nvblas.conf

#Copyright 2013 NVIDIA Corporation.  All rights reserved.
# This is the configuration file to use NVBLAS Library
# Setup the environment variable NVBLAS_CONFIG_FILE to specify your own config file.
# By default, if NVBLAS_CONFIG_FILE is not defined, 
# NVBLAS Library will try to open the file "nvblas.conf" in its current directory
# Example : NVBLAS_CONFIG_FILE  /home/cuda_user/my_nvblas.conf

# Specify which output log file (default is stderr)
NVBLAS_LOGFILE  nvblas.log

#Put here the CPU BLAS fallback Library of your choice
#NVBLAS_CPU_BLAS_LIB  libopenblas.so
NVBLAS_CPU_BLAS_LIB  libmkl_rt.so

# List of GPU devices Id to participate to the computation 
# Use ALL if you want all your GPUs to contribute
# Use ALL0, if you want all your GPUs of the same type as device 0 to contribute
# However, NVBLAS consider that all GPU have the same performance and PCI bandwidth
# By default if no GPU are listed, only device 0 will be used

NVBLAS_GPU_LIST 0
#NVBLAS_GPU_LIST ALL
#NVBLAS_GPU_LIST ALL0

# Tile Dimension
NVBLAS_TILE_DIM 2048

# Autopin Memory
NVBLAS_AUTOPIN_MEM_ENABLED

#List of BLAS routines that are prevented from running on GPU (use for debugging purpose
# The current list of BLAS routines supported by NVBLAS are
# GEMM, SYRK, HERK, TRSM, TRMM, SYMM, HEMM, SYR2K, HER2K

#NVBLAS_GPU_DISABLED_SGEMM 
#NVBLAS_GPU_DISABLED_DGEMM 
#NVBLAS_GPU_DISABLED_CGEMM 
#NVBLAS_GPU_DISABLED_ZGEMM 

# Computation can be optionally hybridized between CPU and GPU
# By default, GPU-supported BLAS routines are ran fully on GPU
# The option NVBLAS_CPU_RATIO_<BLAS_ROUTINE> give the ratio [0,1] 
# of the amount of computation that should be done on CPU
# CAUTION : this option should be used wisely because it can actually
# significantly reduced the overall performance if too much work is given to CPU

NVBLAS_CPU_RATIO_CGEMM 0.07