MARTIN BURTSCHER

Associate Professor 2010-present, ECL, CS, TX State
Research Scientist 2007-2010, ISS, ICES, UT Austin
Assistant Professor 2000-2007, CSL, ECE, Cornell

Ph.D. (2000), Computer Science, CU Boulder
M.S. (1996), Computer Science, ETH Zurich
B.S. (1994), Computer Science, ETH Zurich

Current Research Areas
GPGPU, program parallelization, data compression, energy efficiency, performance assessment

Projects and Publications
GPGPU computing (irregularity, points-to analysis, traveling salesman, data compression, n-body, FSM)
[IISWC'14] [SAC'14] [GPGPU'14] [HPCwire'14] [PDPTA'13] [IPDPS'13b] [GPGPU'13] [PPoPP'13] [IISWC'12] [PPoPP'12] [PDPTA'11b] [GPGPU'11] [GCG'11]
Parallel computing (parallelization, irregular programs, race tolerance, MPI acceleration)
[EduPDHPC'13] [IPDPS'13a] [ICS'12] [TC'12] [PLDI'11] [PPoPP'11] [LCPC'10] [PPoPP'10] [ISPASS'09] [PPoPP'09a] [PPoPP'09b] [LCPC'08] [EUROPAR'05] [PDPTA'05] [SC'04] [PDPTA'02]
Energy efficiency (GPU DVFS, compression on handhelds, speculation)
[NAS'14] [IPCCC'13] [PASA'13] [MASCOTS'13] [ISPASS'13] [CF'05]
Performance evaluation and optimization, classification (recommendation systems, phase detection)
[DMIN'14] [3DOR'14] [PDPTA'11a] [ISPASS'11] [SC'10] [JPCS'09] [TG'09] [ISPASS'08] [IISWC'06] [MICRO'04] [PLDI'02]
Lossless data compression (program execution traces, floating-point data, JavaScript source code)
[TC'14] [TC'11] [CASES'10] [WebApps'10] [DCC'10] [ICCD'09] [DCC'09] [TC'09] [DCC'07a] [DCC'07b] [CAN'06] [DCC'06] [TC'05] [CGO'05] [SIGMETRICS'04] [PACT'03]
Computational brain-injury modeling (bioengineering, visualization, BIC)
[BIOCOMP'12] [BIOCOMP'11] [BIOCOMP'08] [MSV'07] [SBC'07] [MSV'06] [SBC'05] [METMBS'05] [SBC'03]
Prefetching and caching (multicore architectures, helper threading, 3D architectures)
[TACO'06] [PACT'06] [D&T'05] [PACT'05] [TECHCON'05] [MSP'05]
Value prediction (hybrid predictors, energy/complexity efficient design, confidence estimators)
[WISA'06] [CAN'05] [WDDD'05] [VPW'04] [TC'02] [CAN'02] [ICCD'00] [DISS'00] [PACT'99] [JILP'99] [PFDC'98]

Software and Data
Benchmark suites: LonestarGPU (irregular GPU code), Lonestar (irregular CPU code)
Parallelization systems: ILCS (iterative local searches), Galois (irregular programs)
GPU code: FSM_GA (bimodal FSM), TSP_GPU (TSP), GFC (compression), Barnes Hut (n-body)
Energy/Performance: K20Power (GPU power profiler), PerfExpert/AutoSCOPE (bottleneck diagnosis)
Sequence mining: CBBT (phase detection), patterns (frequent subsequences)
Floating-point compression: GFC, gFPC, pFPC, and FPC (compression algorithms), data (13 datasets)
Trace compression: TCgen (compressor generator), VPC3 (compression algorithm)
Brain-injury modeling: TBI (model, BIC, animations)

Teaching Material
Lecture slides: Teaching modules (introduction to parallel programming for undergraduates)

Research Students
Peter Janovics: Debugging of large-scale heterogeneous programs
Bhavya Medishetty: Parallelization of irregular codes for efficient GPU execution
Annie Yang: Data compression algorithms for massively-parallel architectures
Jared Coplin: Energy-efficiency optimization of GPU programs
Hari Mukka: High-speed and real-time lossless data compression
Farbod Hesaaraki: Unobtrusive real-time tracing of parallel programs
Saeed Taheri: Automatic optimization suggestions for GPU programs
Molly O'Neil: Using GPUs to accelerate irregular programs
Paruj Ratanaworabhan: Automatic race tolerance (Ph.D. in 2009, now at Kasetsart University)
Ilya Ganusov: Multi-core helper threading (Ph.D. in 2007, now at Xilinx)

Professional Activities
Committee Member: Cluster'15, PLDI'15, PPoPP'15, PLDI'14, PPoPP'14, GPGPU'13, PPoPP'13, GPGPU'12, PPoPP'12, PACT'11, ICSEC'11, PLDI'11, HPCA'11, PPoPP'10, ISCA'09, PPoPP'09, IISWC'08, MSPC'06, IISWC'05, CGO'05, ICS'02
Workshops & Tutorials: TUES1, COT5, COT4, PET5, COT3, PET4, PET3, COT2, PET2, COT1, PET1, VPW2, VPW1
Senior Member: ACM, IEEE, IEEE CS
Official Texas State University Disclaimer