会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 12. 发明申请
    • Adaptive execution method for multithreaded processor-based parallel system
    • 基于多线程处理器的并行系统的自适应执行方法
    • US20070130568A1
    • 2007-06-07
    • US11453288
    • 2006-06-15
    • Chang JungDae LimJae LeeSang Han
    • Chang JungDae LimJae LeeSang Han
    • G06F9/46
    • G06F8/456G06F9/5066G06F11/3404G06F2201/88
    • Provided is a parallel program execution method in which in order to reflect structural characteristics of a multithreaded processor-based parallel system, performance of the parallel loop is predicted while compiling or executing using a performance prediction model and then the parallel program is executed using an adaptive execution method. The method includes the steps of: generating as many threads as the number of physical processors of the parallel system in order to execute at least one parallel loop contained in the parallel program; by the generated threads, executing at least one single loop of each parallel loop; measuring an execution time, the number of executed instructions, and the number of cache misses for each parallel loop; determining an execution mode of each parallel loop by determining the number of threads used to execute each parallel loop based on the measured values; and allocating the threads to each physical processor according to the result of the determination to execute each parallel loop. The method significantly improves the performance of the parallel program driven in the multithreaded processor-based parallel system.
    • 提供了一种并行程序执行方法,其中为了反映基于多线程处理器的并行系统的结构特征,在使用性能预测模型编译或执行时预测并行循环的性能,然后使用自适应 执行方式。 该方法包括以下步骤:生成与并行系统的物理处理器的数量一样多的线程,以便执行并行程序中包含的至少一个并行循环; 通过生成的线程执行每个并行循环的至少一个单个循环; 测量执行时间,执行指令的数量以及每个并行循环的高速缓存未命中数; 通过基于测量值确定用于执行每个并行循环的线程数,确定每个并行循环的执行模式; 以及根据确定的结果将线程分配给每个物理处理器以执行每个并行循环。 该方法显着提高了在基于多线程处理器的并行系统中驱动的并行程序的性能。
    • 13. 发明申请
    • Memory device with row shifting for defective row repair
    • 具有行移位的存储器件,用于有缺陷的行修复
    • US20060274585A1
    • 2006-12-07
    • US11145425
    • 2005-06-03
    • Chang Jung
    • Chang Jung
    • G11C29/00
    • G11C29/848
    • A memory device includes N regular rows of memory cells, L redundant rows of memory cells, a shift circuit, and N word lines, where N>1 and L>1. Each word line is associated with a designated row and an alternate row that is L rows away from the designated row. The shift circuit receives the N word lines and couples each word line to either the designated row or the alternate row for that word line. If L is two, then the shift circuit couples even-numbered word lines to even-numbered rows and odd-numbered word lines to odd-numbered rows. The shift circuit may couple each word line to (1) the designated row if this row is non-defective and a preceding word line is not shifted down or (2) the alternate row otherwise.
    • 存储器件包括N个常规行的存储器单元,L个冗余的存储单元行,移位电路和N个字线,其中N> 1和L> 1。 每个字线与指定行和与指定行相距L列的替代行相关联。 移位电路接收N个字线,并将每个字线耦合到该字线的指定行或替代行。 如果L为2,则移位电路将偶数字线偶数行和奇数字线耦合到奇数行。 如果该行是无缺陷的并且先前的字线没有向下移动,或者(2)替代行,移位电路可以将每个字线耦合到(1)指定的行。
    • 14. 发明申请
    • Metal programmable self-timed memories
    • 金属可编程自定时存储器
    • US20050099864A1
    • 2005-05-12
    • US10706110
    • 2003-11-12
    • Jeffrey BrownChang Jung
    • Jeffrey BrownChang Jung
    • G11C5/02G11C8/10G11C11/417G11C7/00
    • G11C8/10G11C5/025G11C11/417
    • A self-timed memory array is disclosed, in which segmentability and metal-programmability are supported while minimizing layout space. Self-timing row decoder circuits are placed at the top and bottom of the array adjacent to respective I/O blocks. A self-timing signal is routed from the top (resp. bottom) of the array to a point halfway down (resp. up) the memory array and then back to a self-timing row decoder at the top (resp. bottom) of the array. The same approach may also be used to account for the bitline wire delay from the bottom (resp. top) of the array to the sense amplifiers in the I/O block. Further flexibility in wire routing is provided by eliminating metal routing layers from unneeded memory cells, and a programmable gate array may be used to allow an arbitrary word size to be chosen for the memory.
