US20160132354A1 - Application scheduling in heterogeneous multiprocessor computing platforms - Google Patents
Application scheduling in heterogeneous multiprocessor computing platforms Download PDFInfo
- Publication number
- US20160132354A1 US20160132354A1 US14/995,198 US201614995198A US2016132354A1 US 20160132354 A1 US20160132354 A1 US 20160132354A1 US 201614995198 A US201614995198 A US 201614995198A US 2016132354 A1 US2016132354 A1 US 2016132354A1
- Authority
- US
- United States
- Prior art keywords
- processor
- core
- performance
- logic
- application
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Abandoned
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/48—Program initiating; Program switching, e.g. by interrupt
- G06F9/4806—Task transfer initiation or dispatching
- G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
- G06F9/4881—Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3404—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment for parallel or distributed programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3409—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment for performance assessment
- G06F11/3433—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment for performance assessment for load management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F12/00—Accessing, addressing or allocating within memory systems or architectures
- G06F12/02—Addressing or allocation; Relocation
- G06F12/08—Addressing or allocation; Relocation in hierarchically structured memory systems, e.g. virtual memory systems
- G06F12/0802—Addressing of a memory level in which the access to the desired data or data block requires associative addressing means, e.g. caches
- G06F12/0806—Multiuser, multiprocessor or multiprocessing cache systems
- G06F12/084—Multiuser, multiprocessor or multiprocessing cache systems with a shared cache
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F15/00—Digital computers in general; Data processing equipment in general
- G06F15/76—Architectures of general purpose stored program computers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/461—Saving or restoring of program or task context
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5083—Techniques for rebalancing the load in a distributed system
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3409—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment for performance assessment
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2201/00—Indexing scheme relating to error detection, to error correction, and to monitoring
- G06F2201/88—Monitoring involving counting
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Definitions
- the present disclosure generally relates to the field of electronics. More particularly, an embodiment of the invention relates to techniques for scheduling applications in heterogeneous multiprocessor computing platforms.
- some computing systems include multiple processors.
- scaling of multi-processor computing systems is restricted by power constraints. Namely, as more processors are added to a system, power consumption increases. Also, the additional power consumption generates more heat. Hence, heat and power requirements may restrict scaling of multi-processor computing systems.
- FIGS. 1, 5, and 6 illustrate block diagrams of embodiments of computing systems, which may be utilized to implement various embodiments discussed herein.
- FIG. 2 illustrates a block diagram of portions of a processor core and other components of a computing system, according to an embodiment.
- FIGS. 3-4 illustrate flow diagrams in accordance with some embodiments.
- CMP Chip-MultiProcessor
- one of the key challenges in heterogeneous CMP platform design is application scheduling, i.e., mapping applications to the plurality of processor cores that optimizes performance and/or power efficiency.
- application scheduling i.e., mapping applications to the plurality of processor cores that optimizes performance and/or power efficiency.
- one embodiment relates to dynamically scheduling applications among heterogeneous cores (e.g., on a single integrated circuit (IC) chip/die).
- two components may be used to schedule applications.
- a processor core modeling predication heuristics may be provided.
- a scheduling logic may be used to schedule applications for heterogeneous processor cores based on the core modeling predication heuristics.
- FIG. 1 illustrates a block diagram of a computing system 100 , according to an embodiment of the invention.
- the system 100 may include one or more processors 102 - 1 through 102 -N (generally referred to herein as “processors 102 ” or “processor 102 ”).
- the processors 102 may communicate via an interconnection network or bus 104 .
- Each processor may include various components some of which are only discussed with reference to processor 102 - 1 for clarity. Accordingly, each of the remaining processors 102 - 2 through 102 -N may include the same or similar components discussed with reference to the processor 102 - 1 .
- the processor 102 - 1 may include one or more processor cores 106 - 1 through 106 -M (referred to herein as “cores 106 ” or more generally as “core 106 ”), a shared cache 108 , and/or a router 110 .
- the processor cores 106 may be implemented on a single integrated circuit (IC) chip.
- the chip may include one or more shared and/or private caches (such as cache 108 ), buses or interconnections (such as a bus or interconnection network 112 ), memory controllers (such as those discussed with reference to FIGS. 5 and 6 ), or other components.
- the cores 106 may be heterogeneous (e.g., having different sizes, performance characteristics, power consumption characteristics, etc. as discussed herein).
- the router 110 may be used to communicate between various components of the processor 102 - 1 and/or system 100 .
- the processor 102 - 1 may include more than one router 110 .
- the multitude of routers ( 110 ) may be in communication to enable data routing between various components inside or outside of the processor 102 - 1 .
- the shared cache 108 may store data (e.g., including instructions) that are utilized by one or more components of the processor 102 - 1 , such as the cores 106 .
- the shared cache 108 may locally cache data stored in a memory 114 for faster access by components of the processor 102 .
- the cache 108 may include a mid-level cache (such as a level 2 (L2), a level 3 (L3), a level 4 (L4), or other levels of cache), a last level cache (LLC), and/or combinations thereof.
- various components of the processor 102 - 1 may communicate with the shared cache 108 directly, through a bus (e.g., the bus 112 ), and/or a memory controller or hub.
- one or more of the cores 106 may include a level 1 (L1) and/or level 2 (L2) cache ( 116 - 1 ) (generally referred to herein as “L1/L2 cache 116 ”).
- L1 and/or L2 cache 116 may be private or shared in various embodiments.
- each of the cores may include a logic 120 to assist in assigning applications to various processor cores in the system.
- the applications may be assigned (e.g., by an Operating System (OS)) based on information stored in counter(s) 122 (such as performance counter(s) that indicate the performance of one or more other cores in the system).
- the applications may also be assigned (e.g., by the OS) based on a process identifier (ID) which may be used to index into a table (such as a performance history table (PHT) 124 - 1 ).
- ID process identifier
- the table may be stored in shared memory (such as memory 114 and/or shared cache 108 ) or a dedicated storage device in the processor 102 or core 106 (e.g., PHT 124 - 1 ), such a private cache (e.g., L1/L2 cache 116 ).
- the table may provide information/hints to the Operating System (OS) when scheduling applications, as will be further discussed below with reference to FIGS. 2-4 , for example.
- the OS and application may be stored in memory 114 (or memories 512 of FIG. 5 and 610 / 612 of FIG. 6 ).
- FIG. 2 illustrates a block diagram of portions of a processor core 106 and other components of a computing system, according to an embodiment of the invention.
- the arrows shown in FIG. 2 illustrate the flow direction of instructions through the core 106 .
- One or more processor cores may be implemented on a single integrated circuit chip (or die) such as discussed with reference to FIG. 1 .
- the chip may include one or more shared and/or private caches (e.g., caches 106 and 108 of FIG. 1 ), interconnections (e.g., interconnections 104 and/or 112 of FIG. 1 ), logic 120 , counter(s) 122 , memory controllers, or other components.
- the processor core 106 may include a fetch unit 202 to fetch instructions (including instructions with conditional branches) for execution by the core 106 .
- the instructions may be fetched from any storage devices such as the memory 114 and/or the memory devices discussed with reference to FIGS. 4 and 5 .
- the core 106 may also include a decode unit 204 to decode the fetched instruction. For instance, the decode unit 204 may decode the fetched instruction into a plurality of uops (micro-operations). Additionally, the core 106 may include a schedule unit 206 .
- the schedule unit 206 may perform various operations associated with storing decoded instructions (e.g., received from the decode unit 204 ) until the instructions are ready for dispatch, e.g., until all source values of a decoded instruction become available.
- the schedule unit 206 may schedule and/or issue (or dispatch) decoded instructions to an execution unit 208 for execution.
- the execution unit 208 may execute the dispatched instructions after they are decoded (e.g., by the decode unit 204 ) and dispatched (e.g., by the schedule unit 206 ).
- the execution unit 208 may include more than one execution unit.
- the execution unit 208 may also perform various arithmetic operations such as addition, subtraction, multiplication, and/or division, and may include one or more an arithmetic logic units (ALUs).
- ALUs arithmetic logic units
- a co-processor (not shown) may perform various arithmetic operations in conjunction with the execution unit 208 .
- the execution unit 208 may execute instructions out-of-order.
- the processor core 106 may be an out-of-order processor core in one embodiment.
- the core 106 may also include a retirement unit 210 .
- the retirement unit 210 may retire executed instructions after they are committed. In an embodiment, retirement of the executed instructions may result in processor state being committed from the execution of the instructions, physical registers used by the instructions being de-allocated, etc.
- the core 106 may also include a bus unit 214 to enable communication between components of the processor core 106 and other components (such as the components discussed with reference to FIG. 1 ) via one or more buses (e.g., buses 104 and/or 112 ).
- the core 106 may also include one or more counters 122 to store data accessed by various components of the core 106 , including the logic 120 , as discussed with reference to FIGS. 1 and 3-4 ).
