This paper presents experimental measurements of the differences between a 90-nm CMOS field programmable gate array (FPGA) and 90-nm CMOS standard-cell application-specific integrated circuits (ASICs) in terms of logic density, circuit speed, and power consumption for core logic. We are motivated to make these measurements to enable system designers to make better informed choices between these two media and to give insight to FPGA makers on the deficiencies to attack and, thereby, improve FPGAs. We describe the methodology by which the measurements were obtained and show that, for circuits containing only look-up table-based logic and flip-flops, the ratio of silicon area required to implement them in FPGAs and ASICs is on average 35. Modern FPGAs also contain "hard" blocks such as multiplier/accumulators and block memories. We find that these blocks reduce this average area gap significantly to as little as 18 for our benchmarks, and we estimate that extensive use of these hard blocks could potentially lower the gap to below five. The ratio of critical-path delay, from FPGA to ASIC, is roughly three to four with less influence from block memory and hard multipliers. The dynamic power consumption ratio is approximately 14 times and, with hard blocks, this gap generally becomes smaller

Measuring the Gap Between FPGAs and ASICs

This paper presents experimental measurements of the differences between a 90nm CMOS FPGA and 90nm CMOS Standard Cell ASICs in terms of logic density, circuit speed and power consumption. We are motivated to make these measurements to enable system designers to make better informed hoices between these two media and to give insight to FPGA makers on the deficiencies to attack and thereby improve FPGAs. In the paper, we describe the methodology by which the measurements were obtained and we show that, for circuits containing only combinational logic and flip-flops, the ratio of silicon area required to implement them in FPGAs and ASICs is on average 40. Modern FPGAs also contain "hard" blocks such as multiplier/accumulators and block memories and we find that these blocks reduce this average area gap significantly to as little as 21. The ratio of critical path delay, from FPGA to ASIC, is roughly 3 to 4, with less influence from block memory and hard multipliers. The dynamic power onsumption ratio is approximately 12 times and, with hard blocks, this gap generally becomes smaller.

/pdf/measuring-the-gap-between-fpgas-and-asics-28jbm34599.pdf

Measuring the gap between FPGAs and ASICs

Field-Programmable Gate Arrays (FPGAs) have become one of the key digital circuit implementation media over the last decade. A crucial part of their creation lies in their architecture, which governs the nature of their programmable logic functionality and their programmable interconnect. FPGA architecture has a dramatic effect on the quality of the final device's speed performance, area efficiency, and power consumption. This survey reviews the historical development of programmable logic devices, the fundamental programming technologies that the programmability is built on, and then describes the basic understandings gleaned from research on architectures. We include a survey of the key elements of modern commercial FPGA architecture, and look toward future trends in the field.

/pdf/fpga-architecture-survey-and-challenges-n7zq0kh5x3.pdf

FPGA Architecture: Survey and Challenges

While advances in semiconductor technologies have pushed achievable scale and performance to phenomenal limits for ICs, nanoscale physical realities dictate IC production based on what we can afford. We believe that IC design and manufacturing can be made more affordable, and reliable, by removing some design and implementation flexibility and enforcing new forms of design regularity. This paper discusses some of the trade-offs to consider for determination of how much regularity a particular IC or application can afford. A Via Patterned Gate Array is proposed as one such example that trades performance for cost by way of new forms of design regularity.

/pdf/exploring-regular-fabrics-to-optimize-the-performance-cost-2nsg76zepk.pdf

Exploring regular fabrics to optimize the performance-cost trade-off

A semiconductor device includes a substrate and a number of diffusion regions defined within the substrate. The diffusion regions are separated from each other by a non-active region of the substrate. The semiconductor device includes a number of linear gate electrode tracks defined to extend over the substrate in a single common direction. Each linear gate electrode track is defined by one or more linear gate electrode segments. Each linear gate electrode track that extends over both a diffusion region and a non-active region of the substrate is defined to minimize a separation distance between ends of adjacent linear gate electrode segments within the linear gate electrode track, while ensuring adequate electrical isolation between the adjacent linear gate electrode segments.

