real-time processing of mass spectrometer data by...

17
REAL-TIME PROCESSING OF MASS SPECTROMETER DATA BY THE GRAPHICS PROCESSING UNIT Evan Hauck

Upload: others

Post on 28-May-2020

4 views

Category:

Documents


0 download

TRANSCRIPT

REAL-TIME PROCESSING OF

MASS SPECTROMETER DATA BY THE

GRAPHICS PROCESSING UNIT

Evan Hauck

INTRODUCTION

Time-of-flight

Mass Spectrometer

TRADE-OFF

+

Analyte Stream

TRADE-OFF

+

Analyte Stream

TRADE-OFF

CONCEPT

Analyte Stream

DEMULTIPLEXING

0

5

10

15

20

25

30

35

40

200147 200148 200149 200150 200151 200152 200153 200154 200155 200156 200157 200158 200159 200160 200161 200162

0

DEMULTIPLEXING

0

5

10

15

20

25

30

35

40

200147 200148 200149 200150 200151 200152 200153 200154 200155 200156 200157 200158 200159 200160 200161 200162

0

71656

143664

216024

288736

361800

435216

508984

583104

657576

732400

807576

883104

958984

1035216

DEMULTIPLEXING

0

5

10

15

20

25

30

35

40

200147 200148 200149 200150 200151 200152 200153 200154 200155 200156 200157 200158 200159 200160 200161 200162

0

71656

143664

216024

288736

361800

435216

508984

583104

657576

732400

807576

883104

958984

1035216

DEMULTIPLEXING

DEMULTIPLEXING

PIPELINE

• Sensor collects data

• FPGA sums spectra

• FPGA compresses

• Sends over Ethernet to

desktop PC

PIPELINE

• Transfer (CPU to GPU)

• Decompress

• Smooth 2D

• Demultiplex

• Resample (bin)

• Filter (skew-ex, statistics)

• Find Peaks

• Transfer (GPU to CPU)

CUDA VS. C++ AMP

• C++ AMP portable (NVIDIA, AMD GPUs, CPUs)

• Built into compiler, no libraries

• Easy to integrate with existing code

However…

• Cuda usually 2-4x faster

• Cuda has streams; C++ AMP does not (large speedup)

• Cuda tools (debugging, profiling, etc.) much better

CONCLUSION

CONCLUSION

• The GPU made a previously impossible task possible

• CPU ran 10% of realtime, GPU (NVIDIA Titan) runs 400%

• All processing steps previously were on FPGA (except demultiplexing), took years for a team to develop

• GPU code took one summer’s intern to develop

ACKNOWLEDGMENTS

A special thank you to:

• Peter Willis,

• Jon Jaloszynski,

• Dr. Jihong Wang, and

• LECO Corporation

for the opportunity and encouragement to make this

possible.