A circuit design of intelligent cache DRAM with automaticwrite-back capability

An intelligent cache based on a distributed architecture that consists of a hierarchy of three memory sections-DRAM (dynamic RAM), SRAM (static RAM), and CAM (content addressable memory) as an on-chip tag-is reported. The test device of the memory core is fabricated in a 0.6 μm double-metal CMOS standard DRAM process, and the CAM matrix and control logic are embedded in the array. The array architecture can be applied to 16-Mb DRAM with less than 12% of the chip overhead. In addition to the tag, the array embedded CAM matrix supports a write-back function that provides a short read/write cycle time. The cache DRAM also has pin compatibility with address nonmultiplexed memories. By achieving a reasonable hit ratio (90%), this cache DRAM provides a high-performance intelligent main memory with a 12 ns(hit)/34 ns(average) cycle time and 55 mA (at 25 MHz) operating current     

A modular architecture for a 6.4-Gbyte/s, 8-Mb DRAM-integratedmedia chip

A modular architecture for a DRAM-integrated, multimedia chip with a data transfer rate of 6 to 12 Gbyte/s is proposed. The architecture offers the design flexibility in terms of both DRAM capacity and the logic-memory interface for use in a wide variety of applications. A DRAM macro built from cascadable DRAM bank modules having a 256-kb memory capacity and 128-b I/Os provides flexibility and reconfigurability of DRAM capacity and a high data transfer rate with an area of 6.4 mm² /Mb. A data transfer circuit (called the “reconfigurable data I/O attachment”), which is attached to the I/O lines of the DRAM macro, provides a flexible logic-memory interface by changing the data-transfer routes between the DRAM macro and logic circuits in real time. A 6.4-Gbyte/s test chip (called the “media chip”) for three-dimensional computer graphics was fabricated to test the proposed design methodology. It integrates an 8-Mb DRAM and four pixel processors on an 8.35×14.6-mm chip by using a 0.4-μm CMOS design rule     

Quick-turnaround-time improvement for product development andtransfer to mass production

We describe equipment and facility operational methods in a production fab which are designed to achieve quick-turnaround-time (QTAT) manufacturing and ease product transfer from development to mass production. An advanced CIM system with precise lot management is introduced to keep the optimum balance of manufacturing TAT and throughput. Substantial end-user computing reduces the engineering holding time for handling development lots. In situ monitoring technologies are applied for the utilization enhancement of plasma-assisted equipment. A 9% manufacturing TAT reduction and a 14% throughput increase are estimated using a manufacturing simulator. The number of wafers in QTAT lots is reduced for processing time reduction. As a result, manufacturing TAT of QTAT lots with reduction from 24 wafers to three is reduced to 56% compared with that of normal lots in the production fab. This new production fab realizes QTAT development and agile product transfer from development to mass production with full process compatibility     

A 322 MHz random-cycle embedded DRAM with high-accuracy sensing and tuning

A 16 Mb embedded DRAM macro in a fully CMOS logic compatible 90 nm process with a low noise core architecture and a high-accuracy post-fabrication tuning scheme has been developed. Based on the proposed techniques, 61% improvement of the sensing accuracy is realized. Even with the smallest 5 fF/cell capacitance, a 322 MHz random-cycle access while 32 ms data retention time which contributes to save the data retention power down to 60 /spl mu/W are achieved.     

An 8-ns random cycle embedded RAM macro with dual-port interleavedDRAM architecture (D2RAM)

A novel fast random cycle embedded RAM macro with dual-port interleaved DRAM architecture (D²RAM) has been developed. The macro exploits three key circuit techniques: dual-port interleaved DRAM architecture, two-stage pipelined circuit operation, and write before sensing. Random cycle time of 8 ns under worst-case conditions has been confirmed with a 0.25-μm embedded DRAM test chip. This is six times faster than conventional DRAM     

Energy Efficient Real-Time Task Scheduling for Embedded Systems with Hybrid Main Memory

Available energy becomes a critical design issue for the increasingly complex real-time embedded systems. Phase Change Memory (PCM), with high density and low idle power, has recently been extensively studied as a promising alternative of DRAM. Hybrid PCM-DRAM main memory architecture has been proposed to leverage the low power of PCM and high speed of DRAM. In this paper, we propose energy-aware real-time task scheduling strategies for hybrid PCM-DRAM based embedded systems. Given the execution time variation when a task is loaded into PCM or DRAM, we re-design the static table-driven scheduling for a set of fixed tasks, as well as the Rate-Monotonic (RM) and Earliest Deadline First (EDF) scheduling policies for periodic task sets. Furthermore, since the actual execution time can be much shorter than the worst-case execution time in the actual execution, we propose online schedulers which migrates the tasks between PCM and DRAM to optimize the energy consumption by utilizing the slack time resulted from the completed tasks. All the proposed algorithms minimize the number of task migrations from PCM to DRAM by ensuring that aperiodic tasks are not migrated while each periodic task instance can be migrated at most once. Experimental results show our proposed scheduling algorithms satisfy the real-time constraints and significantly reduce the energy consumption.     

