AMD’s math libraries can support a range of programmers from hobbyists to ninja programmers. Kent Knox from AMD’s library team introduces you to OpenCL libraries for linear algebra, FFT, and BLAS, and shows you how to leverage the speed of OpenCL through the use of these libraries. Review the material presented in the AMD Math libraries webinar in this deck. For more: Visit the AMD Developer Forums:http://devgurus.amd.com/welcome Watch the replay: www.youtube.com/user/AMDDevCentral Follow us on Twitter: https://twitter.com/AMDDevCentral

1. HETEROGENEOUS MATH LIBRARIES
KENT KNOX
12/16/2014

2. 2 | HETEROGENEOUS MATH LIBRARIES | DECEMBER 16, 2014
AGENDA
clMATH
‒clBLAS
‒clFFT
ACML
clMAGMA
Bolt
LIBRARIES COVERED
A survey of available libraries

3. 3 | HETEROGENEOUS MATH LIBRARIES | DECEMBER 16, 2014
CLMATHLIBRARIES
clMathLibraries is a github organization for OpenCL™
math related subprojects
https://github.com/clMathLibraries
Currently hosting two subprojects: clBLAS & clFFT

4. Open Source
clBLAS

5. 5 | HETEROGENEOUS MATH LIBRARIES | DECEMBER 16, 2014
CLBLAS - HTTPS://GITHUB.COM/CLMATHLIBRARIES/CLBLAS
 clBLAS implements the NetLib BLAS functionality with OpenCL
‒ Level 3 – Matrix x Matrix operations, O( N^3 ), compute bound
‒ Level 2 – Matrix x Vector operations, O( N^2 ), mostly memory bound
‒ Level 1 – Vector x Vector operations, O( N ), memory bound
 The API is in the same style as NetLib, but appends OpenCL structures
‒ clblasStatus clblasSgemm( clblasOrder order, clblasTranspose transA,
clblasTranspose transB, size_t M, size_t N, size_t K, cl_float alpha, const
cl_mem A, size_t offA, size_t lda, const cl_mem B, size_t offB, size_t ldb,
cl_float beta, cl_mem C, size_t offC, size_t ldc, cl_uint numCommandQueues,
cl_command_queue* commandQueues, cl_uint numEventsInWaitList, const cl_event*
eventWaitList, cl_event* events )
 clBLAS assumes that the user is comfortable with OpenCL programming
‒ The host code is responsible for detecting /choosing devices, transferring memory and synchronizing
operations
API

6. 6 | HETEROGENEOUS MATH LIBRARIES | DECEMBER 16, 2014
CLBLAS - HTTPS://GITHUB.COM/CLMATHLIBRARIES/CLBLAS
 A proof of concept Python wrapper for clBLAS started, but only sgemm wrapped
‒https://github.com/clMathLibraries/clBLAS/tree/master/src/wrappers/python
‒Based on Cython
‒Works with PyOpenCL to manage OpenCL state
‒Would love help from the community to finish this
 The community wrote a Julia wrapper for clBLAS
‒https://github.com/JuliaGPU/CLBLAS.jl
API

7. 7 | HETEROGENEOUS MATH LIBRARIES | DECEMBER 16, 2014
CLBLAS - HTTPS://GITHUB.COM/CLMATHLIBRARIES/CLBLAS
• The user is responsible for running the tool on their machine
as a preprocessing step
• The tool creates a kernel database file (.kdb) that contains the best
performing kernel for a given BLAS routine
• The .kdb file is specific to an OpenCL device; will be named after
that device; e.g. tahiti.kdb
• Example
• export CLBLAS_STORAGE_PATH = /usr/local/lib
• ./tune --gemm --double
clBLAS contains a Tune tool for finding
better OpenCL kernels

8. Open Source
clFFT

9. 9 | HETEROGENEOUS MATH LIBRARIES | DECEMBER 16, 2014
CLFFT - HTTPS://GITHUB.COM/CLMATHLIBRARIES/CLFFT
 clFFT implements an FFTW inspired interface with OpenCL
‒ Provides a fast and accurate platform for calculating discrete FFTs
‒ Supports 1D, 2D, and 3D transforms with a batch size that can be greater than 1
‒ Supports dimension lengths that can be any mix of powers of 2, 3, and 5
‒ Supports single and double precision floating point formats
 clFFT assumes that the user is comfortable with OpenCL programming
‒ The host code is responsible for detecting/choosing devices, transferring memory and synchronizing
operations
 The community wrote a Python wrapper for clFFT
‒https://github.com/geggo/gpyfft
 The community wrote a Julia wrapper for clFFT
‒https://github.com/JuliaGPU/CLFFT.jl
API

