Modeling the effect of technology trends on the soft error rate of combinational logic
read more
Citations
Radiation-induced soft errors in advanced semiconductor technologies
A systematic methodology to compute the architectural vulnerability factors for a high-performance microprocessor
Zyzzyva: speculative byzantine fault tolerance
Outstanding Research Problems in NoC Design: System, Microarchitecture, and Circuit Perspectives
SWIFT: Software Implemented Fault Tolerance
References
The future of wires
The Alpha 21264 microprocessor
DIVA: a reliable substrate for deep submicron microarchitecture design
Transient fault detection via simultaneous multithreading
The microarchitecture of the Pentium 4 processor
Related Papers (5)
Frequently Asked Questions (19)
Q2. What are the future works in "Modeling the effect of technology trends on soft error rate of combinational logic" ?
The implication of this result is that further research is required into methods for protecting combinational logic from soft errors. The authors believe that techniques such as these combined with circuit and process innovations will be required to enable future construction of reliable high performance systems.
Q3. What is the effect of device scaling on the circuits?
Since the flux of particles is substantially greater for particles of lower energy, it follows that all circuits will experience higher soft error rates due to device scaling.
Q4. What is the conservative approximation of the logical masking effect?
Since the authors model a pipestage using a simple linear string of gates, the authors are actually modeling a minimal active path to the latch, which is the most conservative approximation of the logical masking effect.
Q5. How many transistors are allocated to SRAM cells and latches?
The allocation of memory element transistors to SRAM cells and latches depends on the number of latches required by the processor pipeline, which depends on pipeline depth.
Q6. Why do the authors use level sensitive latches in their model?
The authors use level sensitive latches in their pipeline model because they occupy less area than edge triggered flip-flops and so are more suitable for superpipelining.
Q7. What is the hspice simulation used to determine if a voltage pulse has?
When a voltage pulse reaches the input of a latch, the authors use an hspice simulation to determine if it has sufficient amplitude and duration to be captured by the latch.
Q8. What is the effect of device scaling on the SER of logic circuits?
Their study shows an increasing susceptibility to neutron-induced soft errors, particularly in logic circuits, due to device scaling and greater neutron flux at lower energies [27].
Q9. What is the methodology for estimating the soft error rate in combinational logic?
Their methodology for estimating the soft error rate in combinational logic considers the impact of CMOS device scaling and the microarchitectural trend toward increasing depth of processor pipelines.
Q10. How many gates can be placed in a single pipeline stage?
The number of gates in the chain is dependent on the degree of pipelining in the microarchitecture, which the authors characterize by the number of fan-out-of-4 inverter (FO4) gates that can be placed between two latches in a single pipeline stage.
Q11. What are the main reasons for this focus on memory elements?
Two key reasons for this focus on memory elements are: 1) the techniques for protecting memory elements are well understood and relatively inexpensive in terms of the extra circuitry required, and 2) caches take up a large part, and in some cases a majority, of the chip area in modern microprocessors.
Q12. How many stages are there in a processor pipeline?
The datapath of modern processors can be extremely complicated in nature, typically composed of 64 parallel bit lines and divided into 20 or more pipeline stages.
Q13. What is the effect of device scaling and superpipeling on combinational logic?
These effects all work to reduce the masking phenomena that currently provide combinational logic with a form of natural protection against soft errors.
Q14. What are the steps to calculate SER for a combinational logic circuit?
Given the feature size and degree of pipelining, the basic steps to compute SER for a combinational logic circuit are:1. Compute the contribution to SER for each gate in the pipe stage, and2.
Q15. What are the common mechanisms used to protect memory elements?
These mechanisms are typically focused on protecting memory elements, particularly caches, using error-correcting codes (ECC), parity, and other techniques.
Q16. What is the method used to determine if the pulse that reaches the latch input has enough?
The authors use the pulse-latching model to determine if the pulse that reaches the latch input has sufficient amplitude and duration to cause a soft error.
Q17. How many latches are allocated to each pipestage?
The authors allocate one latch for each pipestage, where the number of pipestages is given by Equation 4.pipestages logic transistors gates per pipestage transistors per gate(4)
Q18. How can the authors determine the probability that a pulse causes a soft error?
The authors can determine the probability that the pulse causes a soft error by computing the probability that a randomly placed interval of length overlaps a fixed interval of length within an overall interval of length .
Q19. What is the effect of the reduction in the soft error rate in combinational logic?
weconclude that current technology trends will lead to a substantially more rapid increase in the soft error rate in combinational logic than in storage elements.