10 citations · 18 across the 5 of their papers we have counts for
5 papers
Exploring the limits of Concurrency in ML Training on Google TPUs
Sameer Kumar, James Bradbury, Cliff Young +16
Recent results in language understanding using neural networks have required training hardware of unprecedentedscale, with thousands of chips cooperating on a single training run.…
Geometric Partitioning and Ordering Strategies for Task Mapping on Parallel Computers
Mehmet Deveci, Karen D. Devine, Kevin Pedretti +3
We present a new method for mapping applications' MPI tasks to cores of a parallel computer such that applications' communication time is reduced. We address the case of sparse nod…
Sparse Matrix-Matrix Multiplication on Multilevel Memory Architectures : Algorithms and Experiments
Mehmet Deveci, Simon D. Hammond, Michael M. Wolf +1
Architectures with multiple classes of memory media are becoming a common part of mainstream supercomputer deployments. So called multi-level memories offer differing characteristi…
Multi-threaded Sparse Matrix-Matrix Multiplication for Many-Core and GPU Architectures
Mehmet Deveci, Christian Trott, Sivasankaran Rajamanickam
Sparse Matrix-Matrix multiplication is a key kernel that has applications in several domains such as scientific computing and graph analysis. Several algorithms have been studied i…
GPU accelerated maximum cardinality matching algorithms for bipartite graphs
Mehmet Deveci, Kamer Kaya, Bora Ucar +1
We design, implement, and evaluate GPU-based algorithms for the maximum cardinality matching problem in bipartite graphs. Such algorithms have a variety of applications in computer…