Oracle America, Inc.

Sun Microsystems, Inc.

Oracle International Corporation

Cadence Design Systems, Inc.

International Business Machines Corporation

Western Digital Technologies, Inc.

Open Computing Trust I & II

Motorola Corporation

Open Computing Trust I

Robert T Golla

Christopher Hans Olson

Jama Ismail Barreh

Matthew B Smittle

Manish K Shah

Gregory Frederick Grohoski

Paul Joseph Jordan

Jeffrey S Brooks

Mark Luttrell

Yuan C Chou

Xiang Shan Li

Lee Evan Eisen

Soummya Mallick

Ricky C Hetherington

Thomas M Wicki

Marvin A Denman

Bryan P Black

Albert J Loper, Jr

Russell A Reininger

Jared C Smolens

Deepak Panwar

Terence M Potter

Lawrence Spracklen

Shasank Kisan Chavan

Rabin Sugumar

Sebastian Turullols

Gideon N Levinsky

Timothy A Elliott

Zoran Radovic

Howard L Levy

Jared Smolens

Haowei Zhang

David L Weaver

Zeid Hartuon Samoail

Xiaoying Shen

Muhammad Tauseef Rab

Yue Chang

Jike Chong

Albert Danysh

Prateek Agrawal

Ajay A Ingle

Andrew Ewoldt

A memory circuit may include both an array circuit and multiple register circuits, where the power to retrieve data from one of the register circuits may be less than the power to retrieve data from the array circuit. The array circuit may store multiple data words, and the multiple register circuits may be configured to store a subset of the multiple data words. During a first cycle, a read command and an address may be received. In response to a determination that the address corresponds to a given data word included in the subset of the multiple data words, the array circuit may be de-activated in a second cycle subsequent to the first cycle and an output signal may be generated by selecting data retrieved from a particular register circuit of the multiple register circuits in which the given data word may be stored.

Memory circuit with power registers

A queue circuit that manages access to a memory circuit in a computer system includes multiple sets of entries for storing access requests. The entries in one set of entries are assigned to corresponding sources that generate access requests to the memory circuit. The entries in the other set of entries are floating entries that can be used to store requests from any of the sources. Upon receiving a request from a particular source, the queue circuit checks the entry assigned to the particular source and, if the entry is unoccupied, the queue circuit stores the request in the entry. If, however, the entry assigned to the particular source is occupied, the queue circuit stores the request in one of the floating entries.

Queue circuit for controlling access to a memory circuit

Techniques are disclosed relating to a processor load-store unit. In some embodiments, the load-store unit is configured to execute load/store instructions in parallel using first and second pipelines and first and second tag memory arrays. In tag write conflict situations, the load-store unit may arbitrate between the first and second pipelines to ensure the first and second tag memory array contents remain identical. In some embodiments, a data cache tag replay scheme is utilized. In some embodiments, executing load/store instructions in parallel with fills, probes, and store-updates, using separate but identical tag memory arrays, may advantageously improve performance.

Load-store unit dual tags and replays

A cache memory circuit capable of dealing with multiple conflicting requests to a given cache line is disclosed. In response to receiving an acquire request for the given cache line from a particular lower-level cache memory circuit, the cache memory circuit sends probe requests regarding the given cache line to other lower-level cache memory circuits. In situations where a different lower-level cache memory circuit is simultaneously trying to evict the given cache line at the particular lower-level cache memory circuit is trying to obtain a copy of the cache line, the cache memory circuit performs a series of operations to service both requests and ensure that the particular lower-level cache memory circuit receives a copy of the given cache line that includes any changes in the evicted copy of the given cache line.

Managing multiple cache memory circuit operations

An instruction storage circuit within a processor that includes an instruction memory and a memory control circuit. The instruction memory is configured to store instructions of a program for the processor. The memory control circuit is configured to receive a particular instruction from the instruction memory, detect a data integrity error in the particular instruction, and generate and store a corrected version of the particular instruction in an error storage circuit within the instruction memory. A flush of an execution pipeline may be performed in response to the error. In response to a refetch of the particular instruction after the pipeline flush, the instruction storage circuit may be configured to cause the particular instruction to be provided from the error storage circuit to the execution pipeline to permit forward progress of the processor.

Instruction error handling

Techniques are disclosed relating to an apparatus, including a data storage circuit having a plurality of entries, and a load-store pipeline configured to allocate an entry in the data storage circuit in response to a determination that a first instruction includes an access to an external memory circuit. The apparatus further includes an execution pipeline configured to make a determination, while performing a second instruction and using the entry in the data storage circuit, that the second instruction uses a result of the first instruction, and cease performance of the second instruction in response to the determination.

Removal of dependent instructions from an execution pipeline

The present disclosure is directed to a mechanism for forcing a processor to enter a debug mode. In one embodiment, a processor includes a logic circuit configured to receive a halt request. In response to receiving the halt request while the processor is not in a quiescent state, the logic circuit forces the processor into the quiescent state after a threshold amount of time has elapsed. Processor operation is then halted, and the processor thus becomes accessible for a debugger to perform debug operations.

