[go: up one dir, main page]

WO2018137258A1 - Modules chargeables avec liaison partielle et transfert de temps de charge - Google Patents

Modules chargeables avec liaison partielle et transfert de temps de charge Download PDF

Info

Publication number
WO2018137258A1
WO2018137258A1 PCT/CN2017/072788 CN2017072788W WO2018137258A1 WO 2018137258 A1 WO2018137258 A1 WO 2018137258A1 CN 2017072788 W CN2017072788 W CN 2017072788W WO 2018137258 A1 WO2018137258 A1 WO 2018137258A1
Authority
WO
WIPO (PCT)
Prior art keywords
space
loadable module
literal
memory
loadable
Prior art date
Application number
PCT/CN2017/072788
Other languages
English (en)
Inventor
Zhi Chen
Yusheng Yang
Original Assignee
Qualcomm Incorporated
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Qualcomm Incorporated filed Critical Qualcomm Incorporated
Priority to PCT/CN2017/072788 priority Critical patent/WO2018137258A1/fr
Publication of WO2018137258A1 publication Critical patent/WO2018137258A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06F9/44—Arrangements for executing specific programs
    • G06F9/445—Program loading or initiating
    • G06F9/44521—Dynamic linking or loading; Link editing at or after load time, e.g. Java class loading
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F8/00—Arrangements for software engineering
    • G06F8/40—Transformation of program code
    • G06F8/41—Compilation
    • G06F8/44—Encoding
    • G06F8/447—Target code generation
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F8/00—Arrangements for software engineering
    • G06F8/40—Transformation of program code
    • G06F8/54—Link editing before load time

