International Business Machines Corporation

Globalfoundries Inc.

Robert Dov Herzl

David W Milton

Clarence Rosser Ogilvie

Tad Jeffrey Wilder

Paul Mark Schanely

Kenneth Anthony Lauricella

Christopher Douglas Hanudel

Margaret R Charlebois

Robert J Devins

Bartholomew Blaner

Robert Spencer Horton

Jay Gerald Heaslip

Charles B Winn

Nitin Sharma

Jody B Joyner

David Andrew Schroter

Arnold S Tran

Paul G Ferro

Joseph L Temple, Iii

Kenneth A Mahler

Rashmi D Chatty

Linda L Quinn

Matthew P Szafir

Jeffrey A Stuecheli

Brian Mitchell Bass

Brian William Curran

Charles David Wait

Jon K Kriegel

Benjamin Herrenschmidt

Ross Boyd Leavens

Thomas B Chadwick, Jr

Douglas P Nadeau

Mark E Kautzman

Allan Rowe Steel

Henry Harvey Burkhart

Joseph M D'Onofrio

Richard N Fuqua

Louis J Milich

Paul M Moore

Russell E Schroter

A method, computer program product, and a computer system are disclosed for processing information in a processor that in one or more embodiments includes receiving a request for an Effective Address to Real Address Translation (ERAT); determining whether there is a permissions miss; changing, in response to determining there is a permission miss, permissions of an ERAT cache entry; and providing a Real Address translation. The method, computer program product, and computer system may optionally include providing a promote checkout request to a memory management unit (MMU).

Promotion of ERAT cache entries

A method, computer program product, and a computer system are disclosed for processing information in a processor that in one or more embodiments includes setting a threshold number of free Effective to Real Address Translation (ERAT) cache entries in an ERAT cache; determining whether a total number of free ERAT cache entries is less than or equal to the threshold number of free ERAT cache entries; allocating, in response to determining that the total number of free entries is less than or equal to the threshold number, one or more active ERAT cache entries to be speculatively checked in to a memory management unit (MMU); and speculatively checking in the one or more active ERAT cache entries to the MMU.

Speculative checkin of ERAT cache entries

A technique for operating a memory management unit (MMU) of a processor includes the MMU detecting that one or more address translation invalidation requests are indicated for an accelerator unit (AU). In response to detecting that the invalidation requests are indicated, the MMU issues a raise barrier request for the AU. In response to detecting a raise barrier response from the AU to the raise barrier request the MMU issues the invalidation requests to the AU. In response to detecting an address translation invalidation response from the AU to each of the invalidation requests, the MMU issues a lower barrier request to the AU. In response to detecting a lower barrier response from the AU to the lower barrier request, the MMU resumes handling address translation check-in and check-out requests received from the AU.

Maintaining consistency between address translations in a data processing system

Embodiments of the invention provide a method, system, and program product for predicting a delay of a critical path. In one embodiment, the invention provides a method of predicting a delay of at least one critical path of an integrated circuit, the method comprising: determining a delay of at least one ring oscillator on the integrated circuit; and calculating a predicted delay for the at least one critical path delay based on a delay of components of the critical path at a corner condition, a wire delay of the at least one critical path, a delay of the at least one ring oscillator at a corner condition, and the determined delay of the at least one ring oscillator.

Critical path delay prediction

Disclosed are a chip performance monitoring system, method and a computer program product, wherein a performance monitor output signal is propagated through an adjacent scan chain to avoid signal degradation incident to across-chip transmission of high frequency signals. Since the clock signal frequency used to control signal propagation through the scan chain will typically be less than twice the performance monitor output signal frequency, frequency sub-sampling with aliasing occurs. To compensate, signal propagation through the scan chain can be controlled during different time periods using different clock signals having different clock signal frequencies and, during these different time periods, different data outputs can be captured at an output node of the scan chain. The data output frequencies of these different data outputs can be measured and the performance monitor output signal frequency can be determined based on the different data output frequencies given the different clock signal frequencies.

Chip performance monitoring system and method

A system and method of terminating processing requests dispatched to a coprocessor hardware accelerator in a multi-processor computer system based on matching various fields in the request made to the coprocessor to identify the process to be terminated. A kill command is initiated by a write operation to a coprocessor block kill register and has match enable and value for each field in the coprocessor request to be terminated. Enabled fields may have one or more values associated with a single request or multiple requests for the same coprocessor. At least one match enable must be set to initiate a kill request. A process kill active signal prevents other coprocessor jobs from moving between operational stages in the coprocessor hardware accelerator. Processing jobs that are idle or do not match the fields with match enables set signal done with no match and continue processing. Processing jobs that do match the fields with match enables set are terminated and signal done with match. When all processing jobs have signaled done, a done bit is set in the coprocessor block kill register to indicate completion of the kill to the initiating software. The register also holds the match status of each processing job.

