Pia Naoko Sanda

Bio: Pia Naoko Sanda is an academic researcher from IBM. The author has contributed to research in topics: Integrated circuit & Microprocessor. The author has an hindex of 16, co-authored 40 publications receiving 858 citations.

Soft-error resilience of the IBM POWER6 processor

Abstract: The error detection and correction capability of the IBM POWER6™ processor enables high tolerance to single-event upsets. The soft-error resilience was tested with proton beam- and neutron beam-induced fault injection. Additionally, statistical fault injection was performed on a hardware-emulated POWER6 processor simulation model. The error resiliency is described in terms of the proportion of latch upset events that result in vanished errors, corrected errors, checkstops, and incorrect architected states.

Geometric autogeneration of "hard" phase-shift designs for VLSI

Abstract: A method implemented in a computer aided design (CAD) system automatically generates phase shifted mask designs for very large scale integrated (VLSI) chips from existing circuit design data. The system uses a series of basic geometric operations to design areas requiring phase assignment, resolve conflicting phase assignments, and eliminate unwanted phase edges. This process allows automatic generation of phase shift mask data from any circuit design that allows for phase shifting. Since the dimensional input for all geometric operations is directly linked to the design ground rules given to the circuit designers, any designable circuit layout can also be phase shifted with this algorithm. The autogeneration of phase shift patterns around an existing circuit design is broken down into four major tasks: 1. Define areas that need a phase assignment; 2. Make a first pass phase assignment unique to each critical feature and define "runs" of interrelated critical features; 3. Propagation phase assignment through the "runs"; and 4. Design trim features.

Statistical Fault Injection

Abstract: A method for statistical fault injection (SFI) into arbitrary latches within a full system hardware-emulated model is validated against particle-beam-accelerated SER testing for a modern microprocessor. As performed on the IBM POWER6 microprocessor, SFI is capable of distinguishing between error handling states associated with the injected bit flip. Methodologies to perform random and targeted fault injection are presented.

Fault-Tolerant Design of the IBM Power6 Microprocessor

Abstract: The IBM Power6 microprocessor extends the capabilities of the Power5, dramatically increasing its ability to recover from hard and soft errors without increasing system downtime. The Power6 adds new mainframe-like features for enhanced reliability, availability, and serviceability, including instruction retry and processor failover. Optimized for performance and power, the Power6 implements these RAS enhancements without compromising ultrahigh-frequency operation.

Architectural support for copy and tamper-resistant software

Abstract: Although there have been attempts to develop code transformations that yield tamper-resistant software, no reliable software-only methods are know. This paper studies the hardware implementation of a form of execute-only memory (XOM) that allows instructions stored in memory to be executed but not otherwise manipulated. To support XOM code we use a machine that supports internal compartments---a process in one compartment cannot read data from another compartment. All data that leaves the machine is encrypted, since we assume external memory is not secure. The design of this machine poses some interesting trade-offs between security, efficiency, and flexibility. We explore some of the potential security issues as one pushes the machine to become more efficient and flexible. Although security carries a performance penalty, our analysis indicates that it is possible to create a normal multi-tasking machine where nearly all applications can be run in XOM mode. While a virtual XOM machine is possible, the underlying hardware needs to support a unique private key, private memory, and traps on cache misses. For efficient operation, hardware assist to provide fast symmetric ciphers is also required.

Phase shifting circuit manufacture method and apparatus

Abstract: A method and apparatus for creating a phase shifting mask and a structure mask for shrinking integrated circuit designs. One embodiment of the invention includes using a two mask process. The first mask is a phase shift mask and the second mask is a single phase structure mask. The phase shift mask primarily defines regions requiring phase shifting. The single phase structure mask primarily defines regions not requiring phase shifting. The single phase structure mask also prevents the erasure of the phase shifting regions and prevents the creation of undesirable artifact regions that would otherwise be created by the phase shift mask. Both masks are derived from a set of masks used in a larger minimum dimension process technology.

Phase shift masking for complex patterns with proximity adjustments

Abstract: Techniques are provided for extending the use of phase shift techniques to implementation of masks used for complex layouts in the layers of integrated circuits, beyond selected critical dimension features. The method includes identifying features for which phase shifting can be applied, automatically mapping the phase shifting regions for implementation of such features, resolving phase conflicts which might occur according to a given design rule, and application of assist features and proximity correction features. The method includes applying an adjustment to a phase shift mask pattern including a first and a second phase shift window, and a control chrome with a control width, and/or to a trim mask pattern having a trim shape with a trim width based upon one or both of a rule based correction and a model based correction to improve a match between a resulting exposure pattern and a target feature.

Method for verifying design rule checking software

Abstract: A method using a generate-and-verify computer program product to generate by repetitive passes a design rules checking computer program, wherein the design rules are described in a file called a runset. The design rules checking program is used for exhaustive testing of VLSI chips for compliance to the design rules of a given VLSI fabrication process. The runset is repeatedly iterated in loop fashion with respect to a testcase file containing groups of layout structures or shapes used for verifying the correctness of the runset. A general purpose shapes processing program creates an error shapes file for storing geometrical errors found in each said layout structure. Two additional shapes are used in the verification process: user boundary shapes for defining areas in which errors are not to be detected for a given design rule, and automated boundary shapes created to surround each said layout structure with a boundary that defines regions where error shapes can occur. An association table is created which is a compilation of the error shapes, user boundary shapes, and automated boundary shapes associated with each layout structure. The association table is processed to determine the correctness of the runset. The runset is modified to correct each valid error. The repetitive passes continue until a final runset is generated. This final runset becomes the input to design rules checking computer program product and customizes the program for a given VLSI fabrication process.

On-chip wiring design challenges for gigahertz operation

Abstract: This paper reviews the status of present day on-chip wiring design methodologies and understanding. A brief explanation is given of the fundamental transmission-line properties that should be considered for accurate prediction of crosstalk, common-mode noise and clock skew. The deficiencies of RC-circuit representation are highlighted and design guidelines are given for using modeling and simulation techniques that have been previously used for package interconnections. Such techniques are believed to teach designers how to make better use of available technologies and help them architect systems that operate with many-GHz clock rates.