Abstract: The present invention provides novel power saving methods for programmable logic array (PLA) circuits that includes diodes. One method is to store the results of a previous PLA operation, and bypass a new operation if the inputs are the same as previous operation. Another method is to reset the PLA outputs when the correct results can be achieved by resetting output latches. A large PLA is divided into smaller sub-PLA's while individual sub-PLA's are controlled separately. It is therefore possible to save power by bypassing unrelated sub-PLA's. PLA's of the present invention consume less power than equivalent prior art PLA's by orders of magnitudes. For most cases, PLA's of the present invention also have better performance and better cost efficiency. The design procedures are completely controlled by user-friendly computer aid design tools. The regular structures of PLA and the simplicity in connections allow us to avoid RC effects of conductor lines.

Abstract: This invention discloses a multiple-chip module (MCM) device supported on a semiconductor wafer. The MCM device includes a core module that has a plurality of logic circuits having a layer structure formed by a logic circuit manufacturing process for performing logic functions of said MCM device. The MCM device further includes at least an input/output (I/O) module disposed next to and separate from the core module comprising a plurality of I/O circuits having a layer structure formed by an I/O circuit manufacturing process for performing input/output functions for said MCM device. The core module is flipped to have face-to-face contacts with a plurality of inter-module contact points disposed on the I/O module.

Abstract: An electronic device supported on a semiconductor substrate. The semiconductor device includes a diffusion area in the substrate and a polysilicon layer extending over the substrate and contacting the diffusion area. The electronic device further includes a conductive contact covering and contacting both the polysilicon layer and the diffusion area. Therefore, the semiconductor device disclosed in this invention includes poly-to-diffusion connection for a semiconductor device that has a diffusion are and a polysilicon area. The semiconductor device further includes a contact that covers both the diffusion area and the polysilicon area with a contact filling material forming the connection between these two areas.

Abstract: A dynamic random access memory solves long-existing tight pitch layout problems using a multiple-dimensional bit line structure. Improvement in decoder design further reduces total area of this memory. A novel memory access procedure provides the capability to make internal memory refresh completely invisible to external users. By use of such memory architecture, higher performance DRAM can be realized without degrading memory density. The requirements for system support are also simplified significantly.

Abstract: Using 6 transistor memory cell to replace prior art 10 transistor binary content addressable memory (CAM) cells, and using 10 transistor ternary CAM (TCAM) cell to replace prior art 16 transistor TCAM cells, the present invention provided significant cost saving for high density CAM products. The power consumption problems of prior art high density CAM devices are solved by novel zoned lookup mechanism. For a high density CAM storing sorted data, lookup mechanisms of the present invention can reduce power consumption by two orders of magnitudes.

Abstract: The present invention provides novel power saving methods for programmable logic array (PLA) circuits. One method is to store the results of a previous PLA operation, and bypass a new operation if the inputs are the same as previous operation. Another method is to reset the PLA outputs when the correct results can be achieved by resetting output latches. A large PLA is divided into smaller sub-PLA's while individual sub-PLA's are controlled separately. It is therefore possible to save power by bypassing unrelated sub-PLA's. PLA's of the present invention consume less power than equivalent prior art PLA's by orders of magnitudes. For most cases, PLA's of the present invention also have better performance and better cost efficiency. The design procedures are completely controlled by user-friendly computer aid design tools. The regular structures of PLA and the simplicity in connections allow us to avoid RC effects of conductor lines.

Abstract: High performance memory devices have been realized by applying an Evenly Scaled Multiple Level Architecture (ESMLA) using block select arrangement. A single-bit-line-write mechanism allows us to reduce the number of bit lines by 50% for static memory devices. The resulting memory device can be as fast as registers files while its area is smaller than prior art high-density memory devices. The scaling method of the memory architecture also assures that the speed of the memory devices will scale in the same rate as logic circuits in future IC manufacture technologies.

Abstract: This invention provides practical methods to fabricate sub-micron 3D integrated circuits using multiple layers of diodes manufactured on polycrystalline or amorphous semiconductor thin films. The long existing problems for using poly diodes for high density IC are solved by design and manufacture methods. The circuit design methods of the present invention improve the tolerance in non-ideal properties of diodes. The resulting IC products can function correctly even when many of their diodes are defective. We also developed manufacture procedures fully compatible with current art IC technologies. No additional masking steps or high temperature procedures are used. The 3D IC devices of the present invention are ready to be manufactured by current art IC technologies. Integrated circuits with unprecedented densities are therefore realized by stacking thin film diodes upon common active devices.

Abstract: High performance memory devices have been realized by applying an Evenly Scaled Multiple Level Architecture (ESMLA) using block select arrangement. A single-bit-line-write mechanism allows us to reduce the number of bit lines by 50% for static memory devices. The resulting memory device can be as fast as registers files while its area is smaller than prior art high-density memory devices. The scaling method of the memory architecture also assures that the speed of the memory devices will scale in the same rate as logic circuits in future IC manufacture technologies.

Abstract: High performance memory devices have been realized by applying an Evenly Scaled Multiple Level Architecture (ESMLA) using block select arrangement. A single-bit-line-write mechanism allows us to reduce the number of bit lines by 50% for static memory devices. The resulting memory device can be as fast as registers files while its area is smaller than prior art high-density memory devices. The scaling method of the memory architecture also assures that the speed of the memory devices will scale in the same rate as logic circuits in future IC manufacture technologies.

