A Single Chip Digital Signal Processor and Its Application to Real-Time Speech Analysis

A single chip high-performance digital signal processor (HSP) has been developed for speech, telecommunication, and other applications. The HSP uses 3 µm CMOS technology and its architecture features floating point arithmetic and pipeline structure. By adoption of floating point arithmetic, data covering a wide dynamic range (up to 32 bits) can be manipulated. The input clock frequency is 16 MHz, and the instruction cycle time is 250 ns. Efficient signal processing instructions and a large internal memory (program ROM: 512 words; data RAM: 200 words; data ROM: 128 words) make it possible to construct a compact speech analysis circuit by the LPC (PARCOR) method with two HSP's. This paper describes HSP architecture, LSI design, and a speech analysis application.     

A 400-MHz S/390 microprocessor

A microprocessor implementing IBM S/390 architecture operates in a 10+2 way system at frequencies up to 411 MHz (2.43 ns). The chip is fabricated in a 0.2-μm L_eff CMOS technology with five layers of metal and tungsten local interconnect. The chip size is 17.35 mm×17.30 mm with about 7.8 million transistors. The power supply is 2.5 V and measured power dissipation at 300 MHz is 37 W. The microprocessor features two instruction units (IUs), two fixed point units (FXUs), two floating point units (FPUs), a buffer control element (BCE) with a unified 64-KB L1 cache, and a register unit (RU). The microprocessor dispatches one instruction per cycle. The dual-instruction, fixed, and floating point units are used to check each other to increase reliability and not for improved performance. A phase-locked-loop (PLL) provides a processor clock that runs at 2× the system bus frequency. High-frequency operation was achieved through careful static circuit design and timing optimization, along with limited use of dynamic circuits for highly critical functions, and several different clocking/latching strategies for cycle time reduction. Timing-driven synthesis and placement of the control logic provided the maximum flexibility with minimum turnaround time. Extensive use of self-resetting CMOS (SRCMOS) circuits in the on-chip L1 cache provides a 2.0-ns access time and up to 500 MHz operation     

Design techniques for high-throughput BiCMOS self-timed SRAMs

Design techniques for a high-throughput BiCMOS self-timed SRAM are described. A new BiCMOS read circuit using a pipelined read architecture and a BiCMOS complementary clocked driver (BCCD) are proposed to reduce the operating cycle time. A 8192×9-b dual-port self-timed SRAM designed using the proposed techniques achieved a clock cycle time of 3.0 ns, that is, a 333-MHz operating frequency, by SPICE simulation on model parameters for 0.8-μm BiCMOS technology. A high-speed built-in self-test (BIST) circuit was studied and designed for the 3.0-ns cycle SRAM. It is confirmed that the BIST circuit allows the 3.0-ns cycle SRAM to test at its maximum operating frequency     

A single-chip 16-bit 25-ns real-time video/image signal processor

A single-chip 16-b microprogrammable real-time video/image signal processor (VISP) has been developed for use in real-time motion picture encoding during low-bit-rate transmission for TV conference systems. In addition to stand-alone microprocessor functional units, the VISP integrates a high-speed variable seven-stage pipeline arithmetic circuit for video/image data processing and various controllers for easy I/O (input/output) and multiple-chip connections A 25-ns instruction cycle time is attained by using complementary reduced-swing CMOS logic circuits. The chip (14 mm×13.4 mm) was fabricated using a double-metal-layer 1.2-μm CMOS process technology and contains 220000 transistors     

A hardware accelerator for two-dimensional image analysis

This paper describes the architecture and operation of a new hardware accelerator called MultiRing for performing various geometrical operations on two-dimensional image space. This hardware architecture is shown to be applicable for design rule checking in VLSI layout and many image processing operations including noise suppression and contour extraction. It has both a fast execution speed and extremely high flexibility. Each row data stored in ring memory is processed in the corresponding processor in full parallelism. Each processor is simultaneously configured by the instruction decoder/controller to perform one of the 20 basic instructions each ring cycle, which gives MultiRing maximal flexibility in terms of design rule change or the instruction set enhancement. Correct functional behavior of MultiRing was confirmed by successfully running a software simulator having one-to-one structural correspondence to the MultiRing hardware.     