A 180 MHz 0.8 μm BiCMOS modular memory family of DRAM andmultiport SRAM

A family of modular memories with a built-in self-test interface designed using a synchronous self-timed architecture is described. This approach is ideally suited to modular memories embedded within synchronous systems due to its simple boundary specification, excellent speed/power performance, and ease of modelling. The basic port design is self-contained and extensible to any number of ports sharing access to a common-core cell array. The same design has been used to implement modular one-, two-, and four-part SRAMs and a one-port DRAM based on a four-transistor (4-T) cell. The latter provides a 45% core cell density improvement over the one-port SRAM. Nominal access and cycle times of 5.5 ns for 64 kb blocks have been shown for a 0.8 μm BiCMOS process with no memory process enhancements. System operation at 100 MHz has been demonstrated on a broadband time-switch chip containing 96 kb of two-port SRAM     

An access-sequence control scheme to enhance random-accessperformance of embedded DRAM's

An embedded DRAM enables a high data-transfer rate since it provides an on-chip wide-bus interconnection. However, the net data-transfer rate is reduced by page misses because of the inherently large row-access time of DRAM's. We previously proposed a multibank DRAM macro based on a micromodule architecture to overcome this problem. The pipelined access of the DRAM macro is especially useful for regular access in graphics applications. In this paper, we propose an access-sequence control scheme which enhances the random-access performance of embedded DRAMs. Access ID numbers, an access queue register, and a write-data buffer combined with the multibank DRAM enable out-of-sequence access which reduces the page-miss penalty during random access. In the case of four successive accesses, the estimated total access time was, respectively, reduced by up to 38 and 32% for one and two page misses, and for five successive accesses with one or two page misses, it was, respectively, reduced by up to 44 and 45%     

A 90-MHz 16-Mb system integrated memory with direct interface toCPU

This paper describes a system integrated memory with direct interface to CPU which integrates an SRAM, a DRAM, and control circuitry, including a tag memory (TAG). This memory realizes a computer system without glue chips, and thus enables a computer system which is low cost, low power, and compact size, but still with sufficient performance. Also fast clock cycle time and access time is realized using a newly proposed clock driver and internal signal generator. This memory is fabricated with a quad-polysilicon double-metal 0.55-μm CMOS process which is the same as used in a conventional 16-Mb DRAM. The chip size of 145.3 mm² is only a 12% increase over the conventional 16-Mb DRAM. The maximum operating frequency is 90-MHz and the operating current at cache-bit is 156-mA. This memory is suitable for various types of computer systems such as personal digital assistants (PDA's), personal computer systems, and embedded controller applications     

A temperature-insensitive self-recharging circuitry used in DRAMs

This paper presents a practical self-recharging circuitry for DRAMs. The proposed self-recharging circuitry not only reduces the standby power by monitoring the voltage drop caused by the data loss of a memory cell but also adjusts the recharging period of the memory cell that results from leakage currents. The proposed design is insensitive to temperature variations. A 1-Kb DRAM using our design is fabricated by a TSMC 0.35-/spl mu/m 1P4M CMOS process. The physical measurement of the proposed design on silicon verifies the correctness of the proposed circuitry.     

An embedded DRAM with a 143-MHz SRAM interface using a sense-synchronized read/write

This paper describes a 4-Mb embedded DRAM macro using novel fast random cycle architecture with sense-synchronized read/write (SSR/SSW). The test chip has been fabricated with a 0.15-/spl mu/m logic-based embedded DRAM process and the 1.5-V 143-MHz no-wait row random access operation has been confirmed. Data retention power is suppressed to 92 /spl mu/W owing to the hierarchical power supply and SSR. The macro size is 4.59 mm/sup 2/. The cell occupation ratio of the macro is 46%, which is the same as that of a conventional embedded DRAM macro. The macro size and the data retention power are 30% and 4.6%, respectively, of a 4-Mb embedded SRAM macro fabricated by an identical process.     

A 1.0-V 230-MHz column access embedded DRAM for portable MPEGapplications

This paper describes a 32-Mb embedded DRAM macro fabricated using 0.13-μm triple-well 4-level Cu embedded DRAM technology, which is suitable for portable equipment of MPEG applications. This macro can operate 230-MHz random column access even at 1.0-V power supply condition. The peak power consumption is suppressed to 198 mW in burst operation. The power-down standby mode, which suppresses the leakage current consumption of peripheral circuitry, is also prepared for portable equipment. With the collaboration of array circuit design and the fine Cu metallization technology, macro size of 18.9 mm² and cell efficiency of 51.3% are realized even with dual interface and triple test functions implemented     