Abstract: Using 6 transistor memory cell to replace prior art 10 transistor binary content addressable memory (CAM) cells, and using 10 transistor ternary CAM (TCAM) cell to replace prior art 16 transistor TCAM cells, the present invention provided significant cost saving for high density CAM products. The power consumption problems of prior art high density CAM devices are solved by novel zoned lookup mechanism. For a high density CAM storing sorted data, lookup mechanisms of the present invention can reduce power consumption by two orders of magnitudes.

Abstract: A semiconductor memory array comprises a plurality of memory cells wherein each memory cell further includes a first and a second bit-lines and a first and a second word-lines connected to each of the memory cells. The memory array further includes a memory cell read/write voltage control circuit for controlling each of the first and second bit-lines to have a bitline voltage higher, lower and within a medium voltage range between a first voltage V0 and second voltage V1 wherein Vdd>V1>V0>Vgnd where Vdd is a power supply voltage, and Vgnd is a ground voltage for the memory array. The memory array further includes a first read/write port and a second read/write port for independently carrying out a read/write operation by activating the first and second word-lines respectively and by controlling the first and second bit-lines respectively to have a bit-line voltage higher, lower or within the medium voltage range between the first and the second voltage.

Abstract: A demodulator for demodulating a modulated input signal transmitted at a carrier frequency includes a current mirror for receiving the modulated input signal and genera tine a first and a second current-mirror output signals of same amplitude and frequency as the modulated input signal. The demodulator further includes a first and a second switch-controlled sampling circuits connected to the current mirror for receiving the first and second current mirror output signals respectively. The demodulator further includes a switching signal generator provided for generating a first and a second switch control signals having a frequency substantially equals to the carrier frequency with a flexibly adjustable phase difference between the first and the second switch control signals.

Abstract: The present invention discloses a data handling device that includes a plurality of distributed execution units (EU) each disposed next to and connected to a local data storage unit for accessing and executing instructions on data stored in the local data storage unit. In a preferred embodiment, each of the plurality of distributed execution units (EU) further includes an arithmetic logic unit (ALU). In another preferred embodiment, each of the plurality of distributed execution units (EU) further includes a floating point unit (FPU). And, each of the plurality of distributed execution units (EU) further includes an address generation unit (AGU).

Abstract: This invention discloses a dynamic random access memory (DRAM) memory cell. The DRAM memory cell includes a first transistor-capacitor circuit connected to a first bitline BL and a second transistor-capacitor circuit connected to a second bitline BL#. The memory cell further includes a gate of the first transistor connected to a gate of the second transistor. The DRAM cell further includes a sense amplifier connected to the first bit line BL and the second bit line BL# for measuring a binary bit from sensing a voltage difference between the first and second transistor-capacitor circuits independent from a pre-charged bit-line voltage.

Abstract: A dynamic random access memory solves long-existing tight pitch layout problems using a multiple-dimensional bit line structure. Improvement in decoder design further reduces total area of this memory. A novel memory access procedure provides the capability to make internal memory refresh completely invisible to external users. By use of such memory architecture, higher performance DRAM can be realized without degrading memory density. The requirements for system support are also simplified significantly.

Abstract: High performance memory devices have been realized by applying an Evenly Scaled Multiple Level Architecture (ESMLA) using block select arrangement. A single-bit-line-write mechanism allows us to reduce the number of bit lines by 50% for static memory devices. The resulting memory device can be as fast as registers files while its area is smaller than prior art high-density memory devices. The scaling method of the memory architecture also assures that the speed of the memory devices will scale in the same rate as logic circuits in future IC manufacture technologies.

Abstract: High performance memory devices have been realized by applying an Evenly Scaled Multiple Level Architecture (ESMLA) using block select arrangement. A single-bit-line-write mechanism allows us to reduce the number of bit lines by 50% for static memory devices. The resulting memory device can be as fast as registers files while its area is smaller than prior art high-density memory devices. The scaling method of the memory architecture also assures that the speed of the memory devices will scale in the same rate as logic circuits in future IC manufacture technologies.

Abstract: A semiconductor erasable programmable read-only memory (EPROM) device provided for operation with a plurality of first level sense-circuits. The EPROM memory device includes an EPROM memory cell array having a plurality of first-direction first-level bit lines disposed in a parallel manner along a first direction. The EPROM memory device further includes a plurality of word lines intersected with the first-direction first-level bit lines. The EPROM memory cell array further includes a plurality of EPROM memory cells wherein each of the plurality of memory cells being coupled between one of the first-direction first level bit lines and one of the word lines for storing data therein. And, the EPROM memory device further includes a plurality of different-direction first level bit-lines disposed along at least one different direction different from the first direction.

Abstract: The present invention provides novel power saving methods for programmable logic array (PLA) circuits. One method is to store the results of a previous PLA operation, and bypass a new operation if the inputs are the same as previous operation. Another method is to reset the PLA outputs when the correct results can be achieved by resetting output latches. A large PLA is divided into smaller sub-PLA's while individual sub-PLA's are controlled separately. It is therefore possible to save power by bypassing unrelated sub-PLA's. PLA's of the present invention consume less power than equivalent prior art PLA's by orders of magnitudes. For most cases, PLA's of the present invention also have better performance and better cost efficiency. The design procedures are completely controlled by user-friendly computer aid design tools. The regular structures of PLA and the simplicity in connections allow us to avoid RC effects of conductor lines.