Definitions

  • Loadable module is a technology extensively used in designing software modules and device drivers.
  • loadable modules provide a flexible way to design software and reduce memory size requirements.
  • a loadable module generally refers to an object file that contains code to extend a running kernel (or base kernel) associated with an operating system.
  • loadable modules may be used to define device drivers to support new hardware, to support new filesystems, and add system calls that allow applications running in an unprivileged or restricted mode to request a service from the operating system kernel, among other things.
  • Loadable modules therefore offer various advantages, including that operating systems lacking loadable module support would be required to have all possible functionality compiled directly into the base kernel, which would waste memory because substantial unused functionality would reside in memory.
  • the loadable module can be dynamically loaded into memory and later unloaded to free memory and other resources when not needed.
  • loadable module technology can offer, there are some computing platforms that are unable to use loadable modules.
  • hardware-limited platforms with small memory size e.g., Internet of Things (IoT) devices
  • processors that lack a memory management unit (MMU) may have processors that lack a memory management unit (MMU) . Consequently, difficulties may arise with respect to managing memory allocations associated with loadable modules because all memory access instructions have to use absolute addresses.
  • processors that use absolute memory addresses at least some instructions may only have the ability to access a restricted memory range, which means that the compiler may be unable to generate position-independent code that can be executed at any memory address regardless of the absolute address.
  • a method for implementing a loadable module may comprise reserving literal memory space to the loadable module on a processor running in an absolute addressing mode, generating a partial linking that combines one or more object files associated with the loadable module with operating system exported symbols, and allocating literal space to the loadable module from the reserved literal memory space to initialize the loadable module.
  • an apparatus may comprise a memory comprising at least an instruction random access memory (RAM) and a processor configured to reserve literal memory space to a loadable module running in an absolute addressing mode, generate, via a linking tool, a partial linking that combines one or more object files associated with the loadable module with operating system exported symbols, and allocate literal space to the loadable module from the reserved literal memory space to initialize the loadable module.
  • RAM instruction random access memory
  • an apparatus may comprise means for reserving literal memory space to a loadable module configured to run in an absolute addressing mode, means for generating a partial linking that combines one or more object files associated with the loadable module with operating system exported symbols, and means for allocating literal space to the loadable module from the reserved literal memory space to initialize the loadable module.
  • a computer-readable medium may store computer-executable instructions, which may be configured to cause one or more processors to reserve literal memory space to a loadable module configured to run in an absolute addressing mode, generate a partial linking that combines one or more object files associated with the loadable module with operating system exported symbols, and allocate literal space to the loadable module from the reserved literal memory space to initialize the loadable module.
  • FIG. 1 illustrates an exemplary layered computer architecture in which in which loadable modules as described herein may be implemented, according to various aspects.
  • FIG. 2 illustrates an exemplary memory space reservation that can be used to implement a loadable module as described herein, according to various aspects.
  • FIG. 3 illustrates an exemplary design approach to generate a loadable module with a partial linking as described herein, according to various aspects.
  • FIG. 4 illustrates an exemplary load-time memory relocation that can be used to implement a loadable module as described herein, according to various aspects.
  • FIG. 5 illustrates an exemplary method to implement a loadable module with partial linking and load-time relocation as described herein, according to various aspects.
  • FIG. 6 illustrates an example electronic device in which loadable modules as described herein may be advantageously implemented.
  • various aspects and/or embodiments may be described in terms of sequences of actions to be performed by, for example, elements of a computing device.
  • Those skilled in the art will recognize that various actions described herein can be performed by specific circuits (e.g., an application specific integrated circuit (ASIC)) , by program instructions being executed by one or more processors, or by a combination of both.
  • ASIC application specific integrated circuit
  • these sequences of actions described herein can be considered to be embodied entirely within any form of non-transitory computer-readable medium having stored thereon a corresponding set of computer instructions that upon execution would cause an associated processor to perform the functionality described herein.
  • FIG. 1 illustrates an exemplary layered computer architecture 100 in which in which loadable modules as described herein may be implemented.
  • the layered computer architecture 100 shown in FIG. 1 includes various logical components and interfaces to explain certain aspects associated with the loadable module design approach described herein.
  • those skilled in the art will appreciate that the present disclosure contemplates that various changes may be made to the architecture 100 as shown in FIG. 1 and that certain details that are not germane to the loadable module design approach described herein may be omitted for clarity.
  • the example architecture 100 includes both hardware components and software components, wherein the hardware components generally include physical memory 104, input/output (I/O) devices 106, and execution hardware 102 (e.g., an application processor, a digital signal processor, etc. ) .
  • the software components may include an operating system 112, a libraries module 122, and one or more application programs 132.
  • the application programs 132 generally use an application program interface (API) 130 to issue library calls to the libraries module 122, which may use an application binary interface (ABI) 120 to invoke services on the operating system 112 (e.g., via system calls) .
  • API application program interface
  • ABSI application binary interface
  • the operating system 108 therefore runs instructions in supervisor mode to communicate with the hardware components using a specific instruction set architecture (ISA) 110, which may include specific operation codes (opcodes) and native commands implemented on the execution hardware 102.
  • ISA instruction set architecture
  • the ABI 120 defines the machine as seen from the perspective of the application program processes, whereas the API 132 specifies the machine characteristics as seen from the perspective of a high-level language program and the ISA 110 defines the machine as seen from the perspective of the operating system 112.
  • the software components may be further divided into a kernel space and a user space to provide hardware protection from malicious or unexpected software behavior, to allow different instructions to execute with different privilege levels, etc.
  • the architecture 100 as shown in FIG. 1 may support loadable modules that are often used to design software and reduce memory requirements.
  • the operating system 112 may include a base kernel and provide support to dynamically load and unload one or more loadable modules to extend the base kernel.
