-
公开(公告)号：EP0698235A1
公开(公告)日：1996-02-28
申请号：EP94916588.0
申请日：1994-04-28
Applicant: MicroUnity Systems Engineering, Inc.
Inventor： HERNDON, William, H.
CPC classification number: G05F3/24
Abstract: The present invention describes a bias potential distribution system which provides bias potentials to MOS devices while ensuring the devices' operating conditions remain constant over temperature, process, and power supply fluctuations. Further, bias potentials are generated at one main location within the logic circuit and then distributed throughout the logic circuit to all of the MOS devices or to bias voltage conversion circuits.
Abstract translation: 本发明描述了一种偏压电势分布系统，其向MOS器件提供偏压电势，同时确保器件的工作条件在温度，工艺和电源波动中保持恒定。 此外，在逻辑电路内的一个主要位置处产生偏置电位，然后将其分布在整个逻辑电路中的所有MOS器件或偏置电压转换电路。
-
公开(公告)号：EP0655177A1
公开(公告)日：1995-05-31
申请号：EP93914239.0
申请日：1993-05-28
Applicant: MicroUnity Systems Engineering, Inc.
Inventor： WONG, Ban, Pak
IPC: H03K19
CPC classification number: H03K19/018521 , H03K19/00361 , H03K19/0136 , H03K19/017518
Abstract: An ECL-to-CMOS level translator and BiCMOS buffer are described. The current supplied from the first input PMOS transistor (P1) is the input current to a current mirror comprising the first and second NMOS transistors (N1 and N2). The current mirror controls the current sourcing and sinking capability of the translator. Third and fourth NMOS transistors (N3 and N4) are coupled to the first and second NMOS transistors in the current mirror and function to vary the source-to-body voltage of the first and second NMOS transistors and consequently their gain which results in increased current drive and sinking capability. The BiCMOS differential buffer of the present invention provides a differential output signal on first and second output nodes (115 and 215). It is comprised of first and second cross-coupled buffers (100B and 200B). Cross-coupling the buffers results in improved high-to-low transition times.
-
公开(公告)号：EP0628215A1
公开(公告)日：1994-12-14
申请号：EP93905013.0
申请日：1993-02-10
Applicant: MicroUnity Systems Engineering, Inc.
Inventor： MATTHEWS, James, A.
CPC classification number: H01L29/66272 , H01L21/8249 , H01L29/0826 , Y10S257/927
Abstract: Un transistor bipolaire à jonctions (TBJ) à effet Kirk supprimé comprend une région collectrice (11) de type n légèrement dopée formée sur une couche n+ (12) plus fortement dopée. Directement sur le collecteur se trouve une base de type p présentant une région extrinsèque (17) disposée latéralement autour d'une région intrinsèque (18). Un émetteur n+ (20) est positionné directement au-dessus de la région de base intrinsèque. Le TBJ comprend également une région n+ (15) localisée située directement au-dessous de la région de base intrinsèque, laquelle accroît significativement les capacités de traitement de courant du transistor.
-
公开(公告)号：US08812821B2
公开(公告)日：2014-08-19
申请号：US13584235
申请日：2012-08-13
Applicant: Craig Hansen , John Moussouris , Alexia Massalin
Inventor： Craig Hansen , John Moussouris , Alexia Massalin
IPC: G06F9/30
CPC classification number: G06F9/30014 , G06F9/30007 , G06F9/30021 , G06F9/30029 , G06F9/30032 , G06F9/30036 , G06F9/30043 , G06F9/30101 , G06F9/30109 , G06F9/30112 , G06F9/30145 , G06F9/3016 , G06F9/30167 , G06F9/32 , G06F9/34 , G06F9/3824 , G06F9/383 , G06F9/3885 , G06F12/0886
Abstract: A programmable processor and method for improving the performance of processors by expanding at least two source operands, or a source and a result operand, to a width greater than the width of either the general purpose register or the data path width. The present invention provides operands which are substantially larger than the data path width of the processor by using the contents of a general purpose register to specify a memory address at which a plurality of data path widths of data can be read or written, as well as the size and shape of the operand. In addition, several instructions and apparatus for implementing these instructions are described which obtain performance advantages if the operands are not limited to the width and accessible number of general purpose registers.