- the logic 120 not only keeps track of performance of an application, but also predicts the application's execution and/or power consumption performance if it were to execute on another core in the system (e.g., based on the values stores in the counters 122 ). This information may be provided to OS which may perform scheduling based on various thresholds such as power, performance, energy, combinations thereof, etc. For example, the OS and/or logic 120 may compare the various execution or power consumption performance data of the processor cores being considered and make a determination regarding which core would provide the better execution or power consumption performance (based on various thresholds discussed herein.
- a signature based approach may be used.
- each application may be executed on one or more cores in the system and the application performance statistics may be stored in the PHT a performance history table (PHT).
- Performance statistics may include CPI (Cycles Per Instruction), MPI (Misses Per Instruction), etc.
- CPI Chips Per Instruction
- MPI Machines Per Instruction
- each table entry may have three or more fields. The first one indicates the process ID, second is for storing the CPI of the application while executing on big core and, the last one stores the performance of the application while executing on a small core.
- logic 120 may obtain new information and update the PHT 124 .
- the size of the PHT 124 may be quite small. For instance, if only CPI is used, 12 bytes per entry is the memory needed to store the history information.
- the PHT 124 may also be stored in the Process Control Block (PCB) of the application and/or may be loaded into another memory (e.g., PHT 124 , cache 106 , memory 114 , cache 108 , etc.) whenever the application is scheduled to run. This methodology may be extended beyond a process and may be used for various hotspots within a process.
- PCB Process Control Block
- the logic 120 reads the information from PHT and provides hints to OS for optimal scheduling policies based on predefined metrics (such as power/performance, etc), as shown in FIG. 3 .
- FIG. 3 a flow diagram for a signature-based core modeling prediction heuristics approach is illustrated, according to an embodiment.
- various components discussed with reference to FIGS. 1-2 and 5-6 may be utilized to perform one or more of the operations discussed with reference to FIG. 3 .
- the application is loaded (e.g., from a process control block or another location as discussed herein).
- logic 120 reads the information from PHT.
- logic 120 collects further history information (e.g., based on the latest determination at operation 306 ) and updates the PHT information.
- FIG. 4 a flow diagram for a performance-based core modeling prediction heuristics approach is illustrated, according to an embodiment.
- various components discussed with reference to FIGS. 1-2 and 5-6 may be utilized to perform one or more of the operations discussed with reference to FIG. 4 .
- the application is loaded (e.g., from a process control block or another location as discussed herein).
- logic 120 reads the values stored in the performance counters (e.g., counters 122 ).
- logic 120 collects further history information (e.g., based on the latest determination at operation 406 ) and updates the performance counter (e.g., counters 122 ).
- a dynamic model may be used which may effectively predict the performance of an application on a small core while it is executing on a big core and vice-versa.
- This approach uses the performance counters (e.g., counters 122 ) and predicts performance based on the following equation:
- Cycles in Small core ((Cycles in Big core-stall cycles on big core)*Issue width of small core/Issue width of big core*Multiplication factor)+( L 1 Miss in big core* L 1 miss penalty of small core)+( L 2 Miss in big core* L 2 miss penalty of small core)
- the multiplication factor may be derived empirically based on L2 misses and number of load/store instructions.
- the big core may have twice the number of load/store units as compared to small core.
- significant L2 miss applications may not benefit by the out-of-order nature of a big core due to lack of memory level parallelism observed in some workloads.
- Cycles in Big core ((Cycles in Small core-stall cycles on small core)*Issue width of Big core/Issue width of Small core)/(1-stall factor)
- Stall factor may be derived by running the applications once on the big core and collecting the stall cycles and total cycles performance data.
- some platforms may include various performance counters to identify stalls due to long latency operations such as cache miss, floating point stalls, etc. These stalls combined with other counters such as load/store instructions retired, L2 misses, etc., when used in logic 120 , may help predict the performance of the application if it were to run on another core. Even if there is no specific memory stall counter in the platforms, the stalls may be estimated using other stall counters in the platform.
- some embodiments may map various applications to big and small cores based on the performance information provided by logic 120 as follows: (1) For a single application, if the performance ratio of big to small core is greater than a programmable value, then schedule the application on the big core; otherwise schedule it on the small core. This programmable value may reside in the core and may be written using MSR's (Machine State Register) based on various power/performance metrics; (2) For multiple applications, with N applications that need to be scheduled for example, order applications based on their Performance ratio of big to small core. The top N/2 apps are (e.g., apps with maximal gains) are scheduled onto the big core, and the bottom N/2 apps are scheduled on the small core.
- MSR's Machine State Register
- one or more of the following counters may be used (e.g., for counters 122 ): (1) Core clock cycles: this counter counts the number of cycles in which the core was active executing instructions; (2) Instructions retired: this counter counts the number of instructions the core retired during the given time sample; (3) L2 Misses: this counter counts the number of memory references that missed the L2; (4) Scheduler stalls: this counter counts the number of cycles in which the small core could not schedule instructions (this count can also be derived based on the product of L2 misses and L2 miss latency in the small core); (5) Resource stalls: this counter counts the number of cycles the big core stalled due to unavailability of resources such as reservation stations, long latency misses, etc.; and/or (6) Branch stalls: this counter counts the total number of cycles lost due to branch mispredictions.
- FIG. 5 illustrates a block diagram of a computing system 500 in accordance with an embodiment of the invention.
- the computing system 500 may include one or more central processing unit(s) (CPUs) 502 or processors that communicate via an interconnection network (or bus) 504 .
- the processors 502 may include a general purpose processor, a network processor (that processes data communicated over a computer network 503 ), or other types of a processor (including a reduced instruction set computer (RISC) processor or a complex instruction set computer (CISC)).
- RISC reduced instruction set computer
- CISC complex instruction set computer
- the processors 502 may have a single or multiple core design.
- the processors 502 with a multiple core design may integrate different types of processor cores on the same integrated circuit (IC) die.
- processors 502 with a multiple core design may be implemented as symmetrical or asymmetrical multiprocessors.
- one or more of the processors 502 may be the same or similar to the processors 102 of FIG. 1 .
- one or more of the processors 502 may include the cores 106 discussed with reference to FIGS. 1-4 .
- the operations discussed with reference to FIGS. 1-4 may be performed by one or more components of the system 500 .
- a chipset 506 may also communicate with the interconnection network 504 .
- the chipset 506 may include a memory control hub (MCH) 508 .
- the MCH 508 may include a memory controller 510 that communicates with a memory 512 (which may be the same or similar to the memory 114 of FIG. 1 ).
- the memory 512 may store data, including sequences of instructions that may be executed by the CPU 502 , or any other device included in the computing system 500 .
- the memory 512 may include one or more volatile storage (or memory) devices such as random access memory (RAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), static RAM (SRAM), or other types of storage devices.
- RAM random access memory
- DRAM dynamic RAM
- SDRAM synchronous DRAM
- SRAM static RAM
- Nonvolatile memory may also be utilized such as a hard disk. Additional devices may communicate via the interconnection network 504 , such as multiple CPUs and/or multiple system memories.
- the MCH 508 may also include a graphics interface 514 that communicates with a display device 516 .
- the graphics interface 514 may communicate with the display device 516 via an accelerated graphics port (AGP).
- AGP accelerated graphics port
- the display 516 (such as a flat panel display) may communicate with the graphics interface 514 through, for example, a signal converter that translates a digital representation of an image stored in a storage device such as video memory or system memory into display signals that are interpreted and displayed by the display 516 .
- the display signals produced by the display device may pass through various control devices before being interpreted by and subsequently displayed on the display 516 .
- a hub interface 518 may allow the MCH 508 and an input/output control hub (ICH) 520 to communicate.
- the ICH 520 may provide an interface to I/O device(s) that communicate with the computing system 500 .
- the ICH 520 may communicate with a bus 522 through a peripheral bridge (or controller) 524 , such as a peripheral component interconnect (PCI) bridge, a universal serial bus (USB) controller, or other types of peripheral bridges or controllers.
- the bridge 524 may provide a data path between the CPU 502 and peripheral devices. Other types of topologies may be utilized.
- multiple buses may communicate with the ICH 520 , e.g., through multiple bridges or controllers.
- peripherals in communication with the ICH 520 may include, in various embodiments of the invention, integrated drive electronics (IDE) or small computer system interface (SCSI) hard drive(s), USB port(s), a keyboard, a mouse, parallel port(s), serial port(s), floppy disk drive(s), digital output support (e.g., digital video interface (DVI)), or other devices.
- IDE integrated drive electronics
- SCSI small computer system interface
- the bus 522 may communicate with an audio device 526 , one or more disk drive(s) 528 , and a network interface device 530 (which is in communication with the computer network 503 ). Other devices may communicate via the bus 522 . Also, various components (such as the network interface device 530 ) may communicate with the MCH 508 in some embodiments of the invention. In addition, the processor 502 and the MCH 508 may be combined to form a single chip. Furthermore, the graphics accelerator 516 may be included within the MCH 508 in other embodiments of the invention.
