Chapter 5 | Csci | Complete

0.0(0)
Studied by 0 people
call kaiCall Kai
learnLearn
examPractice Test
spaced repetitionSpaced Repetition
heart puzzleMatch
flashcardsFlashcards
GameKnowt Play
Card Sorting

1/95

encourage image

There's no tags or description

Looks like no tags are added yet.

96 Terms

1
New cards

High-Performance Computing (HPC)

What is the process of aggregating computing power to solve problems that are too large, complex, or time-critical for a workstation?

2
New cards

Capability and Capacity

What two objectives does HPC achieve by aggregating computing power?

3
New cards

Computational Complexity

What measures how the time and resources required by an algorithm grow as the problem size increases?

4
New cards

Big O Notation

What notation is usually used to express time complexity?

5
New cards

O(n³)

What computational complexity represents cubic growth, where work increases with the cube of the problem size?

6
New cards

O(2ⁿ)

What computational complexity represents exponential growth, where work doubles with each additional input?

7
New cards

Computational Complexity

What helps estimate computation time, memory requirements, and the potential benefits of parallelization?

8
New cards

Data Scale

What refers to the volume of data that must be generated, stored, transferred, and analyzed during computation?

9
New cards

Lustre, GPFS (Spectrum Scale), and BeeGFS

What are the three parallel file systems used in HPC for storage?

10
New cards

Data Movement Bottleneck

What occurs when transferring data takes longer and costs more than computing on it?

11
New cards

Machine Learning and Data Analytics

What techniques help scientists identify patterns, detect anomalies, and extract insights automatically from massive datasets?

12
New cards

Time Constraint

What is the maximum acceptable time to complete a computation and deliver a useful result?

13
New cards

Time-to-Solution

What HPC metric measures how long it takes to obtain the final answer for a given problem?

14
New cards

FLOPS

What metric measures floating-point operations per second?

15
New cards

Compute Nodes

What are the main building blocks of an HPC system?

16
New cards

CPU, GPU/Accelerators, and Main Memory (RAM)

What are the three main components found inside a compute node?

17
New cards

Rack

What houses multiple compute nodes and provides organized deployment, shared power and cooling, and easier maintenance?

18
New cards

Cluster

What is a collection of racks working together as one HPC system?

19
New cards

Interconnect

What communication fabric connects all nodes and racks in an HPC system?

20
New cards

MPI Message Passing, Node-to-Node Communication, and Fast Data Transfer

What are the responsibilities of an HPC interconnect?

21
New cards

Storage

What HPC component provides shared access to data across the entire cluster?

22
New cards

Node

Which HPC component performs computations?

23
New cards

Rack

Which HPC component groups nodes?

24
New cards

Cluster

Which HPC component groups racks?

25
New cards

Interconnect

Which HPC component enables communication between nodes and racks?

26
New cards

Storage

Which HPC component holds and serves data?

27
New cards

Lustre

What is the high-performance parallel distributed file system designed for large-scale HPC clusters and supercomputers?

28
New cards

Lustre

What file system allows thousands of compute nodes to access the same data simultaneously at high speeds?

29
New cards

Metadata Target (MDT)

What Lustre component stores file system metadata such as filenames, directories, and permissions?

30
New cards

Object Storage Targets (OSTs)

What Lustre components store actual file data across multiple storage targets?

31
New cards

LNET (Lustre Networking)

What provides the network connection for Lustre clients and enables high-performance parallel I/O?

32
New cards

Task Parallelism

What type of parallelism involves executing different tasks concurrently, such as atmosphere, ocean, and land climate models?

33
New cards

Data Parallelism

What type of parallelism performs the same operation on different sets of data?

34
New cards

Amdahl's Law

What law predicts the maximum speedup achievable by parallelizing a program?

35
New cards

S = 1 / ((1 − P) + P/N)

What is the formula for Amdahl's Law?

36
New cards

P

In Amdahl's Law, what represents the parallel fraction of a program?

37
New cards

N

In Amdahl's Law, what represents the number of processors or cores?

38
New cards

10× Speedup

What is the maximum speedup when 10% of a program must execute sequentially, even with unlimited processors?

39
New cards

Gustafson's Law

Assumes that when more processors become available, scientists solve larger problems instead of keeping the workload fixed

40
New cards

Amdahl's Law

Assumes the workload remains fixed. If part of a program is sequential, it limits the maximum speedup.

41
New cards

Scalability

What concept is emphasized by Gustafson's Law?

42
New cards

Speed Limitation

What concept is emphasized by Amdahl's Law?

43
New cards

MPI (Message Passing Interface)

What is the standard programming model used in HPC for communication between processes running on different nodes?

44
New cards

InfiniBand

What network technology can be used for communication between nodes in an HPC cluster?

45
New cards

Send Messages, Receive Messages, Synchronize Processes, and Share Results

What are the four functions MPI provides for communication between nodes?

46
New cards

OpenMP (Open Multi-Processing)

What API is used for shared-memory parallel programming on multicore CPUs?

47
New cards

Threads

What does OpenMP create to allow a program to use multiple CPU cores within one node?