Abstract translation: 一种可编程处理器和方法，用于通过将至少两个源操作数或源和结果操作数扩展到大于通用寄存器或数据路径宽度的宽度的宽度来提高处理器的性能。 本发明通过使用通用寄存器的内容来指定可以读取或写入数据的多个数据路径宽度的存储器地址，并且基本上大于处理器的数据路径宽度的操作数，以及 操作数的大小和形状。 此外，描述了用于实现这些指令的几个指令和装置，其如果操作数不限于通用寄存器的宽度和可访问数量，则获得性能优点。
-
公开(公告)号：US08769248B2
公开(公告)日：2014-07-01
申请号：US13493738
申请日：2012-06-11
Applicant: Craig Hansen , John Moussouris , Alexia Massalin
Inventor： Craig Hansen , John Moussouris , Alexia Massalin
IPC: G06F9/302
CPC classification number: G06F9/30014 , G06F9/30018 , G06F9/30025 , G06F9/30029 , G06F9/30032 , G06F9/30036 , G06F9/3004 , G06F9/30043 , G06F9/30054 , G06F9/30087 , G06F9/30101 , G06F9/30109 , G06F9/30112 , G06F9/3012 , G06F9/30123 , G06F9/30145 , G06F9/3016 , G06F9/30167 , G06F9/3816 , G06F9/3824 , G06F9/383 , G06F9/3851 , G06F9/3861 , G06F9/3873 , G06F9/3885 , G06F15/7832
Abstract: Systems and apparatuses are presented relating a programmable processor comprising an execution unit that is operable to decode and execute instructions received from an instruction path and partition data stored in registers in the register file into multiple data elements, the execution unit capable of executing group data handling operations that re-arrange data elements in different ways in response to data handling instructions, the execution unit further capable of executing a plurality of different group floating-point and group integer arithmetic operations that each arithmetically operates on the multiple data elements stored in registers in the register file to produce a catenated result that is returned to a register in the register file, wherein the catenated result comprises a plurality of individual results.
-
Patent Agency Ranking
166.发明授权公开(公告)号：US08683182B2
公开(公告)日：2014-03-25
申请号：US13493750
申请日：2012-06-11
Applicant: Craig Hansen , John Moussouris , Alexia Massalin
Inventor： Craig Hansen , John Moussouris , Alexia Massalin
IPC: G06F9/302
CPC classification number: G06F9/30014 , G06F9/30018 , G06F9/30025 , G06F9/30029 , G06F9/30032 , G06F9/30036 , G06F9/3004 , G06F9/30043 , G06F9/30054 , G06F9/30087 , G06F9/30101 , G06F9/30109 , G06F9/30112 , G06F9/3012 , G06F9/30123 , G06F9/30145 , G06F9/3016 , G06F9/30167 , G06F9/3816 , G06F9/3824 , G06F9/383 , G06F9/3851 , G06F9/3861 , G06F9/3873 , G06F9/3885 , G06F15/7832
Abstract: Systems and apparatuses are presented relating a programmable processor comprising an execution unit that is operable to decode and execute instructions received from an instruction path and partition data stored in registers in the register file into multiple data elements, the execution unit capable of executing group data handling operations that re-arrange data elements in different ways in response to data handling instructions, the execution unit further capable of executing a plurality of different group floating-point and group integer arithmetic operations that each arithmetically operates on the multiple data elements stored in registers in the register file to produce a catenated result that is returned to a register in the register file, wherein the catenated result comprises a plurality of individual results.
