Question 1

A _________ is a bundle of 32 threads that start at the same starting address and their thread IDs are consecutive.

Accepted Answer

A) warp 
B) grid 
C) block 
D) grouping 
A) warp 
B) grid 
C) block 
D) grouping

Question 2

The EU can issue up to ________ different instructions simultaneously from different threads.

Accepted Answer

A) four 
B) five 
C) six 
D) seven 
A) four 
B) five 
C) six 
D) seven

Question 3

The number of blocks per kernel launch is called a __________ .

Accepted Answer

The answer of The number of blocks per kernel launch...

Question 4

__________ is a parallel computing platform and programming model created by NVIDIA and implemented by the GPUs that they produce.

Accepted Answer

CUDA (Comp

Question 5

__________ are caused by limited SFUs,double-precision multiplication,and branching.

Accepted Answer

A) Structural hazards 
B) RAW data hazards 
C) Vertical hazards 
D) Latency hazards 
A) Structural hazards 
B) RAW data hazards 
C) Vertical hazards 
D) Latency hazards

A _________ is a bundle of 32 threads that start at the same starting address and their thread IDs are consecutive.

The EU can issue up to ________ different instructions simultaneously from different threads.

The number of blocks per kernel launch is called a __________ .

__________ is a parallel computing platform and programming model created by NVIDIA and implemented by the GPUs that they produce.

__________ are caused by limited SFUs,double-precision multiplication,and branching.

Basic Concepts and Computer Evolution

Performance Issues

A Top-Level View of Computer Function and Interconnection

Cache Memory

Internal Memory

External Memory

Input Output

Operating System Support

Number Systems

Computer Arithmetic

Digital Logic

Characteristics and Functions

Addressing Modes and Formats

Processor Structure and Function

Reduced Instruction Set Computers

Parallelism and Superscalar Processors

Parallel Processing

Multicore Computers

Control Unit Operation

Microprogrammed Control

Filters

Exam 19: General-Purpose Graphic Processing Units

A _________ is a bundle of 32 threads that start at the same starting address and their thread IDs are consecutive.

The EU can issue up to ________ different instructions simultaneously from different threads.

The number of blocks per kernel launch is called a __________ .

__________ is a parallel computing platform and programming model created by NVIDIA and implemented by the GPUs that they produce.

__________ are caused by limited SFUs,double-precision multiplication,and branching.

Basic Concepts and Computer Evolution

Performance Issues

A Top-Level View of Computer Function and Interconnection

Cache Memory

Internal Memory

External Memory

Input Output

Operating System Support

Number Systems

Computer Arithmetic

Digital Logic

Characteristics and Functions

Addressing Modes and Formats

Processor Structure and Function

Reduced Instruction Set Computers

Parallelism and Superscalar Processors

Parallel Processing

Multicore Computers

Control Unit Operation

Microprogrammed Control

Filters