José Moreira, James R. Larus
Proceedings of the 19th Symposium on Principles and Practice of Parallel Programming
PPoPP, 2014.

@proceedings{PPoPP-2014,
	acmid         = "2555243",
	address       = "Orlando, Florida, USA",
	editor        = "José Moreira and James R. Larus",
	isbn          = "978-1-4503-2656-8",
	publisher     = "{ACM}",
	title         = "{Proceedings of the 19th Symposium on Principles and Practice of Parallel Programming}",
	year          = 2014,
}

Contents (46 items)

10 ×#concurrent
9 ×#parallel
8 ×#performance
7 ×#named
6 ×#thread
5 ×#programming
4 ×#scheduling
3 ×#algorithm
3 ×#data type
3 ×#detection

PPoPP-2014-Hill #architecture

21st century computer architecture (MDH), pp. 1–2.

PPoPP-2014-LiuTHB #detection #named #predict

PREDATOR: predictive false sharing detection (TL, CT, ZH, EDB), pp. 3–14.

PPoPP-2014-ThomsonDB #bound #concurrent #empirical #testing #using

Concurrency testing using schedule bounding: an empirical study (PT, AFD, AB), pp. 15–28.

PPoPP-2014-SamakR #concurrent #detection

Trace driven dynamic deadlock detection and reproduction (MS, MKR), pp. 29–42.

PPoPP-2014-ChiangGRS #fault #float #performance

Efficient search for inputs causing high floating-point errors (WFC, GG, ZR, AS), pp. 43–52.

PPoPP-2014-TardieuHCGKSSTV

X10 and APGAS at Petascale (OT, BH, DC, DG, PK, VAS, AS, MT, MV), pp. 53–66.

PPoPP-2014-CunninghamGHIKMSTT #performance #programming

Resilient X10: efficient failure-aware programming (DC, DG, BH, AI, KK, HM, VAS, MT, OT), pp. 67–80.

PPoPP-2014-YangBMB #fortran

Portable, MPI-interoperable coarray fortran (CY, WB, JMMC, PB), pp. 81–92.

PPoPP-2014-YangZ #concurrent #named #parallel #thread

CUDA-NP: realizing nested thread-level parallelism in GPGPU applications (YY, HZ), pp. 93–106.

PPoPP-2014-YanLZZ #framework #named

yaSpMV: yet another SpMV framework on GPUs (SY, CL, YZ, HZ), pp. 107–118.

PPoPP-2014-BauerTA #named #performance

Singe: leveraging warp specialization for high performance on GPUs (MB, ST, AA), pp. 119–130.

PPoPP-2014-OdairaCT #hardware #interpreter #memory management #ruby #transaction

Eliminating global interpreter locks in ruby through hardware transactional memory (RO, JGC, HT), pp. 131–142.

PPoPP-2014-PetrovicRS #concurrent #hardware #message passing #performance #thread

Leveraging hardware message passing for efficient thread synchronization (DP, TR, AS), pp. 143–154.

PPoPP-2014-HerlihyL #locality

Well-structured futures and cache locality (MH, ZL), pp. 155–166.

PPoPP-2014-DieguesR #lightweight #memory management #named #transaction

Time-warp: lightweight abort minimization in transactional memory (NLD, PR), pp. 167–178.

PPoPP-2014-Olukotun #domain-specific language #parallel #programming

Beyond parallel programming with domain specific languages (KO), pp. 179–180.

PPoPP-2014-SongH #3d #design #parallel

Designing and auto-tuning parallel 3-D FFT for computation-communication overlap (SS, JKH), pp. 181–192.

PPoPP-2014-CatanzaroKG #composition #matrix

A decomposition for in-place matrix transposition (BCC, AK, MG), pp. 193–206.

PPoPP-2014-SungGGGH #matrix

In-place transposition of rectangular matrices on accelerators (IJS, JGL, JMGL, NG, WmWH), pp. 207–218.

PPoPP-2014-MalekiMM #convergence #programming #rank

Parallelizing dynamic programming through rank convergence (SM, MM, TM), pp. 219–232.

PPoPP-2014-MehtaLY #framework

Revisiting loop fusion in the polyhedral framework (SM, PHL, PCY), pp. 233–246.

