Nvidia Corporation

Columbia University

Mohamed Tarek Bnziad Mohamed Hassan

Aamer Jaleel

Lakshminarasimhan Sethumadhavan

Michael Brendan Sullivan

Miguel A Arroyo

Mark William Stephenson

Evgeny Manzhosov

Mark Stephenson

Hiroshi Sasaki

Implicit Memory Tagging (IMT) mechanisms utilizing alias-free memory tags that enable hardware-assisted memory tagging without incurring storage overhead above those incurred by conventional tagging mechanisms, while providing enhanced data integrity and memory security. The IMT mechanisms enhance the utility of error correcting codes (ECCs) to test memory tags in addition to the traditional utility of ECCs for detecting and correcting data errors and enable a finer granularity of memory tagging than many conventional approaches.

Alias-free tagged error correcting codes for machine memory operations

While a compiler compiles source code to create an executable binary, code is added into the compiled source code that, when executed, identifies and stores in a metadata table base and bounds information associated with memory allocations. Additionally, additional code is added into the compiled source code that enables hardware to determine a safety of memory access requests during an implementation of the compiled source code by performing an out-of-bounds (OOB) check in hardware using the base and bounds information stored in the metadata table. This enables the identification and avoidance of unsafe memory operations during the implementation of the executable by a GPU.

Implementing hardware-based memory safety for a graphic processing unit

Disclosed are devices, methods, systems, media, and other implementations that include a method comprising accessing during execution of a process a memory element, determining whether data stored in the accessed memory element includes security data representative of locations that, if accessed, indicate a potential system violation condition, determining, in response to a determination that the accessed memory element includes the security data, whether execution of the process involves access of one or more memory locations in the accessed memory element containing the security data, and performing one or more remedial actions in response to a determination that the one or more memory locations in the memory element containing the security data are being accessed.

Methods and systems for fine granularity memory blacklisting to detect memory access violations

Disclosed are methods, systems, devices, media, circuits, and other implementations, including a method that includes generating for a code block of a process executing on a controller-based device one or more code block copies defined in a virtual address space of the controller-based device, with the code block of the process being stored in a particular segment of a physical address space of the controller-based device, and with the code block configured to separately map to each of the one or more of the code block copies in the virtual address space. The method further includes processing at least a portion of one of the one or more code block copies defined in the virtual address space when the corresponding code block of the process is to be processed.

Control flow protection based on phantom addressing

While a compiler compiles source code to create an executable binary, code is added into the compiled source code that, when executed, identifies and stores in a metadata table base and bounds information associated with memory allocations. Additionally, additional code is added into the compiled source code that performs memory safety checks during execution. This updated compiled source code automatically determines a safety of memory access requests during execution by performing an out-of-bounds (OOB) check using the base and bounds information retrieved and stored in the metadata table. This enables the identification and avoidance of unsafe memory operations during the implementation of the executable by a GPU.

Growing community of inventors

New York, NY, United States of America

Mohamed Tarek Bnziad Mohamed Hassan