International Business Machines Corporation

Vivek Britto

Mohit Karve

George W Rohrbaugh, Iii

Brian William Thompto

Tharunachalam Pindicura

Shricharan Srivatsan

John Andrew Schumann

Aishwarya Dhandapani

Yan Xia

Bryan J Lloyd

Karen E Yokum

Bryant Cockcroft

David A Campbell

Debapriya Chatterjee

Edmund Joseph Gieske

Madhumitha Venkataraman

A method for performing automated detection of transaction latency for a processor design model running an application in a hardware simulation accelerator. The method includes loading the processor design model into the hardware simulation accelerator, loading the application into the processor design model running within the hardware simulation accelerator, simulating the processor design model running the application within the hardware simulation accelerator, and for each individual transaction of the application: establishing a first checkpoint at a start of an execution of the individual transaction by creating a breakpoint and resetting a counter, establishing a second checkpoint at a completion of the transaction by creating another breakpoint and obtaining latency information for the second checkpoint. The latencies of the individual transaction from the start to the completion are measured based on the latency information.

Method for latency detection on a hardware simulation accelerator

A computer system includes a processor and a prefetch engine. The processor is configured to generate a demand access stream. The prefetch engine is configured to generate a first prefetch request and a second prefetch request based on the demand access stream, to output the first prefetch request to a first translation lookaside buffer (TLB), and to output the second prefetch request to a second TLB that is different from the first TLB. The processor performs a first TLB lookup in the first TLB based on one of the demand access stream or the first prefetch request, and performs a second TLB lookup in the second TLB based on the second prefetch request.

Translation bandwidth optimized prefetching strategy through multiple translation lookaside buffers

Embodiments of the present disclosure provide a method, a system, and a computer readable storage medium for detecting deviations from targeted design performance in accelerator/emulator environment. In an embodiment, the method comprises loading target vales for a performance metric onto a hardware-accelerated simulator; setting breakpoints to pause the simulator at defined intervals; simulating, by the hardware-accelerated simulator, execution of a circuit design. The method further comprises during the simulating, using said breakpoints to pause the simulating at the defined intervals, and during each pause, comparing a measured value for the performance metric to the target value for the performance metric; and ending the simulation when a specified condition based on said comparing is met. In embodiments, when a difference between the measured value for the performance metric and the target value for the performance metric is within a preset tolerance, the pause is ended and the simulation continues.

Detecting deviations from targeted design performance in accelerator/emulator environment

In at least one embodiment, a processing unit includes a processor core and a vertical cache hierarchy including at least a store-through upper-level cache and a store-in lower-level cache. The upper-level cache includes a data array and an effective address (EA) directory. The processor core includes an execution unit, an address translation unit, and a prefetch unit configured to initiate allocation of a directory entry in the EA directory for a store target EA without prefetching a cache line of data into the corresponding data entry in the data array. The processor core caches in the directory entry an EA-to-RA address translation information for the store target EA, such that a subsequent demand store access that hits in the directory entry can avoid a performance penalty associated with address translation by the translation unit.

Prefetch store preallocation in an effective address-based cache directory

A method, system and computer program product are disclosed for reducing the memory load time for logic simulator. In an embodiment, the method comprises identifying a memory for a program, and selectively loading onto a logic simulator parts of the memory that are pre-determined as parts of the memory that will be accessed by the program when the program is executed on the simulator. In an embodiment, the selectively loading onto a logic simulator parts of the memory includes pre-determining subsets of the memory that will be accessed by the program when the program is executed on the simulator, and loading the pre-determined subsets of the memory on the simulator. In an embodiment, the pre-determining subsets of the memory includes using addresses of the memory that are accessed by the program when the program is executed on a computer system, to create the pre-determined subsets of the memory.

Reducing the memory load time for logic simulator by leveraging architecture simulator

Disclosed is a computer implemented method and system to dynamically adjust prefetch depth, the method comprising, identifying a first prefetch stream, wherein the first prefetch stream is identified in a prefetch request queue (PRQ), and wherein the first prefetch stream includes a first prefetch depth. The method also comprises determining a number of inflight prefetches, and comparing, a number of prefetch machines against the number of inflight prefetches, wherein each of the prefetch machines is configured to monitor one prefetch request. The method further includes adjusting, in response to the comparing, the first prefetch depth of the first prefetch stream.

