As zero-knowledge proofs gain increasing adoption, the cryptography community has designed domain-specific languages (DSLs) that facilitate the construction of zero-knowledge proofs (ZKPs). Many of these DSLs, such as Circom, facilitate the construction of arithmetic circuits, which are essentially polynomial equations over a finite field. In particular, given a program in a zero-knowledge proof DSL, the compiler automatically produces the corresponding arithmetic circuit. However, a common and serious problem is that the generated circuit may be underconstrained, either due to a bug in the program or a bug in the compiler itself. Underconstrained circuits admit multiple witnesses for a given input, so a malicious party can generate bogus witnesses, thereby causing the verifier to accept a proof that it should not. Because of the increasing prevalence of such arithmetic circuits in blockchain applications, several million dollars worth of cryptocurrency have been stolen due to underconstrained arithmetic circuits. Motivated by this problem, we propose a new technique for finding ZKP bugs caused by underconstrained polynomial equations over finite fields. Our method performs semantic reasoning over the finite field equations generated by the compiler to prove whether or not each signal is uniquely determined by the input. Our proposed approach combines SMT solving with lightweight uniqueness inference to effectively reason about underconstrained circuits. We have implemented our proposed approach in a tool called QED 2 and evaluate it on 163 Circom circuits. Our evaluation shows that QED 2 can successfully solve 70% of these benchmarks, meaning that it either verifies the uniqueness of the output signals or finds a pair of witnesses that demonstrate non-uniqueness of the circuit. Furthermore, QED 2 has found 8 previously unknown vulnerabilities in widely-used circuits.

In this paper, we discuss the advantages and opportunities presented by high-speed (> 50 GHz) reconfigurable integrated circuits and how they may drive reconfigurable systems applications, such as software-defined radio, radar, and imaging. We propose silicon-germanium (SiGe) BiCMOS as an example technology that enables ultrafast reconfigurable systems and present several circuit designs based on SiGe heterojunction bipolar transistors (HBTs). We compare circuit designs between generations of IBM's SiGe process, including a recent 9HP process featuring devices with a cutoff frequency (fT) of 300 GHz. We describe an architecture for an 8-b 80-Gs/s analog-to-digital converter (ADC) and a 48 × 48 cell field programmable gate array (FPGA), which provide powerful solutions for useful functions, such as digital signal processing (DSP) and polyphase filtering. Other circuit concepts are described, including a voltage-controlled oscillator (VCO) with a tuning range of 26 GHz and a high-performance (80 Gb/s) crossbar switch, which provide utility in reconfigurable system applications. Measured results from fabricated implementations of these described systems are presented. We comment on future prospects of these systems and examine an emerging lateral bipolar device (fT1/4 825 GHz) having 100x less power consumption than conventional vertical HBTs.

Slow cache memory systems and low memory bandwidth present a major bottleneck in performance of modern microprocessors. 3-D integration of processor and memory subsystems provides a means to realize a wide data bus that could provide a high bandwidth and low latency on-chip cache. This paper presents a three-tier, 3-D 192-kB cache for a 3-D processor-memory stack. The chip is designed and fabricated in a 0.18 m fully depleted SOI CMOS process. An ultra wide data bus for connecting the 3-D cache with the microprocessor is implemented using dense vertical vias between the stacked wafers. The fabricated cache operates at 500 MHz and achieves up to 96 GB/s aggregate bandwidth at the output.

Three-dimensional chip (3-D) stacking technology provides a new approach to address the so-called memory wall problem. Memory processor chip stacking reduces this memory wall problem, permitting faster clock rates (with suitable processor logic) or permitting multicore access to shared memory using a large number of vertical vias between tiers in the stack, for ultrawide bit path transfer of data and address information to and from various levels of cache. Although a limited amount of parallel access is possible using conventional two-dimensional (2-D) chip memory-processor approaches, 3-D memory-processor stacking greatly extends this to much larger capacity memories. We evaluate high-clock-rate processors as well as shared memory processors with a large number of cores. Various architectural design options to reduce the impact of the memory wall on the processor performance are explored and validated through simulations. Certain architectural features can be implemented in a 3-D chip, such as an ultrawide, ultrashort vertical bus with low parasitic resistance and the elimination of conventional electrostatic discharge, and packaging parasitics required in multiple package 2-D solutions. The objective is to reduce the clocks per instruction figure of merit for high clock speeds in order to deliver significant performance levels. High-clock-rate processors can be designed with SiGe heterostructure bipolar transistors to obtain processors operating on the order of 16 or 32 GHz.

