Intel Corporation

Sunpyo Hong

Konstantin Levit-Gurevich

Michael Berezalsky

Noam Itzhaki

Arik Narkis

Sion Berkowits

Julia Fedorova

Anton V Gorshkov

Aleksey Alekseev

Disclosed examples to perform instruction-level graphics processing unit (GPU) profiling based on binary instrumentation include: accessing, via a GPU driver executed by a processor, binary code generated by a GPU compiler based on application programming interface (API)-based code provided by an application; accessing, via the GPU driver executed by the processor, instrumented binary code, the instrumented binary code generated by a binary instrumentation module that inserts profiling instructions in the binary code based on an instrumentation schema provided by a profiling application; and providing, via the GPU driver executed by the processor, the instrumented binary code from the GPU driver to a GPU, the instrumented binary code structured to cause the GPU to collect and store profiling data in a memory based on the profiling instructions while executing the instrumented binary code.

Methods and apparatus to perform instruction-level graphics processing unit (GPU) profiling based on binary instrumentation

An apparatus for generating dynamic trace data of binary code running on one or more execution units of a Graphics Processing Unit (GPU) though binary instrumentation is presented. In embodiments, the apparatus may include an input interface disposed in the GPU to receive instrumented binary code and communication data, and an output interface disposed in the GPU, and coupled to a memory of a computer hosting the GPU. In embodiments, the memory may be further coupled to the input interface and a Central Processing Unit (CPU) of the computer, the memory having a trace buffer and a control buffer, the control buffer including an overflow flag of the trace buffer. In embodiments, the apparatus may further include an execution unit (EU) disposed in the GPU and coupled to the input interface and to the output interface, to conditionally execute the instrumented binary code and generate dynamic trace data when the overflow flag is not set to indicate an overflow condition. In embodiments, if it is set, the overflow flag may be cleared by the CPU.

Apparatus and methods for generating dynamic trace data on a GPU

Growing community of inventors

Framingham, MA, United States of America

Sunpyo Hong