In this paper, we present an efficient technique for finding the mean and variance of the full-chip leakage of a candidate design, while considering logic structures and both die-to-die and within-die (WID) process variations, and taking into account the spatial correlation due to WID variations. Our model uses a ldquorandom-gaterdquo concept to capture high-level characteristics of a candidate chip design, which are sufficient to determine its leakage. These high-level characteristics include information about the process, the standard cell library, and expected design characteristics. We show empirically that, for large gate count, the set of all chip designs that share the same high-level characteristics have approximately the same leakage, with very small error. Therefore, our model can be used as either anearlyor alateestimator of leakage, with high accuracy. In its simplest form, we show that full-chip-leakage estimation reduces in finding the area under a scaled version of the WID channel length autocorrelation function, which can be done in constant time.

We present an efficient technique for finding the mean and variance of the full-chip leakage of a candidate design, while considering logic-structures and both die-to-die and within-die process variations, and taking into account the spatial correlation due to within-die variations. Our model uses a random concept to capture high-level characteristics of a candidate chip design, which are sufficient to determine its leakage. We show empirically that, for large gate count, the set of all chip designs that share the same high level characteristics have approximately the same leakage, with very small error. Therefore, our model can be used as either an early or a late estimator of leakage, with high accuracy. In its simplest form, we show that full-chip leakage estimation reduces to finding the area under a scaled version of the within-die channel length auto-correlation function, which can be done in constant time.

We present a new methodology which takes into consideration the effect of within-die (WID) process variations on a low-voltage parallel system. We show that in the presence of process variations one should use a higher supply voltage than would otherwise be predicted to minimize the power consumption of a parallel systems. Previous analyses, which ignored WID process variations, provide a lower nonoptimal supply voltage which can underestimate the energy/operation by 8.2. We also present a novel technique to limit the effect of temperature variations in a parallel system. As temperatures increases, the scheme reduces the power increase by 43% allowing the system to remain at it's optimal supply voltage across different temperatures. To further limit the effect of variations, and allow for a reduced power consumption, we analyzed the effects of clustering. It was shown that providing different voltages to each cluster can provide a further 10% reduction in energy/operation to a low-voltage parallel system, and that the savings by clustering increase as technology scales.

Modern integrated circuits require careful attention to the soft-error rate (SER) resulting from bit upsets, which are normally caused by alpha particle or neutron hits. These events, also referred to as single-event upsets (SEUs), will become more problematic in future technologies. This paper presents a ternary content-addressable memory (CAM) design with high immunity to SEU. Conventionally, error-correcting codes (ECC) have been used in SRAMs to address this issue, but these techniques are not immediately applicable to CAMs because they depend on processing the full contents of the memory word outside the array, which is not possible in a normal CAM access. We propose a family of TCAM cells that reduce the SER at the cost of some area increase. An SER reduction of up to 40% can be obtained with a 18% increase of area; another design reduces the SER by 16% with only a 5% increase in area.

Process induced threshold voltage variations bring about fluctuations in circuit delay, that affect the FPGA timing yield. We propose an adaptive FPGA architecture that compensates for these fluctuations. The architecture includes an additional characterizer circuit that classifies logic and routing blocks on each die according to their performance. Based on this classification, the architecture adaptively body-biases these resources by either speeding up the slow blocks or by slowing down the leaky ones. This procedure mitigates the effect of the variations and provides a better yield. We further diminish leakage by slowing down areas of the FPGA that have a positive slack. Overall, this architecture minimizes the timing variance of within-die and die-to-die Vth variations by up to 3.45X and reduces leakage power in the non-critical areas of the FPGA by 3X with no effect on frequency.

We present a new methodology which takes into consideration the effect of Within-Die (WID) process variations on a low-voltage parallel system. We show that in the presence of process variations one should use a higher supply voltage than would otherwise be predicted to minimize the power consumption of a parallel systems. Previous analyses, which ignored WID process variations, provide a lower non-optimal supply voltage which can underestimate the energy/ operation by 8.2X. We also present a novel technique to limit the effect of temperature variations in a parallel system. As temperatures increases, the scheme reduces the power increase by 43% allowing the system to remain at it's optimal supply voltage across different temperatures.