PPoPP-2014-RodriguesJDH #algorithm #clustering #interface #named #programming

Triolet: a programming system that unifies algorithmic skeleton interfaces for high-performance cluster computing (CIR, TBJ, AD, WmWH), pp. 247–258.

PPoPP-2014-LiuM #architecture #parallel #performance #source code #thread

A tool to analyze the performance of multithreaded programs on NUMA architectures (XL, JMMC), pp. 259–272.

PPoPP-2014-RaoZ #performance #scheduling #towards #virtual machine

Towards fair and efficient SMP virtual machine scheduling (JR, XZ), pp. 273–286.

PPoPP-2014-LuZBW #multi #performance #thread

Efficient deterministic multithreading without global barriers (KL, XZ, TB, XW), pp. 287–300.

PPoPP-2014-EslamimehrP #concurrent #scheduling #source code

Race directed scheduling of concurrent programs (ME, JP), pp. 301–314.

PPoPP-2014-Rubin #compilation #question #research #what

Heterogeneous computing: what does it mean for compiler research? (NR), pp. 315–316.

PPoPP-2014-NatarajanM #concurrent #performance

Fast concurrent lock-free binary search trees (AN, NM), pp. 317–328.

PPoPP-2014-BrownER

A general technique for non-blocking trees (TB, FE, ER), pp. 329–342.

PPoPP-2014-DrachslerVY #concurrent #logic

Practical concurrent binary search trees via logical ordering (DD, MTV, EY), pp. 343–356.

PPoPP-2014-TimnatP #data type #simulation

A practical wait-free simulation for lock-free data structures (ST, EP), pp. 357–368.

PPoPP-2014-PusukuriGB #concurrent #thread

Lock contention aware thread migrations (KKP, RG, LNB), pp. 369–370.

PPoPP-2014-LeeKZ #concurrent #execution #multi

Infrastructure-free logging and replay of concurrent execution on multiple cores (KHL, DK, XZ), pp. 371–372.

PPoPP-2014-AgustonBH #parallel

Parallelization hints via code skeletonization (CA, YBA, GH), pp. 373–374.

PPoPP-2014-WangWYYWL0 #concurrent #debugging #locality #memory management #using

Concurrency bug localization using shared memory access pairs (WW, CW, PCY, XY, ZW, JL, XF), pp. 375–376.

PPoPP-2014-LeungBEFPRS

Task mapping stencil computations for non-contiguous allocations (VJL, DPB, JE, SPF, NWP, ZDR, MS), pp. 377–378.

PPoPP-2014-0003VTCT #data type #scheduling

Data structures for task-based priority scheduling (MW, FV, JLT, DC, PT), pp. 379–380.

PPoPP-2014-Bautista-GomezC #detection #monitoring

Detecting silent data corruption through data dynamic monitoring for scientific applications (LABG, FC), pp. 381–382.

PPoPP-2014-SandesMMMA #comparison #parallel #sequence

Fine-grain parallel megabase sequence comparison with multiple heterogeneous GPUs (EFdOS, GM, ACMAdM, XM, EA), pp. 383–384.

PPoPP-2014-Golan-GuetaRSY #automation #semantics

Automatic semantic locking (GGG, GR, MS, EY), pp. 385–386.

PPoPP-2014-HassanPR #transaction

Optimistic transactional boosting (AH, RP, BR), pp. 387–388.

PPoPP-2014-AgrawalFSSU #data type #parallel #scheduling #source code

Provably good scheduling for parallel programs that use data structures through implicit batching (KA, JTF, BS, JS, RU), pp. 389–390.

PPoPP-2014-MaAC #algorithm #analysis #manycore #thread

Theoretical analysis of classic algorithms on highly-threaded many-core GPUs (LM, KA, RDC), pp. 391–392.

PPoPP-2014-TomkinsSAR #algorithm #component #named #parallel

SCCMulti: an improved parallel strongly connected components algorithm (DT, TGS, NMA, LR), pp. 393–394.

PPoPP-2014-LuoLHKP #hybrid #manycore #programming #runtime

Initial study of multi-endpoint runtime for MPI+OpenMP hybrid programming model on multi-core systems (ML, XL, KH, KCK, DKP), pp. 395–396.

PPoPP-2014-IsaacsGBBSH #execution #identification #logic #parallel

Extracting logical structure and identifying stragglers in parallel execution traces (KEI, TG, AB, PTB, MS, BH), pp. 397–398.