Sun Microsystems, Inc.

Intel Corporation

Samsung Electronics Co., Ltd.

Ramesh K Panwar

Ricky C Hetherington

Adam R Talcott

Dani Y Dakhil

Sanjay Patel

Sharad Mehrotra

Rajasekhar Cherabuddi

Arjun Prabhu

Joseph I Chamdani

Robert G Hathaway

Ralph Portillo

Naveen Krishnamurthy

Pk Chidambaran

A method and apparatus for performing multiple branch predictions per cycle is disclosed. The method and apparatus according to the present invention determine, within one fetch cycle, which instructions in a plurality of fetch instructions are branches and whether such branches are taken or not taken thereby finding the oldest taken branch, which has a target address that is fetched within the same fetch cycle.

Method and apparatus for performing multiple branch predictions per cycle

A method for repairing a pipeline in response to a branch instruction having a branch, includes the steps of providing a branch repair table having a plurality of entries, allocating an entry in the branch repair table for the branch instruction, storing a target address, a fall-through address, and repair information in the entry in the branch repair table, processing the branch instruction to determine whether the branch was taken, and repairing the pipeline in response to the repair information and the fall-through address in the entry in the branch repair table when the branch was not taken.

Method and apparatus for resolving multiple branches

Two-way set associative data is stored in a cache memory array. An odd set data bank stores odd number sets of the two-way set associative data, where the two ways of each odd number set are aligned horizontally within the odd set data bank. An even set data bank stores even number sets of the two-way set associative data, where the two ways of each even number set are aligned horizontally within the even set data bank. Also, the odd set data bank is aligned horizontally with the even set data bank such that each odd number set is aligned horizontally with a next even number set. The horizontally aligned ways are interleaved for data path width reduction. Set and way selection circuits extract lines of data from the array. The array may be structurally implemented by single-ported RAM cells.

Method for storing data in two-way set associative odd and even banks of a cache memory

A method and apparatus for dynamically reconfiguring a processor involves placing the processor in a first configuration having a first number (m) of strands while the coded instructions comprise instructions from a number (m) threads. The instructions in each of the m threads are executed on one of the m strands using execution resources at least some of which are shared among the m strands. While the coded instructions comprise instructions from a number (n) threads, the processor is placed in a second configuration having a second number (n) of strands. The instruction are executed in each of the n strands using execution resources at least some of which are shared among the n strands.

Apparatus for dynamically reconfiguring a processor

A processor including at least one execution unit generating out-of-order results and out-of-order condition codes. Precise architectural state of the processor is maintained by providing a results buffer having a number of slots and providing a condition code buffer having the same number of slots as the results buffer, each slot in the condition code buffer in one-to-one correspondence with a slot in the results buffer. Each live instruction in the processor is assigned a slot in the results buffer and the condition code buffer. Each speculative result produced by the execution units is stored in the assigned slot in the results buffer. When an instruction is retired, the results for that instruction are transferred to an architectural result register and any condition codes generated by that instruction are transferred to an architectural condition code register.

Apparatus for generating out-of-order results and out-of-order condition codes in a processor

A system and method for thermal overload detection and protection for a processor which allows the processor to run at near maximum potential for the vast majority of its execution life. This is effectuated by the provision of circuitry to detect when the processor has exceeded its thermal thresholds and which then causes the processor to automatically reduce the clock rate to a fraction of the nominal clock while execution continues. When the thermal condition has stabilized, the clock may be raised in a stepwise fashion back to the nominal clock rate. Throughout the period of cycling the clock frequency from nominal to minimum and back, the program continues to be executed. Also provided is a queue activity rise time detector and method to control the rate of acceleration of a functional unit from idle to full throttle by a localized stall mechanism at the boundary of each stage in the pipe. This mechanism can detect when an idle queue is suddenly overwhelmed with input such that over a short period of approximately 10-20 machine cycles, the queue activity rate has increased from idle to near stall threshold.

Method and apparatus for moderating current demand in an integrated circuit processor

A data cache unit associated with a processor, the data cache unit including a first non-blocking cache receiving a data access from a device in the processor. A second non-blocking cache is coupled to the first non-blocking cache to service misses in the first non-blocking cache. A data return path coupled to the second non-blocking cache couples data returning from the second non-blocking cache to both the first non-blocking cache and the device generating the access to the first non-blocking cache.

