Design and early evaluation of a 3-D die stacked chip multi-vector processor

Modern vector processors have significant advantages over commodity-based scalar processors for memory-intensive scientific applications. However, vector processors still keep single core architecture, though chip multiprocessors (CMPs) have become the mainstream in recent processor architectures. To realize more efficient and powerful computations on a vector processor, this paper proposes a 3-D stacked chip multi-vector processor (CMVP) by combining a chip multi-vector processor architecture and the coarse-grain die stacking technology. The 3-D stacked CMVP consists of I/O layers, core layers and the vector cache layers. The I/O layer significantly improves off-chip memory bandwidth, and the vector core layer enables to install many vector cores on a die. The vector cache layer increases the capacity of on-chip memory and a high memory bandwidth to achieve the performance improvement and energy reduction by deceasing the number of off-chip memory accesses. The results of performance evaluation using real scientific and engineering applications show the potential of the 3-D stacked CMVP. Moreover, this paper clarifies that introducing the vector cache is more energy-effective than increasing the off-chip memory bandwidth to achieve the same sustained performance on the 3-D stacked CMVP.

I. Introduction

Modern vector processors have significant advantages over commodity-based scalar processors for memory-intensive scientific applications [1]. However, vector processors still keep a single core architecture, though chip multiprocessors (CMPs) have become the mainstream in recent processor architectures. To realize more efficient and powerful computations on a vector processor, CMP architectures should be applied to vector processor design in the near future. Since the computational efficiency of vector processors relies on their high memory bandwidth, a novel memory design that provides each vector core on a chip with a sufficiently-high memory bandwidth is strongly required to keep the high computational efficiency on a chip multi-vector processor (CMVP).