Oracle International Corporation

Sun Microsystems, Inc.

Oracle America, Inc.

Oracle International Business Machines Corporation

Darryl J Gove

Zoran Radovic

David L Weaver

Lawrence Spracklen

Santosh Abraham

Sanjiv Kapil

Graham Ricketson Murphy

Robert E Mains

Stevan A Vlaovic

George J Chen

Jonathan William Adams

Gerald Zuraski

In some embodiments, a memory initialization detection process includes detecting a read instruction of a program, where the read instruction addresses a particular memory location, and where data corresponding to the particular memory location is cached in a particular cache line of a memory cache. The memory initialization detection process further includes determining, based on metadata stored in the memory cache, that a section of the particular cache line does not store valid data of the program. The memory initialization detection process further includes obtaining validity data from the section of the particular cache line. The memory initialization detection process further includes determining, based on the validity data, whether the read instruction is authorized to proceed.

Memory initialization detection system

The disclosed embodiments relate to a computing system that facilitates performing prefetching for scatter/gather operations. During operation, the system receives a scatter/gather prefetch instruction at a processor core, wherein the scatter/gather prefetch instruction specifies a virtual base address, and a plurality of offsets. Next, the system performs a lookup in a translation-lookaside buffer (TLB) using the virtual base address to obtain a physical base address that identifies a physical page for the base address. The system then sends the physical base address and the plurality of offsets to a cache. This enables the cache to perform prefetching operations for the scatter/gather instruction by adding the physical base address to the plurality of offsets to produce a plurality of physical addresses, and then prefetching cache lines for the plurality of physical addresses into the cache.

Facilitating efficient prefetching for scatter/gather operations

In some embodiments, a memory corruption prevention process includes detecting a memory instruction of a program, where the memory instruction specifies a virtual memory address of data. The memory corruption prevention process further includes accessing, in response to the memory instruction, a translation lookaside buffer (TLB) using at least a portion of the virtual memory address. The memory corruption prevention process further includes, in response to accessing the TLB, obtaining a physical memory address corresponding to the virtual memory address, where the physical memory address corresponds to the data. The memory corruption prevention process further includes, in response to accessing the TLB, obtaining an authentication value corresponding to the physical memory address. The memory corruption prevention process further includes determining, using the authentication value, whether the memory instruction is authorized to proceed.

Memory corruption prevention system

A processor having a streaming unit is disclosed. In one embodiment, a processor includes a streaming unit configured to load one or more input data streams from a memory coupled to the processor. The streaming unit includes an internal network having a plurality of queues configured to store streams of data. The streaming unit further includes a plurality of operations circuits configured to perform operations on the streams of data. The streaming unit is software programmable to operatively couple two or more of the plurality of operations circuits together via one or more of the plurality of queues. The operations circuits may perform operations on multiple streams of data, resulting in corresponding output streams of data.

Flexible configuration hardware streaming unit

A processor, method, and medium for using vector operations to compress selected elements of a vector. An input vector is compared to a criteria vector, and then a subset of the plurality of elements of the input vector are selected based on the comparison. A permutation vector is generated based on the locations of the selected elements and then the permutation vector is used to permute the selected elements of the input vector to an output vector. The selected elements of the input vector are stored in contiguous locations in the leftmost elements of the output vector. Then, the output vector is stored to memory and a pointer to the memory location is incremented by the number of selected elements.

Vector operations for compressing selected vector elements

Techniques for handling version information using a copy engine. In one embodiment, an apparatus comprises a copy engine configured to perform one or more operations associated with a block memory operation in response to a command. Examples of block memory operations may include copy, clear, move, and/or compress operations. In one embodiment, the copy engine is configured to handle version information associated with the block memory operation based on the command. The one or more operations may include operating on data in a cache and/or modifying entries in a memory. In one embodiment, the copy engine is configured to compare version information in the command with stored version information. The copy engine may overwrite or preserve version information based on the command. The copy engine may be a coprocessing element. The copy engine may be configured to maintain coherency with other copy engines and/or processing elements.

Block memory engine with memory corruption detection

A processor having a streaming unit is disclosed. In one embodiment, a processor includes one or more execution units configured to execute instructions of a processor instruction set. The processor further includes a streaming unit configured to execute a first instruction of the processor instruction set, wherein executing the first instruction comprises the streaming unit loading a first data stream from a memory of a computer system responsive to execution of a first instruction. The first data stream comprises a plurality of data elements. The first instruction includes a first argument indicating a starting address of the first stream, a second argument indicating a stride between the data elements, and a third argument indicative of an ending address of the stream. The streaming unit is configured to output a second data stream corresponding to the first data stream.