Forced debug mode entry

Techniques are disclosed relating to an apparatus that includes a plurality of execution pipelines including first and second execution pipelines, a shared circuit that is shared by the first and second execution pipelines, and a decode circuit. The first and second execution pipelines are configured to concurrently perform operations for respective instructions. The decode circuit is configured to assign a first program thread to the first execution pipeline and a second program thread to the second execution pipeline. In response to determining that respective instructions from the first and second program threads that utilize the shared circuit are concurrently available for dispatch, the decode circuit is further configured to select between the first program thread and the second program thread.

Program thread selection between a plurality of execution pipelines

A circuit for fast interrupt handling is disclosed. An apparatus includes a processor circuit having an execution pipeline and a table configured to store a plurality of pointers that correspond to interrupt routines stored in a memory circuit. The apparatus further includes an interrupt redirect circuit configured to receive a plurality of interrupt requests. The interrupt redirect circuit may select a first interrupt request among a plurality of interrupt requests of a first type. The interrupt redirect circuit retrieves a pointer from the table using information associated with the request. Using the pointer, the execution pipeline retrieves first program instruction from the memory circuit to execute a particular interrupt routine.

Circuit for fast interrupt handling

A system is disclosed, including a plurality of access units, a plurality of circuit nodes each coupled to a respective access unit, and a plurality of data processing nodes each coupled to a respective access unit. A particular data processing node may be configured to generate a plurality of data transactions. The particular data processing node may also be configured to determine an availability of a coupled access unit. In response to a determination that the coupled access unit is unavailable, the particular data processing node may be configured to halt a transfer of the plurality of data transactions to the coupled access unit and assert a halt indicator signal. In response to a determination that the coupled access unit is available, the particular data processing node may be configured to transfer the particular data transaction to the coupled access unit.

Distributed fairness protocol for interconnect networks

Techniques are disclosed relating to using non-debug path circuitry to perform debug commands. In some embodiments, an apparatus includes a processor core that includes path circuitry configured to access data for instructions executed by the processor core and storage elements which the path circuitry is configured to access via one or more ports. In some embodiments, the apparatus includes debug circuitry configured to receive external debug inputs and send abstract commands to the processor core based on the external debug inputs. In some embodiments, the apparatus includes control circuitry in the processor core configured to, in response to an abstract command to access one or more of the storage elements: generate signaling to access the one or more storage elements using the path circuitry, access read data from the one or more storage elements based on the signaling, and transmit the accessed read data to the debug circuitry.

Debug command execution using existing datapath circuitry

Techniques are disclosed relating to the handling of exceptions generated by illegal instructions in a processor. In an embodiment, a processor may be configured to fetch instructions defined according to an instruction set architecture (ISA). The ISA may include a set of uncompressed instructions and a set of compressed instructions. The processor may further be configured to, upon detecting a given one of the set of compressed instructions, cause a copy of the given compressed instruction to be saved and convert the given compressed instruction to a corresponding given uncompressed instruction. The processor may also be configured to detect that the given uncompressed instruction is illegal and was converted from the given compressed instruction, and based at least in part on these, cause an illegal instruction exception to be generated using the copy of the given compressed instruction.

Illegal instruction exception handling

Techniques are disclosed relating to cache debug using control registers based on debug commands. In some embodiments, an apparatus includes a processor core, debug circuitry, and control circuitry. In some embodiments, the debug circuitry is configured to receive external debug inputs and send abstract commands to the processor core based on the external debug inputs. In some embodiments, the control circuitry is configured to, in response to an abstract command to read data from the cache: write cache address information to a first control register, assert a trigger signal to cause a read of the data from the cache to a second control register, based on the cache address information in the first control register, and send data from the second control register to the debug circuitry. In various embodiments, this may facilitate hardware cache debug using debug circuitry that also controls software debugging.

Cache diagnostic techniques

An instruction buffer for a processor configured to execute multiple threads is disclosed. The instruction buffer is configured to receive instructions from a fetch unit and provide instructions to a selection unit. The instruction buffer includes one or more memory arrays comprising a plurality of entries configured to store instructions and/or other information (e.g., program counter addresses). One or more indicators are maintained by the processor and correspond to the plurality of threads. The one or more indicators are usable such that for instructions received by the instruction buffer, one or more of the plurality entries of a memory array can be determined as a write destination for the received instructions, and for instructions to be read from the instruction buffer (and sent to a selection unit), one or more entries can be determined as the correct source location from which to read.

Multi-threaded instruction buffer design

Approaches are described to improve database performance by implementing a RLE decompression function at a low level within a general-purpose processor or an external block. Specifically, embodiments of a hardware implementation of an instruction for RLE decompression are disclosed. The described approaches improve performance by supporting the RLE decompression function within a processor and/or external block. Specifically, a RLE decompression hardware implementation is disclosed that produces a 64-bit RLE decompression result, with an example embodiment performing the task in two pipelined execution stages with a throughput of one per cycle. According to embodiments, hardware organization of narrow-width shifters operating in parallel, controlled by computed shift counts, is used to perform the decompression. Because of the decreased time required to perform RLE decompression according to embodiments, the performance of tasks that use embodiments described herein for decompression of run-length encoded data is made more efficient.

Run-length encoding decompression

Growing community of inventors

Round Rock, TX, United States of America

Robert T Golla