Xiaowei Wang

Xiaowei Wang

Auto-generated profile, based on publicly available information

Xiaowei Wang

Department of Computer Science and Engineering, University of Michigan, Ann Arbor, MI, USA

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 September 2019 in IEEE Journal of Solid-State Circuits
Verified
Journal Article
Closed access
JWJingcheng Wang
Jingcheng Wang
XWXiaowei Wang
Xiaowei Wang
CECharles Eckert
Charles Eckert
ASArun Subramaniyan
Arun Subramaniyan
RDReetuparna Das
Reetuparna Das
DSDennis Sylvester
Dennis Sylvester
This article proposes a general-purpose hybrid in-/near-memory compute SRAM (CRAM) that combines an 8T transposable bit cell with vector-based, bit-serial in-memory arithmetic to accommodate a wide range of bit-widths, from single to 32 or 64 bits, as well as a complete set of operation types, including integer and floating-point addition, multiplication, and division. This approach provides the flexibility and programmability necessary for evolving software algorithms ranging from neural networks to graph and signal processing. The proposed design was implemented in a small Internet of Things (IoT) processor in the 28-nm CMOS consisting of a Cortex-M0 CPU and 8 CRAM banks of 16 kB each (128 kB total). The system achieves 475-MHz operation at 1.1 V and, with all CRAMs active, produces 30 GOPS or 1.4 GFLOPS on 32-bit operands. It achieves an energy efficiency of 0.56 TOPS/W for 8-bit multiplication and 5.27 TOPS/W for 8-bit addition at 0.6 V and 114 MHz.

12 October 2022 in IEEE Transactions on Computers
Verified
Journal Article
Closed access
CECharles Eckert
Charles Eckert
ASArun Subramaniyan
Arun Subramaniyan
XWXiaowei Wang
Xiaowei Wang
CACharles Augustine
Charles Augustine
RIRavishankar Iyer
Ravishankar Iyer
RDReetuparna Das
Reetuparna Das
This paper presents the Eidetic architecture, which is an SRAM-based ASIC neural network accelerator that eliminates the need to continuously load weights from off-chip, while also minimizing the need to go off chip for intermediate results. Using in-situ arithmetic in the SRAM arrays, this architecture can supports a variety of precision types allowing for effective inference. We also present different data mapping policies for matrix-vector based networks (RNN and MLP) on the Eidetic architecture and describe the tradeoffs involved. With this architecture, multiple layers of a network can be concurrently mapped, storing both the layer weights and intermediate results on-chip, removing the energy and latency penalty of off-chip memory accesses. We evaluate Eidetic on Google's Neural Machine Translation System (GNMT) encoder and demonstrate a 17.20× increase in throughput and 7.77× reduction in average latency over a single TPUv2 chip.