Useful Information on Intel Software Suite

1. Intel Parallel Studio XE home page
   https://software.intel.com/en-us/intel-parallel-studio-xe - 
2. Intel SW Tools Training Videos
   https://software.intel.com/en-us/intel-parallel-studio-xe-support/training#gsvideos
3. Case Studies
   https://software.intel.com/en-us/articles/sdp-case-studies
4. Intel Software Academic Program
   https://software.intel.com/en-us/academic 
5. Courseware; everything you need to know about parallel computing – from the basics to hybrid and power optimization
   https://software.intel.com/en-us/courseware/hpc
6. Free Software
   https://software.intel.com/en-us/qualify-for-free-software
7. Free licenses for the classroom
   https://software.intel.com/en-us/qualify-for-free-software/educator 
8. Free licenses for Students
   https://software.intel.com/en-us/qualify-for-free-software/student

Using Intel IMB-MPI1 to check Fabrics and expected performances

In your .bashrc, do source the

source /usr/local/intel_2015/parallel_studio_xe_2015/bin/psxevars.sh intel64
source /usr/local/intel_2015/impi/5.0.3.049/bin64/mpivars.sh intel64
source /usr/local/intel_2015/composerxe/bin/compilervars.sh intel64
source /usr/local/intel_2015/mkl/bin/mklvars.sh intel64
MKLROOT=/usr/local/intel_2015/mkl

To simulate 3 workloads pingpong, sendrecv, and exchange with IMB-MPT1

$ mpirun -r ssh -RDMA -n 512 -env I_MPI_DEBUG 5 IMB-MPT1

Compiling Intel FFTW3 and FFTW2 Interface Wrapper Library

FFTW3 wrappers to Intel MKL are delivered both in Intel MKL and as source code which can be compiled to build to build standalone wrapper library with exactly the same functionality. The source code for the wrappers, makefiles are found .....\interfaces\fftw3xc subdirectory in the Intel MKL Directory

Intel FFTW3 Interface Wrapper Library. Do the same for fftw3xc and fftw3xf

# cd $MKLROOT
# cd interfaces/fftw3xc
# make libintel  INSTALL_DIR=$MKLROOT/lib/intel64

Once Compiled, the libraries are kept $MKLROOT/lib/intel64  


Intel FFTW2 Interface Wrapper Library. Do the same for fftw2xc and fftw2xf

# cd $MKLROOT
# cd interfaces/fftw2xc
# make libintel  PRECISION=MKL_DOUBLE
# make libintel  PRECISION=MKL_SINGLE

Once Compiled, the libraries are kept $MKLROOT/lib/intel64

Information on Intel Omni-Path Fabric and Xeon Phi

1. Intel® Omni-Path Architecture
2. Intel® Xeon Phi™ Product Family

Intel Software Development Tools - Price List

This link (https://software.intel.com/en-us/try-buy-tools) is very useful especially if you are budgeting to acquire Intel Compilers and Tools

Intel NIC driver causing multicast flooding (intermittent wired network disconnection)

Symptom:
The symptom can range from random disconnection to slowness in the entire school/building wired network. Eventually, the cause of this problem was found to be due to intel-chipset nic card (Intel I2xx/825xx series) sending out erratic & massive multicast traffic, causing flooding of the network and high CPU on the switches. The below link are some url which describe the same problem faced by other user environment:


Resolution:
The recommended step to resolve this problem is to upgrade the intel nic card driver to version 19.0 and above.


References:

1. IPv6 multicast flood during sleep from i217-LM
2. ICMPv6 'Multicast Listener Report' messages are flooding the local network 
3. ICMPv6 'Multicast Listener Report' messages flooding the local network

Food. Water. Data Center

This is a very hilarious short video clip titled "Food. Water. Data Center" from Intel .

