Multipurpose DRAM architecture for optimal power, performance, and product flexibility
نویسندگان
چکیده
An 18Mb DRAM has been designed in a 3.34, 0.5-pm CMOS process. The array consists of four independent, self-contained 4.5Mb quadrants. The chip output configuration defaults to 1 Mb x 18 for optimization of wafer screen tests, while 3 .34 or 5.04 operation is selected by choosing one of two M2 configurations. Selection of 2Mb x 9 or 1 Mb x 18 operation with the various address options, in extended data-out or fast-page mode, is accomplished by selective wire-bonding during module build. Laser fuses enable yield enhancement by substituting eight 512Kb array I/O slices for nine in each quadrant of the 18Mb array. This substitution is independent in each quadrant and results in 1 Mb x 16 operation with 2Mb x 8, 4Mb x 4, and 4Mb x 4 with any 4Mb independently selectable (4Mb x 4 w/4 CE). Input and control circuitry are designed such that performance margins are constant across output and functional configurations. The architecture also provides for “cut-downs” to 16Mb, 4.5Mb, and 4Mb chips with I/O and function as above.
منابع مشابه
Evaluating Power Management Strategies for High Performance Memory (DRAM): A Case Study for Achieving Effective Analysis by Combining Simulation Platforms and Real Hardware Performance Monitoring
Developing dynamic power management strategies for high performance systems requires a good understanding of the power-performance trade-offs underlining the workload-strategy-system interactions. The feasibility of detailed simulations to help here is severely limited by the range of problem sizes that can be simulated and simulation speed. For our work we want to understand the effectiveness ...
متن کاملDestructive-read in embedded DRAM, impact on power consumption
This paper explores power consumption for destructive-read embedded DRAM. Destructive-read DRAM is based on conventional DRAM design, but with sense amplifiers optimized for lower latency. This speed increase is achieved by not conserving the content of the DRAM cell after a read operation. Random access time to DRAM was reduced from 6 ns to 3 ns in a prototype made by Hwang et. al. A write-bac...
متن کاملSapphire: A Framework to Explore Power/Performance Implications of Tiled Architecture on Chip Multicore Platform
Sapphire is a multi-processor/multicore simulator where the memory hierarchy, interconnect (network on chip) and offchip DRAM are parametrized and can be configured to model various configurations. Sapphire addresses shortcomings in SESC by integrating it with Ruby from the GEMS framework. Sapphire also integrates Intacte, an interconnect power model. DRAMSim models off-chip DRAM in great detai...
متن کاملRe-Architecting DRAM Memory Systems with 3D Integration and Photonic Interfaces
In recent years, due to well-known “memory-wall” limitations, DRAM latency and energy/bit characteristics have not improved as rapidly as DRAM capacity and bandwidth with technology scaling. Despite plenty of research efforts during the last decade to overcome the hurdles in DRAM scaling, high performance computing systems of the future will still require improvements in DRAM latency and bandwi...
متن کامل3D Systems with On-Chip DRAM for Enabling Low-Power High-Performance Computing
Communication between the last-level caches and main memory is one of the main performance bottlenecks of today’s computer systems. 3D stacking enables integrating DRAM layers and processor cores on the same chip—improving memory bandwidth and reducing memory access time. We believe the performance increase achieved by 3D systems with on-chip DRAM can lead to high-performance system design with...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- IBM Journal of Research and Development
دوره 39 شماره
صفحات -
تاریخ انتشار 1995