Mapping Biomedical Applications onto GPU Platforms Joseph JaJa University of Maryland
Fluid-Structure I nteractions • Collaboration between GWU (Balaras), UMD (Solares, Wu), and University of Chicago (Dubey). • Goal: Development of high performance algorithms applicable to fluid-structure interactions in viscous incompressible flows. • Example application: interactions between the red blood cells and plasma • Critical Components: Poisson equation solver combined with a multigrid algorithm. Multi- dimensional FFTs and several types of matrix computations 2
Data-Driven Understanding of Brain Disorders • Collaboration between the University of Maryland (Varshney and JaJa) and the University of Maryland at Baltimore (Gullapalli, Herskovits, etc.) • Understanding of brain connectivity differences between subjects with brain disorders and normal subjects using diffusion MRI. • Dynamics of functional brain connectivity using resting state fMRI, for subjects with moderate TBI. 3
Connectivity Matrix • Diffusion MRI images with 64 diffusion frames with resolution 128× 128× 52. • Probabilistic Tractography • Number of entries in the sparse connectivity matrix: 100,000,000- 200,000,000. • Number of voxels in ROI: 100,000-200,000. 4
I nflammatory Responses and Wound Healing in Vocal Fold N. Seekhao Collaborators: N. Li, C. Shung, L. Mongeau (McGill U.) Bio me c ha nic a l Stre ss Muc o sa l Da ma g e Ce ll Re c ruitme nt Ce ll F unc tio n
I nflammatory Responses & Wound Healing in Vocal Fold Biome c ha nic a l F o rc e a pplie d o n Stre ss tissue . T a lking , sho uting e tc . Muc o sa l Da ma g e Ce ll Re c ruitme nt Ce ll F unc tio n Image from : http://2.bp.blogspot.com/- DI0yRAeRKjA/TrDdREMzr_I/AAAAAAAAH6o/QFgZ7xFFRjg/s320/s hout png
I nflammatory Responses & Wound Healing in Vocal Fold Bio me c ha nic a l Stre ss Da ma g e in the tissue o f the vo c a l Muc osa l Da ma g e fo ld Ce ll Re c ruitme nt Ce ll F unc tio n Image from : https://wiki.uiowa.edu/download/attachments/39001206/nodules%2 0op%205 png?api=v2
I nflammatory Responses & Wound Healing in Vocal Fold Bio me c ha nic a l Attra c ting c e lls suc h a s Stre ss pla te le ts, ne utro phils, Muc o sa l Da ma g e a nd ma c ro pha g e s to the wo und site Ce ll Re c ruitme nt Ce ll F unc tio n Image from : http://www.biospectrumasia.com/IMG/362/44362/atherosclerotic-lesions- generates-robust-t-cell-anti-inflammatory-response-262x174 jpg
I nflammatory Responses & Wound Healing in Vocal Fold Bio me c ha nic a l E a c h c e ll pe rfo rm its duty. Stre ss One o r mo re o f the fo llo wing : Muc o sa l Da ma g e • Se c re te c he mic a l (I L -1, MMP-8 e tc .) to a ttra c t, Ce ll Re c ruitme nt e xc ite o r inhib it o the r c e lls • De po sit E CM pro te in Ce ll F unc tion (c o lla g e n, e la stin e tc .) to he a l da ma g e d tissue • Cle a n up c e ll de b ris
Agent-Based Modeling (ABM) 1. Bottom-up, rule-based, discrete-event and discrete-time computational model 2. Initial “World” and a collection of “agents.” 3. Interactions between agents and the world. – Agents migrate to area of injury – Remove dead cells and tissue debris – Remodel ECM to heal damaged tissue 4. Stochastic moves 5. Emergent behavior
ABMs of Vocal Fold Wound Healing Process T issue a re a o f inte re st (ABMs te rm: Wo rld) Slic e s o f tissue (ABMs te rm: Pa tc he s)
ABMs of Vocal Fold Wound Healing Process T issue a re a o f inte re st (ABMs te rm: Wo rld) Slic e s o f tissue (ABMs te rm: Pa tc he s) IL -1 MMP-8 …
ABMs of Vocal Fold Wound Healing Process T issue a re a o f inte re st (ABMs te rm: Wo rld) Slic e s o f tissue (ABMs te rm: Pa tc he s) IL -1 MMP-8 … Co mpo ne nts o f tissue (E CM) suc h a s Co lla g e n, E la stin, Hya luro nic Ac id
ABMs of Vocal Fold Wound Healing Process T issue a re a o f inte re st (ABMs te rm: Wo rld) Slic e s o f tissue (ABMs te rm: Pa tc he s) IL -1 MMP-8 … Co mpo ne nts o f tissue (E CM) suc h a s Co lla g e n, Che mic a l L e ve ls E la stin, Hya luro nic (ABMs te rm: Pa tc he s Attrib ute s) Ac id
ABMs of Vocal Fold Wound Healing Process F ib ro b la st (Ce ll) (ABMs te rm: Ag e nts) Ne utro phil (Ce ll) (ABMs te rm: Ag e nts) Ma c ro pha g e (Ce ll) (ABMs te rm: Ag e nts)
ABMs of Vocal Fold Wound Healing Process F ib ro b la st (Ce ll) (ABMs te rm: Ag e nts) Ne utro phil (Ce ll) (ABMs te rm: Ag e nts) Ma c ro pha g e (Ce ll) (ABMs te rm: Ag e nts)
ABMs of Vocal Fold Wound Healing Process F ib ro b la st (Ce ll) (ABMs te rm: Ag e nts) Ne utro phil (Ce ll) (ABMs te rm: Ag e nts) Ma c ro pha g e (Ce ll) (ABMs te rm: Ag e nts)
Problem Scale * Number of cells increase throughout the simulation due to proliferation. Current model shows a doubling of number of cells after the end of “5-day” simulation.
Characteristic Features of Applications • Computationally demanding applications with irregular memory access patterns and involving large data sizes that cannot fit on the GPU memory • Need to use heterogeneous platforms involving multicore CPU with one or more many-core GPUs. • Performance Goal: try to achieve the same performance rate or throughput as in the case when the data fits on the GPU. 19
Heterogeneous Platforms CPU Mem GPU GDDR5 (128GB) Mem (5GB) 208GB/s 73GB/s Dual-socket Massively Multi-core Parallel CPU -16 cores GPU K20 I/O I/O 5.7GB/s
Dense Matrix Multiplication • DGEMM: where the matrices are of dimensions: × × × A m k B k n C m n : , : , : • Why? – An important kernel for many problems – Optimization ideas can be used in other problems – Perhaps the most-studied algorithm in high performance computing • Can we solve very large DGEMM with the same performance throughput as small DGEMM?
Block Matrix Multiplication • Decompose into blocks A B C
Multiple CUDA Stream Scheduling
Performance Evaluation
Performance Evaluation
Conclusion • Many biomedical applications can make effective use of heterogeneous platforms. • But a significant amount of work is required to organize the computation into multi- stream of data transfers and kernel executions with no or very small stall time. • Portability of high performance code remains a problem. 26
Recommend
More recommend