- nonvolatile memory may include one or more of the following: read-only memory (ROM), programmable ROM (PROM), erasable PROM (EPROM), electrically EPROM (EEPROM), a disk drive (e.g., 528 ), a floppy disk, a compact disk ROM (CD-ROM), a digital versatile disk (DVD), flash memory, a magneto-optical disk, or other types of nonvolatile machine-readable media that are capable of storing electronic data (e.g., including instructions).
- ROM read-only memory
- PROM programmable ROM
- EPROM erasable PROM
- EEPROM electrically EPROM
- a disk drive e.g., 528
- CD-ROM compact disk ROM
- DVD digital versatile disk
- flash memory e.g., a magneto-optical disk, or other types of nonvolatile machine-readable media that are capable of storing electronic data (e.g., including instructions).
- FIG. 6 illustrates a computing system 600 that is arranged in a point-to-point (PtP) configuration, according to an embodiment of the invention.
- FIG. 6 shows a system where processors, memory, and input/output devices are interconnected by a number of point-to-point interfaces.
- the operations discussed with reference to FIGS. 1-5 may be performed by one or more components of the system 600 .
- the system 600 may include several processors, of which only two, processors 602 and 604 are shown for clarity.
- the processors 602 and 604 may each include a local memory controller hub (MCH) 606 and 608 to enable communication with memories 610 and 612 .
- MCH memory controller hub
- the memories 610 and/or 612 may store various data such as those discussed with reference to the memory 512 of FIG. 5 .
- the processors 602 and 604 may be one of the processors 502 discussed with reference to FIG. 5 .
- the processors 602 and 604 may exchange data via a point-to-point (PtP) interface 614 using PtP interface circuits 616 and 618 , respectively.
- the processors 602 and 604 may each exchange data with a chipset 620 via individual PtP interfaces 622 and 624 using point-to-point interface circuits 626 , 628 , 630 , and 632 .
- the chipset 620 may further exchange data with a graphics circuit 634 via a graphics interface 636 , e.g., using a PtP interface circuit 637 .
- At least one embodiment of the invention may be provided within the processors 602 and 604 .
- the cores 106 of FIGS. 1-5 may be located within the processors 602 and 604 .
- Other embodiments of the invention may exist in other circuits, logic units, or devices within the system 600 of FIG. 6 .
- other embodiments of the invention may be distributed throughout several circuits, logic units, or devices illustrated in FIG. 6 .
- the chipset 620 may communicate with a bus 640 using a PtP interface circuit 641 .
- the bus 640 may communicate with one or more devices, such as a bus bridge 642 and I/O devices 643 .
- the bus bridge 642 may communicate with other devices such as a keyboard/mouse 645 , communication devices 646 (such as modems, network interface devices, or other communication devices that may communicate with the computer network 503 ), audio I/O device 647 , and/or a data storage device 648 .
- the data storage device 648 may store code 649 that may be executed by the processors 602 and/or 604 .
- the operations discussed herein may be implemented as hardware (e.g., logic circuitry), software, firmware, or combinations thereof, which may be provided as a computer program product, e.g., including (e.g., a non-transitory) machine-readable or computer-readable medium having stored thereon instructions (or software procedures) used to program a computer to perform a process discussed herein.
- the machine-readable medium may include a storage device such as those discussed with respect to FIGS. 1-6 .
- Such computer-readable media may be downloaded as a computer program product, wherein the program may be transferred from a remote computer (e.g., a server) to a requesting computer (e.g., a client) by way of data signals embodied in a carrier wave or other propagation medium via a communication link (e.g., a bus, a modem, or a network connection).
- a remote computer e.g., a server
- a requesting computer e.g., a client
- a communication link e.g., a bus, a modem, or a network connection
- Coupled may mean that two or more elements are in direct physical or electrical contact. However, “coupled” may also mean that two or more elements may not be in direct contact with each other, but may still cooperate or interact with each other.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Power Sources (AREA)
- Microcomputers (AREA)
- Multi Processors (AREA)
- Memory System Of A Hierarchy Structure (AREA)
Abstract
Description
- This is a Continuation of application Ser. No. 12/890,653, filed Sep. 25, 2010, currently pending.
- The present disclosure generally relates to the field of electronics. More particularly, an embodiment of the invention relates to techniques for scheduling applications in heterogeneous multiprocessor computing platforms.
- To improve performance, some computing systems include multiple processors. However, scaling of multi-processor computing systems is restricted by power constraints. Namely, as more processors are added to a system, power consumption increases. Also, the additional power consumption generates more heat. Hence, heat and power requirements may restrict scaling of multi-processor computing systems.
- The detailed description is provided with reference to the accompanying figures. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. The use of the same reference numbers in different figures indicates similar or identical items.
-
FIGS. 1, 5, and 6 illustrate block diagrams of embodiments of computing systems, which may be utilized to implement various embodiments discussed herein. -
FIG. 2 illustrates a block diagram of portions of a processor core and other components of a computing system, according to an embodiment. -
FIGS. 3-4 illustrate flow diagrams in accordance with some embodiments. - In the following description, numerous specific details are set forth in order to provide a thorough understanding of various embodiments. However, various embodiments of the invention may be practiced without the specific details. In other instances, well-known methods, procedures, components, and circuits have not been described in detail so as not to obscure the particular embodiments of the invention. Further, various aspects of embodiments of the invention may be performed using various means, such as integrated semiconductor circuits (“hardware”), computer-readable instructions organized into one or more programs (“software”), or some combination of hardware and software. For the purposes of this disclosure reference to “logic” shall mean either hardware, software, or some combination thereof. Also, the use of “instruction” and “micro-operation” (uop) is interchangeable as discussed herein.
- As Chip-MultiProcessor (CMP) systems become popular, e.g., for server and client platforms, heterogeneous CMP starts to gain momentum. For example, smaller processor cores may provide better performance/watt advantage. So adding smaller processor cores along with bigger processor cores can be attractive. As discussed herein, heterogeneous CMP contains a set of cores that are different in performance, area, and/or power dissipation. Such a platform provides opportunities to allow better mapping of compute resources to various application so that both performance and power efficiency may be achieved in some embodiments.
- However, one of the key challenges in heterogeneous CMP platform design is application scheduling, i.e., mapping applications to the plurality of processor cores that optimizes performance and/or power efficiency. To this end, one embodiment relates to dynamically scheduling applications among heterogeneous cores (e.g., on a single integrated circuit (IC) chip/die). In one embodiment, two components may be used to schedule applications. First, a processor core modeling predication heuristics may be provided. Second, a scheduling logic may be used to schedule applications for heterogeneous processor cores based on the core modeling predication heuristics.