In this paper, we make the case for building high-performance asymmetric-cell caches (ACCs) that employ recently-proposed asymmetric SRAMs to reduce leakage proportionally to the number of resident zero bits. Because ACCs target memory value content (independent of cell activity and access patterns), they complement prior proposals for reducing cache leakage that target memory access characteristics. Through detailed simulation and leakage estimation using a commercial 0.13-/spl mu/m CMOS process model, we show that: 1) on average 75% of resident data cache bits and 64% of resident instruction cache bits are zero; 2) while prior research carefully evaluated the fraction of accessed zero bytes, we show that a high fraction of accessed zero bytes is neither a necessary nor a sufficient condition for a high fraction of resident zero bits; 3) the zero-bit program behavior persists even when we restrict our attention to live data, thereby complementing prior leakage-saving techniques that target inactive cells; and 4) ACCs can reduce leakage on the average by 4.3/spl times/ compared to a conventional data cache without any performance loss, and by 9/spl times/ at the cost of a 5% increase in overall cache access latency.

Current high-performance applications are typically implemented on large-scale general-purpose distributed or multiprocessing systems often based on commodity microprocessors. Field-Programmable Gate Arrays (FPGAs) have now reached a level of sophistication that they too could be used for such applications. In this paper we explore the feasibility of using FPGAs to implement large-scale application-specific computations by way of a case study that implements a novel molecular dynamics system. The system has been designed such that it is scalable and parallelizable. On the Transmogrifier 3 (TM3), the system performs calculations on an 8,192 particle system in 37 seconds at 26 MHz. This implementation shows that by scaling to more modern parts running at 100 MHz, a speedup of over 20 x can be achieved compared to a state-of-the-art microprocessor. This can also be achieved at less cost, using less power and taking less space than a standard microprocessor-based system, while maintaining the computational precision required.

Current high-performance supercomputing applications are typically implemented on large-scale general-purpose distributed or multiprocessing systems often based on commodity microprocessors. FPGAs have now reached a level of sophistication that they too could be used for such applications. We explore the feasibility of using FPGAs to implement large-scale application-specific computations by way of a case study that implements a novel Molecular Dynamics system. The system has been designed such that it is scalable and parallelizable. On the Transmogrifier 3, the system performs calculations on an 8,192 particle system in 37 seconds at 26MHz. This implementation shows that by scaling to more modern parts running at 100MHz and using a better architecture, a speedup of over 20x can be achieved compared to a state-of-the-art microprocessor. This can also be achieved at less cost, using less power and taking less space than a standard microprocessor-based system, while maintaining the computational precision required.

We introduce a novel family of asymmetric dual-V/sub t/ static random access memory cell designs that reduce leakage power in caches while maintaining low access latency. Our designs exploit the strong bias toward zero at the bit level exhibited by the memory value stream of ordinary programs. Compared to conventional symmetric high-performance cells, our cells offer significant leakage reduction in the zero state and, in some cases, also in the one state, albeit to a lesser extent. A novel sense amplifier, in combination with dummy bitlines, allows for read times to be on par with conventional symmetric cells. With one cell design, leakage is reduced by 7/spl times/ (in the zero state) with no performance degradation, but with a stability degradation of 6%. Another cell design reduces leakage by 2/spl times/ (in the zero state) with no performance or stability loss. An alternative cell design reduces leakage by 58/spl times/ (in the zero state) with a performance degradation of 1% and an area increase of 2.4% and no stability degradation.

We introduce a novel family of asymmetric dual-Vt SRAM cell designs that reduce leakage power in caches while maintaining low access latency. Our designs exploit the strong bias towards zero at the bit level exhibited by the memory value stream of ordinary programs. Compared to conventional symmetric high-performance cells, our cells offer significant leakage reduction in the zero state and in some cases also in the one state albeit to a lesser extend. A novel sense-amplifier, in coordination with dummy bitlines, allows for read times to be on par with conventional symmetric cells. With one cell design, leakage is reduced by 7X (in the zero state) with no performance degradation. An alternative cell design reduces leakage by 40X (in the zero state) with a performance degradation of 5%.