Journal
ACM SIGPLAN NOTICES
Volume 53, Issue 2, Pages 1-14Publisher
ASSOC COMPUTING MACHINERY
DOI: 10.1145/3173162.3173171
Keywords
-
Categories
Funding
- NSF [CAREER-1652294, XPS-1628991]
- C-FAR, one of the six SRC STAR-net centers - MARCO
- C-FAR, one of the six SRC STAR-net centers - DARPA
Ask authors/readers for more resources
Recent developments in Non-Volatile Memories (NVMs) have opened up a new horizon for in-memory computing. Despite the significant performance gain offered by computational NVMs, previous works have relied on manual mapping of specialized kernels to the memory arrays, making it infeasible to execute more general workloads. We combat this problem by proposing a programmable in-memory processor architecture and data-parallel programming framework. The efficiency of the proposed in-memory processor comes from two sources: massive parallelism and reduction in data movement. A compact instruction set provides generalized computation capabilities for the memory array. The proposed programming framework seeks to leverage the underlying parallelism in the hardware by merging the concepts of data-flow and vector processing. To facilitate in-memory programming, we develop a compilation framework that takes a TensorFlow input and generates code for our in-memory processor. Our results demonstrate 7.5x speedup over a multi-core CPU server for a set of applications from Parsec and 763x speedup over a server-class GPU for a set of Rodinia benchmarks.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available