- The techniques discussed herein may be used in any type of a processor with performance state settings, such as the processors discussed with reference to
FIGS. 1 and 5-6 . More particularly,FIG. 1 illustrates a block diagram of acomputing system 100, according to an embodiment of the invention. Thesystem 100 may include one or more processors 102-1 through 102-N (generally referred to herein as “processors 102” or “processor 102”). Theprocessors 102 may communicate via an interconnection network orbus 104. Each processor may include various components some of which are only discussed with reference to processor 102-1 for clarity. Accordingly, each of the remaining processors 102-2 through 102-N may include the same or similar components discussed with reference to the processor 102-1. - In an embodiment, the processor 102-1 may include one or more processor cores 106-1 through 106-M (referred to herein as “
cores 106” or more generally as “core 106”), a sharedcache 108, and/or arouter 110. Theprocessor cores 106 may be implemented on a single integrated circuit (IC) chip. Moreover, the chip may include one or more shared and/or private caches (such as cache 108), buses or interconnections (such as a bus or interconnection network 112), memory controllers (such as those discussed with reference toFIGS. 5 and 6 ), or other components. Also, thecores 106 may be heterogeneous (e.g., having different sizes, performance characteristics, power consumption characteristics, etc. as discussed herein). - In one embodiment, the
router 110 may be used to communicate between various components of the processor 102-1 and/orsystem 100. Moreover, the processor 102-1 may include more than onerouter 110. Furthermore, the multitude of routers (110) may be in communication to enable data routing between various components inside or outside of the processor 102-1. - The shared
cache 108 may store data (e.g., including instructions) that are utilized by one or more components of the processor 102-1, such as thecores 106. For example, the sharedcache 108 may locally cache data stored in amemory 114 for faster access by components of theprocessor 102. In an embodiment, thecache 108 may include a mid-level cache (such as a level 2 (L2), a level 3 (L3), a level 4 (L4), or other levels of cache), a last level cache (LLC), and/or combinations thereof. Moreover, various components of the processor 102-1 may communicate with the sharedcache 108 directly, through a bus (e.g., the bus 112), and/or a memory controller or hub. As shown inFIG. 1 , in some embodiments, one or more of thecores 106 may include a level 1 (L1) and/or level 2 (L2) cache (116-1) (generally referred to herein as “L1/L2 cache 116”). The L1 and/orL2 cache 116 may be private or shared in various embodiments. - In one embodiment, as will be further discussed below with reference to
FIGS. 2-4 , each of the cores may include alogic 120 to assist in assigning applications to various processor cores in the system. For example, the applications may be assigned (e.g., by an Operating System (OS)) based on information stored in counter(s) 122 (such as performance counter(s) that indicate the performance of one or more other cores in the system). The applications may also be assigned (e.g., by the OS) based on a process identifier (ID) which may be used to index into a table (such as a performance history table (PHT) 124-1). The table may be stored in shared memory (such asmemory 114 and/or shared cache 108) or a dedicated storage device in theprocessor 102 or core 106 (e.g., PHT 124-1), such a private cache (e.g., L1/L2 cache 116). The table may provide information/hints to the Operating System (OS) when scheduling applications, as will be further discussed below with reference toFIGS. 2-4 , for example. In some embodiments, the OS and application may be stored in memory 114 (ormemories 512 ofFIG. 5 and 610 /612 ofFIG. 6 ). -
FIG. 2 illustrates a block diagram of portions of aprocessor core 106 and other components of a computing system, according to an embodiment of the invention. In one embodiment, the arrows shown inFIG. 2 illustrate the flow direction of instructions through thecore 106. One or more processor cores (such as the processor core 106) may be implemented on a single integrated circuit chip (or die) such as discussed with reference toFIG. 1 . Moreover, the chip may include one or more shared and/or private caches (e.g.,caches FIG. 1 ), interconnections (e.g.,interconnections 104 and/or 112 ofFIG. 1 ),logic 120, counter(s) 122, memory controllers, or other components. - As illustrated in
FIG. 2 , theprocessor core 106 may include a fetchunit 202 to fetch instructions (including instructions with conditional branches) for execution by thecore 106. The instructions may be fetched from any storage devices such as thememory 114 and/or the memory devices discussed with reference toFIGS. 4 and 5 . Thecore 106 may also include adecode unit 204 to decode the fetched instruction. For instance, thedecode unit 204 may decode the fetched instruction into a plurality of uops (micro-operations). Additionally, thecore 106 may include aschedule unit 206. Theschedule unit 206 may perform various operations associated with storing decoded instructions (e.g., received from the decode unit 204) until the instructions are ready for dispatch, e.g., until all source values of a decoded instruction become available. In one embodiment, theschedule unit 206 may schedule and/or issue (or dispatch) decoded instructions to anexecution unit 208 for execution. Theexecution unit 208 may execute the dispatched instructions after they are decoded (e.g., by the decode unit 204) and dispatched (e.g., by the schedule unit 206). In an embodiment, theexecution unit 208 may include more than one execution unit. Theexecution unit 208 may also perform various arithmetic operations such as addition, subtraction, multiplication, and/or division, and may include one or more an arithmetic logic units (ALUs). In an embodiment, a co-processor (not shown) may perform various arithmetic operations in conjunction with theexecution unit 208. - Further, the
execution unit 208 may execute instructions out-of-order. Hence, theprocessor core 106 may be an out-of-order processor core in one embodiment. Thecore 106 may also include aretirement unit 210. Theretirement unit 210 may retire executed instructions after they are committed. In an embodiment, retirement of the executed instructions may result in processor state being committed from the execution of the instructions, physical registers used by the instructions being de-allocated, etc. - The
core 106 may also include abus unit 214 to enable communication between components of theprocessor core 106 and other components (such as the components discussed with reference toFIG. 1 ) via one or more buses (e.g.,buses 104 and/or 112). Thecore 106 may also include one ormore counters 122 to store data accessed by various components of thecore 106, including thelogic 120, as discussed with reference toFIGS. 1 and 3-4 ). - Moreover, in some embodiments, the
logic 120 not only keeps track of performance of an application, but also predicts the application's execution and/or power consumption performance if it were to execute on another core in the system (e.g., based on the values stores in the counters 122). This information may be provided to OS which may perform scheduling based on various thresholds such as power, performance, energy, combinations thereof, etc. For example, the OS and/orlogic 120 may compare the various execution or power consumption performance data of the processor cores being considered and make a determination regarding which core would provide the better execution or power consumption performance (based on various thresholds discussed herein. - In accordance with an embodiment, a signature based approach may be used. For example, each application may be executed on one or more cores in the system and the application performance statistics may be stored in the PHT a performance history table (PHT). Performance statistics may include CPI (Cycles Per Instruction), MPI (Misses Per Instruction), etc. For example, as shown in sample Table 1, each table entry may have three or more fields. The first one indicates the process ID, second is for storing the CPI of the application while executing on big core and, the last one stores the performance of the application while executing on a small core. Whenever the application is context switched to the other core,
logic 120 may obtain new information and update thePHT 124. - The size of the
PHT 124 may be quite small. For instance, if only CPI is used, 12 bytes per entry is the memory needed to store the history information. ThePHT 124 may also be stored in the Process Control Block (PCB) of the application and/or may be loaded into another memory (e.g.,PHT 124,cache 106,memory 114,cache 108, etc.) whenever the application is scheduled to run. This methodology may be extended beyond a process and may be used for various hotspots within a process. - Once the PHT is setup, every time the application is scheduled to run, the
logic 120 reads the information from PHT and provides hints to OS for optimal scheduling policies based on predefined metrics (such as power/performance, etc), as shown inFIG. 3 . - Referring to
FIG. 3 , a flow diagram for a signature-based core modeling prediction heuristics approach is illustrated, according to an embodiment. In some embodiments, various components discussed with reference toFIGS. 1-2 and 5-6 may be utilized to perform one or more of the operations discussed with reference toFIG. 3 . - Referring to
FIGS. 1-3 , at anoperation 302, on a context switch, the application is loaded (e.g., from a process control block or another location as discussed herein). At anoperation 304,logic 120 reads the information from PHT. Atoperation 306, it is determined based on the PHT information whether the process is optimal (e.g., for performance or power consumption purposes) for a big or a small processor core. This information is then sent to the OS at operation 308 (in an embodiment based on power consumption and/or performance considerations as determined by thelogic 120 for example). At anoperation 310,logic 120 collects further history information (e.g., based on the latest determination at operation 306) and updates the PHT information. - Referring to
FIG. 4 , a flow diagram for a performance-based core modeling prediction heuristics approach is illustrated, according to an embodiment. In some embodiments, various components discussed with reference toFIGS. 1-2 and 5-6 may be utilized to perform one or more of the operations discussed with reference toFIG. 4 . - Referring to
FIGS. 1-2 and 4 , at anoperation 402, on a context switch, the application is loaded (e.g., from a process control block or another location as discussed herein). At anoperation 404,logic 120 reads the values stored in the performance counters (e.g., counters 122). Atoperation 406, it is determined based on the performance counter information whether the process is optimal (e.g., for performance or power consumption purposes) for a big or a small processor core. This information is then sent to the OS at operation 408 (in an embodiment based on power consumption and/or performance considerations as determined by thelogic 120 for example). At anoperation 410,logic 120 collects further history information (e.g., based on the latest determination at operation 406) and updates the performance counter (e.g., counters 122). - In a performance counter based approach, in accordance with some embodiments, a dynamic model may be used which may effectively predict the performance of an application on a small core while it is executing on a big core and vice-versa. This approach uses the performance counters (e.g., counters 122) and predicts performance based on the following equation:
-
Cycles in Small core=((Cycles in Big core-stall cycles on big core)*Issue width of small core/Issue width of big core*Multiplication factor)+(L1 Miss in big core*L1 miss penalty of small core)+(L2 Miss in big core*L2 miss penalty of small core) - In an embodiment, the multiplication factor may be derived empirically based on L2 misses and number of load/store instructions. In some embodiments, the big core may have twice the number of load/store units as compared to small core. Further, in some implementations, significant L2 miss applications may not benefit by the out-of-order nature of a big core due to lack of memory level parallelism observed in some workloads.