Forty years ago Gene Amdahl published a figure of merit for parallel computation, which proved extremely controversial. The controversy still rages today, although those that have looked closely at this figure of merit conclude that it is correct, but perhaps misinterpreted. In this paper we will look at a small variation on that law that suggests computer designers should take a closer look at two emerging technologies, SiGe HBT BiCMOS and 3D chip stacking. We may be overlooking a way to continue the clock race, and in so doing accomplish better parallelism.

A 7-12-Gb/s demultiplexer implemented with circuits for a high-speed field-programmable gate array (FPGA) is introduced in this paper. Since the first FPGA was released by Xilinx in 1985, FPGAs have become denser and more powerful. The first FPGA that operates in the microwave range was designed in 2000. Various methods, such as a new basic cell structure and multimode routing, are used to make that design faster and less power consuming. Sequential logic functions are analyzed and tested in this paper with a DEMUX implementation using these high-speed FPGA circuits. A chip measurement has shown that the FPGA can operate at a 12-GHz system clock when configured to perform sequential logic. A DEMUX that operates at 12 Gb/s is used here to demonstrate the potential for high-performance and low-power FPGA features.

High performance parallel programs are currently difficult to write and debug. One major source of difficulty is protecting concurrent accesses to shared data with an appropriate synchronization mechanism. Locks are the most common mechanism but they have a number of disadvantages, including possibly unnecessary serialization, and possible deadlock. Transactional memory is an alternative mechanism that makes parallel programming easier. With transactional memory, a transaction provides atomic and serializable operations on an arbitrary set of memory locations. When a transaction commits, all operations within the transaction become visible to other threads. When it aborts, all operations in the transaction are rolled back.Transactional memory can be implemented in either hardware or software. A straightforward hardware approach can have high performance, but imposes strict limits on the amount of data updated in each transaction. A software approach removes these limits, but incurs high overhead. We propose a novel hybrid hardware-software transactional memory scheme that approaches the performance of a hardware scheme when resources are not exhausted and gracefully falls back to a software scheme otherwise.

FPGAs have been a popular topic among electrical engineers for over a decade. Modern FPGAs are denser, faster and use less power compared to PLD and CPLD. This paper presents a high speed FPGA that operates in the gigahertz range. An improved reconfigurable circuit is described. State-of-the-art IBM SiGe BiCMOS technology is used to realize this high speed FPGA. A measurement on a fabricated chip proves that this FPGA is capable of operating at 11 GHz, a SONET OC-192 standard, for optical applications.

This paper describes the implementation of a large scale SiGe FPGA that serves as a high speed FPGA test platform. In the FPGA core, 20 x 20 building blocks (Basic Cells) are used to implement logic applications. This chip contains 106 devices including SiGe NPNs and MOSFETs. This chip is fabricating with the IBM SiGe 7HP process with cut off frequency of 120GHz. The target running frequency of this FPGA is 10GHz. Clock repeaters are added for improved clock distribution. A test circuit whose building block cell runs up to 10GHz is fabricated and measured by the same process. Future work and some potential applications of the SiGe FPGA are also described.

This paper describes the implementation of a scalable SiGe FPGA that serves as a high speed FPGA test platform. A new configurable block (Basic Cell) has been evolved from the Xilinx 6200 specification, and is designed to perform in the gigahertz range. Two chips, a 4:1 multiplexer and 1:4 demultiplexer, were designed using the IBM SiGe 7HP process. The two designs can process 10 Gbps data streams.