From ATMs to GPS navigation the data center powers our day. What would a day without the data center look like

Using SR-IOV with Intel® Ethernet Server Adapters

The FAQ on Using SR-IOV with Intel® Ethernet Server Adapters

1. Which Intel® Ethernet Adapters and Controllers support SR-IOV? 
2. Which hypervisors support SR-IOV on Intel® Ethernet Adapters? 
3. Which guest operating systems have virtual function drivers? 
4. Where can I get the virtual function (VF) drivers? 
5. How can I make SR-IOV work in Linux*? 
6. Can I use SR-IOV with Microsoft Hyper-V*? 
7. Can I use SR-IOV with VMware products*?

 Download of Network Adapter Virtual Function Driver for 10 Gigabit Network Connections

Architecting a High Performance Lustre Storage Solution

The Solution Architect group within Intel HPDD has recently updated the Architecting a High Performance Storage System technical white paper. This paper outlines a systematic, requirements-driven approach for designing Lustre-powered storage solutions.

See Architecting a High Performance Storage System

References:

1. Intel® Solutions for Lustre* software

Intel Recommended Reading List for Q1 2014

The Intel Recommended Reading List for 2014 are out. Intel Press Book always grab my attention. You may want to take a look at Intel Press Book and Recommended List for Developer (pdf)

Coprocessors Programming Codebook and Parallel Universe Magazine By Intel

Intel has put a 16-pages code book titled - Application Optimization for Intel® Processors and Coprocessors Programming CodeBook. Explore some of the tools, techniques, and models for creating highly parallelized code optimized for Intel® Core™, Intel® Xeon® processors, or the Intel® Xeon Phi™ coprocessor.

Download the latest issue of The Parallel Universe magazine and explore the implications of real-time everything as high-performance computing (HPC) moves out of the science lab and onto Main Street. Check out the features in OpenMP* 4.0, discover what’s new in Intel® Cluster Studio XE 2013 SP1, learn techniques for ID’ing and correcting HPC application bottlenecks, and more

Intel Books24X7 Online Library

 

Key features of this unique online library configuration:

 

1. Choose two library options customized for your area of specialization:

•  IT Pro™ (12,000 titles)
• Engineering Pro™ (4,000 titles)

2. Search within any or all books by software source code (C, Java, C++ etc.)

3. Add notes and bookmarks (and share with your workgroup)

 

For more information, do look at the Intel Books24X7 Online Library 

Requirements to Support AVX

For more information, do take a look at  Wikipedia Advanced Vector Extensions for more information.

Centos OS / RH OS
Linux Kernel must be 2.6.30 and above. CentOS 6.2 and later will have full support for AVX. See PGI Forum discussion ). Do upgrade the OS 


Intel Compilers
From the Wikipedia, Intel Compiler version 11.1 onwards support AVXIt is recommended to use icc version 12.1.8 to make it work. You may want to take a look at StackOverflow Forum


GNU Compilers:
From the Wikipedia, GNU Compilers 4.6 and above.

Hardware
Sandy Bridge processor, Q1 2011[12]
Sandy Bridge E processor, Q4 2011[13]
Ivy Bridge processor, Q1 2012
Ivy Bridge E processor, Q3 2013
Haswell processor, Q2 2013.
Broadwell processor, 2014.

Intel unveils Quark-based "maker board"

Intel has just launched the Intel Galileo board, the first product in a new family of Arduino-compatible development boards featuring Intel® architecture, and based on the recently announced Quark family of processors.

The Galileo development board is a great tool for quickly prototyping simple, interactive designs such as LED light displays that respond to social media, or for tackling more complex projects, from automating home appliances to building life-size robots controlled by a smartphone.

 This platform provides the ease of Intel architecture development through support for the Microsoft Windows*, Mac OS* and Linux* host operating systems. It also brings the simplicity of the Arduino software integrated development environment (IDE).........