  • loadable modules offer the ability to define device drivers to support new I/O devices 106 or other hardware, to support new filesystems, and add system calls that allow application programs 132 running in an unprivileged or restricted mode to request a service from the operating system 112 without requiring that functionality to be directly linked within the base kernel when the operating system 112 is compiled.
  • Loadable modules therefore offer various advantages, including that certain functionality can be excluded from the base kernel, which may improve memory efficiency.
  • loadable modules are well-suited to defining device drivers because the base kernel can communicate with the underlying hardware without having to know how the hardware works and without requiring every driver to be built into the base kernel.
  • loadable modules have various advantageous aspects, loadable modules are not easily implemented in all computing platforms.
  • the memory 104 may have a small size and processors or other execution hardware 102 may lack a memory management unit (MMU) . Consequently, difficulties may arise with respect to managing memory allocations associated with loadable modules in memory-constrained platforms where memory access instructions use absolute addresses.
  • processors that use absolute memory addresses at least some instructions may only have the ability to access a restricted memory range, which means that the compiler may be unable to generate position-independent code that can be executed at any memory address regardless of the absolute address.
  • implementing loadable modules may be difficult in platforms in which the operating system 112 and applications 132 (and/or libraries 122) are compiled together as one binary image because the symbol table may be stripped from the binary image, meaning that there is no symbol information at run-time.
  • the following description provides a design approach that can be used to implement loadable modules in these hardware-limited platforms.
  • the loadable module design approach described herein may be suitably applied in other platforms that may or may not be considered hardware-limited, memory-constrained, etc.
  • the loadable module design approach may include a memory space reservation to support instructions that may only have the ability to access a restricted memory range, a compile-time partial linking, and a load-time relocation.
  • FIG. 2 illustrates an exemplary memory space reservation 200 that can be used to implement a loadable module in a platform that includes one or more instructions that can only access a restricted memory range.
  • FIG. 2 illustrates an exemplary instruction random access memory (RAM) 210, which may provide an internal read-write instruction memory on a processor.
  • the instruction RAM 210 may be used (or useful) when all the code to run a particular application can fit within a small memory such that a separate instruction cache may not be necessary.
  • the instruction RAM 210 could be used as an additional instruction store in parallel with the instruction cache to store instructions associated with code that requires constant access time.
  • the instruction RAM 210 may be provided on a processor (not explicitly shown) that can run in an “absolute” mode in which all memory accesses use absolute addresses (or specific addresses) as distinct from relative addresses that specify a memory location relative to some base address.
  • the ISA may include one or more absolute address related instructions that cannot access all memory locations.
  • the instruction “L32R” can only access a 256KB memory space that starts at a literal base address 220.
  • the instruction RAM 210 may include a valid address-restricted range 226 with a first space 222 allocated to operating system and application literals.
  • the term “literal” and variants thereof may generally refer to a source code notation used to represent a fixed value (e.g., atomic integer values, floating-point numbers, strings, etc., in contrast to variables or constants that are symbols that can take on a literal value) .
  • the memory space reservation 200 may reserve literal memory space 224 to the loadable module (s) within the address-restricted instruction range 226 while compiling the operating system and application (s) into a binary image.
  • the reserved literal memory space 224 may be dedicated to storing data associated with any literals that may be defined in the loadable module (s) , whereby absolute address related instructions permitted to access the instruction RAM 210 may be guaranteed the ability to reach any memory locations that store literals associated with the operating system, applications, and any loadable modules dynamically loaded at run-time.
  • the instruction RAM 210 may include a space 230 allocated to operating system and application text (e.g., the executable object code) and an unused portion 240 that may dynamically allocated to text or executable object code associated with the loadable modules, as described below.
  • FIG. 3 illustrates an exemplary design approach 300 to generate a loadable module with a partial linking as described herein.
  • the loadable module may generally be defined in one or more source files 310, 312, 314, which may be suitably compiled into corresponding object files 320, 322, 324 using any suitable known or future-developed technique (s) .
  • the object files 320, 322, 324 may be provided to a linking tool 340 along with any operating system and application exported symbols 330.
  • the linking tool 340 may be configured to generate a partial linking that combines the loadable module object files 320, 322, 324 and the operating system and application exported symbols 330.
  • the linking tool 340 may be the “ld” command line utility, which may generate a partial linking when invoked with the optional “-r” (or “relocatable output) parameter.
  • the output from the linking tool 340 may be an output file that can in turn serve as an input to the linking tool 340.
  • the partial linking may be used to output a loadable module object file 350 in which all external symbols (e.g., the operating system and application exported symbols 330) are linked as absolute addresses.
  • the loadable module object file 350 may be generated according to the Executable and Linkable Format (ELF) standard binary file format supported on many different operating systems and platforms.
  • ELF Executable and Linkable Format
  • an exemplary load-time memory relocation 400 that can be used to implement a loadable module as described herein will now be described with reference to FIG. 4. More particularly, the load-time memory relocation 400 as shown in FIG. 4 may generally be carried out on a processor configured to run in an absolute mode in which all memory access instructions use absolute addresses and one or more applications are compiled together with an operating system as one binary image with a symbol table stripped from the binary image. As shown in FIG. 4, an instruction RAM 410 may include an operating system and application literal space 422 and a loadable module reserved literal space 424, which may collectively span a valid range that one or more address-restricted instructions can access.
  • the instruction RAM 430 may include space allocated to operating system and application text (e.g., executable object code) .
  • management code built into the operating system may dynamically load one or more loadable modules into the instruction RAM 410. Accordingly, as shown in FIG. 4, the operating system may allocate literal space 426 to the loadable module from the reserved literal space 424. Furthermore, the operating system may allocate text space 442 to the loadable module from the unused portion 440 in the instruction RAM 410 and further allocate data space 466 to initialized data associated with the loadable module from unused space 470 in a data RAM 450.
  • the operating system and application may be allocated data space 462 in the data RAM 450 and one or more dynamic buffers 464 may be further allocated in the data RAM 450.