A 9-ns HIT-delay 32-kbyte cache macro for high-speed RISC

A 32-kB cache macro with an experimental reduced instruction set computer (RISC) is realized. A pipelined cache access to realize a cycle time shorter than the cache access time is proposed. A double-word-line architecture combines single-port cells, dual-port cells, and CAM cells into a memory array to improve silicon area efficiency. The cache macro exhibits 9-ns typical clock-to-HIT delay as a result of several circuit techniques, such as a section word-line selector, a dual transfer gate, and 1.0-μm CMOS technology. It supports multitask operation with logical addressing by a selective clear circuit. The RISC includes a double-word load/store instruction using a 64-b bus to fully utilize the on-chip cache macro. A test scheme allows measurement of the internal signal delay. The test device design is based on the unified design rules scalable through multigenerations of process technologies down to 0.8 μm     

一种电机FOC算法DSP系统设计及实现

本文设计了一种适用于电机矢量控制算法的数字信号处理系统的微架构定义,包括其指令集定义、存储器模型以及与主CPU的交互模式.该设计具有通过固定部分多操作数有效缩减指令编码长度提高代码密度以及后台执行多周期指令提高ALU并行效率的显著优点.文中给出了典型的FOC控制算法在DSP （Digital Signal Processor）指令集上实现的指令周期数,也给出了对应架构的电路实现情况,最终以ARM CORTEX-M0及几款主流DSP作为比较基线,通过实测实验数据证明了体系结构的高能效比,以较为有限的电路面积代价,极大提高了集成DSP的嵌入式系统的运行效率.     

The design for a Josephson micro-pipelined processor

A novel processor with micro-pipelined architecture is proposed for latch-type Josephson logic devices. The processor is segmented into several operating stages activated by a multi-phase power system. Independent register groups are allocated to each stage in order to support pipeline processing of several instruction streams. This architecture allows building of a fine pipeline pitch processor which is capable of MIMD processing. A 12-bit micro-pipelined Josephson processor, containing an ALU, a multiplier and 16 registers, is described. Driven by a 3-phase AC power system, it is able to process 4 instruction streams simultaneously. A pipeline pitch of 3.3 GHz is expected using conventional Josephson device technology. A 4-bit processor design for 12-bit data length is also discussed     

A 1.2-W, 2.16-GOPS/720-MFLOPS embedded superscalar microprocessorfor multimedia applications

We have designed a microprocessor that is based on a single instruction multiple data stream (SIMD) architecture. It features a two-way superscalar architecture for multimedia embedded systems that need to support especially MPEG2 video decoding/encoding and 3DCG image processing. This microprocessor meets all requirements of embedded systems, including (a) MPEG2 (MP@ML) decoding and graphic processing capabilities for three-dimensional images, (b) programming flexibility, and (c) low power consumption and low manufacturing cost. High performance was achieved by enhanced parallel processing capabilities while adopting a SIMD architecture and a two-way superscalar architecture. Programming flexibility was increased by providing 170 dedicated multimedia instructions. Low power consumption was achieved by utilizing advanced process technology and power-saving circuits. The processor supports a general-purpose RISC instruction set. This feature is important, as the processor will have to work as a controller of various target systems. The processor has been fabricated by 0.21-μm CMOS four-metal technology on a 9.84×10.12 mm die. It performs 2.16 GOPS/720 MFLOPS at an operating frequency of 180 MHz, with a power consumption of 1.2 W and a power supply of 1.8 V     

1.8-V 800-Mb/s/pin DDR2 and 2.5-V 400-Mb/s/pin DDR1 compatibly designed 1Gb SDRAM with dual-clock input-latch scheme and hybrid multi-oxide output buffer