Dynamically adjusting prefetch depth

Disclosed is a computer implemented method to dynamically adjust prefetch depth, the method comprising sending, to a first prefetch machine, a first prefetch request configured to fetch a first data address from a first stream at a first depth to a lower level cache. The method also comprises sending, to a second prefetcher, a second prefetch request configured to fetch the first data address from the first stream at a second depth to a highest-level cache. The method further comprises determining the first data address is not in the lower level cache, determining, that the first prefetch request is in the first prefetch machine, and determining, in response to the first prefetch request being in the first prefetch machine, that the first stream is at steady state. The method comprises adjusting, in response to determining that the first stream is at steady state, the first depth.

A system and method including a processor configured to, based on encountering an instruction that does not modify the architectural state of the processor, preferably a prefetch instruction, that is being executed by the processor, determine whether utilization of a first queue used in processing the instruction is over a first queue utilization limit; in response to the first queue utilization being over the first queue utilization limit, do not execute the prefetch instruction; and in response to the first queue utilization being under the first queue utilization limit, at least partially process the prefetch instruction.

Dynamic modification of instructions that do not modify the architectural state of a processor

A method, computer program product, and a computer system are disclosed for processing information in a processor that in one or more embodiments includes generating workload information of a performance base test; determining characteristics of the workload information; determining one or more constraints that can cause behavioral changes to a design of the processor; combining the determined characteristics and the determined one or more constraints to generate one or more example constraints; testing the one or more example constraints in one or more example performance tests; and generating one or more performance benchmarks for the performance base test and the one or more example performance tests.

Performance benchmark generation

A computer system, processor, and method for processing information is disclosed that includes allocating a prefetch stream; providing a protection bubble to a plurality of cachelines for the allocated prefetch stream; accessing a cacheline; and preventing allocation of a different prefetch stream if the accessed cacheline is within the protection bubble. The system, processor and method in an aspect further includes providing a safety zone to a plurality of cachelines for the allocated prefetch stream, and advancing the prefetch stream if the accessed cacheline is one of the plurality of cachelines in the safety zone. In an embodiment, the number of cachelines within the safety zone is less than the number of cachelines in the protection bubble.

Prefetch queue allocation protection bubble in a processor

A processor, system and/or techniques are disclosed for prefetching data streams in a processor. A prefetcher issues a plurality of requests to pre-fetch data from a stream in a plurality of streams; evaluates a confidence level of at least the first request based on an amount of confirmations observed in the stream; and assigns at least a first more aggressive prefetching ramping mode or a second less aggressive prefetching ramping mode based upon the confidence level of a thread associated with the prefetch request, wherein the prefetcher has one or more probationary states and is configured to transition between the first and second prefetching ramp mode by entering at least one of the probation states wherein the prefetcher continues to operate in the first prefetching ramp mode. In another aspect, the prefetcher may transition to the one or more probation states after a number of cycles.

Processor prefetcher mode governor for switching between prefetch modes

Examples of techniques for software translation prefetch instructions are described herein. An aspect includes, based on encountering a translation prefetch instruction in software that is being executed by a processor, determining whether an address translation corresponding to the translation prefetch instruction is located in a translation lookaside buffer (TLB) of the processor. Another aspect includes, based on determining that the address translation is not located in the TLB, issuing an address translation request corresponding to the translation prefetch instruction. Another aspect includes storing an address translation corresponding to the address translation request in the TLB.

Software translation prefetch instructions

A computer system for prefetching data in a multithreading environment includes a processor having a prefetching engine and a stride detector. The processor is configured to perform requesting data associated with a first thread of a plurality of threads, and prefetching requested data by the prefetching engine, where prefetching includes allocating a prefetch stream in response to an occurrence of a cache miss. The processor performs detecting each cache miss, and based on detecting the cache miss, monitoring the prefetching engine to detect subsequent cache misses and to detect one or more events related to allocations performed by the prefetching engine. The processor further performs, based on the stride detector detecting a selected number of events, directing the stride detector to switch from the first thread to a second thread by ignoring stride-1 allocations for the first thread and evaluating stride-1 allocations for potential strided accesses on the second thread.

Growing community of inventors

Austin, TX, United States of America

Vivek Britto