Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Extreme-bandwidth scalable performance-per-watt GPU architecture

Patent ·
OSTI ID:1600412
;
A technique for accessing memory in an accelerated processing device coupled to stacked memory dies is provided herein. The technique includes receiving a memory access request from an execution unit and identifying whether the memory access request corresponds to memory cells of the stacked dies that are considered local to the execution unit or non-local. For local accesses, the access is made “directly”, that is, without using a bus. A control die coordinates operations for such local accesses, activating particular through-silicon-vias associated with the memory cells that include the data for the access. Non-local accesses are made via a distributed cache fabric and an interconnect bus in the control die. Various other features and details are provided below.
Research Organization:
Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
Sponsoring Organization:
USDOE
DOE Contract Number:
AC52-07NA27344;
Other Award/Contract Number:
B620717
Assignee:
Advanced Micro Devices, Inc. (Santa Clara, CA)
Patent Number(s):
10,509,596
Application Number:
15/851,476
OSTI ID:
1600412
Country of Publication:
United States
Language:
English

References (4)

Harmonica: An FPGA-Based Data Parallel Soft Core
  • Kersey, Chad; Yalamanchili, Sudhakar; Kim, Hyojong
  • 2014 IEEE 22nd Annual International Symposium on Field-Programmable Custom Computing Machines https://doi.org/10.1109/FCCM.2014.53
conference May 2014
A case for exploiting subarray-level parallelism (SALP) in DRAM conference June 2012
3D-Integrated SRAM Components for High-Performance Microprocessors journal October 2009
Exploring DRAM organizations for energy-efficient and resilient exascale memories
  • Giridhar, Bharan; Cieslak, Michael; Duggal, Deepankar
  • Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis https://doi.org/10.1145/2503210.2503215
conference November 2013

Similar Records

Related Subjects

97 MATHEMATICS AND COMPUTING