Abstract translation: 提出了一种可编程处理器的系统和装置，其包括执行单元，该执行单元可操作以解码和执行从指令路径接收的指令，并将存储在寄存器堆中的寄存器中的数据分割成多个数据元素，该执行单元能够执行群组数据处理 响应于数据处理指令以不同方式重新布置数据元素的操作，所述执行单元还能够执行多个不同的组浮点和组整数运算，每个算术运算对存储在寄存器中的多个数据元素进行算术运算 该寄存器文件产生一个返回到该寄存器文件中的一个寄存器的连线结果，其中该连接结果包括多个单独的结果。
-
公开(公告)号：US08289335B2
公开(公告)日：2012-10-16
申请号：US11346213
申请日：2006-02-03
Applicant: Craig Hansen , John Moussouris , Alexia Massalin
Inventor： Craig Hansen , John Moussouris , Alexia Massalin
CPC classification number: G06F9/3001 , G03F1/36 , G06F9/30 , G06F9/30007 , G06F9/30014 , G06F9/30018 , G06F9/30029 , G06F9/30032 , G06F9/30036 , G06F9/3004 , G06F9/30043 , G06F9/30054 , G06F9/30098 , G06F9/30101 , G06F9/30109 , G06F9/30112 , G06F9/30145 , G06F9/30149 , G06F9/3016 , G06F9/30167 , G06F9/35 , G06F9/383 , G06F9/3851 , G06F9/3861 , G06F9/3885 , G06F9/4484 , G06F9/45533 , G06F12/02 , G06F17/5068 , G06F17/5072 , G06F17/5081 , G06F2217/12 , H03M13/158 , H03M13/4169 , Y02D10/13 , Y02D10/26 , Y02D10/28 , Y02P90/265
Abstract: A programmable processor and method for improving the performance of processors by expanding at least two source operands, or a source and a result operand, to a width greater than the width of either the general purpose register or the data path width. The present invention provides operands which are substantially larger than the data path width of the processor by using the contents of a general purpose register to specify a memory address at which a plurality of data path widths of data can be read or written, as well as the size and shape of the operand. In addition, several instructions and apparatus for implementing these instructions are described which obtain performance advantages if the operands are not limited to the width and accessible number of general purpose registers.
Abstract translation: 一种可编程处理器和方法，用于通过将至少两个源操作数或源和结果操作数扩展到大于通用寄存器或数据路径宽度的宽度的宽度来提高处理器的性能。 本发明通过使用通用寄存器的内容来指定可以读取或写入数据的多个数据路径宽度的存储器地址，并且基本上大于处理器的数据路径宽度的操作数，以及 操作数的大小和形状。 此外，描述了用于实现这些指令的几个指令和装置，其如果操作数不限于通用寄存器的宽度和可访问数量，则获得性能优点。
-
168.发明申请SYSTEM AND METHOD TO IMPLEMENT A MATRIX MULTIPLY UNIT OF A BROADBAND PROCESSOR 有权用于实现宽带处理器的矩阵多项式单元的系统和方法公开(公告)号：US20120215826A1
公开(公告)日：2012-08-23
申请号：US13462648
申请日：2012-05-02
Applicant: Craig Hansen , Bruce Bateman , John Moussouris
Inventor： Craig Hansen , Bruce Bateman , John Moussouris
CPC classification number: G06F7/5338 , G06F7/4812 , G06F7/49994 , G06F7/57 , G06F7/724 , G06F9/30014 , G06F9/30036 , G06F17/15 , G06F17/16 , G06F2207/3812 , G06F2207/382 , G06F2207/3824 , G06F2207/3828
Abstract: The present invention provides a system and method for improving the performance of general-purpose processors by implementing a functional unit that computes the product of a matrix operand with a vector operand, producing a vector result. The functional unit fully utilizes the entire resources of a 128b by 128b multiplier regardless of the operand size, as the number of elements of the matrix and vector operands increase as operand size is reduced. The unit performs both fixed-point and floating-point multiplications and additions with the highest-possible intermediate accuracy with modest resources.