-
Cycles in Big core=((Cycles in Small core-stall cycles on small core)*Issue width of Big core/Issue width of Small core)/(1-stall factor) - Stall factor may be derived by running the applications once on the big core and collecting the stall cycles and total cycles performance data. Also, some platforms may include various performance counters to identify stalls due to long latency operations such as cache miss, floating point stalls, etc. These stalls combined with other counters such as load/store instructions retired, L2 misses, etc., when used in
logic 120, may help predict the performance of the application if it were to run on another core. Even if there is no specific memory stall counter in the platforms, the stalls may be estimated using other stall counters in the platform. - With respect to scheduling, some embodiments may map various applications to big and small cores based on the performance information provided by
logic 120 as follows: (1) For a single application, if the performance ratio of big to small core is greater than a programmable value, then schedule the application on the big core; otherwise schedule it on the small core. This programmable value may reside in the core and may be written using MSR's (Machine State Register) based on various power/performance metrics; (2) For multiple applications, with N applications that need to be scheduled for example, order applications based on their Performance ratio of big to small core. The top N/2 apps are (e.g., apps with maximal gains) are scheduled onto the big core, and the bottom N/2 apps are scheduled on the small core. - In some embodiments, one or more of the following counters may be used (e.g., for counters 122): (1) Core clock cycles: this counter counts the number of cycles in which the core was active executing instructions; (2) Instructions retired: this counter counts the number of instructions the core retired during the given time sample; (3) L2 Misses: this counter counts the number of memory references that missed the L2; (4) Scheduler stalls: this counter counts the number of cycles in which the small core could not schedule instructions (this count can also be derived based on the product of L2 misses and L2 miss latency in the small core); (5) Resource stalls: this counter counts the number of cycles the big core stalled due to unavailability of resources such as reservation stations, long latency misses, etc.; and/or (6) Branch stalls: this counter counts the total number of cycles lost due to branch mispredictions.
-
FIG. 5 illustrates a block diagram of acomputing system 500 in accordance with an embodiment of the invention. Thecomputing system 500 may include one or more central processing unit(s) (CPUs) 502 or processors that communicate via an interconnection network (or bus) 504. Theprocessors 502 may include a general purpose processor, a network processor (that processes data communicated over a computer network 503), or other types of a processor (including a reduced instruction set computer (RISC) processor or a complex instruction set computer (CISC)). Moreover, theprocessors 502 may have a single or multiple core design. Theprocessors 502 with a multiple core design may integrate different types of processor cores on the same integrated circuit (IC) die. Also, theprocessors 502 with a multiple core design may be implemented as symmetrical or asymmetrical multiprocessors. In an embodiment, one or more of theprocessors 502 may be the same or similar to theprocessors 102 ofFIG. 1 . For example, one or more of theprocessors 502 may include thecores 106 discussed with reference toFIGS. 1-4 . Also, the operations discussed with reference toFIGS. 1-4 may be performed by one or more components of thesystem 500. - A
chipset 506 may also communicate with theinterconnection network 504. Thechipset 506 may include a memory control hub (MCH) 508. TheMCH 508 may include amemory controller 510 that communicates with a memory 512 (which may be the same or similar to thememory 114 ofFIG. 1 ). Thememory 512 may store data, including sequences of instructions that may be executed by theCPU 502, or any other device included in thecomputing system 500. In one embodiment of the invention, thememory 512 may include one or more volatile storage (or memory) devices such as random access memory (RAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), static RAM (SRAM), or other types of storage devices. Nonvolatile memory may also be utilized such as a hard disk. Additional devices may communicate via theinterconnection network 504, such as multiple CPUs and/or multiple system memories. - The
MCH 508 may also include agraphics interface 514 that communicates with adisplay device 516. In one embodiment of the invention, thegraphics interface 514 may communicate with thedisplay device 516 via an accelerated graphics port (AGP). In an embodiment of the invention, the display 516 (such as a flat panel display) may communicate with the graphics interface 514 through, for example, a signal converter that translates a digital representation of an image stored in a storage device such as video memory or system memory into display signals that are interpreted and displayed by thedisplay 516. The display signals produced by the display device may pass through various control devices before being interpreted by and subsequently displayed on thedisplay 516. - A
hub interface 518 may allow theMCH 508 and an input/output control hub (ICH) 520 to communicate. TheICH 520 may provide an interface to I/O device(s) that communicate with thecomputing system 500. TheICH 520 may communicate with abus 522 through a peripheral bridge (or controller) 524, such as a peripheral component interconnect (PCI) bridge, a universal serial bus (USB) controller, or other types of peripheral bridges or controllers. Thebridge 524 may provide a data path between theCPU 502 and peripheral devices. Other types of topologies may be utilized. Also, multiple buses may communicate with theICH 520, e.g., through multiple bridges or controllers. Moreover, other peripherals in communication with theICH 520 may include, in various embodiments of the invention, integrated drive electronics (IDE) or small computer system interface (SCSI) hard drive(s), USB port(s), a keyboard, a mouse, parallel port(s), serial port(s), floppy disk drive(s), digital output support (e.g., digital video interface (DVI)), or other devices. - The
bus 522 may communicate with anaudio device 526, one or more disk drive(s) 528, and a network interface device 530 (which is in communication with the computer network 503). Other devices may communicate via thebus 522. Also, various components (such as the network interface device 530) may communicate with theMCH 508 in some embodiments of the invention. In addition, theprocessor 502 and theMCH 508 may be combined to form a single chip. Furthermore, thegraphics accelerator 516 may be included within theMCH 508 in other embodiments of the invention. - Furthermore, the
computing system 500 may include volatile and/or nonvolatile memory (or storage). For example, nonvolatile memory may include one or more of the following: read-only memory (ROM), programmable ROM (PROM), erasable PROM (EPROM), electrically EPROM (EEPROM), a disk drive (e.g., 528), a floppy disk, a compact disk ROM (CD-ROM), a digital versatile disk (DVD), flash memory, a magneto-optical disk, or other types of nonvolatile machine-readable media that are capable of storing electronic data (e.g., including instructions). -
FIG. 6 illustrates acomputing system 600 that is arranged in a point-to-point (PtP) configuration, according to an embodiment of the invention. In particular,FIG. 6 shows a system where processors, memory, and input/output devices are interconnected by a number of point-to-point interfaces. The operations discussed with reference toFIGS. 1-5 may be performed by one or more components of thesystem 600. - As illustrated in
FIG. 6 , thesystem 600 may include several processors, of which only two,processors processors memories memories 610 and/or 612 may store various data such as those discussed with reference to thememory 512 ofFIG. 5 . - In an embodiment, the
processors processors 502 discussed with reference toFIG. 5 . Theprocessors interface 614 usingPtP interface circuits processors chipset 620 via individual PtP interfaces 622 and 624 using point-to-point interface circuits chipset 620 may further exchange data with agraphics circuit 634 via agraphics interface 636, e.g., using aPtP interface circuit 637. - At least one embodiment of the invention may be provided within the
processors cores 106 ofFIGS. 1-5 may be located within theprocessors system 600 ofFIG. 6 . Furthermore, other embodiments of the invention may be distributed throughout several circuits, logic units, or devices illustrated inFIG. 6 . - The
chipset 620 may communicate with abus 640 using aPtP interface circuit 641. Thebus 640 may communicate with one or more devices, such as a bus bridge 642 and I/O devices 643. Via abus 644, the bus bridge 642 may communicate with other devices such as a keyboard/mouse 645, communication devices 646 (such as modems, network interface devices, or other communication devices that may communicate with the computer network 503), audio I/O device 647, and/or adata storage device 648. Thedata storage device 648 may storecode 649 that may be executed by theprocessors 602 and/or 604. - In various embodiments of the invention, the operations discussed herein, e.g., with reference to
FIGS. 1-6 , may be implemented as hardware (e.g., logic circuitry), software, firmware, or combinations thereof, which may be provided as a computer program product, e.g., including (e.g., a non-transitory) machine-readable or computer-readable medium having stored thereon instructions (or software procedures) used to program a computer to perform a process discussed herein. The machine-readable medium may include a storage device such as those discussed with respect toFIGS. 1-6 . - Additionally, such computer-readable media may be downloaded as a computer program product, wherein the program may be transferred from a remote computer (e.g., a server) to a requesting computer (e.g., a client) by way of data signals embodied in a carrier wave or other propagation medium via a communication link (e.g., a bus, a modem, or a network connection).
- Reference in the specification to “one embodiment,” “an embodiment,” or “some embodiments” means that a particular feature, structure, or characteristic described in connection with the embodiment(s) may be included in at least an implementation. The appearances of the phrase “in one embodiment” in various places in the specification may or may not be all referring to the same embodiment.
- Also, in the description and claims, the terms “coupled” and “connected,” along with their derivatives, may be used. In some embodiments of the invention, “connected” may be used to indicate that two or more elements are in direct physical or electrical contact with each other. “Coupled” may mean that two or more elements are in direct physical or electrical contact. However, “coupled” may also mean that two or more elements may not be in direct contact with each other, but may still cooperate or interact with each other.
- Thus, although embodiments of the invention have been described in language specific to structural features and/or methodological acts, it is to be understood that claimed subject matter may not be limited to the specific features or acts described. Rather, the specific features and acts are disclosed as sample forms of implementing the claimed subject matter.