Dynamic array architecture

This paper introduces a new hybrid ASIC/FPGA chip architecture that is being developed in collaboration between IBM and Xilinx, and highlights some of the design challenges this offers for designers and CAD developers. We review recent data from both the ASIC and FPGA industries, including technology features, and trends in usage and costs. This background data indicates that there are advantages to using standard ASICs and FPGAs for many applications, but technical and financial considerations are increasingly driving the need for a hybrid ASIC/FPGA architecture at specific volume tiers and technology nodes. As we describe the hybrid chip architecture ,we point out evolving tool and methodology issues that will need to be addressed to enable customers to effectively design hybrid ASIC/FPGAs. The discussion highlights specific automation issues in the areas of logic partitioning, logic simulation, verification, timing, layout and test.

/pdf/a-hybrid-asic-and-fpga-architecture-2m8yin05pw.pdf

A hybrid ASIC and FPGA architecture

Video subsystem power savings are achieved by shutting off power to unused subcircuits during blanking. Digital circuitry within the video subsystem not used during blanking is shut-down by turning off the clock thereto. Analog circuitry within a digital to analog converter is shut-down by turning off the constant current reference thereto. A functional unit containing digital circuitry within a serializer palette digital to analog converter (SPDAC) is shut-down by turning off the clock thereto during system operation in a mode where the functional unit is not utilized. A computer system having a monochrome display saves power by shutting off DAC digital circuitry clocks and DAC analog circuitry constant current references of all DACs but one. A portable computer with a liquid crystal display (LCD), a SPDAC for driving an external display and a LCD controller, saves power by shutting down video subsystem functional units and analog DAC circuitry not used for driving the LCD. Digital circuitry within the LCD controller is shut-down when an external display is being driven. In a portable computer operating in a SUSPEND state, video subsystem functional units are shut-down.

Method and apparatus for power management in video subsystems

Disclosed is an integrated circuit chip structure that has a chip level test access port (TAP) controller and a plurality of embedded TAPs connected to the chip level TAP. Because the embedded TAPs have lengths that differ from the chip level TAP IR, and the embedded TAP IR lengths may differ from each, the chip level TAP includes a flexible length instruction register architecture adapted to accommodate the different length instruction registers of the embedded TAPs while using a constant length chip level instruction register definition for all IR accesses through the chip level TAP. Further, the invention includes selection logic adapted to actively connect only a single embedded TAP to the chip level TAP at a time.

Access method for embedded jtag tap controller instruction registers

A system and method is provided to accurately model bidirectional wire I/O using hardware description language (HDL). The preferred model and method uses an HDL model that provides two parallel paths between ports of the bidirectional wire I/O. During simulation, the ports are monitored for activity. When an event is detected on either port, the model checks both ports to see if they are different values. If the ports are different values, one of the two parallel paths is enabled and the other disabled. For example, the model enables the path in which the new signal has appeared and thus passes the signal to the other port. The preferred model allows for the use of HDL elements that support full timing annotation. The preferred embodiment also removes the possibility of high impedance transition error that can result from false transitions to a high impedance state.

Bidirectional wire I/O model and method for device simulation

Novel structures and testing methods for the FPGAs (Field-Programmable Gate Arrays) embedded in an ASIC (Application-Specific Integrated Circuits). Basically, a shift/interface system is coupled between the FPGAs and the ASIC. During normal operation, the shift/interface system electrically couples the FPGAs to the ASIC. During the testing of the FPGAs, the shift/interface system scans in FPGA test data in series, then feeds the FPGA test data to the FPGAs, then receives FPGA response data from the FPGAs, and then scans out the FPGA response data in series. During the testing of the ASIC, the shift/interface system scans in ASIC test data in series, then feeds the ASIC test data to the ASIC, then receives ASIC response data from the ASIC, and then scans out the ASIC response data in series.

Richard J. Grupp

Papers

A hybrid ASIC and FPGA architecture

Method and apparatus for power management in video subsystems

Access method for embedded jtag tap controller instruction registers

Bidirectional wire I/O model and method for device simulation

Mechanism to provide test access to third-party macro circuits embedded in an ASIC (application-specific integrated circuit)