/
On December 31, 2013 On December 31, 2013

On December 31, 2013 - PowerPoint Presentation

debby-jeon
debby-jeon . @debby-jeon
Follow
385 views
Uploaded On 2015-11-25

On December 31, 2013 - PPT Presentation

I was blindfolded I was taken from my home I was led to a dark room Meet Olaf A snowman who looks forward to summer Specious reasoning friend Olaf   The hot and the cold are both so intense ID: 204940

system dsp card gpus dsp system gpus card memory software channels units motorola wah tools processors purpose channel bit

Share:

Link:

Embed:

Download Presentation from below link

Download Presentation The PPT/PDF document "On December 31, 2013" is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.


Presentation Transcript

Slide1

On December 31, 2013

I was blindfolded

I was taken from my home

I was led to a dark roomSlide2
Slide3

Meet Olaf

A snowman who looks forward to summer

Specious reasoning, friend Olaf

 

The hot and the cold are both so intense

Put them together – it just makes sense! Slide4

Pro Tools Audio Recording

1991 –

NuBus

card, 2x Motorola 56001 DSP, 4 channel

24-bit fixed point

Integrated SCSI controllers important

1998 – PCI card, 6x Motorola 56301 DSP, 64 channel1999 – Livin’ La Vida Loca recorded & mixed entirely in Pro Tools

2002 – PCI card, 9x Motorola

56321 

DSP, 192 channels

2010 – HD Native, a non-DSP system, 256 channels

DSPs no longer “just make sense”

2011 –

PCIe

card, 18x TI DSP, 256 channels

32-bit floating pointSlide5

Biggest architecture win in 10 years

GPUs

Ahem!Slide6

Biggest architecture win in 10 years

GPGPUs

General-purpose graphics processing unitsSlide7

Modern GPUs are general purpose

Successful because of generality

Applicable to many domains

Though only effective for data-parallel problems

Systems trump programs

How many programs to create amazon’s home page?GPUs need system services

GPUfs [ASPLOS ‘13]GPUnet [coming soon I hope…]Slide8

Specialization, the good and the bad

Improves performance, decreases energy

“Fixed-function” units

E.g., encryption, hashing, video decoder

Little need for system software, easy to multiplex

“Programmable” units – end users write software

E.g., early GPUs, IBM Cell, digital signal processors (DSP), network processorsRequire much care & feeding from system softwareDifficult programming modelSlide9

Rebuttal slidesSlide10

Wah

,

wah,

wah

Dennard scaling…

10x, 100x memory bandwidth2 cycle memory access latencyPersistent byte-addressable memory

Abundant wireless bandwidth