Advanced Micro Devices Corporation

Douglas R Williams

Marius Evers

Ashok Tirupathy Venkatachar

Vydhyanathan Kalyanasundharam

Debjit Das Sarma

Ronny Lee Arnold

Nikhil Gupta

David Jonathan Chalk

Wei-Yu Chen

Michael K Fertig

Donald A Priore

Edward Chang

Paul L Rogers

Sudherssen Kalaiselvan

Arunachalam Annamalai

Josef A Dvorak

Dhanaraj Bapurao Tavare

Sahil Arora

Mahadev S Deshpande

A branch predictor predicts a first outcome of a first branch in a first block of instructions. Fetch logic fetches instructions for speculative execution along a first path indicated by the first outcome. Information representing a remainder of the first block is stored in response to the first predicted outcome being taken. In response to the first branch instruction being not taken, the branch predictor is restarted based on the remainder block. In some cases, entries corresponding to second blocks along speculative paths from the first block are accessed using an address of the first block as an index into a branch prediction structure. Outcomes of branch instructions in the second blocks are concurrently predicted using a corresponding set of instances of branch conditional logic and the predicted outcomes are used in combination with the remainder block to restart the branch predictor in response to mispredictions.

Storing incidental branch predictions to reduce latency of misprediction recovery

The techniques described herein provide an instruction fetch and decode unit having an operation cache with low latency in switching between fetching decoded operations from the operation cache and fetching and decoding instructions using a decode unit. This low latency is accomplished through a synchronization mechanism that allows work to flow through both the operation cache path and the instruction cache path until that work is stopped due to needing to wait on output from the opposite path. The existence of decoupling buffers in the operation cache path and the instruction cache path allows work to be held until that work is cleared to proceed. Other improvements, such as a specially configured operation cache tag array that allows for detection of multiple hits in a single cycle, also improve latency by, for example, improving the speed at which entries are consumed from a prediction queue that stores predicted address blocks.

Low latency synchronization for operation cache and instruction cache fetching and decoding instructions

A processor, a device, and a non-transitory computer readable medium for performing branch prediction in a processor are presented. The processor includes a front end unit. The front end unit includes a level 1 branch target buffer (BTB), a BTB index predictor (BIP), and a level 1 hash perceptron (HP). The BTB is configured to predict a target address. The BIP is configured to generate a prediction based on a program counter and a global history, wherein the prediction includes a speculative partial target address, a global history value, a global history shift value, and a way prediction. The HP is configured to predict whether a branch instruction is taken or not taken.

Bandwidth increase in branch prediction unit and level 1 instruction cache

A processor uses a token scheme to govern the maximum number of memory access requests each of a set of processor cores can have pending at a northbridge of the processor. To implement the scheme, the northbridge issues a minimum number of tokens to each of the processor cores and keeps a number of tokens in reserve. In response to determining that a given processor core is generating a high level of memory access activity the northbridge issues some of the reserve tokens to the processor core. The processor core returns the reserve tokens to the northbridge in response to determining that it is not likely to continue to generate the high number of memory access requests, so that the reserve tokens are available to issue to another processor core.

Resource management for northbridge using tokens

A multiplexer (MUX) circuit with balanced select line loading is provided. The MUX circuit includes a plurality of 2:1 MUX units coupled together in a multistage cascading arrangement, along with a selection module coupled to the MUX units. The MUX units are arranged in an initial MUX stage, at least one intermediate MUX stage coupled to and following the initial MUX stage, and a final MUX stage coupled to and following the at least one intermediate MUX stage. Each MUX unit is controlled with a respective select bit input value provided by the selection module. The selection module controls the operation of the MUX units in the initial MUX stage with a first plurality of different select bits, controls the operation of the MUX units in the at least one intermediate MUX stage with a second plurality of different select bits, and controls the operation of the final MUX stage with a devoted select bit.

Multiplexer circuit with load balanced fanout characteristics

A first address is received and is used to determine a first address range. The first address range includes a second address range and a third address range. If the first address is in the second address range, a fourth address range is determined. The fourth address range is different from the first address range. Information is retrieved from a memory in response to determining that a second address is in the first address range or the fourth address range. If the first address is in the third address range, a fifth address range is determined. The fifth address range is different from the first address range. Other information is retrieved from the memory in response to determining the second address is in the first address range or the fifth address range.

Hybrid region CAM for region prefetcher and methods thereof

Growing community of inventors

Mountain View, CA, United States of America

Douglas R Williams