10. 10 | HETEROGENEOUS MATH LIBRARIES | DECEMBER 16, 2014
CLFFT - HTTPS://GITHUB.COM/CLMATHLIBRARIES/CLFFT
• Users set all FFT state in an FFT plan object when initializing
• Call ‘BakePlan’ using the plan object to tell the library to JIT and
compile the kernel outside of performance sensitive loops
• Reuse those plans as much as possible!
clFFT contains the concept of ‘plans’,
which allows the library to tune OpenCL
kernels at runtime

11. 11 | HETEROGENEOUS MATH LIBRARIES | DECEMBER 16, 2014
CLFFT - HTTPS://GITHUB.COM/CLMATHLIBRARIES/CLFFT
PERFORMANCE
 clFFT v2.3.1 included in ACML
v6.1
 This version contains
optimizations not yet pushed
into public github repo
 You can use the clFFT.h header
file from GitHub to compile
your application, then use the
binary from ACML
 Benchmark system
 64bit Linux
 FirePro W9100
 Catalyst Pro
14.301.1010
 AMD A10-7850K

12. ACML 6

13. 13 | HETEROGENEOUS MATH LIBRARIES | DECEMBER 16, 2014
ACML 6 INTRODUCES HETEROGENEOUS COMPUTE
 OpenCL can be a difficult language to learn
‒ There exists legacy applications that won’t be ported to OpenCL
‒ They might be willing to sacrifice peak performance for program
portability
 ACML 6 includes clBLAS & clFFT as new backends
‒ ACML hides all OpenCL programming from end users
‒ Client programs do not need to change at all; they only relink ACML 6
 When ACML determines that a particular BLAS or FFT call will
gain benefit from offloading computation, it will do so without
knowledge of the client program
LEVERAGING CLMATH LIBRARIES TO ACCELERATE WITH OPENCL
ACML 6 keeps the same API!

14. 14 | HETEROGENEOUS MATH LIBRARIES | DECEMBER 16, 2014
NEW FFTW WRAPPER
ACML 6 now ships with fftw.h
FFTW programs could link with ACML 6 to offload
computation onto OpenCL devices
No changes in host code required!

15. 15 | HETEROGENEOUS MATH LIBRARIES | DECEMBER 16, 2014
ACMLSCRIPT
• The scripting language uses Lua, with custom ACML callback
functions
• http://www.lua.org/
• Refer to chapter 7 of the ACML documentation for more
information on how to modify or create your own scripts
ACML includes a new scripting
language that expresses the logic
ACML uses to offload computation

16. 16 | HETEROGENEOUS MATH LIBRARIES | DECEMBER 16, 2014
ACMLSCRIPT: 3-PART VIDEO TUTORIALS
ACMLScript: Part 1
ACMLScript: Part 2
ACMLScript: Part 3
HTTPS://WWW.YOUTUBE.COM/USER/AMDDEVCENTRAL

17. 17 | HETEROGENEOUS MATH LIBRARIES | DECEMBER 16, 2014
ACML- HTTPS://GITHUB.COM/CLMATHLIBRARIES/CLFFT
PERFORMANCE
 ACML v6.0 sgemm
 Slightly old at this time
 Notice that the green line is
equivalent to Max( blue, red )
 ACML loads the host
processor if the problem
is too small to benefit
from GPU acceleration
 Benchmark system
 AMD A10-7850K
 CPU & GPU
 64bit Linux
 Catalyst 14.301.1001

18. Open Source
clMagma

19. 19 | HETEROGENEOUS MATH LIBRARIES | DECEMBER 16, 2014
CLMAGMA
clMAGMA implements LAPACK functionality with
OpenCL acceleration
https://bitbucket.org/icl/clmagma
Maintained by the University of Tennessee Knoxville