New three-dimensional memory array architecture for futureultrahigh-density DRAM

In this paper, a three-dimensional (3-D) memory array architecture is proposed. This new architecture is realized by stacking several cells in series vertically on each cell located in a two-dimensional array matrix. Therefore, this memory array architecture has a conventional horizontal row and column address and new vertical row address. The total bit-line capacitance of this proposed architecture's DRAM is suppressed to 37% of normal DRAM when one bit-line has 1-Kbit cells and the same design rules are used. Moreover, an array area of 1-Mbit DRAM using the proposed architecture is reduced to 11.5% of normal DRAM using the same design rules. This proposed architecture's DRAM can realize small bit-line capacitance and small array area simultaneously. Therefore, this proposed 3-D memory array architecture is suitable for future ultrahigh-density DRAM     

High-performance embedded SOI DRAM architecture for the low-powersupply

This paper presents the high-performance DRAM array and logic architecture for a sub-1.2-V embedded silicon-on-insulator (SOI) DRAM. The degradation of the transistor performance caused by boosted wordline voltage level is distinctly apparent in the low voltage range. In our proposed stressless SOI DRAM array, the applied electric field to the gate oxide of the memory-cell transistor can he relaxed. The crucial problem that the gate oxide of the embedded-DRAM process must be thicker than that of the logic process can be solved. As a result, the performance degradation of the logic transistor can be avoided without forming the gate oxides of the memory-cell array and the logic circuits individually. In addition, the data retention characteristics can be improved. Secondly, we propose the body-bias-controlled SOI-circuit architecture which enhances the performance of the logic circuit at sub-1.2-V power supply voltage, Experimental results verify that the proposed circuit architecture has the potential to reduce the gate-delay time up to 30% compared to the conventional one. This proposed architecture could provide high performance in the low-voltage embedded SOI DRAM     

A configurable DRAM macro design for 2112 derivative organizationsto be synthesized using a memory generator

This paper describes a DRAM macro design from which 2112 configurations up to 32 Mb can be synthesized using a memory generator. The memory generator automatically creates the layout of a DRAM macro in accordance with specification inputs such as memory capacity, address count, bank count, and I/O bits count. An expandable floor layout scheme achieves the macro size comparable to that of handicraft-designed DRAM. The memory generator can customize a configurable redundancy scheme for various macro configurations. Unified testing circuits make it possible to test DRAM macros with more than 500 interface pins in a direct-memory-access mode with 33 test pads. Up to four macros on the same chip can be tested with them. Test chips with 4-Mb DRAM and with 20-Mb DRAM fabricated with 0.35-μm technology showed 150-MHz operation     

A 1.8-V embedded 18-Mb DRAM macro with a 9-ns RAS access time andmemory-cell area efficiency of 33%

A 1.8-V embedded 18-Mb DRAM macro with a 9-ns row-address-strobe access time and memory-cell area efficiency of 33% has been successfully developed with a single-side interface architecture, high-speed circuit design, and low-voltage design. In the high-speed circuit design, a multiword redundancy scheme and Y-select merged sense scheme are developed to achieve the performance goal. In the low-voltage design, a dual-complement charge-pump scheme and a decoupling capacitor utilizing a tantalum-oxide capacitor are developed to retain high performance at low supply voltage     

High-speed memory architectures for multimedia applications

In order to meet the requirements for multimedia applications, several approaches to DRAM architecture have emerged. Instead of a single, common memory device, several advanced approaches, such as extended data out (EDO) DRAM, and synchronous DRAM (SDRAM) will each play a major role in the future memory market. Furthermore, advanced interface technologies, such as Rambus RAM (RDRAM), RamLink, and SyncLink are very promising for future-generation memory. Also, application-specific memory, such as cache DRAM (CDRAM), enhanced DRAM (EDRAM), and video DRAM (VRAM) offer unique characteristics to improve performance in particular applications. Since it is beneficial to understand which type of high-speed memory can improve the speed performance of a particular system most effectively, this article discusses the fundamental concepts of these recent high-speed performance memory architectures to aid in the selection of memories for multimedia applications     

Parallel contention resolution control for input queueing ATM switches

Input queueing ATM switches requiring fast contentional resolution control have been negatively affected by long turn-around time (TAT) due to the distance between an input port controller and a centralised contention controller. A parallel contention resolution control for input queueing switches is presented. The proposed control allows a TAT of more than one cell slot, resulting in the potential development of a centralised contention controller for an ATM switch with an aggregate capacity of 1 Tbit/s.<>     

基于新型非易失存储器的混合内存架构的内存管理机制

随着互联网和云计算技术的迅猛发展,现有动态随机存储器（Dynamic Random Access Memory,DRAM）已无法满足一些实时系统对性能、能耗的需求.新型非易失存储器（Non-Volatile Memory,NVM）的出现为计算机存储体系的发展带来了新的契机.本文针对NVM和DRAM混合内存系统架构,提出一种高效的混合内存页面管理机制.该机制针对内存介质写特性的不同,将具有不同访问特征的数据页保存在合适的内存空间中,以减少系统的迁移操作次数,从而提升系统性能.同时该机制使用一种两路链表使得NVM介质的写操作分布更加均匀,以提升使用寿命.最后,本文在Linux内核中对所提机制进行仿真实验.并与现有内存管理机制进行对比,实验结果证明了所提方法的有效性.