摘要:
Embodiments are disclosed for emulation of graphics processing unit instructions. An example apparatus includes a kernel accessor to access an instruction of an original GPU kernel, the original GPU kernel intended to be executed at a first GPU. An instruction support determiner is to determine whether execution of the instruction is supported by a second GPU different from the first GPU. An instruction modifier is to, in response to determining that the execution of the instruction is not supported by the second GPU, create an instrumented GPU kernel based on the original GPU kernel. The instrumented GPU kernel includes an emulation sequence. The emulation sequence is to, when executed by the second GPU, cause the second GPU to emulate execution of the instruction by the first GPU.
摘要:
Techniques and apparatus for profiling graphics processing unit (GPU) processes using binary instrumentation are described. In one embodiment, for example, an apparatus may include at least one memory comprising instructions and a processor coupled to the at least one memory. The processor may execute the instructions to determine a plurality of profiling modes for profiling an operating process of a graphics processing unit (GPU) application, access original binary code for the GPU application, and generate a multi-mode instrumented binary code comprising a plurality of instrumentation modes, each of the plurality of instrumentation modes corresponding to at least one of the plurality of profiling modes. Other embodiments are described.
摘要:
Techniques and apparatus for performance analysis of a program are described. In one embodiment, for example, an apparatus may include at least one memory, and logic, at least a portion of comprised in hardware coupled to the at least one memory, to access a program for performance analysis, the program comprising at least one producer instruction and at least one consumer instruction for the at least one producer instruction, and generate an analysis program based on the program, the analysis program comprising a stall time instruction set to determine a stall time of the at least one producer instruction, the stall time instruction set comprising a first time stamp instruction immediately preceding a consumer instruction, a second time stamp instruction immediately following the consumer instruction, and a stall time instruction to determine the stall time as the difference between the second time stamp and the first time stamp. Other embodiments are described and claimed.
摘要:
Detecting a static graphic object (such as a logo, title, or sub-title) in a sequence of video frames may be accomplished by analyzing each selected one of a plurality of pixels in a video frame of the sequence of video frames. Basic conditions for the selected pixel may be tested to determine whether the selected pixel is a static pixel. When the selected pixel is a static pixel, a static similarity measure and a forward motion similarity measure may be determined for the selected pixel. A temporal score for the selected pixel may be determined based at least in part on the similarity measures. Finally, a static graphic object decision for the selected pixel may be made based at least in part on the temporal score.
摘要:
Machine-readable media, methods, apparatus and system for booting a processing system are described. In an embodiment, whether to launch an open operating system or a closed operating system to boot a processing system may be determined. A key may be retrieved from a processor register of the processing system and used to decrypt an encrypted version of the closed operating system based at least in part on a determination of booting the processing system with the closed operating system. In another embodiment, the processor register stored with the key may be flushed based at least in part on a determination of booting the processing system with the open operating system.
摘要:
Technologies for binary loop trip count computation include a computing device that dynamically instruments binary code, executes the instrumented code, and records execution statistics during execution of the instrumented code. The computing device may instrument only instructions affecting local control flow within functions of the binary code. The computing device may combine execution statistics from multiple threads or process instances of the binary code. After completing execution of the instrumented code, the computing device generates a control flow graph indicative of control flow of the binary code and recursively detects binary loops within the binary code. The computing device calculates a trip count for reach detected binary loop using the recorded execution statistics. Other embodiments are described and claimed.
摘要:
Machine-readable media, methods, apparatus and system for booting a processing system are described. In an embodiment, whether to launch an open operating system or a closed operating system to boot a processing system may be determined. A key may be retrieved from a processor register of the processing system and used to decrypt an encrypted version of the closed operating system based at least in part on a determination of booting the processing system with the closed operating system. In another embodiment, the processor register stored with the key may be flushed based at least in part on a determination of booting the processing system with the open operating system.
摘要:
An asymmetric multiprocessor system (ASMP) may comprise computational cores implementing different instruction set architectures and having different power requirements. Program code executing on the ASMP is analyzed by a binary analysis unit to determine what functions are called by the program code and select which of the cores are to execute the program code, or a code segment thereof. Selection may be made to provide for native execution of the program code, to minimize power consumption, and so forth. Control operations based on this selection may then be inserted into the program code, forming instrumented program code. The instrumented program code is then executed by the ASMP.
摘要:
Machine-readable media, methods, apparatus and system for booting a processing system are described. In an embodiment, whether an encrypted version of a closed operating system is authentic may be determined. The encrypted version of the closed operating system may be decrypted with a key retrieved from a processor register to provide the closed operating system, based at least in part on a determination that the encrypted version of the closed operating system is authentic. Then, whether the closed operating system is authentic may be determined and a virtual machine may be created so that the closed operating system may be launched in the virtual machine, if the closed operating system is authentic.
摘要:
Machine-readable media, methods, apparatus and system for booting a processing system are described. In an embodiment, whether to launch an open operating system or a closed operating system to boot a processing system may be determined. A key may be retrieved from a processor register of the processing system and used to decrypt an encrypted version of the closed operating system based at least in part on a determination of booting the processing system with the closed operating system. In another embodiment, the processor register stored with the key may be flushed based at least in part on a determination of booting the processing system with the open operating system.