論文

This paper describes advanced ATM switching system hardware that uses a high-performance and cost-effective MCM-D module as an ATM-layer function device. The MCM-D module is fabricated on a Si-substrate using the stacking RAM technique to reduce module size. The MCM has a 4-layer Si substrate, a high-performance ASIC, 8 high-speed SRAMs, and an FPGA. By using the stacking RAM technique, MCM-D module size is reduced to 50.8mm x 50.8mm. This is 40% ofthat (100mm x 65mm) of a double-side mounted sub-board module with conventional packaging (QFP and SOP). The MCM-D module realizes the ATM-layer functions that require a highperformance ASIC with a high-speed (access time 20ns) and large-capacity (l MBytes) SRAM cache. The MCM approach is quite effective in increasing memory access speed because it realizes high-density packaging. The MCM-D module is mounted on an ATM line interface circuit, and realizes 150 Mbit/s throughput ATM-layer functions (header conversion and on-line monitoring) in an ATM switching system. In addition, advanced ATM switching system hardware technologies with sub-module structure are also described. The MCM-D module is one of the sub-modules of the system. This MCM technology and sub-module technology can be applied to advanced ATM switching systems.

This paper describes an advanced MCM-D micro-processor module and its high-performance cooling technologies for an ATM-WAN (Wide-Area Network) switching system. The MCM-D module is fabricated on 2 Si-substrates using the stacking RAM technique to reduce module size. The MCM has 4-layer Si substrates, a micro-processor LSI, 4 ASIC-LSIs, 12 high-speed SRAMs, an FPGA and bus-driver ICs. By using the stacking RAM technique, MCM-D module size was reduced to 65 mm×85 mm. This is 14% of that (200 mm×200 mm) of assembly area of a conventional circuit using conventional packaging technologies. The MCM-D module was mounted on an ATM line interface circuit board, and realized 25 MHz micro-processor functions with high-speed (access time 25 ns) and large-capacity (4 MBytes) SRAM cache and ATM line interface circuit functions in an ATM-WAN switching system. The line interface circuit board mounted the MCM-D module has high-performance cooling architecture without fin-structure. The MCM-D module is mounted on a sub-board and has thermal contact to the main board through a rubber with low thermal resistance. By using this high-performance cooling architecture, the MCM-D micro-processor module and the ATM line interface circuit board operate under conventional forced air cooling condition without fin-structure. This MCM technology and high-performance cooling technology can be applied to ATM-WAN switching systems and future B-ISDN ATM switching systems.

This paper proposes a multiple QoS control scheme that combines the head-of-line priority (HOLP) discipline with equivalent-window connection admission control (CAC). The proposed scheme can support the different cell loss ratios of both delay-sensitive traffic in high-priority buffers and delay-tolerant traffic in low-priority buffers. The CAC scheme extends a measurement-based CAC algorithm for a single buffer to the low-priority buffer with the HOLP discipline to provide the cell loss ratio objective. We introduce an equivalent window for monitoring low-priority cell streams. The equivalent window size equals the period within which the number of times the low-priority buffer is scanned to read cells is constant. Thus the equivalent window size varies with the high-priority queueing state. Numerical results indicate that the proposed QoS control scheme using the equivalent-window CAC can utilize network resources more effectively than the conventional control scheme which is Virtual Path (VP) separation for different cell loss requirement services. In addition, it is confirmed that the proposed scheme provides conservative admissible loads. Thus, this proposed scheme can achieve large statistical gains while providing both high-priority and low-priority cell loss ratio objectives. The proposed scheme will be very useful for cost-effective multimedia services that have different QoS requirements.

This paper proposes a high-speed connection admission control scheme, named PERB CAC (CAC based on Prior Estimation for Residual Bandwidth). This scheme estimates the residual bandwidth in advance by generating a series of virtual requests for connection. When an actual connection request occurs, PERB CAC can instantaneously judge if the required bandwidth is larger than the estimated residual bandwidth, so the connection set-up time can be greatly reduced. Therefore, PERB CAC can realize high-speed connection set-up.