Claims (10)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US14/995,198 US20160132354A1 (en) | 2010-09-25 | 2016-01-13 | Application scheduling in heterogeneous multiprocessor computing platforms |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US12/890,653 US9268611B2 (en) | 2010-09-25 | 2010-09-25 | Application scheduling in heterogeneous multiprocessor computing platform based on a ratio of predicted performance of processor cores |
US14/995,198 US20160132354A1 (en) | 2010-09-25 | 2016-01-13 | Application scheduling in heterogeneous multiprocessor computing platforms |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US12/890,653 Continuation US9268611B2 (en) | 2010-09-25 | 2010-09-25 | Application scheduling in heterogeneous multiprocessor computing platform based on a ratio of predicted performance of processor cores |
Publications (1)
Publication Number | Publication Date |
---|---|
US20160132354A1 true US20160132354A1 (en) | 2016-05-12 |
Family
ID=45871864
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US12/890,653 Active 2031-09-05 US9268611B2 (en) | 2010-09-25 | 2010-09-25 | Application scheduling in heterogeneous multiprocessor computing platform based on a ratio of predicted performance of processor cores |
US14/995,198 Abandoned US20160132354A1 (en) | 2010-09-25 | 2016-01-13 | Application scheduling in heterogeneous multiprocessor computing platforms |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US12/890,653 Active 2031-09-05 US9268611B2 (en) | 2010-09-25 | 2010-09-25 | Application scheduling in heterogeneous multiprocessor computing platform based on a ratio of predicted performance of processor cores |
Country Status (9)
Country | Link |
---|---|
US (2) | US9268611B2 (en) |
JP (1) | JP5774707B2 (en) |
KR (2) | KR20140114074A (en) |
CN (1) | CN103119580B (en) |
BR (1) | BR112013006483A2 (en) |
DE (1) | DE112011103216T5 (en) |
GB (1) | GB2497449B (en) |
TW (3) | TWI603207B (en) |
WO (1) | WO2012040684A2 (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140337849A1 (en) * | 2013-05-13 | 2014-11-13 | Korea Advanced Institute Of Science And Technology | Apparatus and job scheduling method thereof |
Families Citing this family (46)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8397088B1 (en) | 2009-07-21 | 2013-03-12 | The Research Foundation Of State University Of New York | Apparatus and method for efficient estimation of the energy dissipation of processor based systems |
US10185566B2 (en) * | 2012-04-27 | 2019-01-22 | Intel Corporation | Migrating tasks between asymmetric computing elements of a multi-core processor |
WO2013178864A1 (en) * | 2012-05-29 | 2013-12-05 | Nokia Corporation | A method and apparatus for deferring processor selection |
WO2013177765A1 (en) | 2012-05-30 | 2013-12-05 | Intel Corporation | Runtime dispatching among heterogeneous group of processors |
KR102001414B1 (en) | 2012-09-27 | 2019-07-18 | 삼성전자주식회사 | System-on-chip controlling power supply correspond to data transaction and operating method thereof |
US9037889B2 (en) | 2012-09-28 | 2015-05-19 | Intel Corporation | Apparatus and method for determining the number of execution cores to keep active in a processor |
US9619284B2 (en) | 2012-10-04 | 2017-04-11 | Intel Corporation | Dynamically switching a workload between heterogeneous cores of a processor |
US8949659B2 (en) | 2012-10-18 | 2015-02-03 | International Business Machines Corporation | Scheduling workloads based on detected hardware errors |
DE112012007115T5 (en) * | 2012-12-28 | 2015-08-20 | Paul Brett | Optional logic processor count and type selection for a given workload based on platform heat and power budget constraints |
US9442559B2 (en) | 2013-03-14 | 2016-09-13 | Intel Corporation | Exploiting process variation in a multicore processor |
US9727345B2 (en) | 2013-03-15 | 2017-08-08 | Intel Corporation | Method for booting a heterogeneous system and presenting a symmetric core view |
KR102110812B1 (en) * | 2013-05-30 | 2020-05-14 | 삼성전자 주식회사 | Multicore system and job scheduling method thereof |
US9842040B2 (en) | 2013-06-18 | 2017-12-12 | Empire Technology Development Llc | Tracking core-level instruction set capabilities in a chip multiprocessor |
CN105765524B (en) * | 2013-10-04 | 2019-10-18 | 英特尔公司 | Technology for heterogeneous nucleus distribution |
CN103645954B (en) * | 2013-11-21 | 2018-12-14 | 华为技术有限公司 | A kind of CPU dispatching method based on heterogeneous multi-core system, device and system |
CN103646006B (en) * | 2013-11-26 | 2016-08-31 | 乐视致新电子科技(天津)有限公司 | The dispatching method of a kind of processor, device and system |
JP6260303B2 (en) | 2014-01-29 | 2018-01-17 | 富士通株式会社 | Arithmetic processing device and control method of arithmetic processing device |
CN103942103A (en) * | 2014-04-16 | 2014-07-23 | 乐视致新电子科技(天津)有限公司 | Method and device for generating processor scheduling policy in multi-core system and scheduling system |
WO2015165045A1 (en) * | 2014-04-29 | 2015-11-05 | 华为技术有限公司 | Power control method and apparatus |
KR102197874B1 (en) | 2014-09-01 | 2021-01-05 | 삼성전자주식회사 | System on chip including multi-core processor and thread scheduling method thereof |
KR102354848B1 (en) | 2014-11-28 | 2022-01-21 | 삼성전자주식회사 | Cache Memory Device and Electronic System including the Same |
US10101786B2 (en) * | 2014-12-22 | 2018-10-16 | Intel Corporation | Holistic global performance and power management |
US10133602B2 (en) * | 2015-02-19 | 2018-11-20 | Oracle International Corporation | Adaptive contention-aware thread placement for parallel runtime systems |
CN104809078B (en) * | 2015-04-14 | 2019-05-14 | 苏州中晟宏芯信息科技有限公司 | Based on the shared cache hardware resource access method for exiting yielding mechanism |
US11003565B2 (en) | 2015-04-21 | 2021-05-11 | Hewlett-Packard Development Company, L.P. | Performance change predictions |
US10073718B2 (en) | 2016-01-15 | 2018-09-11 | Intel Corporation | Systems, methods and devices for determining work placement on processor cores |
US10303488B2 (en) * | 2016-03-30 | 2019-05-28 | Sony Interactive Entertainment Inc. | Real-time adjustment of application-specific operating parameters for backwards compatibility |
US10296074B2 (en) | 2016-08-12 | 2019-05-21 | Qualcomm Incorporated | Fine-grained power optimization for heterogeneous parallel constructs |
US11513805B2 (en) * | 2016-08-19 | 2022-11-29 | Wisconsin Alumni Research Foundation | Computer architecture with synergistic heterogeneous processors |
FR3056786B1 (en) * | 2016-09-29 | 2019-11-22 | Commissariat A L'energie Atomique Et Aux Energies Alternatives | METHOD FOR MANAGING CALCULATING TASKS ON A FUNCTIONALLY ASYMMETRIC MULTI-CORE PROCESSOR |
US9747139B1 (en) * | 2016-10-19 | 2017-08-29 | International Business Machines Corporation | Performance-based multi-mode task dispatching in a multi-processor core system for high temperature avoidance |
CN110121698A (en) * | 2016-12-31 | 2019-08-13 | 英特尔公司 | System, method and apparatus for Heterogeneous Computing |
US11281586B2 (en) | 2017-05-09 | 2022-03-22 | Andes Technology Corporation | Processor and way prediction method thereof |
US10628223B2 (en) * | 2017-08-22 | 2020-04-21 | Amrita Vishwa Vidyapeetham | Optimized allocation of tasks in heterogeneous computing systems |
CN109937410B (en) * | 2017-10-25 | 2021-02-23 | 华为技术有限公司 | Core scheduling method and terminal |
US11138037B2 (en) | 2017-11-02 | 2021-10-05 | Mediatek Inc. | Switch policy for hybrid scheduling in multi-processor systems |
US10812416B2 (en) * | 2017-12-27 | 2020-10-20 | International Business Machines Corporation | Reduced number of counters for reliable messaging |
JP7047114B2 (en) | 2018-02-08 | 2022-04-04 | アリババ・グループ・ホールディング・リミテッド | Hybrid system-on-chip for power and performance prediction and control |
CN108664285A (en) * | 2018-05-10 | 2018-10-16 | Oppo广东移动通信有限公司 | Application program preloads method, apparatus, storage medium and mobile terminal |
TWI698798B (en) * | 2018-10-22 | 2020-07-11 | 致茂電子股份有限公司 | A multicore operation device and an operating method thereof |
US10649688B1 (en) * | 2018-11-01 | 2020-05-12 | Intel Corporation | Precise longitudinal monitoring of memory operations |
KR102552954B1 (en) * | 2018-11-07 | 2023-07-06 | 삼성전자주식회사 | Computing system and method for operating computing system |
GB2583103B (en) | 2019-04-16 | 2022-11-16 | Siemens Ind Software Inc | Tracing instruction execution |
