Sign In
Not register? Register Now!
Essay Available:
Pages:
1 page/≈275 words
Sources:
2 Sources
Style:
Other
Subject:
IT & Computer Science
Type:
Coursework
Language:
English (U.S.)
Document:
MS Word
Date:
Total cost:
$ 6.48
Topic:

Breakthrough in Parallel Computer Architecture Technology: Frontier

Coursework Instructions:

Search the literature and discuss in your own words what could be seen as a breakthrough in parallel computer architecture technology that could lead in the near future or has led recently (in the last ten years) to improvement in computer performance. List references (only books, journal and conference papers are accepted – no web sites will be accepted) that you used using IEEE style. You may choose the topic number corresponding to your 2 ID digits or that corresponding to adding of the 2 ID digits, or preferably choose your own Parallel Computing topic but not from this list:
1. Quantum Computers
2. Superparamagnetism
3. In-memory computing
4. EPIC Architecture
5. Find a recent supercomputer/parallel computer and describe its most important features and important performance figures (e.g. Watson, Summit, Pangea III, Cray XC50, etc.)
6. Superscalar and VLIW machines
7. Superpipelining
8. Vector processors
9. Neural Network processors
10. Dataflow computing
11. Systolic Arrays
12. GPU Architectures
13. Neuromorphic Computing
14. Hyper-dimensional Computing
( ID digits are 5 & 4 )

Coursework Sample Content Preview:

Supercomputer: Frontier
Name
Affiliation
Supercomputer: Frontier
The Frontier supercomputer system is based on Slingshot interconnect and the HPE Cray EX. To this end, it includes 9,408 nodes that are stored in 74 cabinets [2]. Each node of the supercomputer is called HPE Cray EX235a, and it is made up of the third-generation AMD EPYC processors that have been specifically customized for the Frontier supercomputer supported by 4 AMD Instinct M1250X GPU accelerators, which are connected [1]. Each node has a memory of 1024 GB [1].
To serve the Frontier supercomputer, the EPYC CPU was customized through the addition of XGMI links to facilitate the sharing of memory across CPU and GPUs on the frontier node. In addition, extra PCIe lanes were added to the CPU so that they could facilitate the use of 4 TB of Non-Volatile Memory on every node. The customization was essential to boosting the IOPS rate for artificial intelligence and machine learning operations. The EPYC CPU has 512 GB DDR$ memory, 64 cores with a cycle time of 2.0 GHz, and can be able to issue 4 instructi...
Updated on
Get the Whole Paper!
Not exactly what you need?
Do you need a custom essay? Order right now:
Order

👀 Other Visitors are Viewing These Other Coursework Samples:

HIRE A WRITER FROM $11.95 / PAGE
ORDER WITH 15% DISCOUNT!
Order Now