Parallel and Distributed Computing Unit - 2 mcq
1. CUDA stand for
(A) Compute Unified Device Architecture
(B) Compute Unit Device Architecture
(C) Compute Unified Disk Architecture
(D) Compute Unit Device Architecture
2. CUDA is a
(A) Parallel computing platform
(B) Programming model
(C) Both A & B
(D) None of these
3. CUDA is developed by
(A) NVIDIA
(B) AMD
(C) INTEL
(D) RAPIDS
4. CUDA is used to enabled ___
(A) Graphics Processing Unit
(B) Graphical Processing Unit
(C) Graphics Processed Unit
(D) Graphical Processed Unit
5. CUDA platform is designed to work with programming languages
(A) C
(B) C++
(C) Fortan
(D) All of the above
6. Which of the following statements are true with regard to compute capability in CUDA
(A) Code compiled for hardware of one compute capability will not need to be re-compiled to run on hardware of another
(B) Different compute capabilities may imply a different amount of local memory per thread
(C) Compute capability is measured by the number of FLOPS a GPU accelerator can compute.
7. Which of the following correctly describes a GPU kernel
(A) All thread blocks involved in the same computation use the same kernel
(B) A kernel is part of the GPU's internal micro-operating system, allowing it to act as in independent host
(C) A kernel may contain a mix of host and GPU code
(D) None of these
8. Which of the following is not a form of parallelism supported by CUDA
(A) Vector parallelism - Floating point computations are executed in parallel on wide vector units
(B) Thread level task parallelism - Different threads execute a different tasks
(C) Block and grid level parallelism - Different blocks or grids execute different tasks
(D) Data parallelism - Different threads and blocks process different parts of data in memory
9. The style of parallelism supported on GPUs is best described as
(A) SISD - Single Instruction Single Data
(B) MISD - Multiple Instruction Single Data
(C) SIMT - Single Instruction Multiple Thread
(D) None of these
10. Shared memory in CUDA is accessible to
(A) All threads associated with a single kernel
(B) All threads in a single block
(C) Both the host and GPU
(D) None of these
11. Parallel portions of an application are executed on the device as.
(A) Kernels
(B) Thread
(C) Both A & B
(D) None of these
12. A CUDA kernel is executed by an _____
(A) array of batches
(B) array of threads
(C) single thread
(D) single batches
13. _____ is a form of parallelization which relies on splitting the computation by subdividing data across multiple processors.
(A) Data parallelism
(B) Task parallelism
(C) Function parallelism
(D) Object parallelism
14. Data parallelism performed ____, Task parallelism performed _____ .
(A) Synchronous, Asynchronous Computation
(B) Synchronous, Synchronous Computation
(C) Asynchronous, Synchronous Computation
(D) Asynchronous, Asynchronous Computation
15. CUDA source file can have a mixture of
(A) Host Code
(B) Device Code
(C) Both A & B
(D) None of these
16. Declares a function that is executed on device and callable from device only
(A) _device_
(B) _global_
(C) _host_
(D) None of these
17. What is(are) true about __global__?
(A) Declares a function as kernel
(B) Must have void return type
(C) The function is only executable on the device, callable from the host and device
(D) All of these
18. What is(are) true about variable types qualifier _device_ ?
(A) Resides in global memory (DRAM)
(B) Is accessible from all the threads within the grid
(C) Is accessible from the host through the runtime library
(D) All of these
19. What is(are) true about variable types qualifier _shared_ ?
(A) Resides in shared memory of a thread block
(B) Is only accessible from all the threads within the block
(C) Both A & B
(D) None of these
20. What strategy does the GPU employ if the threads within a warp diverge in their execution?
(A) All possible execution paths are run by all threads in a warp serially so that thread instructions do not diverge
(B) Threads are moved to different warps so that divergence does not occur within a single warp
(C) Threads are allowed to diverge
(D) None of these
No comments:
Post a Comment