  • a relocation may then be performed to calculate and patch addresses associated with all internal functions and all internal variables associated with the loadable module according to the start addresses associated with the loadable module text segment 442 and the loadable module data segment 466.
  • one or more absolute address related instructions e.g., “L32R”
  • L32R absolute address related instructions
  • the loadable module literal segment 426, the loadable module text segment 442, and the loadable module data segment 466 may collectively represent the dynamically relocated segments 480 associated with the loadable module, which are allocated among the instruction RAM 410 and the data RAM 450 as shown in FIG. 4.
  • the “init” function associated with the loadable module may then be executed to start the loadable module, and at some future point in time, the “exit” function may be executed to start an unloading stage. Accordingly, after the “exit” function is executed, the loadable module literal segment 426, the loadable module text segment 442, and the loadable module data segment 466 may be released from the instruction RAM 410 and the data RAM 450.
  • FIG. 5 illustrates an exemplary method 500 to implement a loadable module with partial linking and load-time relocation as described herein.
  • literal space may be reserved to the loadable module while compiling an operating system binary image.
  • the literal space may be reserved in an instruction RAM within a valid range accessible to one or more absolute address related instructions.
  • a partial linking that combines one or more object files associated with the loadable module and any operating system and application exported symbols may be generated.
  • the partial linking generated at block 520 may be an output file that can in turn serve as an input to a linking tool or utility that generated the partial linking, which may link all external symbols as absolute addresses.
  • the memory space reservation and the partial linking may thereby enable an operating system to dynamically load and unload the loadable module at run-time. More particularly, at block 530, the operating system may allocate literal space to the loadable module from the literal space that was reserved at block 510, while text and data spaces may be allocated from unused space in an instruction RAM and a data RAM, respectively. At block 540, addresses associated with all internal functions and all internal variables associated with the loadable module may be calculated and patched according to the start address associated with the literal, text, and data segments allocated to the loadable module. Furthermore, one or more absolute address related instructions may be patched with the address associated with the literal segment allocated to the loadable module.
  • a function to initialize the loadable module may be executed to start the loadable module, and at some future point in time, a function to exit or otherwise terminate the loadable module may be executed. After the exit function has been executed, the operating system may release the literal, text, and data segments allocated to the loadable module at block 560.
  • FIG. 6 illustrates an example electronic device 600 that may advantageously implement loadable modules with partial linking and load-time relocation as described in further detail above with reference to FIG. 1 through FIG. 5.
  • the electronic device 600 may be configured as a wireless device.
  • the electronic device 600 may include a processor 610, which can be a digital signal processor (DSP) or any general purpose processor or central processing unit (CPU) as known in the art, for example.
  • the processor 610 may include an instruction random access memory (RAM) 410 and a data RAM 450 that are configured to store various dynamically relocated segments associated with a loadable module as described in further detail above with reference to FIG. 4.
  • DSP digital signal processor
  • CPU central processing unit
  • the processor 610 may be configured to implement at least blocks 530-560 in the method 500 shown in FIG. 5 and described in further detail above. As further shown in FIG. 6, the processor 610 may include and/or be communicatively coupled to a memory 650, which may comprise one or more caches or other memory structures as described herein.
  • FIG. 6 also shows that the electronic device 600 may include a display controller 626 coupled to the processor 610 and to a display 628.
  • the electronic device 600 may further include a coder/decoder (CODEC) 634 (e.g., an audio and/or voice CODEC) coupled to processor 610.
  • CODEC coder/decoder
  • Other components such as a wireless controller 640 (e.g., a modem) are also illustrated in FIG. 6.
  • a speaker 636 and a microphone 638 can be coupled to the CODEC 634.
  • the wireless controller 640 can be coupled to a wireless antenna 642.
  • the processor 610, the display controller 626, the memory 650, the CODEC 634, and/or the wireless controller 640 may be provided in a system-in-package or a system-on-chip device 622.
  • an input device 630 and a power supply 644 may be coupled to the system-on-chip device 622.
  • the display 628, the input device 630, the speaker 636, the microphone 638, the wireless antenna 642, and the power supply 644 are shown as being external to the system-on-chip device 622.
  • the display 628, the input device 630, the speaker 636, the microphone 638, the wireless antenna 642, and/or the power supply 644 can be coupled to a component associated with the system-on-chip device 622 (e.g., via an interface or a controller) .
  • FIG. 6 depicts the electronic device 600 as a wireless communications device, those skilled in the art will appreciate that the various components illustrated in FIG. 6 may be integrated into a set top box, a music player, a video player, an entertainment unit, a navigation device, a personal digital assistant (PDA) , a fixed location data unit, a computer, a laptop, a tablet, a communications device, a mobile phone, etc.
  • PDA personal digital assistant
  • DSP digital signal processor
  • ASIC application specific integrated circuit
  • FPGA field programmable gate array
  • a general purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine.
  • a processor may also be implemented as a combination of computing devices (e.g., a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration) .
  • a software module may reside in RAM, flash memory, ROM, EPROM, EEPROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of non-transitory computer-readable medium known in the art.
  • An exemplary non-transitory computer-readable medium may be coupled to the processor such that the processor can read information from, and write information to, the non-transitory computer-readable medium.
  • the non-transitory computer-readable medium may be integral to the processor.
  • the processor and the non-transitory computer-readable medium may reside in an ASIC.
  • the ASIC may reside in an IoT device.
  • the processor and the non-transitory computer-readable medium may be discrete components in a user terminal.
  • the functions described herein may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functions may be stored on or transmitted over as one or more instructions or code on a non-transitory computer-readable medium.
  • Computer-readable media may include storage media and/or communication media including any non-transitory medium that may facilitate transferring a computer program from one place to another.
  • a storage media may be any available media that can be accessed by a computer.
  • such computer-readable media can comprise RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.
  • any connection is properly termed a computer-readable medium.
  • the software is transmitted from a website, server, or other remote source using a coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of a medium.
  • disk and disc which may be used interchangeably herein, includes CD, laser disc, optical disc, DVD, floppy disk, and Blu-ray discs, which usually reproduce data magnetically and/or optically with lasers. Combinations of the above should also be included within the scope of computer-readable media.

