

# - F77 / C interface --------------------------------------------------

# ----------------------------------------------------------------------

# You can skip this section  if and only if  you are not planning to use

# a  BLAS  library featuring a Fortran 77 interface.  Otherwise,  it  is

# necessary  to  fill out the  F2CDEFS  variable  with  the  appropriate

# options.  **One and only one**  option should be chosen in **each** of

# the 3 following categories:

#

# 1) name space (How C calls a Fortran 77 routine)

#

# -DAdd_              : all lower case and a suffixed underscore  (Suns,

#                       Intel, ...),                           [default]

# -DNoChange          : all lower case (IBM RS6000),

# -DUpCase            : all upper case (Cray),

# -DAdd__             : the FORTRAN compiler in use is f2c.

#

# 2) C and Fortran 77 integer mapping

#

# -DF77_INTEGER=int   : Fortran 77 INTEGER is a C int,         [default]

# -DF77_INTEGER=long  : Fortran 77 INTEGER is a C long,

# -DF77_INTEGER=short : Fortran 77 INTEGER is a C short.

#

# 3) Fortran 77 string handling

#

# -DStringSunStyle    : The string address is passed at the string loca-

#                       tion on the stack, and the string length is then

#                       passed as  an  F77_INTEGER  after  all  explicit

#                       stack arguments,                       [default]

# -DStringStructPtr   : The address  of  a  structure  is  passed  by  a

#                       Fortran 77  string,  and the structure is of the

#                       form: struct {char *cp; F77_INTEGER len;},

# -DStringStructVal   : A structure is passed by value for each  Fortran

#                       77 string,  and  the  structure is  of the form:

#                       struct {char *cp; F77_INTEGER len;},

# -DStringCrayStyle   : Special option for  Cray  machines,  which  uses

#                       Cray  fcd  (fortran  character  descriptor)  for

#                       interoperation.

#

F2CDEFS      = -DUpCase -DF77_INTEGER=long -DStringCrayStyle \

               -DCRAY_BLAS -DHPL_USE_TIMES

#

# When UpCase is defined,  CRAY_BLAS redefines the BLAS routines used in

# HPL to be prefixed with an S. In the Cray programming environment, the

# default INTEGER and REAL size is 64 bits.  This  is  reflected  in the

# Cray Scientific Library as well,  so SGEMM is the 64-bit matrix multi-

# ply.

#

# ----------------------------------------------------------------------

# - HPL includes / libraries / specifics -------------------------------

# ----------------------------------------------------------------------

#

HPL_INCLUDES = -I$(INCdir) -I$(INCdir)/$(ARCH) $(LAinc) $(MPinc)

HPL_LIBS     = $(HPLlib) $(LAlib) $(MPlib)

#

# - Compile time options -----------------------------------------------

#

# -DHPL_COPY_L           force the copy of the panel L before bcast;

# -DHPL_CALL_CBLAS       call the cblas interface;

# -DHPL_CALL_VSIPL       call the vsip  library;

# -DHPL_DETAILED_TIMING  enable detailed timers;

#

# By default HPL will:

#    *) not copy L before broadcast,

#    *) call the BLAS Fortran 77 interface,

#    *) not display detailed timing information.

#

HPL_OPTS     =

#

# ----------------------------------------------------------------------

#

HPL_DEFS     = $(F2CDEFS) $(HPL_OPTS) $(HPL_INCLUDES)

#

# ----------------------------------------------------------------------

# - Compilers / linkers - Optimization flags ---------------------------

# ----------------------------------------------------------------------

#

CC           = cc

CCNOOPT      = $(HPL_DEFS)

CCFLAGS      = $(HPL_DEFS) -O3

#

LINKER       = f77

LINKFLAGS    = -O3,unroll2,pipeline2

#

ARCHIVER     = ar

ARFLAGS      = r

RANLIB       = echo

#

# ----------------------------------------------------------------------