Abstract: The present invention provides a GPU resource allocation method. A to-be-distributed kernel program in a kernel status register table is identified by using a global logic controller (201). The global logic controller searches in an SM status register table for an SM that can run at least one complete block, and the SM status register table is configured to store a quantity of available resources in each SM (202). When the global logic controller does not find the SM that can run at least one complete block, the SM status register table is searched for a first SM, and the first SM is an SM that can run at least one warp (203). When the global logic controller finds the first SM, a block in the to-be-distributed kernel program is distributed to the first SM (204).

Abstract: A GPU resource allocation method and system relate to the field of computer technologies. A global logic controller determines a to-be-distributed kernel program in a kernel status register table; searches an SM status register table for an SM capable of running at least one entire thread block; when the SM capable of running at least one entire block is not found, searches the SM status register table for a first SM, where the first SM is an SM capable of running at least one thread warp; and when the first SM is found, distributes a block from the to-be-distributed kernel program to the first SM; or when the first SM is not found, searches for a second SM and then distributes the block from the to-be-distributed kernel program to the second SM. The GPU resource allocation method and system are applicable to GPU resource allocation.

Abstract: The present invention provides a GPU resource allocation method. A to-be-distributed kernel program in a kernel status register table is identified by using a global logic controller (201). The global logic controller searches in an SM status register table for an SM that can run at least one complete block, and the SM status register table is configured to store a quantity of available resources in each SM (202). When the global logic controller does not find the SM that can run at least one complete block, the SM status register table is searched for a first SM, and the first SM is an SM that can run at least one warp (203). When the global logic controller finds the first SM, a block in the to-be-distributed kernel program is distributed to the first SM (204).

Abstract: A GPU resource allocation method and system relate to the field of computer technologies. A global logic controller determines a to-be-distributed kernel program in a kernel status register table; searches an SM status register table for an SM capable of running at least one entire thread block; when the SM capable of running at least one entire block is not found, searches the SM status register table for a first SM, where the first SM is an SM capable of running at least one thread warp; and when the first SM is found, distributes a block from the to-be-distributed kernel program to the first SM; or when the first SM is not found, searches for a second SM and then distributes the block from the to-be-distributed kernel program to the second SM. The GPU resource allocation method and system are applicable to GPU resource allocation.