This paper describes three circuit techniques for a DDR1/DDR2-compatible chip architecture designed for both high-speed and high-density DRAMs: 1) a dual-clock input-latch scheme, which reduces the excessive timing margin for random input commands by using a pair of latch circuits controlled by dual-phase one-shot clock signals, achieves a 0.9-ns reduction in cycle time from 3.05 to 2.15 ns; 2) a hybrid multi-oxide output buffer reduces the area penalty of the output buffer caused by compatible chip design from 1.35% to 0.3%; and 3) a quasi-shielded distributed data transfer scheme enables a 2.6-ns reduction in access time to 10.25 ns in both 2-b and 4-b prefetch operations. By using these techniques, we developed a 175.3-mm/sup 2/ 1-Gb SDRAM that operates as an 800-Mb/s/pin DDR2 or 400-Mb/s/pin DDR1.     

A 20-ns CMOS micro DSP core for video-signal processing

A programmable 8-b digital signal processor core with an instruction cycle time of 20 ns is developed. A 37.5-mm chip is fabricated by advanced 1.0-μm double-level-metal CMOS technology. This processor has a reconfigurable high-speed data path supporting several multiply/accumulate function, including 16-tap linear-phase transversal filtering, high-speed adaptive filtering, and eight-point discrete cosine transformation. To provide high-speed operation within the chip, a programmable phase-locked loop circuit is built on the chip. This circuit generates a high-speed clock, which is a multiple of the system clock fed from outside, and is synchronized to the system clock     

A 1.5-GHz 130-nm Itanium/sup /spl reg// 2 Processor with 6-MB on-die L3 cache

This 130-nm Itanium 2 processor implements the explicitly parallel instruction computing (EPIC) architecture and features an on-die 6-MB 24-way set-associative level-3 cache. The 374-mm/sup 2/ die contains 410 M transistors and is implemented in a dual-V/sub t/ process with six Cu interconnect layers and FSG dielectric. The processor runs at 1.5 GHz at 1.3 V and dissipates a maximum of 130 W. This paper reviews circuit design and package details, power delivery, the reliability, availability, and serviceability (RAS) features, design for test (DFT), and design for manufacturability (DFM) features, as well as an overview of the design and verification methodology. The fuse-based clock deskew circuit achieves 24-ps skew across the entire die, while the scan-based skew control further reduces it to 7 ps. The 128-bit front-side bus has a bandwidth of 6.4 GB/s and supports up to four processors on a single bus.     

An 80-MFLOPS (peak) 64-b microprocessor for parallel computer

An 80-MFLOPS (peak) 64-b microprocessor that employs superscalar architecture to execute two instructions simultaneously in one 25-ns cycle, including the combination of 64-b floating-point add and multiply instructions, is described. The processor implemented in a 0.8-μm CMOS technology contains 1300 K transistors. The processor also employs a RISC architecture and Harvard-style bus organization. The authors provide an overview of the processor, especially focusing on processor architecture, floating-point hardware, and performance     

A pixel-parallel image processor using logic pitch-matched todynamic memory

A pixel-parallel image processor provides the capability for desktop systems to perform low-level image processing tasks in real time. Compact logic units are pitch-matched to DRAM columns to form dense blocks of processing elements. The processing elements are interconnected to form a 64×64 array, with each processing element assigned to a single pixel. Operating with a 60-ns clock cycle in a complete system, fully functional devices dissipate 300 mW. Using the devices, low-level image processing tasks have been performed in real time with input images provided at rates exceeding 30 frames/s     

1 /spl mu/m MOSFET VLSI technology. III. Logic circuit design methodology and applications

For pt. II see ibid., vol.SC14, no.2, p.247 (1979). Logic circuits were designed and fabricated in a 1 /spl mu/m silicon-gate MOSFET technology. First, conventional random logic chip images using the largely one-dimensional `Weinberger' layout are examined. The image is able to provide chips with an average circuit delay of 3 ns at the 8000 circuit level of integration. Second, two forms of PLA and PLA-based macros are discussed. A dynamic PLA, used in a microprocessor cross section and including 105 product terms, which achieves a 56 ns cycle time is described. A static PLA, designed for 21-ns delay and achieving measured delays from 13 to 21 ns, is also described. Extensions, particularly into low-temperature operation, are discussed.     

