Sonic Millip3De: A massively parallel 3D-stacked accelerator for 3D ultrasound

Three-dimensional (3D) ultrasound is becoming common for non-invasive medical imaging because of its high accuracy, safety, and ease of use. Unlike other modalities, ultrasound transducers require little power, which makes hand-held imaging platforms possible, and several low-resolution 2D devices are commercially available today. However, the extreme computational requirements (and associated power requirements) of 3D ultrasound image formation has, to date, precluded hand-held 3D capable devices. We describe the Sonic Millip3De, a new system architecture and accelerator for 3D ultrasound beamformation-the most computationally intensive aspect of image formation. Our three-layer die-stacked design features a custom beamsum accelerator that employs massive data parallelism and a streaming transform-select-reduce pipeline architecture enabled by our new iterative beamsum delay calculation algorithm. Based on RTL-level design and floorplanning for an industrial 45nm process, we show Sonic Millip3De can enable 3D ultrasound with a fully sampled 128×96 transducer array within a 16W full-system power budget (400× less than a conventional DSP solution) and will meet a 5W safe power target by the 11nm node.

[1]  J. Jensen,et al.  Calculation of pressure fields from arbitrarily shaped, apodized, and excited ultrasound transducers , 1992, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[2]  Christoforos E. Kozyrakis,et al.  Towards energy-proportional datacenter memory with mobile DRAM , 2012, 2012 39th Annual International Symposium on Computer Architecture (ISCA).

[3]  J Persliden,et al.  Mobile computerized tomography scanning in the neurosurgery intensive care unit: increase in patient safety and reduction of staff workload. , 2000, Journal of neurosurgery.

[4]  Peter Falkensammer,et al.  Ultrasound Technology Update: 4D Fetal Echocardiography Spatio-Temporal Image Correlation (STIC) for Fetal Heart Acquisition , 2004 .

[5]  J. Arendt.  Paper presented at the 10th Nordic-Baltic Conference on Biomedical Imaging: Field: A Program for Simulating Ultrasound Systems , 1996 .

[6]  Travis N. Blalock,et al.  Direct sampled I/Q beamforming: a strategy for very low cost ultrasound , 2003, IEEE Symposium on Ultrasonics, 2003.

[7]  J Brian Fowlkes,et al.  Ultrasound Biosafety Considerations for the Practicing Sonographer and Sonologist , 2009, Journal of ultrasound in medicine : official journal of the American Institute of Ultrasound in Medicine.

[8]  R. Cobbold.  Foundations of Biomedical Ultrasound , 2006 .

[9]  Scott A. Mahlke,et al.  MEDICS: Ultra-portable processing for medical image reconstruction , 2010, 2010 19th International Conference on Parallel Architectures and Compilation Techniques (PACT).

[10]  M. O'Donnell,et al.  Subaperture processing for ultrasonic imaging , 1998, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[11]  G.R. Lockwood,et al.  Real-time 3-D ultrasound imaging using sparse synthetic aperture beamforming , 1998, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[12]  H. Ermert,et al.  A 100-MHz ultrasound imaging system for dermatologic and ophthalmologic diagnostics , 1996, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[13]  Murtaza Ali,et al.  White Paper SPRAB 12 – November 2008 Signal Processing Overview of Ultrasound Systems for Medical Imaging , 2008 .

[14]  David Blaauw,et al.  Centip3De: A 3930DMIPS/W configurable near-threshold 3D stacked system with 64 ARM Cortex-M3 cores , 2012, 2012 IEEE International Solid-State Circuits Conference.

[15]  Gregg E. Trahey,et al.  The effects of image degradation on ultrasound-guided HIFU , 2010, 2010 IEEE International Ultrasonics Symposium.

[16]  Konstantinos N. Plataniotis,et al.  Parallelization and performance of 3D ultrasound imaging beamforming algorithms on modern clusters , 2002, ICS '02.

[17]  Karthikeyan Sankaralingam,et al.  Dark Silicon and the End of Multicore Scaling , 2012, IEEE Micro.

[18]  Lei Jiang,et al.  Die Stacking (3D) Microarchitecture , 2006, 2006 39th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO'06).

[19]  Jan Craninckx,et al.  A 1.7mW 11b 250MS/s 2× interleaved fully dynamic pipelined SAR ADC in 40nm digital CMOS , 2012, 2012 IEEE International Solid-State Circuits Conference.

[20]  Stergios Stergiopoulos.  Advanced Signal Processing : Theory and Implementation for Sonar, Radar, and Non-Invasive Medical Diagnostic Systems, Second Edition , 2009 .

[21]  Brian Leibowitz,et al.  A 4.3GB/s mobile memory interface with power-efficient bandwidth scaling , 2009, 2009 Symposium on VLSI Circuits.

[22]  Krisztián Flautner,et al.  PicoServer: using 3D stacking technology to enable a compact energy efficient chip multiprocessor , 2006, ASPLOS XII.

[23]  Hairong Zheng,et al.  Real-Time Visualized Freehand 3D Ultrasound Reconstruction Based on GPU , 2010, IEEE Transactions on Information Technology in Biomedicine.

[24]  Olivier Salvado,et al.  Ultrasound goes GPU: real-time simulation using CUDA , 2009, Medical Imaging.

[25]  Gabriel H. Loh,et al.  3D-Stacked Memory Architectures for Multi-core Processors , 2008, 2008 International Symposium on Computer Architecture.

[26]  M. O'Donnell,et al.  Synthetic aperture imaging for small scale systems , 1995, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[27]  H LohGabriel.  3D-Stacked Memory Architectures for Multi-core Processors , 2008 .

[28]  Christian Cachard,et al.  3D Ultrasound real-time monitoring of surgical tools , 2010, 2010 IEEE International Ultrasonics Symposium.

[29]  K. Boone,et al.  Effect of skin impedance on image quality and variability in electrical impedance tomography: a model study , 1996, Medical and Biological Engineering and Computing.

[30]  Yongmin Kim,et al.  Software-based Ultrasound Beamforming on Multi-core DSPs , 2011 .

[31]  Michael Bucher,et al.  A 4.3 GB/s Mobile Memory Interface With Power-Efficient Bandwidth Scaling , 2010, IEEE Journal of Solid-State Circuits.

[32]  KozyrakisChristos,et al.  Towards energy-proportional datacenter memory with mobile DRAM , 2012 .

[33]  Travis N. Blalock,et al.  Real time imaging with the Sonic Window: A pocket-sized, C-scan, medical ultrasound device , 2009, 2009 IEEE International Ultrasonics Symposium.