Infineon Technologies North America Corp.

Infineon Technologies Ag

Klaus J Oberlaender

Rod G Fleck

Sabeen Randhawa

Gigy Baror

Vincent Rezard

Le Trong Nguyen

Rami Zemach

Doron Shoham

Muhammad Afsar

Yannick Martelloni

Niv Margalit

Alfred Eder

Manfred Henftling

Zohar Peleg

Oded Trainin

Christian Wiedholz

A simulation/debugging method for SOC designs that utilizes initial memory values loaded into a simulation model. A test program is then executed, and incremetal transaction records are generated for each incremental memory access (e.g., data write operations). Each transaction record includes a timestamp, address and data values. The transaction record information is stored/captured on a high level-based (i.e., system address-based) domain that takes into account all the tiling, interleaving, scrambling, and unaligned accessing used in the simulated SOC design, rather than on a low level-based (i.e., physical memory address-based) domain. Upon completing the simulation, the instantaneous memory contents at any selected point in time during the simulated execution are calculated by combining the initial data and intermediate transaction record information. Automatic memory dump and sanity check tests verify the integrity of the final data value and incremental transactions. Cache memory information is collected and displayed using a system-level format.

Memory debugger for system-on-a-chip designs

An integrated memory comprises a plurality of data lines and a plurality of decoders being associated to each data line. Each data line can address a single memory cell or a plurality of memory cells. Also, each data line can be either a word line or a bit line of a memory. Each decoder generates an enable signal upon receiving of its associated address signal. A plurality of multiplexers having two inputs and an output associated to each data line are provided. The enable signal of each decoder is supplied to a first input of the associated multiplexer and to a second input of the multiplexer associated to the next higher addressed data line, and a control input for controlling said multiplexers.

Memory device with support for unaligned access

An interface circuit for coupling a data handling unit with a memory unit having control inputs, an address signal input, a data signal input, and a data signal output is described. The interface circuit comprises an address buffer having an input and an output, said input receiving an address signal from said data handling unit, a first multiplexer which couples said memory unit with either said output of said address buffer or with said address signal, a data buffer having an input and an output, said input receiving a data signal from said data handling unit and said output being coupled with said memory data input, a second multiplexer for selecting either said memory data signal output or said data buffer output, and a comparator for comparing said address signal with the signal from said address buffer output, generating a control signal which controls said second multiplexer.

Interface for a memory unit

A data processing unit is disclosed with a register file having a plurality of registers. A memory having a plurality of n-bit input/output ports, and a coupling unit for coupling the memory with the register file, a memory address and select unit for addressing the memory banks are provided. The coupling unit comprises a bus having a bus width of at least 2n-bits forming at least a first and second sub-bus, first couplers for coupling each memory bank or the register file selectively with one of the sub-busses, and second couplers for coupling the register file or the memory banks with the bus.

Data processing device with memory coupling unit

Prefetching data to a low level memory of a computer system is accomplished utilizing an instruction location indicator related to an upcoming instruction to identify a next data prefetch indicator and then utilizing the next data prefetch indicator to locate the corresponding prefetch data within the memory of the computer system. The prefetch data is located so that the prefetch data can be transferred to a primary cache where the data can be quickly fetched by a processor when the upcoming instruction is executed. The next data prefetch indicator is generated by carrying out the addressing mode function that is embedded in an instruction only when the addressing mode of the instruction is a deterministic addressing mode such as a sequential. The next data prefetch indicator, preferably in the form of an effective address, is identified by the instruction location indicator, preferably in the form of a program counter, by relating calculated next effective addresses to corresponding program counter tags in a searchable table.

Dynamic data prefetching based on program counter and addressing mode

Growing community of inventors

San Jose, CA, United States of America

Klaus J Oberlaender