Landscapes

  • Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Theoretical Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Stored Programmes (AREA)

Abstract

L'invention concerne un modèle de module chargeable qui peut être implémenté sur des plates-formes limitées par le matériel. En particulier, selon divers aspects, un espace mémoire littéral (424) peut être réservé au module chargeable sur un processeur (610) s'exécutant dans un mode d'adressage absolu, l'espace littéral (424) pouvant être réservé dans une plage d'adresses valides accessibles par une ou plusieurs instructions limitées à l'adresse. Au moment de la construction, il est possible de générer une liaison partielle combinant un ou plusieurs fichiers objets (320, 322, 324) associés au module chargeable comportant des symboles exportés du système d'exploitation (330). Par conséquent, au moment du chargement, un espace littéral peut être attribué au module chargeable à partir de l'espace mémoire littéral réservé (424) et des espaces de texte et de données peuvent être attribués à partir de la mémoire non utilisée (440) de telle sorte que les adresses associées à toutes les fonctions et variables internes peuvent être relocalisées selon les adresses de départ associées à l'espace littéral, à l'espace de texte et à l'espace de données.
PCT/CN2017/072788 2017-01-30 2017-01-30 Modules chargeables avec liaison partielle et transfert de temps de charge WO2018137258A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2017/072788 WO2018137258A1 (fr) 2017-01-30 2017-01-30 Modules chargeables avec liaison partielle et transfert de temps de charge

