Installation problems Magma 2.3.0 - Nov 15, 2017

[nquesada]

Hi -- I am trying to install MAGMA. My machine is described as follows:

Code: Select all

$ nvidia-smi
Mon Dec 18 17:09:36 2017       
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 384.90                 Driver Version: 384.90                    |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|===============================+======================+======================|
|   0  TITAN Xp            Off  | 00000000:05:00.0  On |                  N/A |
| 23%   34C    P8    10W / 250W |     63MiB / 12186MiB |      0%      Default |
+-------------------------------+----------------------+----------------------+
|   1  TITAN Xp            Off  | 00000000:06:00.0 Off |                  N/A |
| 23%   32C    P8     9W / 250W |      2MiB / 12189MiB |      0%      Default |
+-------------------------------+----------------------+----------------------+
                                                                               
+-----------------------------------------------------------------------------+
| Processes:                                                       GPU Memory |
|  GPU       PID   Type   Process name                             Usage      |
|=============================================================================|
|    0      2121      G   /usr/lib/xorg/Xorg                            61MiB |
+-----------------------------------------------------------------------------+

and the make.inc file I am using is:

Code: Select all

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

# GPU_TARGET contains one or more of Fermi, Kepler, Maxwell, Pascal, Volta
# to specify for which GPUs you want to compile MAGMA:
#     Fermi   - NVIDIA compute capability 2.x cards
#     Kepler  - NVIDIA compute capability 3.x cards
#     Maxwell - NVIDIA compute capability 5.x cards
#     Pascal  - NVIDIA compute capability 6.x cards
#     Volta   - NVIDIA compute capability 7.x cards
# The default is "Kepler Maxwell Pascal".
# Note that NVIDIA no longer supports 1.x cards, as of CUDA 6.5.
# See http://developer.nvidia.com/cuda-gpus
#
#GPU_TARGET ?= Kepler Maxwell Pascal

# --------------------
# programs

CC        = gcc
CXX       = g++
NVCC      = nvcc
FORT      = gfortran

ARCH      = ar
ARCHFLAGS = cr
RANLIB    = ranlib


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

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

CFLAGS    = -O3 $(FPIC) -DNDEBUG -DADD_ -Wall -fopenmp
FFLAGS    = -O3 $(FPIC) -DNDEBUG -DADD_ -Wall -Wno-unused-dummy-argument
F90FLAGS  = -O3 $(FPIC) -DNDEBUG -DADD_ -Wall -Wno-unused-dummy-argument -x f95-cpp-input
NVCCFLAGS = -O3         -DNDEBUG -DADD_       -Xcompiler "$(FPIC)"
LDFLAGS   =     $(FPIC)                       -fopenmp

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


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

# gcc with OpenBLAS (includes LAPACK)
LIB       = -lopenblas

LIB      += -lcublas -lcusparse -lcudart -lcudadevrt


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

# define library directories preferably in your environment, or here.
#OPENBLASDIR ?= /usr/local/openblas
#CUDADIR ?= /usr/local/cuda
-include make.check-openblas
-include make.check-cuda

LIBDIR    = -L$(CUDADIR)/lib64 \
            -L$(OPENBLASDIR)/lib

INC       = -I$(CUDADIR)/include

When I try to run make I get the following error:

Code: Select all

$ make
nvcc -O3         -DNDEBUG -DADD_       -Xcompiler "-fPIC"  -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_60,code=compute_60 -I/usr/local/cuda/include -I./include -I./control -c -o magmablas/zaxpycp.o magmablas/zaxpycp.cu
nvcc fatal   : Unsupported gpu architecture 'compute_60'
Makefile:602: recipe for target 'magmablas/zaxpycp.o' failed
make: *** [magmablas/zaxpycp.o] Error 1

Any ideas how to fix the error?

Thanks in advance!

[mgates3]

What version of CUDA do you have installed?
I was going to say, set GPU_TARGET = Kepler or Maxwell, depending what your card supports. But a TITAN Xp card is Pascal. The error message suggests your installed CUDA version doesn't support Pascal. I think Pascal was added in CUDA 8.0.

For instance:

Code: Select all

prompt> nvcc --version
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2016 NVIDIA Corporation
Built on Sun_Oct_30_22:18:43_CDT_2016
Cuda compilation tools, release 8.0, V8.0.54

-mark

[mgates3]

Also, thanks for including all the information about your system, make.inc, and the error message. Super helpful!
-mark

[nquesada]

Hi mark --- Thanks for the reply! You are correct, we had to update to CUDA 8.0. This happened because the ubuntu version I am using is 16.04. The latest version come with CUDA 8.0

Thanks!