A Gomez T Tat Cesga

15
timTrack tracking of charged particles By J.A.Rodríguez

Transcript of A Gomez T Tat Cesga

Page 1: A Gomez T Tat Cesga

timTracktracking of charged particles

By J.A.Rodríguez

Page 2: A Gomez T Tat Cesga

 TRASGO Project

labCAF

Page 3: A Gomez T Tat Cesga

RPC TRB timTrack

Page 4: A Gomez T Tat Cesga

timTrack

Resultados.txt(output file)

- 6 SAETA (x,y,x',y',v,t)- 6 Errors -15 Covariances

running ...

Datos.txt Detector.txt

Page 5: A Gomez T Tat Cesga

Why C language ? Very fast Flexible Parallelism A rich set of libraries

Libraries was used to program timTrack (“algorithms ”)

LAPACK

Intel® IPP

Page 6: A Gomez T Tat Cesga

BLAS /LAPACK

Is a software library for numerical linear algebra.

It provides routines for solving systems of linear equations and linear least squares, eigenvalue problems, and singular value decomposition.

Specific versions for each CPU model provided by the vendors

Page 7: A Gomez T Tat Cesga

Intel® IPP

Integrated Performance Primitives (Intel® IPP)

Is a library of multicore-ready, highly optimized

software functions for digital media and data-processing applications.

Intel IPP contains a rich set of matrix and vector operations for a wide variety of applications.

Page 8: A Gomez T Tat Cesga

timTrack SAETAs solutions

PREVIOUS VERSION

timTrack v1.0 (LAPACK)

timTrack v1.1 (IPP)

NEW algebra VERSION

timTrack v2.0 (LAPACK)

Page 9: A Gomez T Tat Cesga

timTrack variance-covariance matrix

PREVIOUS VERSIONS

timTrack v1.0 (LAPACK)

timTrack v1.1 (IPP)

NEW algebra VERSION

timTrack v2.0 (LAPACK)

Page 10: A Gomez T Tat Cesga

Example Implemented

Z

Y

T1 T2

X

Page 11: A Gomez T Tat Cesga

Times for 1.000.000 particles

Old Python and Matlab versions (only 500.000 particles) 165m 47.137 s

timTrack v2.0 LAPACK 23.615 s

timTrack v1.1 intel®IPP 23.495 s

timTrack v1.0 LAPACK 31.188 s

:)

Page 12: A Gomez T Tat Cesga

Next Steps

• Analyze systematic computing errors

• Check single-precision version

• Parallelize– Shared memory (OpenMP)

– MPI (master-slave)

– Full distributed

• Implement in GPU

• Study full problem

Page 13: A Gomez T Tat Cesga

timTrack v2.1

Next step ( still in progress… )

Parallelims with Intel® MPI librariesShared parallelism with OpenMP for Multi-core

Page 14: A Gomez T Tat Cesga

Future !

timtrack v 3.0

CUDA parallel computing architecture in GPUs

CUDA has several advantages over traditional general purpose computation on GPUs

* Scattered reads

* Shared memory

* Faster downloads from the GPU

* Full support for integer and bitwise operations

Page 15: A Gomez T Tat Cesga