Client and Server processors

1
Client and Server processors

• Client incorporates
• Multi Media (sound and video)
• Imaging (3D)
• Security and network accessibility
• wireless communications
• Server incorporates
• High speed processing
• Management of large memory and file store
  complexes

2
Client processors

• Modern processors are being enhanced to support
  multimedia, security, etc.
• Most of the recent interesting processor
  developments have been in client processors
• largest market, not dominated by clock speed, and
  more amenable to low power implement.
• system on a die includes dsp arithmetic and as
  much structured memory as possible.

3
Multi Media

• Includes video, audio, 3 D graphic imaging, as
  well as subsidiary functions such as music
  (composition and rendering), voice recognition,
  handwriting rec., animation
• Closely coupled to the display / presentation
  technology (raster line or pixel density, audio
  speaker fidelity / range)

4
Still Images/ Video/ Audio

• The problem is compression and meeting real time
  constraints
• a B/W still image, 512x512 pixels, represents
  about 1/4 MB (8b/pixel) color (3B/pixel) almost
  1MB use 1 MB as a typical image
• video requires 30 frames/sec 30MB/sec 1 hour is
  108GB
• voice requires 44k samples/sec 3B/samples/sec 2
  or more channels about 1/4 MB/sec.

5
Still Images

• Lossless vs. Lossy compression
• a simple bounded Huffman code gives 31 lossless
  compression
• JPEG is standard
• offers (say) 251 lossy compression
• tradeoffs image quality - file size -
  computational complexity

6
JPEG

• Image is partitioned into 8x8 pixel blocks
• transform into frequency domain by DCT (the high
  freq components are at the high index values of
  the resultant 8x8 matrix and often 0.
• Quantize (the lossy step) map values to few
  numbers
• Zig zag access, to access low freq components
  (non 0) values first.
• Huffman (run length) encode values

7
Discrete cosine transform (DCT)

• Map X (spatial domain) to Y (freq. domain)
• more compact representation, use 8x8 pixel blk
• yu,v (4C(u) C(v)/n2) SjSkx(u,v) cos(2j1)
  up/2n cos(2k1) vp/2n
• C(w) 1for w1,2 or C(w) 1/sqrt2 for
  w0
• better than discrete Fourier transform, but
  needs more computation

8
DCT basis functions
9
Block diagram of JPEG encoder
10
Video

• Popular standards
• H263 (video conferencing)
• MPEG 1 (VHS quality)
• MPEG 2 (Broadcast quality)
• MPEG 4 (uses VOPs to achieve high quality with
  good compression). More complex, an emerging
  standard

11
Typical compression

• Image size, quality and delay are factors
• Lossless 31
• JPEG 251
• MPEG1 1001 uses 352x288 CIF 1-2 sec
• H 263 maybe 3001 QCIF 176x144 1/4sec
• MPEG2 4xCIF uses lower Q longer delay

12
MPEG frames

• Three types of frames
• I intra-picture, like lossy JPEG
• P predicted picture, motion prediction based on
  earlier I motion vector plus error terms, as
  error terms are small quantizing gives good
  compression
• B bidirectional pictures, motion prediction based
  on past and future I or P
• result is GOP, e.g. IPBBPBBPBBPBBPBBI

13
I frames

• In MPEG typically use 1 I per 15 frames
• In H263 maybe 1 I per 300 frames
• I frames take (maybe) 4x bits to represent than a
  P or B frame.

14
MPEG block diagram
15
P frames

• Motion prediction is computationally intensive
  based on macro blocks 2x2 blocks
• 16x16 of luminance, 1 8x8 Cr, 1 8x8 Cb, color is
  interleaved (called 420)

16
Motion estimation process
17
Forward motion compensation
18
Motion estimation

• Computation intensive
• Compute SAD for all neighboring macro block
  combinations (index by 1 pixel).
• S xi,j-yi,k across all macro blocks
• Find location that minimizes SAD

19
Bidirectional motion compensation
20
Block diagram of MPEG encoder
21
Instructions /pixel

• JPEG about 320 to compress280 to decode
• MPEG1 about 1100 to compress about 80 to decode.
• Note problem in motion estimation need 352
  x 288 x 1100 x 30 instr /sec 3.3 GIPS for
  MPEG1 to compress.
• MPEG2 uses bigger frames better motion
  estimation and color maybe20 GIPS

22
Video memory

• Even if we have enough arithmetic BW, memory
  (cache) access is a problem. A single CIF frame
  has 200 - 400 kB and wont fit into a L2 caches
  less than (say) 1 or 2 MB. Worse is the behavior
  of the L1 D cache. There are NO hits after a line
  is used.
• Solution prefetch and stride prediction caches
  at L1.

23
Audio

• Frequency range 20-20k Hz _at_ 2x sampling
• Sample rates
• 8k telephone
• 22k personal computers
• 32k digital audio and TV
• 44k CDs
• 48k HDTV, DAT

24
Audio

• Dynamic range 0 to 120db about 20 bits of
  exponent
• Phasing 2 or more channels to locate source
• Clipping ear tolerates about 200ms delay, after
  300ms becomes annoying.
• Bit rates 44k x 20 x 2 1.7 Mbps or (PCs) 22k
  x 16 352 kbps

25
Audio

• Can do better by compression use ADPCM and send
  the difference between adjacent pulses G722
  standard 16k with ADPCM to fit into 64kbps.
• G728 uses linear predictive coder achieves
  16kbps. Models voice as a linear filter matches
  sample with codebook, send index into receivers
  codebook

26
MPEG audio

• Compresses digital audio signals (PCM)
• Uses 32 sub band filters (512 taps), samples
  shifted 32 at a time. Computation is s(i)
  Snx(t- n) Hi(n) over n 512 per sample Hi(n)
  is the impulse response for the ith filter. Thus
  we have 512 multiply-accumulates per sample.
  About 22Mops/sec

27
MPEG Audio

• Sample rates 32, 44, 48 kHz
• Mono, stereo or joint stereo
• Bit rates 64kbps to 128kbps, several layers and
  coder complexity to get better bit rates and/or
  better quality.
• Computationally requires probably 5 - 100 million
  multiply-adds per second (16b).

28
MPEG audio encoder