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2017/072788 WO2018137258A1 (fr) 2017-01-30 2017-01-30 Modules chargeables avec liaison partielle et transfert de temps de charge

Publications (1)

Publication Number Publication Date
WO2018137258A1 true WO2018137258A1 (fr) 2018-08-02

Family

ID=62977913

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/072788 WO2018137258A1 (fr) 2017-01-30 2017-01-30 Modules chargeables avec liaison partielle et transfert de temps de charge

Country Status (1)

Country Link
WO (1) WO2018137258A1 (fr)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120005445A1 (en) * 2010-06-30 2012-01-05 International Business Machines Corporation Memory allocation with identification of requesting loadable kernel module
US20140143507A1 (en) * 2012-11-20 2014-05-22 International Business Machines Corporation Techniques for managing pinned memory
CN105893085A (zh) * 2016-03-30 2016-08-24 百度在线网络技术（北京）有限公司 内核模块加载方法和装置
US20160246276A1 (en) * 2015-02-19 2016-08-25 Rockwell Automation Technologies, Inc. Techniques for Improving Industrial Control Systems

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120005445A1 (en) * 2010-06-30 2012-01-05 International Business Machines Corporation Memory allocation with identification of requesting loadable kernel module
US20140143507A1 (en) * 2012-11-20 2014-05-22 International Business Machines Corporation Techniques for managing pinned memory
US20160246276A1 (en) * 2015-02-19 2016-08-25 Rockwell Automation Technologies, Inc. Techniques for Improving Industrial Control Systems
CN105893085A (zh) * 2016-03-30 2016-08-24 百度在线网络技术（北京）有限公司 内核模块加载方法和装置

Similar Documents

Publication Publication Date Title
US7805582B2 (en) Method of managing memory in multiprocessor system on chip
US10713021B2 (en) Geometric 64-bit capability pointer
US9323508B2 (en) Method and system for compiler optimization
US9507613B2 (en) Methods and apparatus for dynamically preloading classes
US10127018B2 (en) Dynamic addition of code in shared libraries
US8341615B2 (en) Single instruction multiple data (SIMD) code generation for parallel loops using versioning and scheduling
US8650537B2 (en) Optimizing an object-oriented program by transforming invocations of synthetic accessor methods
US20140115585A1 (en) String cache file for optimizing memory usage in a java virtual machine
KR101059633B1 (ko) 멀티태스킹 가상 머신을 위한 힙 구성
CN113468079B (zh) 内存访问方法及装置
KR20230007377A (ko) Gpr 릴리스 메커니즘에 기초한 gpu 의 gpr 최적화
CN116097216A (zh) 用于优化对常量内存的访问的方法和系统
EP4155950A1 (fr) Appareil, support lisible par ordinateur et procédé de réduction de surdébit de vérification de limites par l'instrumentation de pointeur arithmétique
US9158545B2 (en) Looking ahead bytecode stream to generate and update prediction information in branch target buffer for branching from the end of preceding bytecode handler to the beginning of current bytecode handler
JP2019523480A (ja) Ｎａｎｄストレージデバイスのためのプリエンプティブ圧縮解除スケジューリング
CN112783823B (zh) 共享代码的系统与代码共享方法
CN115906014A (zh) 一种数据处理方法及相关装置
WO2018137258A1 (fr) Modules chargeables avec liaison partielle et transfert de temps de charge
US10163189B2 (en) Automatically enabling a read-only cache in a language in which two arrays in two different variables may alias each other
US10866817B2 (en) Computing system, and driving method and compiling method thereof
US11398004B2 (en) Allocating device buffer on GPGPU for an object with metadata using access boundary alignment
CN117785728A (zh) 数据处理方法和装置
CN119201129A (zh) 一种程序编译方法、程序运行方法、芯片、设备及介质
CN118035131A (zh) 数据预取方法及装置、处理器和计算机可读存储介质
CN119781955A (zh) 用于嵌入式系统的内存资源分配方法和计算机设备

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17894560

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 17894560

Country of ref document: EP

Kind code of ref document: A1