US11544105B2 (en) * | 2019-09-11 | 2023-01-03 | Google Llc | Recommendations for scheduling jobs on distributed computing devices |
TWI791929B (en) * | 2019-11-28 | 2023-02-11 | 瑞昱半導體股份有限公司 | Universal profiling device and method |
CN113609126B (en) * | 2021-07-06 | 2022-03-11 | 无锡四维时空信息科技有限公司 | Integrated storage management method and system for multi-source space-time data |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040215987A1 (en) * | 2003-04-25 | 2004-10-28 | Keith Farkas | Dynamically selecting processor cores for overall power efficiency |
US20050020434A1 (en) * | 2001-10-25 | 2005-01-27 | Joachi Ansorge | Process for liquefying natural gas and producing hydrocarbons |
US20060016857A1 (en) * | 2003-12-09 | 2006-01-26 | Headings Robert S | High production welding fixture |
US7254812B1 (en) * | 2002-05-31 | 2007-08-07 | Advanced Micro Devices, Inc. | Multi-processor task scheduling |
US20090005582A1 (en) * | 2007-06-22 | 2009-01-01 | Greg Anderson | Vessels and methods for synthesis of biofuel |
US20090032805A1 (en) * | 2007-07-30 | 2009-02-05 | Michael Renne Ty Tan | Microresonator systems and methods of fabricating the same |
US20090210740A1 (en) * | 2008-02-14 | 2009-08-20 | Song Huang | Off-chip access workload characterization methodology for optimizing computing efficiency |
Family Cites Families (71)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
FR2683344B1 (en) * | 1991-10-30 | 1996-09-20 | Bull Sa | MULTIPROCESSOR SYSTEM WITH MICROPROGRAMS FOR THE DISTRIBUTION OF PROCESSES TO PROCESSORS. |
GB2272085A (en) | 1992-10-30 | 1994-05-04 | Tao Systems Ltd | Data processing system and operating system. |
JPH09167141A (en) | 1995-12-18 | 1997-06-24 | Hitachi Ltd | Load distribution control method |
US6298370B1 (en) | 1997-04-04 | 2001-10-02 | Texas Instruments Incorporated | Computer operating process allocating tasks between first and second processors at run time based upon current processor load |
US6134675A (en) | 1998-01-14 | 2000-10-17 | Motorola Inc. | Method of testing multi-core processors and multi-core processor testing device |
US6021076A (en) | 1998-07-16 | 2000-02-01 | Rambus Inc | Apparatus and method for thermal regulation in memory subsystems |
US6161188A (en) | 1998-11-17 | 2000-12-12 | Ip-First, L.L.C. | Microprocessor having fuse control and selection of clock multiplier |
US6728892B1 (en) | 1999-09-15 | 2004-04-27 | Koninklijke Philips Electronics N.V. | Method for conserving power in a can microcontroller and a can microcontroller that implements this method |
JP2001175627A (en) * | 1999-12-21 | 2001-06-29 | Toshiba Corp | Decentralized processing computer system |
US7165257B2 (en) | 2000-02-08 | 2007-01-16 | Mips Technologies, Inc. | Context selection and activation mechanism for activating one of a group of inactive contexts in a processor core for servicing interrupts |
US7032119B2 (en) | 2000-09-27 | 2006-04-18 | Amphus, Inc. | Dynamic power and workload management for multi-server system |
US20030070013A1 (en) | 2000-10-27 | 2003-04-10 | Daniel Hansson | Method and apparatus for reducing power consumption in a digital processor |
US7140016B2 (en) | 2000-11-29 | 2006-11-21 | Texas Instruments Incorporated | Media accelerator quality of service |
JP3817449B2 (en) | 2001-07-30 | 2006-09-06 | 株式会社ルネサステクノロジ | Data processing device |
US6804632B2 (en) | 2001-12-06 | 2004-10-12 | Intel Corporation | Distribution of processing activity across processing hardware based on power consumption considerations |
US6907548B2 (en) | 2002-01-02 | 2005-06-14 | Intel Corporation | Automatic testing for multi-core architecture |
US20040006729A1 (en) | 2002-07-03 | 2004-01-08 | Pendurkar Rajesh Y. | Hierarchical test methodology for multi-core chips |
KR100498487B1 (en) | 2003-02-08 | 2005-07-01 | 삼성전자주식회사 | Processor having a high speed control circuit and a low-speed and low-power control circuit |
JP4090908B2 (en) | 2003-02-21 | 2008-05-28 | シャープ株式会社 | Image processing apparatus and image forming apparatus |
DE10313605B4 (en) | 2003-03-26 | 2009-03-19 | Qimonda Ag | Apparatus and method for controlling a plurality of memory devices |
US7197652B2 (en) | 2003-12-22 | 2007-03-27 | International Business Machines Corporation | Method and system for energy management in a simultaneous multi-threaded (SMT) processing system including per-thread device usage monitoring |
EP1555595A3 (en) | 2004-01-13 | 2011-11-23 | LG Electronics, Inc. | Apparatus for controlling power of processor having a plurality of cores and control method of the same |
US7984442B2 (en) | 2004-01-29 | 2011-07-19 | Klingman Edwin E | Intelligent memory device multilevel ASCII interpreter |
US20050204346A1 (en) * | 2004-03-09 | 2005-09-15 | Intel Corporation | Using sampling data for program phase detection |
JP3862715B2 (en) | 2004-06-01 | 2006-12-27 | 株式会社ソニー・コンピュータエンタテインメント | Task management method, task management device, semiconductor integrated circuit, electronic device, and task management system |
JP4197672B2 (en) | 2004-09-30 | 2008-12-17 | 株式会社東芝 | Multiprocessor computer and program |
US7788670B2 (en) * | 2004-10-26 | 2010-08-31 | Intel Corporation | Performance-based workload scheduling in multi-core architectures |
US20060168571A1 (en) * | 2005-01-27 | 2006-07-27 | International Business Machines Corporation | System and method for optimized task scheduling in a heterogeneous data processing system |
US20060212677A1 (en) | 2005-03-15 | 2006-09-21 | Intel Corporation | Multicore processor having active and inactive execution cores |
TW200638267A (en) | 2005-04-22 | 2006-11-01 | Chi Mei Comm Systems Inc | Method for adjusting CPU speed of an electronic appliance |
JP4838240B2 (en) | 2005-04-27 | 2011-12-14 | パナソニック株式会社 | Power control apparatus in information processing apparatus |
TWI300903B (en) | 2005-07-01 | 2008-09-11 | Hon Hai Prec Ind Co Ltd | Method for estimating cpu power |
JP4367856B2 (en) | 2005-07-07 | 2009-11-18 | レノボ シンガポール プライヴェート リミテッド | Process control system and control method thereof |
US7694107B2 (en) * | 2005-08-18 | 2010-04-06 | Hewlett-Packard Development Company, L.P. | Dynamic performance ratio proportionate distribution of threads with evenly divided workload by homogeneous algorithm to heterogeneous computing units |
US7412353B2 (en) | 2005-09-28 | 2008-08-12 | Intel Corporation | Reliable computing with a many-core processor |
GB0519981D0 (en) | 2005-09-30 | 2005-11-09 | Ignios Ltd | Scheduling in a multicore architecture |
TW200805047A (en) | 2005-12-23 | 2008-01-16 | Koninkl Philips Electronics Nv | Performance analysis based system level power management |
WO2007098424A2 (en) | 2006-02-17 | 2007-08-30 | Qualcomm Incorporated | System and method for multi-processor application support |
US7596430B2 (en) | 2006-05-03 | 2009-09-29 | International Business Machines Corporation | Selection of processor cores for optimal thermal performance |
US7406407B2 (en) | 2006-06-01 | 2008-07-29 | Microsoft Corporation | Virtual machine for operating N-core application on M-core processor |
US20070294693A1 (en) | 2006-06-16 | 2007-12-20 | Microsoft Corporation | Scheduling thread execution among a plurality of processors based on evaluation of memory access data |
US7493477B2 (en) | 2006-06-30 | 2009-02-17 | Intel Corporation | Method and apparatus for disabling a processor core based on a number of executions of an application exceeding a threshold |
US7463992B2 (en) | 2006-09-29 | 2008-12-09 | Intel Corporation | Method and system to self-test single and multi-core CPU systems |
JP2008090546A (en) | 2006-09-29 | 2008-04-17 | Toshiba Corp | Multiprocessor system |
US7596714B2 (en) | 2006-11-20 | 2009-09-29 | Intel Corporation | Methods and apparatus to manage throttling in computing environments |
US8819699B2 (en) * | 2006-12-29 | 2014-08-26 | Intel Corporation | Controlling virtual machines based on performance counters |
US8615767B2 (en) | 2007-02-06 | 2013-12-24 | International Business Machines Corporation | Using IR drop data for instruction thread direction |
US7895454B2 (en) | 2007-02-06 | 2011-02-22 | International Business Machines Corporation | Instruction dependent dynamic voltage compensation |
US7560945B2 (en) | 2007-02-06 | 2009-07-14 | International Business Machines Corporation | Integrated circuit failure prediction |