The low operating speed of current CMOS Field Programmable Gate Arrays (FPGAs), i.e., 10-220 MHz, has prevented their use in high-speed digital applications. With the advent of IBM Silicon Germanium (SiGe) 7HP technology, designers have been able to design FPGAs operating in the gigahertz range. This paper is going to elaborate on the implementation of a 4-bit ripple-carry full adder (FA) on the new SiGe FPGA with new architectures and a novel power management strategy. The 1-bit FA can be realized in three Configurable Logic Blocks (CLBs). Apart from these, the FA can operate in multiple modes: FAST, NON-CRITICAL, SLOW and OFF. The propagation delays of the 1-bit FA and 4-bit ripple-carry FA are 240 ps and 675 ps respectively in the FAST mode. All the simulation and layouts were done using Cadence 4.4.6 and IBM SiGe 7HP design kit version 1.1.1.0.

A high speed, low power FPGA design is presented in this paper. This gigahertz FPGA design has an improved XC6200 structure. Redundant multiplexers are eliminated from critical signal path to enhance the performance of the previous design. By balancing between the power consumption and performance, the simulated clock rate is from 5 GHz to 20 GHz and the power consumption is from 4 mW to 12 mW per single cell in the IBM 7HP SiGe HBT BiCMOS process.

The SCORE compute model uses fixed-size, virtual compute and memory pages connected by stream links to capture the definition ofa computation abstracted from the detailed size ofthe physical hardware. When the number of physical compute pages is smaller than the number of virtual compute pages in the abstract computation graph, the design is time-multiplexed onto the available physical hardware. A key component ofthis strategy is an automatic scheduler that selects the temporal sequencing ofvirtual resources onto the physical device. We describe a quasistatic scheduling strategy that retains the full semantic power of the dynamic SCORE flow graph while taking advantage ofstatic scheduling techniques at program load time to hoist most ofthe computational work out of the inner scheduling loops. This strategy reduces online scheduling work per reconfiguration epoch by an order of magnitude. In addition, a more global perspective available from offline-scheduling improves schedule quality, resulting in a net reduction oftotal execution time by 46–81%. 1.

The demand for high speed Field Programmable Gate Arrays (FPGAs) has been on a rise. These were never possible using CMOS as the basic device. People were able to achieve frequencies in the range of 70-250 MHz using CMOS. The availability of Silicon Germanium (SiGe) Heterojunction Bipolar Transistor (HBT) devices has opened the door for Gigahertz FPGAs. An FPGA with a speed of over 5 GHz was reported by B.S. Goda (2000) using SiGe 5HP technology. However in order to scale up FPGAs significantly, a serious power management scheme must be in place. Apart from this, architectural changes can be made to improve the speed and reduce the power. This paper elaborates on the architecture of the new SiGe FPGA and its advantages over the previous generation SiGe FPGAs. The entire Configuration Logic Block (CLB) has been implemented using seven Current Mode Logic (CML) trees. Apart from these, a novel power management scheme is implemented which allows the FPGA to operate at multiple modes: fast, non-critical, slow and off. The new FPGA can run in the fast mode when speed is critical or in the slow mode when power is the limiting issue. The CLB can run up to 5.96 GHz.

Generators, parameterized code which produces a digital design, have long been a staple of the VLSI community. In recent years, several field programmable gate array (FPGA) design tools have adopted generators, as it is a convenient way to specify reusable designs in a familiar programming environment. We have built a generator framework in Java as a basis for programming reconfigurable devices and as a tool to be embedded in larger development systems. In addition to the conventional benefits of generators, this powerful framework allows for partial evaluation, simulation, specialization, and easy inclusion of other automatic services. In order to verify the utility of this system, we have implemented several applications using this framework and compared them with implementations using schematic capture and HDL synthesis. Our system runs significantly faster and produces comparable or superior results when mapped to a target FPGA.

Database visualization is an area of growing importance as database systems become larger and more accessible. DataSplash is an easy-to-use, integrated environment for navigating, creating, and querying visual representations of data. We will demonstrate the three main components which make up the DataSplash environment: a navigation system, a direct-manipulation interface for creating and modifying visualizations, and a direct-manipulation visual query system.