Executing a Program on the MIT Tagged Token Dataflow Architecture | CSE 240C, Study notes of Computer Science

Download Executing a Program on the MIT Tagged Token Dataflow Architecture | CSE 240C and more Study notes Computer Science in PDF only on Docsity!

Executing a Program on

the MIT Tagged Token

Dataflow Architecture

Arvind and Nikhil

Notes on the paper

This is a “Big A” Architecture paper

It’s a PL, an ISA, and an execution model

and a dash of hardware

Execution Model: Dataflow  Not a new idea [Dennis, ISCA’75]  Programs are dataflow graphs  Instructions fire when data arrives  Instructions act independently  All ready instructions can fire at once  Massive parallelism

Execution Model: Dataflow  Not a new idea [Dennis, ISCA’75]  Programs are dataflow graphs  Instructions fire when data arrives  Instructions act independently  All ready instructions can fire at once  Massive parallelism

Execution Model: Dataflow  Not a new idea [Dennis, ISCA’75]  Programs are dataflow graphs  Instructions fire when data arrives  Instructions act independently  All ready instructions can fire at once  Massive parallelism

Von Neumann example A[j + ii] = i; b = A[ij]; Mul t1 ← i, j Mul t2 ← i, i Add t3 ← A, t Add t4 ← j, t Add t5 ← A, t Store (t5) ← i Load b ← (t3)

Dataflow example A[j + ii] = i; b = A[ij];

Load Store

j i

b

A

Dataflow example A[j + ii] = i; b = A[ij];

Load Store

j i

b

A

Dataflow example A[j + ii] = i; b = A[ij];

Load Store

j i

b

A

Dataflow example A[j + ii] = i; b = A[ij];

Load Store

j i

b

A

Conditionals  Use a “steering” operator.

Loops

Managing Parallelism: Dynamic dataflow  Dynamic dataflow  Multiple inputs on an arc at one time  Parallelism is possible -- pipeline iterations through the loops graph  Unbounded state  Circulation speed mismatch -- mis-matched inputs  Tags are required.

A A A (^) B B B S S S

1:A 3:A 2:A (^) 3:B 1:B 2:B 3:S 2:S 1:S

Dataflow tags  Tags distinguish between different dynamic instances of the same value  Tag management in TTDA  Tags are the address of an activation record (aka stack frame)  A dynamic instance of an “instruction block” has a tag.  A central manager allocates/reclaims them.