PHOENIX: Efficient computation in memory
Paper i proceeding, 2017

Parallelism is inherent in most problems but due to current programming models and architectures which have evolved from a sequential paradigm, the parallelism exploited is restricted. We believe that the most efficient parallel execution is achieved when applications are represented as graphs of operations and data, which can then be mapped for execution on a modular and scalable processing-in-memory architecture. In this paper, we present PHOENIX, a general-purpose architecture composed of many Processing Elements (PEs) with memory storage and efficient computational logic units interconnected with a mesh network-on-chip. A preliminary design of PHOENIX shows it is possible to include 10,000 PEs with a storage capacity of 0.6GByte on a 1.5cm2 chip using 14nm technology. PHOENIX may achieve 6TFLOPS with a power consumption of up to 42W, which results in a peak energy efficiency of at least 143GFLOPS/W. A simple estimate shows that for a 4K FFT, PHOENIX achieves 117GFLOPS/W which is more than double of what is achieved by state-of-the-art systems.

Energy-efficient

Processing-in-memory (PIM)

Parallel architectures

High-performance computing (HPC)

Författare

Mats Rimborg

Chalmers, Data- och informationsteknik, Datorteknik

Pedro Trancoso

Chalmers, Data- och informationsteknik, Datorteknik

Gunnar Carlstedt

Chalmers, Data- och informationsteknik, Datorteknik

ACM International Conference Proceeding Series. 2017 International Symposium on Memory Systems, MEMSYS 2017; Washington; United States; 2-5 October 2017

Vol. Part F131197 15-25

Ämneskategorier

Data- och informationsvetenskap

DOI

10.1145/3132402.3132430

ISBN

978-145035335-9

Mer information

Skapat

2017-12-15