Intel Corporation

Peter J Smith

Subramaniam M Maiyuran

Satish K Damaraju

Harikrishna B Baliga

Joydeep Ray

Stephan Jourdan

Niranjan L Cooray

Bharat S Pillilli

Ilhyun Kim

Shlomi Alkalay

Mongkol Ekpanyapong

Truyen Trinh

Parag Raval

Navin Monteiro

Asim Nisar

Michael S Yu

Clock signal generation circuitry. A frequency multiplier is coupled to receive a clock signal and to generate a frequency-multiplied clock signal. A switching circuit is coupled to receive at least two reference clock signals. The switching circuit provides one of the reference clock signals in response to a reference select signal. A phase locked loop (PLL) is coupled to receive the frequency-multiplied clock signal and the selected reference clock signal. The PLL generates an output clock signal.

Frequency selection granularity for integrated circuits

An apparatus and method for converting between a full memory address and a compressed memory address. For example, one embodiment comprises one or more translation tables having a plurality of translation entries, each translation entry identifiable with a pointer value and storing a portion of a full memory address usable within the processor to address data and instructions; and address translation logic to use the translation tables to convert between the full address and a compressed version of the full address, the compressed version of the full address having the pointer value substituted for the portion of the full memory address, wherein a first portion of the processor performs operations using the compressed version of the full address and a second portion of the processor performs operations using the full address.

Apparatus and method for compressing a memory address

Techniques for controlling alignment of conditions between modular functional blocks in an integrated circuit having a hierarchical network of modular functional blocks. The output of each functional block can be logically determined by its external inputs combined with internal state feedback and internal state and is derived from a pattern of prior external inputs. Alignment of output conditions from independent and interdependent functional blocks within the hierarchical network of functional blocks is induced to provide unique conditions by modifying internal state and timing alignments with internal data and internal controls within one or more of the modular functional blocks. Functional outputs from one or more of the modular functional blocks can be monitored based on the modified internal state and timing alignments. Pattern results can be generated based on the monitoring. Test results based on the pattern results can be stored.

Alignment of microarchitectural conditions

A method and apparatus for tracking temporal use associated with cache evictions to reduce allocations in a victim cache is disclosed. Access data for a number of sets of instructions in an instruction cache is tracked at least until the data for one or more of the sets reach a predetermined threshold condition. Determinations whether to allocate entry storage in the victim cache may be made responsive in part to the access data for sets reaching the predetermined threshold condition. A micro-operation can be inserted into the execution pipeline in part to synchronize the access data for all the sets. Upon retirement of the micro-operation from the execution pipeline, access data for the sets can be synchronized and/or any previously allocated entry storage in the victim cache can be invalidated.

Tracking temporal use associated with cache evictions

The number of ways in an N-way set associative sequential cache is modulated to trade power and performance. Way selection is restricted during the allocation based on address so that only a subset of the N-ways is used for a range of addresses allowing the N-ways that are not in use to be powered off.

Power-performance modulation in caches using a smart least recently used scheme

In one embodiment, the present invention includes a cache memory, which may be a sequential cache, having multiple banks. Each of the banks includes a data array, a decoder coupled to the data array to select a set of the data array, and a sense amplifier. Only a bank to be accessed may be powered, and in some embodiments early way information may be used to maintain remaining banks in a power reduced state. In some embodiments, clock gating may be used to maintain various components of the cache memory in a power reduced state. Other embodiments are described and claimed.

Reducing power consumption in a sequential cache

A high-speed memory management technique that minimizes clobber in sequentially accessed memory, including but not limited to, for example, a trace cache. The method includes selecting a victim set from a sequentially accessed memory; selecting a victim way for the selected victim set; reading a next way pointer from a trace line of a trace currently stored in the selected victim way, if the selected victim way has the next way pointer; and writing a next line of the new trace into the selected victim way over the trace line of the currently stored trace. The method also includes forcing a replacement algorithm of next set to select a victim way of the next set using the next way pointer, if the trace line of the currently stored trace is not an active trace tail line.

Look ahead LRU array update scheme to minimize clobber in sequentially accessed memory

A method and apparatus for a loop predictor for predicting the end of a loop is disclosed. In one embodiment, the loop predictor may have a predict counter to hold a predict count representing the expected number of times that a predictor stew value will repeat during the execution of a given loop. The loop predictor may also have one or more running counters to hold a count of the times that the stew value has repeated during the execution of the present loop. When the counter values match the predictor may issue a prediction that the loop will end.

Method and apparatus for a stew-based loop predictor

A method and apparatus for a trace end predictor for a trace cache is disclosed. In one embodiment, the trace end predictor may have one or more buffers to contain a head address for a subsequent trace. The head address may include the way number and set number of the next head, along with partial stew data to support additional execution predictors. The buffers may also include tag data of the current trace's tail address, and may additionally include control bits for determining whether to replace the buffer's contents with information from another trace's tail. Reading the next head address from the trace end predictor, as opposed to reading it from the trace cache array, may reduce certain execution time delays.

Growing community of inventors

Folsom, CA, United States of America

Peter J Smith