International Business Machines Corporation

Shih-Hsiung Stephen Tung

Dwain Alan Hicks

Bryan J Lloyd

Balaram Sinharoy

David Scott Ray

Hung Qui Le

Michael John Mayfield

Kin Shing Chan

Jonathan H Raymond

Dung Q Nguyen

George W Rohrbaugh, Iii

Harold Wade Cain, Iii

David Allen Hrusecky

Susan Elizabeth Eisen

Ronald Nick Kalla

Cathy May

William Elton Burky

Edward John Silha

David Andrew Schroter

Michael Thomas Vaden

Benjamin W Stolt

Barry Duane Williamson

Kevin Arthur Chiarot

Sundeep Chadha

Gregory William Alexander

Elizabeth A McGlone

Peichun Peter Liu

Bruce Joseph Ronchetti

Avijit Saha

Douglas Craig Bossen

Richard J Schmalz

Rajinder Paul Singh

Arnold S Tran

Peter Steven Lenk

Pei-Chun Peter Liu

Theodore J Schmitt

Juan Jose Arevalo

Manratha Rajasekharaiah Jaisimha

Pei Chun Liu

Operation of a multi-slice processor that includes a plurality of execution slices, a plurality of load/store slices, and one or more page walk caches, where operation includes: receiving, at a load/store slice, an instruction to be issued; determining, at the load/store slice, a process type indicating a source of the instruction to be a host process or a guest process; and determining, in accordance with an allocation policy and in dependence upon the process type, an allocation of an entry of the page walk cache, wherein the page walk cache comprises one or more entries for both host processes and guest processes.

Operation of a multi-slice processor implementing a unified page walk cache

Technical solutions are described for hazard detection of out-of-order execution of load and store instructions without using real addresses in a processing unit. An example includes an out-of-order load-store unit (LSU) for transferring data between memory and registers. The LSU detects a store-hit-load (SHL) in an out-of-order execution of instructions based only on effective addresses by: determining an effective address associated with a store instruction; determining whether a load instruction entry using said effective address is present in a load reorder queue; and indicating that a SHL has been detected based at least in part on determining that load instruction entry using said effective address is present in the load reorder queue. The LSU, in response to detecting the SHL, flushes instructions starting from a load instruction corresponding to the load instruction entry.

Hazard detection of out-of-order execution of load and store instructions in processors without using real addresses

Operation of a multi-slice processor that includes a plurality of execution slices, a plurality of load/store slices, and one or more translation caches, where operation includes: determining, at the load/store slice, a real address from a cache hit in the translation cache for an effective address for an instruction received at a load/store slice; determining, at the load/store slice, an error condition corresponding to an access of the real address; determining, at the load/store slice, a process type indicating a source of the instruction to be a guest process; and responsive to determining the error condition, initiating, in dependence upon the process type indicating a source of the instruction to be a guest process, an effective address translation corresponding to a cache miss in the translation cache for the effective address for the instruction.

Operation of a multi-slice processor implementing exception handling in a nested translation environment

Mechanisms are provided, in a processor, for executing instructions that are younger than a previously dispatched synchronization (sync) instruction is provided. An instruction sequencer unit of the processor dispatches a sync instruction. The sync instruction is sent to a nest of one or more devices outside of the processor. The instruction sequencer unit dispatches a subsequent instruction after dispatching the sync instruction. The dispatching of the subsequent instruction after dispatching the sync instruction is performed prior to receiving a sync acknowledgement response from the nest. The instruction sequencer unit performs a completion of the subsequent instruction based on whether completion of the subsequent instruction is dependent upon receiving the sync acknowledgement from the nest and completion of the sync instruction.

Speeding up younger store instruction execution after a sync instruction

Technical solutions are described for executing one or more out-of-order instructions by a processing unit. An example method includes executing, by a load-store unit (LSU), instructions from an out-of-order (OoO) window. The OoO execution includes determining an effective address being used by a load instruction from the OoO window. Further, the execution includes determining presence of the effective address in an effective address directory (EAD) by identifying an EAD entry in the EAD, the EAD entry maps the effective address with an index of a corresponding effective-real table (ERT) entry from an effective-real table (ERT). In response to the effective address being present in the EAD, the execution includes accessing the corresponding ERT entry of the effective address of the load instruction, the corresponding ERT entry including a real address for the effective address, and issuing the load instruction using the real address from the corresponding ERT entry.

Address translation for sending real address to memory subsystem in effective address based load-store unit

Flush avoidance in a load store unit including launching a load instruction targeting an effective address; encountering a set predict hit and an effective-to-real address translator (ERAT) miss for the effective address, wherein the set predict hit comprises a cache address of a cache entry; sending a data valid message for the load instruction to an instruction sequencing unit; and verifying the data valid message, wherein verifying the data valid message comprises: tracking the cache entry during an ERAT update; and upon completion of the ERAT update, encountering an ERAT hit for the effective address in response to relaunching the load instruction.

Flush avoidance in a load store unit

There is provided a method for detecting a conflict between a transaction and a TLB (Translation Lookaside Buffer) shootdown in a transactional memory in which a TLB shootdown operation message is received by a processor to invalidate at least one entry in a TLB of the processor corresponding to at least one page. The processor tracks pages touched by the transaction. The processor determines whether the received TLB shootdown operation message is associated with one of the touched pages. The processor aborts the transaction in response to determining that the received TLB shootdown operation message is associated with one of the touched pages.

Detection of conflicts between transactions and page shootdowns

There is provided a system and a computer program product for detecting a conflict between a transaction and a TLB (Translation Lookaside Buffer) shootdown in a transactional memory in which a TLB shootdown operation message is received by a processor to invalidate at least one entry in a TLB of the processor corresponding to at least one page. The processor tracks pages touched by the transaction. The processor determines whether the received TLB shootdown operation message is associated with one of the touched pages. The processor aborts the transaction in response to determining that the received TLB shootdown operation message is associated with one of the touched pages.

A load instruction that accesses data cache may be off natural alignment, which causes a cache line crossing to complete the access. The illustrative embodiments provide a mechanism for loading data across multiple cache lines without the need for an accumulation register or collection point for partial data access from a first cache line while waiting for a second cache line to be accessed. Because the accesses to separate cache lines are concatenated within the vector rename register without the need for an accumulator, an off-alignment load instruction is completely pipeline-able and flushable with no cleanup consequences.

Loading data to vector renamed register from across multiple cache lines

A method and processor for avoiding check stops in speculative accesses. An execution unit, e.g., load/store unit, may be coupled to a queue configured to store instructions. A register, coupled to the execution unit, may be configured to store a value corresponding to an address in physical memory. When the processor is operating in real mode, the execution unit may retrieve the value stored in the register. Upon the execution unit receiving a speculative instruction, e.g., speculative load instruction, from the queue, a determination may be made as to whether the address of the speculative instruction is at or below the retrieved value. If the address of the speculative instruction is at or below this value, then the execution unit may safely speculatively execute this instruction while avoiding a check stop since all the addresses at or below this value are known to exist in physical memory.

Mechanism for avoiding check stops in speculative accesses while operating in real mode

Growing community of inventors

Austin, TX, United States of America

Shih-Hsiung Stephen Tung