Susumu Narita

An 18-/spl mu/A standby current 1.8-V, 200-MHz microprocessor with self-substrate-biased data-retention mode

A 1.8 V 200 MHz low-subthreshold-leakage-current microprocessor is fabricated in a 0.2 /spl mu/m CMOS technology. It uses a switched substrate-impedance scheme to bias substrates while maintaining 200 MHz operating speed. It also offers a battery backup capability in a self substrate-biased data retention mode, in which it consumes only 17.8 /spl mu/A operating off a 1.0 V supply.

The Gmicro/500 superscalar microprocessor with branch buffers

The Gmicro/500, which features a RISC-like dual-pipeline structure for high-speed execution of basic instructions and represents a significant advance for the TRON architecture, is presented. Upwardly-object-compatible with earlier members of the Gmicro series, this microprocessor uses resident dedicated branch buffers to greatly enhance branch instruction execution speed. Its microprograms simultaneously use dual execution blocks to execute high-level language instructions effectively. Fabricated with a 0.6- mu m CMOS technology on a 10.9-mm*16-mm die, the chip operates at 50/66 MHz and achieves a processing rate of 100/132 MIPS.<<ETX>>

An access-sequence control scheme to enhance random-access performance 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 DRAMs. 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 200 MHz 1.2 W 1.4 GFLOPS microprocessor with graphic operation unit

This 200 MHz CMOS 2-issue superscalar microprocessor is redesigned with a 0.25 /spl mu/m 5-metal-layers CMOS process (L/sub eff/=0.20 /spl mu/m). In this chip 3.2M transistors are implemented in a 7.6/spl times/7.6 mm/sup 2/ die. This chip for low-cost graphic, embedded applications achieves 1.4 GFLOPS at 200 MHz with low-power consumption. This chip integrates CPU, FPU, 8 kB direct-mapped instruction cache (IC), 16 kB direct-mapped data cache (DC), MMU (64-entry unified TLB and 4-entry ITLB), bus interface logic, and six peripherals which are DMAC, timer unit (TMU), real time clock (RTC), serial comm. interface (SCI), interrupt controller (INTC), and emulation/debug unit (EMU). The bus interface provides glueless connections to SRAM, DRAM, SDRAM, burst-ROM, and PCMCIA, bus operation includes 8-, 16-, 32-, and 64b bus widths.

Design methodology for GMICRO/500 TRON microprocessor

Describes the design methodology used for the architecture of the GMICRO/500 TRON CISC superscalar microprocessor. Its minimum performance goal is 50 MHz, 100 VAX-MIPS at 5 V. This severe goal and the CISC superscalar architecture make the design time long and require a lot of manpower and computer resources. The C language and Unix environment are used to reduce the cost of the logic simulation. Synopsis and GDT are used to accelerate the logic design and the cell/macro design. A supercomputer is used to shorten the gate-level simulation time. The total design manpower is under 603 man-months.<<ETX>>

Design methodology of a 200 MHz superscalar macroprocessor: SH-4

A new design methodology focusing on high speed operation and short design time is described for the SH-4 200 MHz superscalar microprocessor. Random test generation, logic emulation, and formal verification are applied to logic verification for shortening design time. Delay budgeting, forward/back annotation, and clock design are key features for timing driven design.

A PA-RISC microprocessor PA/50L for low-cost systems

The PA/50L is a low-cost, low-power microprocessor from Hitachi Ltd. that is fully compatible with the PA-RISC architecture 1.1, third edition. This microprocessor achieves 55 VAX MIPS (Dhrystone 1.1), 10.6 MFLOPS (LINPACK inner loop) and 1.3 W at 33 MHz. In order to achieve high performance with no external cache, a non-blocking cache and a data prefetch instruction are provided. This paper gives an overview of the microprocessor and describes its capabilities.<<ETX>>