A general-purpose processor-per-pixel analog SIMD vision chip

A smart-sensor VLSI circuit suitable for focal-plane low-level image processing applications is presented. The architecture of the device is based on a fine-grain software-programmable SIMD processor array. Processing elements, integrated within each pixel of the imager, are implemented utilising a switched-current analog microprocessor concept. This allows the achievement of real-time image processing speeds with high efficiency in terms of silicon area and power dissipation. The prototype 21 /spl times/ 21 vision chip is fabricated in a 0.6 /spl mu/m CMOS technology and achieves a cell size of 98.6 /spl mu/m /spl times/ 98.6 /spl mu/m. It executes over 1.1 giga instructions per second (GIPS) while dissipating under 40 mW of power. The architecture, circuit design and experimental results are presented in this paper.     

An experimental multiplier circuit based on superconducting Josephson devices

This paper describes the design, testing, and operation of a 4-bit multiplier circuit based on Josephson tunneling logic (JTL) gates. The algorithm adopted was that of a simple serial 4-bit multiplier consisting of a 4-bit adder with ripple carry, together with a four phase, 8-bit accumulator shift register. The circuit, fabricated using a 25-/spl mu/m minimum linewidth technology, operated with a minimum cycle time of 6.67 ns (a limit imposed by the external test equipment) giving a 4-bit multiplication time of 27 ns with an average power dissipation of 35 /spl mu/W per logic gate. With better external pulse generators, or internal Josephson junction generators, the present circuit has been simulated to operate with a 3.0-ns cycle giving a 4-bit multiplication time of 12 ns.     

A CAM-based keyword match processor architecture

This paper demonstrates a keyword match processor capable of performing fast dictionary search with approximate match capability. Using a content addressable memory with processor element cells, the processor can process arbitrary sized keywords and match input text streams in a single clock cycle. We present an architecture that allows priority detection of multiple keyword matches on single input strings. The processor is capable of determining approximate match and providing distance information as well. A 64-word design has been developed using 19,000 transistors and it could be expanded to larger sizes easily. Using a modest 0.5 μm process, we are achieving cycle times of 10 ns and the design will scale to smaller feature sizes.     

A 22-ns 1-Mbit CMOS high-speed DRAM with address multiplexing

Describes a 1-Mbit high-speed DRAM (HSDRAM), which has a nominal random access time of less than 27 ns and a column access time of 12 ns with address multiplexing. A double-polysilicon double-metal CMOS technology having PMOS arrays inside n-wells was developed with an average 1.3- mu m feature size. The chip has also been fabricated in a 0.9*shrunken version with an area of 67 mm/sup 2/, showing a 22-ns access time. The chip power consumption is lower than 500 mW at 60-ns cycle time. This HSDRAM, which provides SRAM-like speed while retaining DRAM-like density, allows DRAMs to be used in a broad new range of applications.<>     

Radix-2 FFT butterfly processor using distributed arithmetic

A parallel-data VLSI architecture for computation of the fast Fourier transform (FFT) is described. The processor is based on a computationally efficient vector rotate algorithm. Use of a 2-dimensional pipeline configuration allows a radix-2 butterfly operation to be performed once every system clock cycle (250 ns) to generate real or imaginary transform components. The architecture is considered to be a computationally efficient VLSI approach for high-bandwidth computation of the FFT. The design and performance of an 8-bit FFT butterfly processor are described.