Abstract translation: 本发明提供了一种用于通过实现一个功能单元来提高通用处理器的性能的系统和方法，所述功能单元使用向量操作数来计算矩阵操作数的乘积，产生向量结果。 功能单元完全利用128b乘128b乘法器的全部资源，无论操作数大小如何，因为矩阵和向量操作数的元素数量随着操作数大小的减小而增加。 该单元通过适度的资源执行具有最高可能的中间精度的定点和浮点乘法和补充。
-
169.发明申请公开(公告)号：US20120117441A1
公开(公告)日：2012-05-10
申请号：US13354214
申请日：2012-01-19
Applicant: Craig Hansen , John Moussouris , Alexia Massalin
Inventor： Craig Hansen , John Moussouris , Alexia Massalin
CPC classification number: G06F9/30014 , G06F9/30007 , G06F9/30021 , G06F9/30029 , G06F9/30032 , G06F9/30036 , G06F9/30043 , G06F9/30101 , G06F9/30109 , G06F9/30112 , G06F9/30145 , G06F9/3016 , G06F9/30167 , G06F9/32 , G06F9/34 , G06F9/3824 , G06F9/383 , G06F9/3885 , G06F12/0886
Abstract: A programmable processor and method for improving the performance of processors by expanding at least two source operands, or a source and a result operand, to a width greater than the width of either the general purpose register or the data path width. The present invention provides operands which are substantially larger than the data path width of the processor by using the contents of a general purpose register to specify a memory address at which a plurality of data path widths of data can be read or written, as well as the size and shape of the operand. In addition, several instructions and apparatus for implementing these instructions are described which obtain performance advantages if the operands are not limited to the width and accessible number of general purpose registers.
Abstract translation: 一种可编程处理器和方法，用于通过将至少两个源操作数或源和结果操作数扩展到大于通用寄存器或数据路径宽度的宽度的宽度来提高处理器的性能。 本发明通过使用通用寄存器的内容来指定可以读取或写入数据的多个数据路径宽度的存储器地址，并且基本上大于处理器的数据路径宽度的操作数，以及 操作数的大小和形状。 此外，描述了用于实现这些指令的几个指令和装置，其如果操作数不限于通用寄存器的宽度和可访问数量，则获得性能优点。
-
170.发明授权Computer system for executing switch and table translate instructions requiring wide operands 有权用于执行开关和表的计算机系统翻译需要广泛操作数的指令公开(公告)号：US08018464B2
公开(公告)日：2011-09-13
申请号：US11981996
申请日：2007-10-31
Applicant: Craig Hansen , John Moussouris , Alexia Massalin
Inventor： Craig Hansen , John Moussouris , Alexia Massalin
CPC classification number: G06F9/3001 , G03F1/36 , G06F9/30 , G06F9/30007 , G06F9/30014 , G06F9/30018 , G06F9/30029 , G06F9/30032 , G06F9/30036 , G06F9/3004 , G06F9/30043 , G06F9/30054 , G06F9/30098 , G06F9/30101 , G06F9/30109 , G06F9/30112 , G06F9/30145 , G06F9/30149 , G06F9/3016 , G06F9/30167 , G06F9/35 , G06F9/383 , G06F9/3851 , G06F9/3861 , G06F9/3885 , G06F9/4484 , G06F9/45533 , G06F12/02 , G06F17/5068 , G06F17/5072 , G06F17/5081 , G06F2217/12 , H03M13/158 , H03M13/4169 , Y02D10/13 , Y02D10/26 , Y02D10/28 , Y02P90/265
Abstract: A programmable processor and method for improving the performance of processors by expanding at least two source operands, or a source and a result operand, to a width greater than the width of either the general purpose register or the data path width. The present invention provides operands which are substantially larger than the data path width of the processor by using the contents of a general purpose register to specify a memory address at which a plurality of data path widths of data can be read or written, as well as the size and shape of the operand. In addition, several instructions and apparatus for implementing these instructions are described which obtain performance advantages if the operands are not limited to the width and accessible number of general purpose registers.
Abstract translation: 一种可编程处理器和方法，用于通过将至少两个源操作数或源和结果操作数扩展到大于通用寄存器或数据路径宽度的宽度的宽度来提高处理器的性能。 本发明通过使用通用寄存器的内容来指定可以读取或写入数据的多个数据路径宽度的存储器地址，并且基本上大于处理器的数据路径宽度的操作数，以及 操作数的大小和形状。 此外，描述了用于实现这些指令的几个指令和装置，其如果操作数不限于通用寄存器的宽度和可访问数量，则获得性能优点。
-
-
-
-
-
-
-
-
-
Search Results
256
records
(took 0.093 seconds)
