Amit Sanghani

Design and implementation of a time-division multiplexing scan architecture using serializer and deserializer in GPU chips

We present the design and implementation details of a time-division demultiplexing/multiplexing based scan architecture using serializer/deserializer. This is one of the key DFT features implemented on NVIDIAs Fermi family GPU (Graphic Processing Unit) chips. We provide a comprehensive description on the architecture and specifications. We also depict a compact serializer/deserializer module design, test timing consideration, design rule and test pattern verification. Finally, we show silicon data collected from Fermi GPUs.

A clock-gating based capture power droop reduction methodology for at-speed scan testing

Excessive power dissipation caused by large amount of switching activities has been a major issue in scan-based testing. For large designs, the excessive switching activities during launch cycle can cause severe power droop, which cannot be recovered before capture cycle, rendering the at-speed scan testing more susceptible to the power droop. In this paper, we present a methodology to avoid power droop during scan capture without compromising at-speed test coverage. It is based on the use of a low area overhead hardware controller to control the clock gates. The methodology is ATPG (Automatic Test Pattern Generation)-independent, hence pattern generation time is not affected and pattern manipulation is not required. The effectiveness of this technique is demonstrated on several industrial designs.

A programmable method for low-power scan shift in SoC integrated circuits

We present a programmable method for shift-clock stagger assignment to reduce power supply noise during system-on-chip (SoC) testing. An SoC design is typically composed of several blocks and two neighboring blocks that share the same power rails should not be toggled at the same time during shift. Therefore, the proposed programmable method does not assign the same stagger value to neighboring blocks. The positions of all blocks are first analyzed and the shared boundary length between blocks is then calculated. Based on the position relationships between the blocks, a mathematical model is presented to derive optimal result for small-to-medium sized problems. For larger designs, a heuristic algorithm is proposed and evaluated. We present assignment results as well as power-analysis results and silicon data for industry designs to highlight the effectiveness of the proposed method.

Test method and scheme for low-power validation in modern SOC integrated circuits

Test Mode power can be 5X higher than functional power in GPUs, while the power grid is designed only for worst-case functional toggle. The large simultaneous switching noise induced on the power rails during at-speed capture testing is constrained by means of hardware solution. To determine the best low power mode for ATPG, we propose novel techniques to: estimate global peak current (di), determine local droop trend and validate and further optimize chosen power settings with exhaustive post-silicon power mode tuning. During Power Optimization (PO) phase, the measured clock frequency (fclk) and Vdroop are analyzed on every pattern and test coverage and pattern count are optimized for the production pattern set. We share correlation results and Power Supply Noise (PSN) distribution for the production pattern set on recent 28-nm GPUs.

Flexible scan interface architecture for complex SoCs

Non-standardized scan interface within and across system-on-chips (SoCs) limits test-data reuse for intellectual properties (IPs). To overcome this limitation, we present a flexible and dynamic scan interface architecture that enables reuse of test-data for a given IP across SoCs with different scan pin configurations. The dynamic nature of this architecture also enables variable shift frequencies across different IPs in a given SoC. The architecture decouples the scan pin requirements from the design cycle of the IPs. It also uses bidirectional scan pins to further reduce test cost by using as few as two pins.

Dynamic docking architecture for concurrent testing and peak power reduction

Interdependence of the clocking architecture across IPs and overall peak power consumption is a major bottleneck that prevents concurrent yet independent testing of an IP at a higher clock frequency. We use a dynamic clocking architecture that eliminates these dependencies and reduces peak shift power by using clock phase staggering at a granular level during system-on-chip (SoC) testing. A SoC design is typically composed of several Intellectual Property (IPs), some of which may be replicated. Generating a full set of test patterns targeting all IPs at the same time is computationally intensive and may be constrained by project schedule. Using this architecture, production test patterns are generated independently at the IP level and applied concurrently at the SoC level without exceeding the power budget of the chip during test. We present various aspects of the clocking architecture design along with simulation and silicon results to highlight the effectiveness of this architecture.

Methodology for fault grading high speed I/O interfaces used in complex Graphics Processing Unit

Graphics Processing Unit (GPU) requires I/O bandwidth of the order of Gbps which can be met by implementation of High Speed Serializer/Deserializer differential I/Os with clock embedded in data stream, traditionally tested using functional Built In Self Test (BIST). Implementation of these I/Os on complex graphics chip poses requirement for fault grading these I/Os. This paper presents the challenges involved in fault grading SerDes I/Os used in Nvidias GPU chips and proposes methodology for extracting fault coverage numbers using industry standard tools.