Method for inhibiting thrashing in a multi-level non-blocking cache

Multi-level non-blocking cache system with inhibiting thrashing

An apparatus for tracking pipeline resources of a processor involves fetching selected ones of the coded instructions and marking the fetched instructions with instruction metadata. The instruction metadata indicates a number of pipeline resources required by each instruction. The marked instructions are issued from the fetch unit and, using the instruction metadata, a count of a number of resources committed to issued instructions in the execution pipelines is maintained. When it is determined that the number of resources committed to issued instructions exceeds a preselected maximum and instructions are prevented from issuing from the fetch unit. As each instruction is retired, the instruction metadata is used to determine a number of resources released by retirement of the issued instruction.

Pipeline processor and computing system including an apparatus for

A first embodiment provides an apparatus including a first execution unit capable of executing a first type and a second type of ready instruction, a second execution unit capable of executing the second type of ready instruction, and a scheduler. The scheduler dispatches the instructions in waves and dispatches the first type of ready instruction to the first execution unit with a higher priority than the second type of ready instruction. The scheduler is capable of dispatching a second type of ready instruction to the second execution unit. A second embodiment provides a method of dispatching instructions in a processor having a scheduler, a first execution unit, and a second execution unit is provided. The method includes dispatching a first type of ready instruction to the first execution unit with a higher priority than dispatching a second type of ready instruction to the first execution unit in each wave. The method includes dispatching the second type of instruction to the second execution unit, the two steps of dispatching being performed in a wave.

Method and apparatus for dispatching instructions to execution units in

In a processor that executes complex instructions which are expanded into microinstructions prior to execution, non-complex instruction execution is optimized by providing a by-passable helper logic for expanding complex instructions into microinstructions. Control logic parses a bundle of instructions into sub-bundles of non-complex instructions and sub-bundles of microinstructions. The control logic detects when a complex instruction is present in a bundle of instructions and directs the complex instruction to the helper logic for expansion into two or more microinstructions. Each non-complex instruction bypasses the helper logic, thereby improving the execution performance of the non-complex instruction.

Fetching and handling a bundle of instructions comprising instructions

In an out-of-order processor having single-precision floating-point registers aliased into double-precision floating-point registers, a single-precision floating-point arithmetic operation having four possible register dependencies is converted into two microinstructions which are processed normally within the processor. The first microinstruction is coded to perform the arithmetic operation specified by the single-precision instruction using the first and second source registers specified and storing the result in a phantom register. The second microinstruction is coded for merging the contents of the phantom register and the destination register specified. Each microinstruction has at most two possible register dependencies, thereby reducing the total number of register dependencies which the processor is required to track.

Reducing data dependent conflicts by converting single precision

Apparatus for precise architectural update in an out-of-order processor

A data cache unit associated with a processor, the data cache unit including a multi-ported non-blocking cache receiving a data access request from a lower level device in the processor. A memory scheduling window includes at least one row of entries, wherein each entry includes an address field holding an address of the access request. A conflict map field within at least some of the entries is coupled to a conflict checking unit. The conflict checking unit responds to the address fields by setting bits in the conflict map fields to indicate intra-row conflicts between entries. A picker coupled to the memory scheduling window responds to the conflict map fields so as to identify groups of non-conflicting entries to launch in parallel at the multi-ported non-blocking cache.

In-line bank conflict detection and resolution in a multi-ported

A system and method for efficient implementation of a multi-port logic first-in, first-out ('FIFO') structure or particular utility in high clock speed integrated circuit ('IC') processor design which provides for reduced on-chip area requirements and fewer and less timing critical electrical interconnect paths. The advantageous reduction in IC area and enhanced performance disclosed herein is enabled through the rotation of the inputs and outputs of the FIFO; maintenance of decoded head and tail pointers, and folding the FIFO entry locations such that the entries are arranged in an interleaved fashion.

Growing community of inventors

Santa Clara, CA, United States of America

Ramesh K Panwar