US7971035B2 (en) | 2007-02-06 | 2011-06-28 | International Business Machines Corporation | Using temperature data for instruction thread direction |
US8022685B2 (en) | 2007-02-06 | 2011-09-20 | International Business Machines Corporation | Temperature dependent voltage source compensation |
US7714635B2 (en) | 2007-02-06 | 2010-05-11 | International Business Machines Corporation | Digital adaptive voltage supply |
US7936153B2 (en) | 2007-02-06 | 2011-05-03 | International Business Machines Corporation | On-chip adaptive voltage compensation |
US7865750B2 (en) | 2007-02-06 | 2011-01-04 | International Business Machines Corporation | Fan speed control from adaptive voltage supply |
US7779235B2 (en) * | 2007-02-06 | 2010-08-17 | International Business Machines Corporation | Using performance data for instruction thread direction |
US8161482B1 (en) * | 2007-04-13 | 2012-04-17 | Marvell International Ltd. | Power optimization for multi-core devices |
US8001338B2 (en) | 2007-08-21 | 2011-08-16 | Microsoft Corporation | Multi-level DRAM controller to manage access to DRAM |
US8055822B2 (en) * | 2007-08-21 | 2011-11-08 | International Business Machines Corporation | Multicore processor having storage for core-specific operational data |
US8005880B2 (en) | 2007-08-24 | 2011-08-23 | International Business Machines Corporation | Half width counting leading zero circuit |
US8185572B2 (en) | 2007-08-24 | 2012-05-22 | International Business Machines Corporation | Data correction circuit |
US7797131B2 (en) * | 2007-08-24 | 2010-09-14 | International Business Machines Corporation | On-chip frequency response measurement |
US8332865B2 (en) | 2008-02-21 | 2012-12-11 | International Business Machines Corporation | Adjunct processor load balancing |
US20090288092A1 (en) * | 2008-05-15 | 2009-11-19 | Hiroaki Yamaoka | Systems and Methods for Improving the Reliability of a Multi-Core Processor |
US8276145B2 (en) * | 2008-06-27 | 2012-09-25 | Microsoft Corporation | Protected mode scheduling of operations |
JP2010039923A (en) * | 2008-08-07 | 2010-02-18 | Hitachi Ltd | Information processor |
US8661129B2 (en) * | 2008-11-05 | 2014-02-25 | Xerox Corporation | System and method for decentralized job scheduling and distributed execution in a network of multifunction devices |
US8161304B2 (en) | 2009-01-20 | 2012-04-17 | Microsoft Corporation | Power management for large memory subsystems |
US8572581B2 (en) * | 2009-03-26 | 2013-10-29 | Microsoft Corporation | Measurement and reporting of performance event rates |
US8055805B2 (en) | 2009-03-31 | 2011-11-08 | Intel Corporation | Opportunistic improvement of MMIO request handling based on target reporting of space requirements |
JP5091912B2 (en) * | 2009-05-21 | 2012-12-05 | 株式会社東芝 | Multi-core processor system |
US8924975B2 (en) * | 2009-07-23 | 2014-12-30 | Empire Technology Development Llc | Core selection for applications running on multiprocessor systems based on core and application characteristics |
-
2010
- 2010-09-25 US US12/890,653 patent/US9268611B2/en active Active
-
2011
- 2011-09-24 DE DE112011103216T patent/DE112011103216T5/en not_active Withdrawn
- 2011-09-24 GB GB1303285.9A patent/GB2497449B/en not_active Expired - Fee Related
- 2011-09-24 KR KR1020147024707A patent/KR20140114074A/en not_active Application Discontinuation
- 2011-09-24 CN CN201180046075.8A patent/CN103119580B/en not_active Expired - Fee Related
- 2011-09-24 JP JP2013529449A patent/JP5774707B2/en not_active Expired - Fee Related
- 2011-09-24 BR BR112013006483A patent/BR112013006483A2/en not_active Application Discontinuation
- 2011-09-24 KR KR1020137007312A patent/KR101561496B1/en active IP Right Grant
- 2011-09-24 WO PCT/US2011/053177 patent/WO2012040684A2/en active Application Filing
- 2011-09-26 TW TW105119960A patent/TWI603207B/en not_active IP Right Cessation
- 2011-09-26 TW TW100134629A patent/TWI450104B/en not_active IP Right Cessation
- 2011-09-26 TW TW103120160A patent/TWI550413B/en not_active IP Right Cessation
-
2016
- 2016-01-13 US US14/995,198 patent/US20160132354A1/en not_active Abandoned
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050020434A1 (en) * | 2001-10-25 | 2005-01-27 | Joachi Ansorge | Process for liquefying natural gas and producing hydrocarbons |
US7254812B1 (en) * | 2002-05-31 | 2007-08-07 | Advanced Micro Devices, Inc. | Multi-processor task scheduling |
US20040215987A1 (en) * | 2003-04-25 | 2004-10-28 | Keith Farkas | Dynamically selecting processor cores for overall power efficiency |
US20060016857A1 (en) * | 2003-12-09 | 2006-01-26 | Headings Robert S | High production welding fixture |
US20090005582A1 (en) * | 2007-06-22 | 2009-01-01 | Greg Anderson | Vessels and methods for synthesis of biofuel |
US20090032805A1 (en) * | 2007-07-30 | 2009-02-05 | Michael Renne Ty Tan | Microresonator systems and methods of fabricating the same |
US20090210740A1 (en) * | 2008-02-14 | 2009-08-20 | Song Huang | Off-chip access workload characterization methodology for optimizing computing efficiency |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140337849A1 (en) * | 2013-05-13 | 2014-11-13 | Korea Advanced Institute Of Science And Technology | Apparatus and job scheduling method thereof |
US9645855B2 (en) * | 2013-05-13 | 2017-05-09 | Samsung Electronics Co., Ltd. | Job scheduling optimization based on ratio of stall to active cycles |
Also Published As
Publication number | Publication date |
---|---|
WO2012040684A2 (en) | 2012-03-29 |
KR20130062999A (en) | 2013-06-13 |
TW201714103A (en) | 2017-04-16 |
TW201437828A (en) | 2014-10-01 |
TWI450104B (en) | 2014-08-21 |
GB201303285D0 (en) | 2013-04-10 |
TWI603207B (en) | 2017-10-21 |
DE112011103216T5 (en) | 2013-07-04 |
CN103119580B (en) | 2016-08-17 |
BR112013006483A2 (en) | 2016-07-26 |
TW201229781A (en) | 2012-07-16 |
TWI550413B (en) | 2016-09-21 |
GB2497449B (en) | 2019-02-20 |
GB2497449A (en) | 2013-06-12 |
KR20140114074A (en) | 2014-09-25 |
JP5774707B2 (en) | 2015-09-09 |
JP2013537346A (en) | 2013-09-30 |
WO2012040684A3 (en) | 2012-06-07 |
US9268611B2 (en) | 2016-02-23 |
KR101561496B1 (en) | 2015-10-20 |
CN103119580A (en) | 2013-05-22 |
US20120079235A1 (en) | 2012-03-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9268611B2 (en) | Application scheduling in heterogeneous multiprocessor computing platform based on a ratio of predicted performance of processor cores | |
Chen et al. | Xuantie-910: A commercial multi-core 12-stage pipeline out-of-order 64-bit high performance RISC-V processor with vector extension: Industrial product | |
US11768533B2 (en) | Platform power consumption reduction via power state switching | |
US7788670B2 (en) | Performance-based workload scheduling in multi-core architectures | |
JP5932044B2 (en) | Application event control (PAEC) based on priority to reduce power consumption | |
US10156884B2 (en) | Local power gate (LPG) interfaces for power-aware operations | |
EP2761394B1 (en) | Constrained boot techniques in multi-core platforms | |
US9152473B2 (en) | Table driven multiple passive trip platform passive thermal management | |
US9684541B2 (en) | Method and apparatus for determining thread execution parallelism | |
Pandey et al. | Performance analysis of intel ivy bridge and intel broadwell microarchitectures using intel vtune amplifier software | |
Do et al. | Application characteristics-aware sporadic cache bypassing for high performance GPGPUs |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
STPP | Information on status: patent application and granting procedure in general |
Free format text: RESPONSE TO NON-FINAL OFFICE ACTION ENTERED AND FORWARDED TO EXAMINER |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: FINAL REJECTION MAILED |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: DOCKETED NEW CASE - READY FOR EXAMINATION |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: NON FINAL ACTION MAILED |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: RESPONSE TO NON-FINAL OFFICE ACTION ENTERED AND FORWARDED TO EXAMINER |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: FINAL REJECTION MAILED |
|
STCB | Information on status: application discontinuation |
Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION |
|
AS | Assignment |
Owner name: TAHOE RESEARCH, LTD., IRELAND Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:INTEL CORPORATION;REEL/FRAME:061175/0176 Effective date: 20220718 |