This paper proposes a high-speed input and output buffering ATM switch, named Tandem-Crosspoint (TDXP) switch. The TDXP switch consists of multiple crossbar switch planes. These switch planes are connected in tandem at every crosspoint. Even if a cell can not be transmitted to an output port on the first plane, it has a chance to be transmitted on the next plane. Cell transmission is executed on each switch plane in a pipeline manner. Therefore, more than one cell can be transmitted to the same output port within one cell time slot, although the internal line speed of each switch is equal to the input /output line speed. The TDXP switch architecture has several advantages in implementation. First, the TDXP switch does not increase the internal line speed in eliminating Head-Of-Line (HOL) blocking. Second, since the TDXP switch employs a simple cell reading algorithm at the input buffer in order to retain the cell sequence, the TDXP switch does not require to rebuild the cell sequences at output buffers using time stamps, as is required by a parallel switch. These merits make implementing the high-speed ATM switch easy. Numerical results show that the TDXP switch can eliminate the HOL blocking effectively and achieve high throughput both for unicasting and multicasting traffic. This switch architecture is expected to enable the development of high-speed ATM switching systems that can realize over 1 Tb/s throughput in a cost-effective way.

A plastic chip-scale package (CSP) smaller than conventional ones has been developed and applied to ATM switching systems. It uses a low-cost glass-epoxy substrate. Because glass epoxy is widely used in the printed circuit boards (PCBs) of ATM switching systems, its use in the CSPs mounted on a PCB reduces the difference in thermal expansion between the PCB and CSPs, thus lengthening CSP life. The power plane, ground plane, and thermal vias of the CSP are designed to offset the increased thermal resistance due to the CSP's smaller size. Simulation showed a thermal resistance for this CSP with copper layers and thermal vias of as much as 22% less than that of one with no copper layers or thermal vias. A six-layer test board mounting four CSPs was used to simulate a sub-board for ATM switching systems. The thermal resistance of the two CSPs located downstream was about 10% higher than that of the two located upstream. Two CSPs were developed for two types of application-specific ICs: a bus interface controller (BIC) and a peripheral interface circuit (PIC). Both CSPs were 18 mm square with a 0.8-mm outer solder-ball pitch and 256 outer balls. These CSPs occupied areas about 87% and 68% smaller than those of a conventional pin grid array (PGA) and quad flat package (QFP), respectively. The junction temperature of both CSPs satisfied the thermal condition. These high-performance CSPs are thus attractive for use in ATM switching systems.

This paper describes newly developed advanced ATM switching system hardware structures based on MCM-D micro-processor modules. The Si-Substrate MCM-D technology which integrates micro-processor, interface control and peripheral control custom VLSIs, high-speed S-RAMs, and FPGAs (Field Programmable Gate Arrays) is employed. An MCM-D micro-processor module is realized by combining a Motorola 68030, high-performance ASICs, and high-speed S-RAM caches. This is made possible by high density packaging and high-speed 4M-byte with parity cache using 25 ns access to 4-Mbit of S-RAM memory. The MCM employs 12 S-RAMs, possible with the stacked RAM technique, to reduce the module size by 7/8 compared to conventional surface mounting modules. This micro-processor module technology and MCM technology will advance the development of practical B-ISDN ATM switching systems.

A new connection admission control method based on actual virtual path traffic measurements is proposed to achieve high bandwidth efficiency for various types of traffic. The proposed method is based on the measurement of instantaneous virtual path utilization, which is defined as the total cell rate of the active virtual channels normalized by the virtual path capacity. A low-pass filter is used to determine the instantaneous virtual path utilization from crude measurements. A smoothing coefficient formula is derived as a function of peak rate of the virtual channel. The residual bandwidth is derived from the maximum instantaneous utilization observed during a monitoring period. Simulation shows that the proposed method achieves statistical multiplexing gains of up to 80% of the limit possible with optimum control for similar traffic sources. It can be implemented with very simple hardware. The admission decision is simple: the requested bandwidth is compared with the residual bandwidth. This method is therefore well suited for practical asynchronous transfer mode switching systems. © 1998 IEEE.

This paper proposes a high-speed connection admission control scheme, named PERB CAC (CAC based on Prior Estimation for Residual Bandwidth). This scheme estimates the residual bandwidth in advance by generating a series of virtual requests for connection. When an actual connection request occurs, PERB CAC can instantaneously judge if the required bandwidth is larger than the estimated residual bandwidth, so the connection set-up time can be greatly reduced. Therefore, PERB CAC can realize high-speed connection set-up.