Introducing the Gileo Development Board Video http://bcove.me/kxeu2dwz

Encountering __intel_sse2_strlen when compiling OpenMPI with Intel Compilers

I was compiling OpenMPI 1.6.x and Intel Compiler XE 2013, I used the following configuration found in

#./configure --prefix=/usr/local CC=icc CXX=icpc F77=ifort FC=ifort

Do specify CC=icc CXX=icpc F77=ifort FC=ifort as if you miss one of the parameters, it will take the default. For example, if you do not specify CXX=icpc, it will adopt CXX=g++
but when I run

# make -j8

I got this error:

..../openmpi-1.6.2/ompi/contrib/vt/vt/tools/opari/tool/../../../util/util.c:45: 
undefined reference to `__intel_sse2_strlen'
..../openmpi-1.6.2/ompi/contrib/vt/vt/tools/opari/tool/../../../util/util.c:61: 
undefined reference to `__intel_sse2_strlen'
..../openmpi-1.6.2/ompi/contrib/vt/vt/tools/opari/tool/../../../util/util.c:46: 
undefined reference to `__intel_sse2_strlen'
..../openmpi-1.6.2/ompi/contrib/vt/vt/tools/opari/tool/../../../util/util.c:46: 
undefined reference to `__intel_sse2_strlen' 
......
......

The solution is to do the following:

Firstly, make sure you compile with the following

# source /usr/local/intel/composerxe/bin/compilervars.sh

Do it again

#./configure --prefix=/usr/local CC=icc CXX=icpc F77=ifort FC=ifort

Run the make again

# make -j8
# make install

Intel Parallel Studio XE 2013 Software Updates

Intel Software has a couple of updates for Compilers, Math Kernel Libraries, Threading Building Blocks that have been released on 28 March

1. Intel® C++ Composer XE for Linux* 2013 Update 3 Eng/Jpn
2. Intel® Fortran Composer XE for Linux* 2013 Update 3 Eng/Jpn
3. Intel® Math Kernel Library for Linux* 11.0 Update 3
4. Intel® Threading Building Blocks for Linux* 4.1 Update 3

For more information, do look at Intel Parallel Studio XE 2013

QUEST 1.3.0 and forrtl severe (173) error

If  you are running codes that uses QUEST 1.3.0 which are compiled with Intel XE, you may encounted the error

forrtl: severe (173): 
A pointer passed to DEALLOCATE points to an array that cannot be deallocated

Do note that QUEST used to work with Intel's ifort, but Intel has tightened their standard of memory allocation/deallocation hence the error you see. It is recommended you use gfrotran for the compilation

Intel Infiniband Solution - TrueScale Infiniband

Information on Intel® TrueScale InfiniBand Solutions.
You would have probably known Intel buy-over of Qlogic. Not much detailed information are revealed yet on Intel site, but you can find similar information at Qlogic site, but without Intel specific part number

1. Intel® TrueScale InfiniBand Edge and Director Switches
2. Intel® TrueScale InfiniBand Fabric Management and Software Tools 
3. Intel® TrueScale InfiniBand Host Adapters
4. Intel® InfiniBand Cables

Article - Intel® Solid-State Drive 910 Series Delivers High Performance, Endurance and Reliability for Data Center Tiering and Caching

An interesting article by Intel to address high-performning SSD.......

Intel® Solid-State Drive 910 Series Delivers High Performance, Endurance and Reliability for Data Center Tiering and Caching (Intel NewsRoom)

Another similar article can be found at Intel's PCI-E 910-Series SSD reviewed: blazing fast, even under pressure (Engadget)

Some of the hightlights:

1. PCIe-based 400GB and 800GB Intel SSD 910 Series provides extreme performance, endurance and reliability for rigorous data center demands.
2. Intel SSD 910 Series offers easy-to-install, seamless post-deployment server storage upgrade with no changes to existing server design.
3. Using Intel High Endurance Technology, Intel SSD 910 offers 10 full drive writes a day for 5 years for 30x endurance.*

Article - No Free Lunch for Intel MIC (or GPU's)

This is an interesting article No Free Lunch for Intel MIC (or GPU's) from Steve Scott on Nvidia site. He mentioned there are 3 major consideration why porting over to MIC will be more challenging than we thought out to be. He mentioned several pointers to look out for that imhibit mass migratio to MIC. Take a read. But do note it is written by NVIDIA a competitor of MIC