Qualcomm Incorporated

Intel Corporation

Peter Sassone

Suresh Kumar Venkumahanti

Lucian Codrescu

Christopher E Koob

Youfeng Wu

Mauricio Breternitz, Jr

Bryan P Black

Dana Michelle Vantrease

Jeffrey P Rupley, Ii

Balaji Vijayan

Sanjay Bhagawan Patil

James Mason

Ankit Ghiya

Suman Mamidi

Aashish Phansalkar

Wesley Attrot

Very long instruction word (VLIW) instruction processing using a reduced-width processor is disclosed. In a particular embodiment, a VLIW processor includes a control circuit configured to receive a VLIW packet that includes a first number of instructions and to distribute the instructions to a second number of instruction execution paths. The first number is greater than the second number. The VLIW processor also includes physical registers configured to store results of executing the instructions and a register renaming circuit that is coupled to the control circuit.

System and method of VLIW instruction processing using reduced-width VLIW processor

Embodiments disclosed in the detailed description include hybrid write-through/write-back cache policy managers, and related systems and methods. A cache write policy manager is configured to determine whether at least two caches among a plurality of parallel caches are active. If all of one or more other caches are not active, the cache write policy manager is configured to instruct an active cache among the parallel caches to apply a write-hack cache policy. In this manner, the cache write policy manager may conserve power and/or increase performance of a singly active processor core. If any of the one or more other caches are active, the cache write policy manager is configured to instruct an active cache among the parallel caches to apply a write-through cache policy. In this manner, the cache write policy manager facilitates data coherency among the parallel caches when multiple processor cores are active.

Hybrid write-through/write-back cache policy managers, and related systems and methods

A method includes identifying, at a scheduling unit, a resource conflict at a shared processing resource that is accessible by a first processing cluster and by a second processing cluster, where the first processing cluster, the second processing cluster, and the shared processing resource are included in a very long instruction word (VLIW) processing unit. The method also includes resolving the resource conflict.

Multiple clustered very long instruction word processing core

Latency-based power mode units for controlling power modes of processor cores, and related methods and systems are disclosed. In one aspect, the power mode units are configured to reduce power provided to the processor core when the processor core has one or more threads in pending status and no threads in active status. An operand of an instruction being processed by a thread may be data in memory located outside processor core. If the processor core does not require as much power to operate while a thread waits for a request from outside the processor core, the power consumed by the processor core can be reduced during these waiting periods. Power can be conserved in the processor core even when threads are being processed if the only threads being processed are in pending status, and can reduce the overall power consumption in the processor core and its corresponding CPU.

Latency-based power mode units for controlling power modes of processor cores, and related methods and systems

In a particular embodiment, a method includes identifying one or more way prediction characteristics of an instruction. The method also includes selectively reading, based on identification of the one or more way prediction characteristics, a table to identify an entry of the table associated with the instruction that identifies a way of a data cache. The method further includes making a prediction whether a next access of the data cache based on the instruction will access the way.

Data cache way prediction

In a particular embodiment, an apparatus includes control logic configured to selectively set bits of a multi-bit way prediction mask based on a prediction mask value. The control logic is associated with an instruction cache including a data array. A subset of line drivers of the data array is enabled responsive to the multi-bit way prediction mask. The subset of line drivers includes multiple line drivers.

Instruction cache having a multi-bit way prediction mask

A system, processor, and method to predict with high accuracy and retain instruction boundaries for previously executed instructions in order to decode variable length instructions is disclosed. In at least one embodiment, a disclosed processor includes an instruction fetch unit, an instruction cache, a boundary byte predictor, and an instruction decoder. In some embodiments, the instruction fetch unit provides an instruction address and the instruction cache produces an instruction tag and instruction cache content corresponding to the instruction address. The instruction decoder, in some embodiments, includes boundary byte logic to determine an instruction boundary in the instruction cache content.

Instruction boundary prediction for variable length instruction set

Implementation of a Bloom filter using multiple single-ported memory slices. A control value is combined with a hashed address value such that the resultant address value has the property that one, and only one, of the k memories or slices is selected for a given input value, a, for each bank. Collisions are thereby avoided and the multiple hash accesses for a given input value, a, may be performed concurrently. Other embodiments are also described and claimed.

Growing community of inventors

Austin, TX, United States of America

Peter Sassone