Lecture 3: Evolution of the Uniprocessor

1
Lecture 3 Evolution of the Uniprocessor

• SIMD
• VLIW
• DAE
• HPS
• Data Flow

2
(No Transcript)
3
(No Transcript)
4
(No Transcript)
5
(No Transcript)
6
The HPS Paradigm

• Incorporated the following
• Aggressive branch prediction
• Speculative execution
• Wide issue
• Out-of-order execution
• In-order retirement
• First published in Micro-18 (1985)
• Patt, Hwu, Shebanow Introduction to HPS
• Patt, Melvin, Hwu, Shebanow Critical issues

7
(No Transcript)
8
(No Transcript)
9
(No Transcript)
10
(No Transcript)
11

• The final flexibility Data Flow

12
(No Transcript)
13
(No Transcript)
14
(No Transcript)
15
Characteristics of Data Flow

• Data Driven execution of inst-level Graphical
  code
• Nodes are operators
• Arcs are I/O
• Only REAL dependencies constrain processing
• Anti-dependencies dont (write-after-read)
• Output dependencies dont (write-after-write)
• NO sequential I-stream (No program counter)
• Operations execute ASYNCHRONOUSLY
• Instructions do not reference memory
• (at least memory as we understand it)
• Execution is triggered by presence of data

16

• Why Data Flow?
• Irregular Parallelism
• Only real dependencies constrain
• Anti-dependencies dont
• Sequential I-stream doesnt (No Program Counter)
• Asynchronous (NOT in the sense of un-clocked)
• Why NOT Data Flow?
• In one word too much architectural state

17
Specific Problems with Data Flow

• Code bloat (everything is explicit)
• Code debug (asynchronous, non-deterministic flow)
• Interrupt handling (providing a consistent state)
• Machine diagnosis (trouble-shooting design
  errors)
• Recursion
• Large data structures
• Node table overflow (cost of CAM is high)
• Performance caveats
• Array copy operations
• Long latencies
• Network (bypass paths) congestion