diff --git a/m/MPI-LIBLINEAR/INTEL_parallel-make.patch b/m/MPI-LIBLINEAR/INTEL_parallel-make.patch
new file mode 100644
index 00000000..acc5a420
--- /dev/null
+++ b/m/MPI-LIBLINEAR/INTEL_parallel-make.patch
@@ -0,0 +1,12 @@
+#This patch fixes the detection of Intel MPI C++ and C compilers.
+#made by PERMON team (http://permon.it4i.cz/)
+--- Makefile.orig	2016-11-08 06:23:58.000000000 +0100
++++ Makefile	2017-04-24 15:17:54.000000000 +0200
+@@ -1,5 +1,5 @@
+-CXX = mpic++
+-CC = mpicc
++CXX = mpiicpc
++CC = mpiicc
+ CFLAGS = -Wall -Wconversion -O3 -fPIC
+ LIBS = blas/blas.a
+ SHVER = 3
diff --git a/m/MPI-LIBLINEAR/MPI-LIBLINEAR-2.11-intel-2017a.eb b/m/MPI-LIBLINEAR/MPI-LIBLINEAR-2.11-intel-2017a.eb
new file mode 100644
index 00000000..87af9581
--- /dev/null
+++ b/m/MPI-LIBLINEAR/MPI-LIBLINEAR-2.11-intel-2017a.eb
@@ -0,0 +1,30 @@
+easyblock = 'MakeCp'
+
+name = 'MPI-LIBLINEAR'
+version = '2.1-1'
+
+homepage = 'https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/distributed-liblinear/mpi/'
+description = """MPI LIBLINEAR is an extension of LIBLINEAR on distributed environments. The usage and the data format are the same as LIBLINEAR.
+It supports L2-regularized logistic regression, L2-regularized logistic regression, L2-regularized L2-loss linear SVM (primal trust-region Newton),
+L2-regularized L1-loss linear SVM (dual), L2-regularized logistic regression (primal limited common directions),
+L2-regularized L2-loss linear SVM (primal limited common directions). Module created by the PERMON Team (http://permon.it4i.cz)."""
+
+toolchain = {'name': 'intel', 'version': '2017a'}
+
+source_urls = [homepage]
+sources = [SOURCELOWER_ZIP]
+
+patches = ['INTEL_parallel-make.patch']
+
+files_to_copy = [(['train', 'predict', 'split.py'], 'bin')]
+
+sanity_check_paths = {
+    'files': ['bin/%s' % x for x in ['train', 'predict', 'split.py']],
+    'dirs': [],
+}
+
+modextrapaths = {
+    'PATH': ['bin'],
+}
+
+moduleclass = 'numlib'