20. 20 | HETEROGENEOUS MATH LIBRARIES | DECEMBER 16, 2014
CLMAGMA
 The newest v1.3 Supports
‒ LU, QR and Cholesky factorizations
‒ Linear and least squares solvers
‒ Reductions to Hessenberg, bidiagonal and tridiagonal forms
‒ Eigen and singular value problem solvers
‒ Orthogonal transformation routines
 clMagma uses clBLAS as the GPU compute backend
‒ It currently provides static load balancing between CPU & GPU cores
 Multi-GPU support
LEVERAGING CLMATH LIBRARIES TO ACCELERATE WITH OPENCL
v1.3 adds support for Windows and
Mac OSX

21. Open Source
Bolt

22. 22 | HETEROGENEOUS MATH LIBRARIES | DECEMBER 16, 2014
BOLT
Bolt implements parallel C++ STL functionality with
AMP & OpenCL acceleration
Bolt on GitHub
Maintained by AMD

23. 23 | HETEROGENEOUS MATH LIBRARIES | DECEMBER 16, 2014
BOLT
 Bolt provides containers and algorithms that enable clients to
accelerate C++ code with minimal GPU knowledge
‒ Sorts
‒ Reductions
‒ Transforms
‒ Scans
 Through control structures, clients control where data is
allocated and computed (minimal knowledge of AMP or OpenCL
is helpful here)
 Bolt provides support for both OpenCL & C++ AMP paths
PARALLEL STL
Bolt provides containers such as
bolt::device_vector<>

24. 24 | HETEROGENEOUS MATH LIBRARIES | DECEMBER 16, 2014
BOLT
#include <bolt/cl/device_vector.h>
#include <bolt/cl/scan.h>
#include <vector>
#include <numeric>
int main()
{
size_t length = 1024;
// Create device_vector and initialize it to 1
bolt::cl::device_vector< int > boltInput( length, 1 );
// Calculate the inclusive_scan of the device_vector
bolt::cl::inclusive_scan(boltInput.begin(),boltInput.end(),boltInput.begin( ) );
// Create an std vector and initialize it to 1
std::vector< int > stdInput( length, 1 );
// Calculate the inclusive_scan of the std vector
bolt::cl::inclusive_scan(stdInput.begin( ),stdInput.end( ),stdInput.begin( ) );
return 0;
}
EXAMPLE CODE

25. 25 | HETEROGENEOUS MATH LIBRARIES | DECEMBER 16, 2014
Q&A & CONTACT INFO
For More Info:
Follow us on Twitter: @AMDDevCentral
Visit our forums: http://devgurus.amd.com/welcome
Visit our website: www.developer.amd.com
Watch the replay: www.youtube.com/user/AMDDevCentral
Download the presentation: www.slideshare.net/DevCentralAMD

26. 26 | HETEROGENEOUS MATH LIBRARIES | DECEMBER 16, 2014
DISCLAIMER & ATTRIBUTION
The information presented in this document is for informational purposes only and may contain technical inaccuracies, omissions and typographical errors.
The information contained herein is subject to change and may be rendered inaccurate for many reasons, including but not limited to product and roadmap
changes, component and motherboard version changes, new model and/or product releases, product differences between differing manufacturers, software
changes, BIOS flashes, firmware upgrades, or the like. AMD assumes no obligation to update or otherwise correct or revise this information. However, AMD
reserves the right to revise this information and to make changes from time to time to the content hereof without obligation of AMD to notify any person of
such revisions or changes.
AMD MAKES NO REPRESENTATIONS OR WARRANTIES WITH RESPECT TO THE CONTENTS HEREOF AND ASSUMES NO RESPONSIBILITY FOR ANY
INACCURACIES, ERRORS OR OMISSIONS THAT MAY APPEAR IN THIS INFORMATION.
AMD SPECIFICALLY DISCLAIMS ANY IMPLIED WARRANTIES OF MERCHANTABILITY OR FITNESS FOR ANY PARTICULAR PURPOSE. IN NO EVENT WILL AMD BE
LIABLE TO ANY PERSON FOR ANY DIRECT, INDIRECT, SPECIAL OR OTHER CONSEQUENTIAL DAMAGES ARISING FROM THE USE OF ANY INFORMATION
CONTAINED HEREIN, EVEN IF AMD IS EXPRESSLY ADVISED OF THE POSSIBILITY OF SUCH DAMAGES.
ATTRIBUTION
© 2014 Advanced Micro Devices, Inc. All rights reserved. AMD, the AMD Arrow logo and combinations thereof are trademarks of Advanced Micro Devices,
Inc. in the United States and/or other jurisdictions. Other names are for informational purposes only and may be trademarks of their respective owners.