In the first stage of ATM switching system development, the specifications are sometimes changed in order to match revisions in ITU standards. Fatal problems due to specification changes and unexpected bugs force ASIC redesign and subsequent debugging is seriously restricted. These situations demand the introduction of new hardware design methodologies. This paper proposes a flexible hardware design methodology, based on a novel real-time emulation technique, suitable for large-scale high-speed communication switching systems. The emulation technique offers desirable system performance without Application Specific Integrated Circuit (ASIC) fabrication by using commercial Field Programmable Gate Arrays (FPGAs) along with many simply-structured high-speed interconnect switch devices for multiple FPGA connection. This technique suits line interface units (LUs) that have ASICs operating at about 20 MHz; each LU employs an LU board and emulation boards, both of which have hierarchical structures with sub-boards. The emulation boards are indispensable for realizing prototype systems rapidly and dealing with specification changes. Different types of LUs can be realized by mounting different sub-boards to the common LU board. Each emulation board is attached to the LU board by the same connector used for LU sub-board mounting. Therefore, the proposed structure has the advantage of utilizing a common LU board for system emulation as well as permitting the development of practical systems. To suppress undesirable multiple FPGA partitioning, we propose the emulation board architecture that has two types of sub-boards, each of which carries a different type of FPGA. We produced some portions of the proposed LU and tested the nearly 20 MHz real-time emulation of a complicated ASIC designed to realize ATM cell header conversion functions. The results of multiple FPGA partitioning on the emulation board suggest that the proposed design methodology will yield economic systems that can be freely modified to overcome hardware bugs and comply with future ITU standards.

This paper proposes a new topological design method, named BXCQ, which optimizes logical network configuration while guaranteeing Quality-of-Service (QoS) requirements for each service class in an ATM network. The BXCQ method determines the optimum logical network topology associated with each service class so as to minimize network cost. In our previously proposed Full-Net architecture these different logical topologies can be suitably mapped at the same time on the same ATM physical network by using the Virtual Channel Handler (VCH) to create different logical interconnection networks. The BXCQ method allows us to clarify the relations between multimedia traffic characteristics and desirable logical network configurations in Full-Net. Evaluation results suggest that a service class that is bursty, delay tolerant, and cell loss sensitive with small demand should be supported by a loop-like topology. This study will be useful for designing flexible and cost-effective multimedia networks that can also adapt to not-yet-known services.

This article proposes active-ATM, a flexible, simple and cost-effective ATM-WAN architecture that can handle multiple user-customized ATM-layer protocols, such as ABR and ABT, by using a simple universal ATM transit network. The proposed active-ATM architecture enables the construction of flexible networks that can evolve easily. With active-ATM and the ATM multi-protocol emulation network architecture called ALPEN, it is easy to implement new ATM-layer protocols by using user-created programs called active-program capsules that modify only the edge nodes. Because these user-sent program capsules can be used to quickly customize the edge nodes, there is no waiting for standardization and implementation of new services. The ATM-layer protocols are emulated only at the edge nodes, making the transit network independent of customer ATM-layer protocols. The active-ATM edge node is based on the flexible programmable node architecture called PUN (programmable unified node). The PUN is a platform for user-programmable ATM-layer services; it is achieved by using programmable devices, such as FPGAs and DSPs. An prototype system has demonstrated the flexibility of the resulting ATM network. The active-ATM architecture is an efficient approach to implementing multimedia, multi-protocol ATM services in an ATM WAN.

A Tb/s WDM interconnection system has been developed that utilizes a newly developed pocket-size 10-Gb/s transmitter/receiver module and wide-channel-spacing arrayed waveguide filter (AWGF). This system has 622-Mb/s ATM cell formats and can be applied to a Tb/s ATM switching system. The developed system uses eight different wavelength 10-Gb/s multiple quantum well modulator (MQW) integrated DFB lasers and one 8×8 optical router AWGF with 525-GHz-channel spacing. High-speed response and stable performance over a wide temperature range have been confirmed.