Hardware streaming unit

A processor, method, and medium for using vector instructions to perform string comparisons. A single instruction compares the elements of two vectors and simultaneously checks for the null character. If an inequality or the null character is found, then the string comparison loop terminates, and a further check is performed to determine if the strings are equal. If all elements are equal and the null character is not found, then another iteration of the string comparison loop is executed. The vectors are loaded with the next portions of the strings, and then the next comparison is performed. The loop continues until either an inequality or the null character is found.

Acceleration of string comparisons using vector instructions

Systems and methods for providing additional instructions for supporting efficient memory corruption detection in a processor. A physical memory may be a DRAM with a spare bank of memory reserved for a hardware failover mechanism. Version numbers associated with data structures allocated in the memory may be generated so that version numbers of adjacent data structures are different. A processor determines that a fetched instruction is a memory access instruction corresponding to a first data structure within the memory. For instructions that are not a version update instruction, the processor compares the first version number and second version number stored in a location in the memory indicated by the generated address and flags an error if there is a mismatch. For version update instructions, the processor performs a memory access operation on the second version number with no comparison check.

Instructions to set and read memory version information

Systems and methods for maximizing a number of available states for a version number used for memory corruption detection. A physical memory may be a DRAM comprising a plurality of regions. Version numbers associated with data structures allocated in the physical memory may be generated so that version numbers of adjacent data structures in a virtual address space are different. A reserved set and an available set of version numbers are associated with each one of the plurality of regions. A version number in a reserved set of a given region may be in an available set of another region. The processor detects no memory corruption error in response to at least determining a version number stored in a memory location in a first region identified by a memory access operation is also in a reserved set associated with the first region.

Maximizing encodings of version control bits for memory corruption detection

A processor configured to synchronize threads in multithreaded applications. The processor includes first and second registers. The processor stores a first bitmask in the first register and a second bitmask in the second register. For each bitmask, each bit corresponds with one of multiple threads. A given bit in the first bitmask indicates the corresponding thread has been assigned to execute a portion of a unit of work. A corresponding bit in the second bitmask indicates the corresponding thread has completed execution of its assigned portion of the unit of work. The processor receives updates to the second bitmask in the second register and provides an indication that the unit of work has been completed in response to detecting that for each bit in the first bitmask that corresponds to a thread that is assigned work, a corresponding bit in the second bitmask indicates its corresponding thread has completed its assigned work.

Using hardware support to reduce synchronization costs in multithreaded applications

A method and apparatus for executing multithreaded algorithm to provide static timing analysis of a chip design includes analyzing a chip design to identify various components and nodes associated with the components. A node tree is built with a plurality of nodes. The node tree identifies groups of nodes that are available in different levels. A size of node grouping for a current level is determined by looking up the node tree. Testing data for parallel processing of different size of node groupings using varied thread counts is compiled. An optimum thread count for the current level based on the size of node grouping in the node tree is identified from compiled testing data. Dynamic parallel processing of nodes in the current level is performed using the number of threads identified by the optimum thread count. An acceptable design of the chip is determined by the dynamic parallel processing.

Multithreaded static timing analysis

One embodiment of the present invention provides a system for using register readiness to facilitate value prediction. The system starts by loading a previously computed result for a function to a destination register for the function from a lookup table. The system then checks the destination register for the function by using a Branch-Register-Not-Ready (BRNR) instruction to check the readiness of the destination register. If the destination register is ready, the system uses the previously computed result in the destination register as the result of the function. Loading the value from the lookup table in this way avoids unnecessarily calculating the result of the function when that result has previously been computed.

Using register readiness to facilitate value prediction

A method is provided for obtaining data to be used in evaluating performance of a computer processor. More specifically, the method provides for efficiently obtaining traces from an application program for use in a simulation of a computer processor. The method uses both an original code defining the application program and an instrumented version of the original code ('instrumented code'). The method includes apportioning a total time of execution of the application program between the original code and the instrumented code. Transition of execution between the original and instrumented codes is conducted through either modification of function calls or through consultation with a mapping of instruction address correspondences between the original and instrumented codes.

Growing community of inventors

Sunnyvale, CA, United States of America

Darryl J Gove