MARTIN BURTSCHER
Professor 2015-present,
ECL,
CS,
TX State
Associate Professor 2010-2015,
ECL,
CS,
TX State
Research Scientist 2007-2010,
ISS,
ICES,
UT Austin
Assistant Professor 2000-2007,
CSL,
ECE,
Cornell
PhD (2000),
Computer Science,
CU Boulder
MS (1996),
Computer Science,
ETH Zurich
BS (1994),
Computer Science,
ETH Zurich
|
|
|
|
Recent Highlights
We just released the Indigo benchmark suite. It contains 1084 CUDA and 636 OpenMP codes with thousands of inputs. Each code implements a different version of a frequent pattern found in parallel graph analytics programs. About half of the codes include planted bugs for testing verification tools. The Indigo suite is described in detail in our ISPASS'22 paper, which received the best paper award.
Short Biography
Martin Burtscher is a Professor in the Department of Computer Science at Texas State University.
He received the BS/MS degree from ETH Zurich and the PhD degree from the University of Colorado at Boulder.
Martin's current research focuses on the parallelization of graph algorithms and complex programs for GPUs
as well as on automatic synthesis of high-speed data-compression algorithms.
He has co-authored over 110 peer-reviewed scientific publications, which have
been cited over 6000 times.
Martin is a distinguished member of the ACM and a senior member of the IEEE.
Current Research Areas
GPU computing, parallel algorithm design, data compression, graph analytics, algorithm synthesis, energy efficiency
I am always looking for creative and motivated students at all levels who are interested in working on these and related topics with me.
Efficient Computing Laboratory
Martin directs the Efficient Computing Laboratory (ECL). Its research goals are developing general
strategies for parallelizing complex and irregular programs, creating techniques to automatically synthesize
high-performance data-compression algorithms, and designing optimizations to improve performance and
energy efficiency. Animations and more information are available here.
Faster computations and better algorithms can help save lives, solve health problems, increase safety, improve
the environment, and keep us connected. At this point, parallelization is the primary way to make more powerful
and energy-efficient computers possible. As we are reaching the limits of human ability, automatic synthesis is
the most promising avenue for creating new and improved algorithms.
Projects
CIVIC (verification of irregular parallel programs) [NSF/CCF - SHF]
LC (high-speed lossy data compression framework) [DOE/ASCR - DRS]
PECOS (simulation of inductively coupled plasma torch) [DOE/NNSA - PSAAP III]
Publications
GPU computing (GC, MIS, CC, recurrences, prefix scans, graph algorithms, compression, n-body, TSP)
[MCHPC'22]
[TOPC'22]
[PDSEC'22]
[SC'21]
[PPoPP'20]
[TOPC'18]
[HPDC'18]
[ASPLOS'18]
[AGRP'16a]
[AGRP'16b]
[PLDI'16]
[HPPAC'16]
[HCW'16]
[Cluster'15]
[PDPTA'15]
[GPGPU'15a]
[GPGPU'15b]
[GPCDP'14]
[IISWC'14]
[NAS'14]
[SAC'14]
[GPGPU'14]
[HPCwire'14]
[IPCCC'13]
[PASA'13]
[PDPTA'13]
[IPDPS'13b]
[GPGPU'13]
[PPoPP'13]
[IISWC'12]
[PPoPP'12]
[PDPTA'11b]
[GPGPU'11]
[GCG'11]
Parallel computing (parallelization, irregular programs, verification suite, tracing, race tolerance, HPC)
[SC'22]
[ISPASS'22]
[PPoPP'21]
[ICCAD'19]
[Cluster'19]
[ESPT'18]
[EduHPC'18]
[WOSET'18]
[SIGCSE'15]
[EduPDHPC'13]
[IPDPS'13a]
[ICS'12]
[TC'12]
[PPoPP'12]
[PLDI'11]
[LCPC'10]
[PPoPP'10]
[ISPASS'09]
[PPoPP'09a]
[PPoPP'09b]
[LCPC'08]
[EUROPAR'05]
[PDPTA'05]
[SC'04]
[PDPTA'02]
Lossless data compression (floating-point data, execution traces, mobile data, JavaScript code)
[IA^3'22]
[DCC'18]
[ACCN'17]
[SC'16]
[SPACE'16]
[ICCCN'15]
[TC'14]
[MASCOTS'13]
[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]
Performance optimization, recommendation systems, classification, phase detection
[CVIU'15]
[DMIN'14]
[3DOR'14]
[PDPTA'11a]
[ISPASS'11]
[SC'10]
[JPCS'09]
[TG'09]
[ISPASS'08]
[IISWC'06]
[MICRO'04]
[PLDI'02]
Prefetching and caching (multicore architectures, helper threading, 3D architectures)
[HPCC'15]
[TACO'06]
[PACT'06]
[D&T'05]
[PACT'05]
[TECHCON'05]
[MSP'05]
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]
Value prediction (value predictors, energy/complexity efficient design, confidence estimators)
[WISA'06]
[CAN'05]
[WDDD'05]
[CF'05]
[VPW'04]
[TC'02]
[CAN'02]
[ICCD'00]
[DISS'00]
[PACT'99]
[JILP'99]
[PFDC'98]
Software and Data
GPU code:
SFP (VLSI routing),
ECL-APSP (all pairs shortest paths),
graphB+ (signed social network balancing),
ECL-MIS (maximal independent sets),
ECL-GC (graph coloring),
ECL-CC (connected components),
PLR (linear recurrences),
SAM (prefix sums),
MPC and
GFC (compression),
TSP_GPU (TSP),
ECL-BH (n-body),
FSM_GA (finite state machines)
