International Business Machines Corporation

David Arnold Luick

Philip Braun Winterfield

Adam James Muff

Eric Oliver Mejdrich

Michael K Gschwind

Erik Richter Altman

John Christopher Willis

Dung Q Nguyen

Hung Qui Le

Richard James Eickemeyer

Sumedh Wasudeo Sathaye

Jude A Rivers

Jeffrey Douglas Brown

John-David Wellman

Daniel Arthur Prener

Steven R Kunkel

Kemal Ebcioglu

Kenneth J Kiefer

Gabriel Mauricio Silberman

Giora Biran

Clarence Rosser Ogilvie

William Paul Hovis

Mark Owen Maxson

Anthony Gus Aipperspach

Susan Elizabeth Eisen

Brian William Curran

Brian R Konigsburg

Jamie Randall Kuesel

Kent Harold Haselhorst

James Anthony Marcella

Robert Allen Drehmel

David Michael Friend

Neil Clair Berglund

Jaime Humberto Moreno

Charles S Woodruff

Nghia Van Phan

Jeffrey Powers Bradford

Ming-i Mark Lin

Charles A Lemaire

Mark E Kautzman

Mahmut K Ebcioglu

Thomas J Beacom

Steven Wayne Kerchberger

Matthew Adam Cushing

Allen James Gavin

A design structure embodied in a machine readable storage medium for designing, manufacturing, and/or testing a design for minimizing unscheduled D-cache miss pipeline stalls is provided. The design structure includes an integrated circuit device, which includes a cascaded delayed execution pipeline unit having two or more execution pipelines that begin execution of instructions in a common issue group in a delayed manner relative to each other, and circuitry. The circuitry is configured to receive an issue group of instructions, determine whether the issue group is a load instruction, and if so, schedule the load instruction in a first pipeline of the two or more execution pipelines, and schedule each remaining instruction in the issue group to be executed in remaining pipelines of the two or more pipelines, wherein execution of the load instruction in the first pipeline begins prior to beginning execution of the remaining instructions in the remaining pipelines.

Scheduling instructions in a cascaded delayed execution pipeline to minimize pipeline stalls caused by a cache miss

Improved techniques for executing instructions in a pipelined manner that may reduce stalls that occur when executing dependent instructions are provided. Stalls may be reduced by utilizing a cascaded arrangement of pipelines with execution units that are delayed with respect to each other. This cascaded delayed arrangement allows dependent instructions to be issued within a common issue group by scheduling them for execution in different pipelines to execute at different times.

Cascaded delayed float/vector execution pipeline

A method of providing history based done logic includes receiving a cache line in a L2 cache; determining if the cache line has a history of access at least three times on a previous call into the L2 cache; providing the cache line directly to a processor if the history of access was less then the at least three times; and loading the cache line into an L1 cache if the history of access was the at least three times.

Cache line use history based done bit modification to D-cache replacement scheme

A method of providing history based done logic for instructions includes receiving an instruction in a cache line in a L2 cache; and loading the cache line into an L1 cache with a history count that indicates the number of read references of the previous access.

Cache line use history based done bit modification to I-cache replacement scheme

A method and apparatus for executing branch instructions is provided. In one embodiment, the method includes receiving a branch instruction, wherein a first path of the branch instruction branches to a target instruction, and wherein a second path of the branch instruction branches to one or more interceding instructions between the branch instruction and the target instruction. The method further includes issuing the one or more interceding instructions and the target instruction and determining if the branch instruction follows the first path or the second path. Upon determining that the branch instruction follows the first path, the one or more interceding instructions between the branch instruction and the target instruction are invalidated.

Predicated issue for conditional branch instructions

A method of providing history based done logic for a D-cache includes receiving a D-cache line in an L2 cache; determining if the D-cache line is unprefetchable; aging the D-cache line without a delay if the D-cache line is prefetchable; and aging the D-cache line with a delay if the D-cache line is unprefetchable.