Termination of requests in a distributed coprocessor system

Aspects of the invention provide for a flexible performance screen ring oscillator (PSRO) integrated within a scan chain. In one embodiment, a circuit structure to create the flexible PSRO includes: a plurality of programmable scan chain elements; and a forward test scan chain path through the plurality of scan chain elements; wherein each of the programmable scan chain elements includes additional circuitry for a backward path, such that the backward path and the forward test scan chain path are combined to create the PSRO.

Flexible performance screen ring oscillator within a scan chain

A performance screen ring oscillator (PSRO) formed from paired scan chains is disclosed. A circuit structure comprises scan chains each having scan chain elements. A scan chain link is configured to pair at least one scan chain element from a first scan chain with at least one scan chain element of a second scan chain to form a PSRO. A forward path associated with data flow through the at least one scan chain element of the first scan chain becomes a backward path of the at least one scan chain element of the second scan chain, and a forward path associated with data flow through the at least one scan chain element of the second scan chain becomes a backward path of the at least one scan chain element of the first scan chain.

Performance screen ring oscillator formed from paired scan chains

A performance screen ring oscillator (PSRO) is formed from multi-dimensional pairings of scan chains. In one embodiment, there is a multi-dimensional arrangement of scan chains in an integrated circuit. Each of the scan chains has interconnected scan chain elements that form a shift register to apply test patterns to inputs of combinational logic in the integrated circuit and read outputs from the combinational logic based on the inputted test patterns. A scan chain link links selected scan chain elements from the scan chains to form at least one PSRO loop within the multi-dimensional arrangement of the scan chains.

Performance screen ring oscillator formed from multi-dimensional pairings of scan chains

Aspects of the invention provide a circuit structure that automatically monitors a plurality of ring oscillators and dynamically selects the fastest or the slowest ring oscillator for feedback into the plurality of ring oscillators. In one embodiment, a circuit includes: a plurality of delay elements, each delay element associated with a ring oscillator; a first logic gate for receiving outputs of each of the delay elements; a second logic gate for receiving outputs of each of the delay elements; and a multiplexer for receiving an output of the first logic gate and an output of the second logic gate and choosing one of the outputs, wherein a selection for the multiplexer is based on an output of the multiplexer. To select the fastest ring oscillator, a second multiplexer is provided.

Ring oscillator

A cache for use in a central processing unit (CPU) of a computer includes a data array; a tag array configured to hold a list of addresses corresponding to each data entry held in the data array; a least recently used (LRU) array configured to hold data indicating least recently used data entries in the data array; a line fill buffer configured to receive data from an address in main memory that is located external to the cache in the event of a cache miss; and a shadow register associated with the line fill buffer, wherein the shadow register is configured to hold LRU data indicating a current state of the LRU array.

Shadow registers for least recently used data in cache

A method for designing an integrated circuit. A computer determines, for one or more paths in a circuit design, for a value of a design variable at which timing closure of the circuit design is achieved, an approximate slope of a function representing path delay as a function of the design variable. When the computer determines that one of the approximate slopes is not within a defined slope range, the computer determines an adjustment direction and an adjustment value based in part on the magnitude by which the slope is not within the defined slope range. The computer changes the circuit design of the path associated with the out-of-range slope, based in part on the adjustment direction and the adjustment value, so as to bring the slope within the defined slope range.

Circuit design using design variable function slope sensitivity

A method of forming and electrical structure. The method includes determining that a first semiconductor device requires an engineering change order (ECO). An additional structure layer required to implement the ECO is determined. A first insertion point location for inserting the additional structure layer within the first semiconductor device is selected. The first insertion point location is associated with a second insertion point location within a design for a second semiconductor device. The second semiconductor device is generated in accordance with the first ECO. The second semiconductor device comprises second structures. The second structures comprise same structures as first structures in the first semiconductor device. The second structures are formed in locations within the second semiconductor device that are associated with locations in the first semiconductor device comprising the first structures. The second semiconductor device comprises the additional structure layer located within the second insertion point location.

Semiconductor layer forming method and structure

A chip design methodology. The methodology includes identifying engineering changeable logic, and replacing the identified engineering changeable logic with flexible logic blocks (FLB).

Method for identifying and implementing flexible logic block logic for easy engineering changes

Growing community of inventors

South Burlington, VT, United States of America

Robert Dov Herzl