Process variation-aware workload partitioning algorithms for GPUs supporting spatial-multitasking

Aguilera, Paula; Lee, Jungseob; Farmahini-Farahani, Amin; Morrow, Katherine; Schulte, Michael; Kim, Nam Sung

doi:10.7873/date2014.189

Cited by 5 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Both of these solutions impose a nonnegligible performance penalty: the former directly diminishes the throughput of a cluster, and the latter imposes extra latency for synchronization of cores with different clock frequency domains. A recent work characterizes GPU application sensitivity to within-die frequency variations in the context of spatial multitasking [Aguilera et al 2014]. The sensitivity information partitions the workload and enables variation-aware allocation of the resources to concurrently executing applications on a GPU.…”

Section: Related Workmentioning

confidence: 99%

Aging-Aware Compilation for GP-GPUs

Lotfi

Rahimi

Benini

et al. 2015

ACM Trans. Archit. Code Optim.

View full text Add to dashboard Cite

General-purpose graphic processing units (GP-GPUs) offer high computational throughput using thousands of integrated processing elements (PEs). These PEs are stressed during workload execution, and negative bias temperature instability (NBTI) adversely affects their reliability by introducing new delay-induced faults. However, the effect of these delay variations is not uniformly spread across the PEs: some are affected more-hence less reliable-than others. This variation causes significant reduction in the lifetime of GP-GPU parts. In this article, we address the problem of "wear leveling" across processing units to mitigate lifetime uncertainty in GP-GPUs. We propose innovations in the static compiled code that can improve healing in PEs and stream cores (SCs) based on their degradation status. PE healing is a fine-grained very long instruction word (VLIW) slot assignment scheme that balances the stress of instructions across the PEs within an SC. SC healing is a coarse-grained workload allocation scheme that distributes workload across SCs in GP-GPUs. Both schemes share a common property: they adaptively shift workload from less reliable units to more reliable units, either spatially or temporally. These software schemes are based on online calibration with NBTI monitoring that equalizes the expected lifetime of PEs and SCs by regenerating adaptive compiled codes to respond to the specific health state of the GP-GPUs. We evaluate the effectiveness of the proposed schemes for various OpenCL kernels from the AMD APP SDK on Evergreen and Southern Island GPU architectures. The aging-aware healthy kernels generated by the PE (or SC) healing scheme reduce NBTIinduced voltage threshold shift by 30% (77% in the case of SCs), with no (moderate) performance penalty compared to the naive kernels.

show abstract

Section: Related Workmentioning

confidence: 99%