Energy/Performance:
K20Power (GPU power profiler),
PerfExpert/AutoSCOPE (bottleneck diagnosis)
FP compression:
FPcrush,
SPDP (tool),
SPDP (HDF5),
MPC,
GFC,
gFPC,
pFPC,
FPC,
DP data,
SP data
Benchmark suites:
Indigo (parallel microbenchmarks),
LonestarGPU (irregular GPU code),
Lonestar (irregular CPU code)
Parallelization systems:
Parla (heterogeneous tasking system),
ILCS (iterative local searches)
Sequence mining:
CBBT (phase detection),
patterns (frequent subsequences)
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)
Programming projects:
Peachy assignments (computing a movie of zooming into a fractal)
Professional Activities
Committee Member:
ISCA'23,
HPCA'23,
DRBSD'22,
IISWC'22,
ISCA'22,
IWBDR'21,
DRBSD'21,
MICRO'21,
ISCA'21,
ISPASS'21,
DRBSD'20,
IWBDR'20,
DRBSD'19,
GPGPU'19,
DRBSD'18b,
DRBSD'18a,
GPGPU'18,
PPoPP'18,
DRBSD'17b,
EuroPar'17,
DRBSD'17a,
GPGPU'17,
PPoPP'17,
EduHPC'16,
GPGPU'16,
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
Distinguished Member of the
ACM;
Senior Member of the
IEEE and
IEEE CS;
Member of the
NCWIT
Current ECL members
Martin Burtscher: Director
Ghadeer Alabandi: GPU-based graph analytics (PhD)
Noushin Azami: Parallel data compression (PhD)
Cameron Bradley: GPU-based motif counting (BS)
Brandon Burtchell: Adaptive data compression (MS)
Alex Fallin: Progressive data compression (PhD)
Benila Jerald: Program parallelization (PhD)
Rain Lawson: Program parallelization (PhD)
Yiqian Liu: Irregular benchmark suites (PhD)
Kian ORyan: Multi-GPU clustering (MS)
Grant Smith: Color-reduction heuristics (BS)
Mackenzie Toliver: GPU-based data compression (BS)
Avery Vanausdal: Parallel C++ benchmarks (BS)
A few words from former ECL members
Kristi Belcher: undergraduate researcher [video]
Sindhu Devale: graduate researcher [video]
Andres Gonzalez: graduate researcher [video]
Sepideh Maleki: graduate researcher [video]
Arthi Nagarajan: graduate researcher [video]
Jarim Seo: graduate researcher [video]
Dean Terrell: undergraduate researcher [video]
Aarti Kothari: graduate researcher [video]
Former thesis/dissertation students
Kayla Wesley: Parallel LZ77 algorithm (MS'22)
Andres Gonzalez: Parallel TSP heuristic (MS'20)
Jarim Seo: Parallel MST generation (MS'20)
Aarti Kothari: Massively parallel routing (MS'20)
Isaac van Til: Parallel graph coloring (BS'20)
Arthi Nagarajan: Energy-efficient memory accesses (MS'17)
Jayadharini Jaiganesh: Fast connected-components algorithms (MS'17)
Sahar Azimi: GPU execution tracing and compression (MS'17)
Kristi Belcher: Multi-GPU execution of irregular codes (BS'16)
Sepideh Maleki: Generalizing prefix-sum computations (MS'16)
Sindhu Devale: Tracing of large-scale parallel programs (MS'16)
Farbod Hesaaraki: Unobtrusive real-time tracing of parallel programs (MS'15)
Molly O'Neil: Using GPUs to accelerate irregular programs (MS'15)
Saeed Taheri: Optimization suggestions for GPU programs (MS'14)
Hari Mukka: Data-compression algorithm synthesis (MS'14)
Paruj Ratanaworabhan: Automatic data-race tolerance (PhD'09)
Ilya Ganusov: Multi-core helper threading (PhD'07)
Former research-group members
Patrick Parker: Undergraduate Research Assistant
Corbin Walters: Undergraduate Research Assistant
Shubhangi Mahajan: Independent Study
Rick Rodriguez: Undergraduate Independent Study
Sirichi Srisan: Independent Study
Grace Adams: Undergraduate Research Assistant
Alex Fallin: Undergraduate Research Assistant
Kameron Bush: Undergraduate Research Assistant
Navya Tulimilli: Graduate Research Assistant
Anthony Cortes: Undergraduate Research Assistant
Fernando Valdes: Undergraduate Research Assistant
Christopher Yanez: Undergraduate Research Assistant
Evan Powers: Undergraduate Research Assistant
Randy Cornell: Undergraduate Research Assistant
Dean Terrell: Undergraduate Research Assistant
Jared Coplin: Undergraduate Research Assistant
Steven Claggett: Undergraduate Research Assistant
James Edwards: Undergraduate Research Assistant
Annie Yang: Undergraduate Research Assistant
Kurstie Lenear: Undergraduate Research Assistant
Christopher Ramirez: Undergraduate Research Assistant
Bhavya Medishetty: Graduate Research Assistant
Peter Janovics: Undergraduate Research Assistant
Raghuveer Kolli: Graduate Research Assistant
Hassan Rabeti: Undergraduate/Graduate Research Assistant
Jim Shockey: Independent Study
Olalekan Sopeju: Graduate Research Assistant
Selected ECL-member highlights
NSF Fellowships ($138,000): Jared, Kristi, Molly
Outstanding thesis awards: Sepideh
Outstanding research awards: Jared, Molly, Sepideh
Best paper awards: Yiqian, Noushin
PhD positions at Texas State, U. of Oregon, UT Austin, U. of Utah
Industry positions at NVIDIA, Intel, Samsung, Thermon, USAA, Charles Schwab, etc.
|
|
|
|
|
