1. [Deprecated] CUDA Occupancy Calculator

The CUDA Occupancy Calculator allows you to compute the multiprocessor occupancy of a GPU by a given CUDA kernel.

[Deprecated] Excel based Occupancy Calculator is deprecated. Occupancy calculator is available in Nsight Compute. Please refer to Nsight Compute Occupancy Calculator documentation for more details on usage.

2. Overview

The CUDA Occupancy Calculator allows you to compute the multiprocessor occupancy of a GPU by a given CUDA kernel. The multiprocessor occupancy is the ratio of active warps to the maximum number of warps supported on a multiprocessor of the GPU. Each multiprocessor on the device has a set of N registers available for use by CUDA program threads. These registers are a shared resource that are allocated among the thread blocks executing on a multiprocessor.

The CUDA compiler attempts to minimize register usage to maximize the number of thread blocks that can be active in the machine simultaneously. If a program tries to launch a kernel for which the registers used per thread times the thread block size is greater than N, the launch will fail.

Click CUDA Occupancy Calculator [XLS] to download the spreadsheet.