D-cache line use history based done bit based on successful prefetchable counter

Embodiments of the invention are generally related to image processing, and more specifically to vector units for supporting image processing. A combined vector/scalar unit is provided wherein one or more processing lanes of the vector unit are used for performing scalar operations. An integrated register file is also provided for storing vector and scalar data. Therefore, the transfer of data to memory to exchange data between independent vector and scalar units is obviated and a significant amount of chip area is saved.

Scalar precision float implementation on the 'W' lane of vector unit

Embodiments of the invention provide logic within the store data path between a processor and a memory array. The logic may be configured to misalign vector data as it is stored to memory. By misaligning vector data as it is stored to memory, memory bandwidth may be maximized while processing bandwidth required to store vector data misaligned is minimized. Furthermore, embodiments of the invention provide logic within the load data path which allows vector data which is stored misaligned to be aligned as it is loaded into a vector register. By aligning misaligned vector data as it is loaded into a vector register, memory bandwidth may be maximized while processing bandwidth required to align misaligned vector data may be minimized.

Store misaligned vector with permute

A method of providing history based done logic for a I-cache includes receiving an I-cache line in an L2 cache; determining if the I-cache line is unprefetchable; aging the I-cache line without a delay if the I-cache line is prefetchable; and aging the I-cache line with a delay is the I-cache line is unprefetchable.

I-cache line use history based done bit based on successful prefetchable counter

A processor includes primary threads of execution that may simultaneously issue instructions, and one or more backup threads. When a primary thread stalls, the contents of its instruction buffer may be switched with the instruction buffer for a backup thread, thereby allowing the backup thread to begin execution. This design allows two primary threads to issue simultaneously, which allows for overlap of instruction pipeline latencies. This design further allows a fast switch to a backup thread when a primary thread stalls, thereby providing significantly improved throughput in executing instructions by the processor.

Multithreaded processor and method for switching threads by swapping instructions between buffers while pausing execution

One embodiment of the invention provides a processor. The processor generally includes a first and second processor core, each having a plurality of pipelined execution units for executing an issue group of multiple instructions and scheduling logic configured to issue a first issue group of instructions to the first processor core for execution and a second issue group of instructions to the second processor core for execution when the processor is in a first mode of operation and configured to issue one or more vector instructions for concurrent execution on the first and second processor cores when the processor is in a second mode of operation.

Vector morphing mechanism for multiple processor cores

The present invention provides system and method for a group priority issue schema for a cascaded pipeline. The system includes a cascaded delayed execution pipeline unit having a plurality of execution pipelines that execute instructions in a common issue group in a delayed manner relative to each other. The system further includes circuitry configured to receiving an issue group of instructions, reordering the issue group of instructions using instruction type priority, and executing the reordered issue group of instructions in the cascaded delayed execution pipeline unit. The method, among others, can be broadly summarized by the following steps: receiving an issue group of instructions, reordering the issue group of instructions using instruction type priority, and executing the reordered issue group of instructions in the cascaded delayed execution pipeline unit.

System and method for a group priority issue schema for a cascaded pipeline

The present invention provides system and method for a group priority issue schema for a cascaded pipeline. The system includes a cascaded delayed execution pipeline unit having a plurality of execution pipelines that execute instructions in a common issue group in a delayed manner relative to each other. The system further includes circuitry configured to: (1) receive an issue group of instructions; (2) determine if a plurality of load instructions are in the issue group, if so, schedule the plurality of load instructions in descending order of longest dependency chain depth to shortest dependency chain depth in a shortest to longest available execution pipelines; and (3) execute the issue group of instructions in the cascaded delayed execution pipeline unit.

System and method for optimization within a group priority issue schema for a cascaded pipeline

Embodiments of the invention provide a look-aside-look-aside buffer (LLB) configured to retain a portion of the real addresses in a translation look-aside (TLB) buffer to allow prefetching of data from a cache. A subset of real address bits associated with an effective address may be retrieved relatively quickly from the LLB, thereby allowing access to the cache before the complete address translation is available and reducing cache access latency.

3-dimensional L2/L3 cache array to hide translation (TLB) delays

Growing community of inventors

Rochester, MN, United States of America

David Arnold Luick