    • 公开了一种自定时存储器阵列,其中支持可分割性和金属可编程性,同时最小化布局空间。 自定时行解码器电路放置在与相应I / O块相邻的阵列的顶部和底部。 自定时信号从阵列的顶部(相应的底部)路由到存储器阵列的中途(分别向上)一点,然后返回到顶部(相应的底部)的自定时行解码器 阵列。 也可以使用相同的方法来解释从阵列的底部(相对顶部)到I / O块中的读出放大器的位线延迟。 通过从不需要的存储器单元中消除金属布线层来提供电线布线的进一步的灵活性,并且可以使用可编程门阵列来允许为存储器选择任意的字大小。
    • 15. 发明授权
    • Metal programmable self-timed memories
    • 金属可编程自定时存储器
    • US07400543B2
    • 2008-07-15
    • US10706110
    • 2003-11-12
    • Jeffrey Scott BrownChang Jung
    • Jeffrey Scott BrownChang Jung
    • G11C7/02
    • G11C8/10G11C5/025G11C11/417
    • A self-timed memory array is disclosed, in which segmentability and metal-programmability are supported while minimizing layout space. Self-timing row decoder circuits are placed at the top and bottom of the array adjacent to respective I/O blocks. A self-timing signal is routed from the top (resp. bottom) of the array to a point halfway down (resp. up) the memory array and then back to a self-timing row decoder at the top (resp. bottom) of the array. The same approach may also be used to account for the bitline wire delay from the bottom (resp. top) of the array to the sense amplifiers in the I/O block. Further flexibility in wire routing is provided by eliminating metal routing layers from unneeded memory cells, and a programmable gate array may be used to allow an arbitrary word size to be chosen for the memory.
    • 公开了一种自定时存储器阵列,其中支持可分割性和金属可编程性,同时最小化布局空间。 自定时行解码器电路放置在与相应I / O块相邻的阵列的顶部和底部。 自定时信号从阵列的顶部(相应的底部)路由到存储器阵列的中途(分别向上)一点,然后返回到顶部(相应的底部)的自定时行解码器 阵列。 也可以使用相同的方法来解释从阵列的底部(相对顶部)到I / O块中的读出放大器的位线延迟。 通过从不需要的存储器单元中消除金属布线层来提供电线布线的进一步的灵活性,并且可以使用可编程门阵列来允许为存储器选择任意的字大小。
    • 16. 发明申请
    • Cdma signal generator using an awgn generator and a saw filter
    • Cdma信号发生器采用awgn发生器和锯式滤波器
    • US20070275663A1
    • 2007-11-29
    • US10560769
    • 2004-07-26
    • Chang Jung
    • Chang Jung
    • H04B17/00
    • H04B17/16
    • There is provided a CDMA generator using an AWGN generator and a SAW filter. The CDMA generator according to the present invention comprises (1) an additive white Gaussian noise generator for generating a first broad band noise in an RF receiving band, (2) a first signal generator for generating a first conversion frequency signal, (3) a first mixer for mixing the first broad band noise in the RF receiving band with the first conversion frequency signal to provide a second broad band noise in an IF band, the IF band including a CDMA band and a remaining frequency band that is exclusive of the CDMA band, (4) a SAW filter for attenuating a third broad band noise in the remaining frequency band within the IF band to a predetermined level to provide a substantially CDMA band noise, (5) a second signal generator for generating a second conversion frequency signal, and (6) a second mixer for mixing the substantially CDMA band noise from the SAW filter with the second conversion frequency signal from the second signal generator to provide an output, wherein the output is usable as a test input signal to an RF block unit.