48
New cards

CUDA (Compute Unified Device Architecture)

What is NVIDIA's parallel computing platform and programming model for general-purpose GPU computing?

49
New cards

Host (CPU)

In CUDA's execution model, what component controls the program?

50
New cards

Device (GPU)

In CUDA's execution model, what component performs the heavy computations?

51
New cards

Hybrid Parallel Programming Model

What programming model combines multiple parallel programming technologies to utilize modern HPC systems?

52
New cards

MPI + OpenMP + CUDA

What three technologies are commonly combined in a hybrid HPC programming model?

53
New cards

MPI

Which hybrid programming technology handles distributed memory, message passing, and cluster-level parallelism?

54
New cards

OpenMP

Which hybrid programming technology handles shared-memory parallelism and multiple CPU cores within a node?

55
New cards

CUDA

Which hybrid programming technology accelerates compute-intensive tasks such as AI, simulations, and matrix operations?

56
New cards

Communication Overhead

What is the time spent sending messages, receiving messages, and synchronizing data instead of computing?

57
New cards

Load Imbalance

What occurs when work is not distributed equally among processors, causing some processors to finish early and wait?

58
New cards

Slowest Processor

Which processor determines when the entire parallel job finishes when workloads are imbalanced?

59
New cards

Memory Wall

What occurs when computation speed grows faster than memory speed, causing CPUs to wait for data?

60
New cards

Overhead

What refers to time spent communicating, waiting, or fetching data instead of computing?

61
New cards

Weak Scaling

What type of scaling measures how well a system handles a larger problem as more processors are added while keeping the execution time approximately constant?

62
New cards

Fixed Problem Size

What remains constant in strong scaling?

63
New cards

Growing Problem Size

What increases with the number of processors in weak scaling?

64
New cards

PAGASA

What organization is used in the file as an example of an application that needs strong scaling for time-critical weather forecasting?

65
New cards

MPI, OpenMP, and CUDA

What parallel programming technologies are combined in the climate simulation example?

66
New cards

Speedup

What performance measure identifies how many times faster an HPC system completes the same task?

67
New cards

Execution Time

What performance measure determines how much the processing time decreases?

68
New cards

Efficiency

What performance measure identifies how effectively available CPU and GPU resources are utilized?

69
New cards

Throughput

What performance measure identifies how many tasks or calculations can be completed within a given period?

70
New cards

Scalability

What performance measure determines how well performance improves when additional processors or computing resources are added?

71
New cards

DOST-ASTI COARE

What Philippine HPC facility is presented in the architecture diagram as the Computing and Archiving Research Environment?

72
New cards

Computing and Archiving Research Environment

What does COARE stand for?

73
New cards

44 Nodes

What is the total number of nodes in the COARE architecture diagram?

74
New cards

36 CPU Nodes and 8 GPU Nodes

What is the breakdown of the 44 COARE nodes?

75
New cards

3,168 CPU Cores

How many total CPU cores are indicated for the COARE CPU nodes?

76
New cards

88 Logical CPUs per Node

How many logical CPUs does each COARE CPU node have?

77
New cards

24 CPUs per Node

How many CPUs are indicated for each P40 GPU node?

78
New cards

1 TB RAM per Node

How much RAM is indicated for each P40 GPU node?

79
New cards

NVIDIA Tesla P40

What GPU model is installed in the six P40 nodes?

80
New cards

6 P40 Nodes

How many P40 nodes are indicated in the COARE architecture diagram?

81
New cards

NVIDIA Tesla A100

What GPU model is installed in the two A100 nodes?

82
New cards

8 GPUs per Node

How many NVIDIA Tesla A100 GPUs are indicated per A100 node?

83
New cards

128 CPUs per Node

How many CPUs are indicated for each A100 node?

84
New cards

1 TB RAM per Node

How much RAM is indicated for each A100 node?

85
New cards

Approximately 75 TFLOPS

What is the combined GPU compute capacity indicated for the A100 nodes?

86
New cards

Approximately 30 TFLOPS

What compute performance is indicated for the P40 nodes?

87
New cards

10 Gb/s Ethernet

What network speed is indicated for the COARE management and storage network?

88
New cards

SLURM

What workload manager is used for resource management in the COARE cluster?

89
New cards

InfiniBand 200 Gb/s

What interconnect technology and link speed are indicated in the COARE architecture?

90
New cards

1–3 Microseconds

What is the indicated low latency of the COARE InfiniBand interconnect?

91
New cards

Lustre Parallel File System

What storage system is used by COARE to provide high-throughput parallel data access?

92
New cards

Approximately 1,015 TB

What is the total Lustre storage capacity indicated in the COARE architecture diagram?

93
New cards

64–512 GB RAM

What is the general RAM range indicated for compute nodes in the educational HPC architecture overview?

94
New cards

Local NVMe SSD

What type of fast local storage is included in the compute node architecture?

95
New cards

Parallel File System

What type of storage system enables multiple compute nodes to access shared data simultaneously?

96
New cards

AI, Weather Modeling, and Data Science

What three research areas are identified as applications supported by DOST-ASTI COA