    • 提供了使用AWGN发生器和SAW滤波器的CDMA发生器。 根据本发明的CDMA发生器包括(1)用于在RF接收频带中产生第一宽带噪声的加性白高斯噪声发生器,(2)用于产生第一转换频率信号的第一信号发生器,(3) 第一混频器,用于将RF接收频带中的第一宽带噪声与第一转换频率信号混合,以在IF频带中提供第二宽频带噪声,所述IF频带包括CDMA频带和除CDMA之外的剩余频带 (4)用于将IF频带内的剩余频带中的第三宽频带噪声衰减到预定电平以提供基本CDMA频带噪声的SAW滤波器,(5)用于产生第二转换频率信号的第二信号发生器 ,和(6)第二混频器,用于将来自SAW滤波器的基本CDMA频带噪声与来自第二信号发生器的第二转换频率信号混合以提供输出,其中输出 可用作到RF块单元的测试输入信号。
    • 17. 发明申请
    • Pseudo-dual port memory where ratio of first to second memory access is clock duty cycle independent
    • 伪双端口存储器,其中第一到第二存储器访问的比率是时钟占空比独立的
    • US20070109909A1
    • 2007-05-17
    • US11282333
    • 2005-11-17
    • Chang Jung
    • Chang Jung
    • G11C8/18
    • G11C8/18G11C7/1012G11C7/1039G11C7/1042G11C7/22G11C7/222G11C8/16
    • A pseudo-dual port memory performs both a first memory access operation and a second memory access operation in a single period of an externally supplied clock signal CLK. The signal CLK is used to latch a first address for the first operation and a second address for the second operation. Control circuitry generates first control signals that initiate the first operation. The time duration of the first operation depends upon a delay through a delay circuit. A precharge period follows termination of the first operation. The time duration of the precharge period depends upon a propagation delay through the control circuit. The memory access of the second operation is initiated following termination of the precharging. The time duration of the second memory access depends on a delay through the delay circuit. The time when the second operation is initiated is independent of the duty cycle of CLK.
    • 伪双端口存储器在外部提供的时钟信号CLK的单个周期中执行第一存储器存取操作和第二存储器存取操作。 信号CLK用于锁存用于第一操作的第一地址和用于第二操作的第二地址。 控制电路产生启动第一操作的第一控制信号。 第一操作的持续时间取决于通过延迟电路的延迟。 在第一次操作结束之后的预充电期间。 预充电周期的持续时间取决于通过控制电路的传播延迟。 第二次操作的存储器访问在预充电结束后启动。 第二存储器访问的持续时间取决于延迟电路的延迟。 启动第二个操作的时间与CLK的占空比无关。
    • 19. 发明申请
    • Clock generator for pseudo dual port memory
    • 时钟发生器用于伪双端口存储器
    • US20050007837A1
    • 2005-01-13
    • US10911457
    • 2004-08-04
    • Chang Jung
    • Chang Jung
    • G11C7/22G11C7/00
    • G11C7/222G11C7/22
    • A clock generating circuit for a pseudo dual port memory incorporates feedback, delays, and latches to ensure that the write (read) operation clock pulse is sufficiently spaced in time from the read (write) operation clock. The clock generating circuit receives an external clock, a read enable signal, a write enable signal, and a reset signal as inputs. Advantages include minimization of the clock cycle time and operation unaffected by the duty ratio of an external clock. Delay circuitry may be added such that the generated clock signal has sufficient fan out and is sufficiently stable.
    • 用于伪双端口存储器的时钟产生电路包含反馈,延迟和锁存器,以确保写(读)操作时钟脉冲在时间上与读(写)操作时钟充分间隔开。 时钟产生电路接收外部时钟,读使能信号,写使能信号和复位信号作为输入。 优点包括最小化时钟周期时间和不受外部时钟占空比的影响。 可以添加延迟电路,使得所生成的时钟信号具有足够的扇出并且足够稳定。