rea-Efficient Instruction Set Synthesis for Reconfigurable System on Chip Designs Philip Brisk Adam Kaplan Majid Sarrafzadeh Embedded and Reconfigurable Systems Lab Computer Science Department University of California, Los Angeles [email protected] u [email protected] [email protected] DAC ’04. June 9, 2004. San Diego Convention Center, San Diego, CA
Area-Efficient Instruction Set Synthesis for Reconfigurable System on Chip Designs
Jan 13, 2016
Area-Efficient Instruction Set Synthesis for Reconfigurable System on Chip Designs. Philip BriskAdam KaplanMajid Sarrafzadeh. [email protected]. [email protected]. [email protected]. Embedded and Reconfigurable Systems Lab. Computer Science Department. - PowerPoint PPT Presentation
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Area-Efficient Instruction Set Synthesis for Reconfigurable
System on Chip Designs
Philip Brisk Adam Kaplan Majid Sarrafzadeh
Embedded and Reconfigurable Systems LabComputer Science Department
University of California, Los Angeles
[email protected] [email protected]@cs.ucla.edu
DAC ’04. June 9, 2004. San Diego Convention Center, San Diego, CA
Outline
• Custom Instruction Generation and Selection
• Resource Sharing
• Algorithm Description with Examples
• Datapath Synthesis Techniques
• Experimental Methodology and Results
• Summary
Custom Instruction Generation
• Compiler Profiles Application Code• Extracts Favorable IR Patterns• Synthesizes Patterns as Hardware Datapaths
Custom Instruction Selection
• Area Constraints Limit on-Chip Functionality• NP-Hard 0-1 Knapsack Problem• Formulated as an Integer Linear Program (ILP)
Custom Instruction Generation and Selection
For each custom instruction iGain(i) : Estimated Performance Gain of iArea(i) : Estimated Area of iSelected(i) : 1 if i is Selected; 0 Otherwise
Goal Maximize Gain of Selected Instructions
ConstraintArea of Selected Instructions FPGA Area
<
ILP Formulation forInstruction Selection Problem
What About Resource Sharing?
Area = 17
Area = 25
Two DFGs
1.5
My Datapath
Area = 28ILP Area Estimate = 42
AreaCosts
85
1
3
Analysis
0-1 Knapsack Problem Formulation Over-Estimated Area by 150%
• ILP Solvers Do Not Consider Resource Sharing
How to Remedy This
• Develop a Resource Sharing Algorithm
• Avoid Additive Area Estimates Based on per-Instruction Costs
Resource Sharing for DFGs
Given: • A Set of DFGs G* = {G1, …, Gn}
Goal: • Construct a Consolidation Graph GC of Minimal Cost
Constraints:• GC Must be Acyclic• GC Must be a Supergraph of each Gi in G*
That’s Life: • The Problem is NP-Hard
Resource Sharing Overview
G3 G4G1 G2
Decompose Patterns into Input-Output Paths• Path Based Resource Sharing (PBRS)
Resource Sharing Overview
G3 G4G1 G2
Decompose Patterns into Input-Output Paths• Path Based Resource Sharing (PBRS)
Resource Sharing Overview
Use Substring Matching to Share Resources• Merge DFGs Along Matched Nodes
G3 G4G1 G2
Resource Sharing Overview
Synthesize GC
• Requires Less Area than Synthesizing G1…G4 Separately
Gc
G3 G4
G1 G2
AreaCosts
85
1
3
Path-BasedResource Sharing
P1: ()
P2: ()
P1: ()
P2: ()
MACStrO(L) L – Length of String
( )
Area of MACStr = 26
Maximum Area Common Substring
AreaCosts
85
1
3
P1: ()
P2: ()
MACSeqO(L2/logL) L – Length of String
( )
Area of MACSeq = 43
AreaCosts
85
1
3
Maximum Area Common Subsequence
Resource Sharing Algorithm
Global Phase
Determine:Which DFGs to MergeAn Initial Path to Merge
Local PhaseAggressively Apply PBRS to Share Resources Between the DFGs Selected by the Global Phase
Repeat Until all DFGs are Merged, or no Further Resource Sharing is Possible
Resource Sharing Algorithm
AreaCosts
85
1
3
G1 G2G3 G4
Global Phase
AreaCosts
85
1
3
G3 G4G1 G2
Global Phase
AreaCosts
85
1
3
G3 G4G1 G2
MACSeq/MACStr
Entering Local Phase
AreaCosts
85
1
3
G1 G2
MACSeq/MACStr
Local Phase
AreaCosts
85
1
3
G1 G2
1 2
2
2
2
2
G12
MACSeq/MACStr
Local Phase
AreaCosts
85
1
3
G1 G2
1 2
2
2
2
2
G12
0
0
0
0
MACSeq/MACStr
Local Phase
AreaCosts
85
1
3
G1 G2
0
0
0
0
1 2
2
2
2
2
G12
Local Phase
AreaCosts
85
1
3
G1 G2
0
0
0
0
1 2
2
2
2
2
G12
MACSeq/MACStr
Local Phase
AreaCosts
85
1
3
G1 G2
0
0
0
0
1 2
2
2
2
2
G12
MACSeq/MACStr
Local Phase
AreaCosts
85
1
3
G1 G2
0
0
0
0
2
2
2
2
G12
MACSeq/MACStr
Local Phase
AreaCosts
85
1
3
G1 G2
0
0
0
0
2
2
2
2
G12
MACSeq/MACStr
Local Phase
AreaCosts
85
1
3
G1 G2
0
0
0
0
2
2
2
2
G12
MACSeq/MACStr
Local Phase
AreaCosts
85
1
3
G1 G2
0
0
0
0
2
2
2
2
G12
Returning To Global Phase
AreaCosts
85
1
3
G12
G3 G4
Global Phase
AreaCosts
85
1
3
G3 G4
G12
Global Phase
AreaCosts
85
1
3
G3 G4
G12
MACSeq/MACStr
Entering Local Phase
AreaCosts
85
1
3
G12
G4
MACSeq/MACStr
Local Phase
AreaCosts
85
1
3
G4
0
0
0
0
G12 G124
4
4
4
12
12
12
12
12
12
MACSeq/MACStr
Local Phase
AreaCosts
85
1
3
G4
0
0
0
0
G12 G124
4
4
4
12
12
12
12
12
12
MACSeq/MACStr
Local Phase
AreaCosts
85
1
3
G4
0
0
0
0
G12 G124
4
4
4
12
12
12
12
12
12
Local Phase
AreaCosts
85
1
3
G4
0
0
0
0
G12 G124
4
4
4
12
12
12
12
12
12
MACSeq/MACStr
Local Phase
AreaCosts
85
1
3
G4
0
0
0
0
G12 G124
4
4
4
12
12
12
12
12
12
MACSeq/MACStr
A Local Decision
AreaCosts
85
1
3
0
0
0
0
G4
G12 G124
4
4
12
12
12
12
12
MACSeq/MACStr
A Local Decision
AreaCosts
85
1
3
0
0
0
0
G4
G12 G124
4
4
12
12
12
12
12
A Local Decision
AreaCosts
85
1
3
0
0
0
0
G4
G12 G124
4
4
12
12
12
12
12
MACSeq/MACStr
A Local Decision
AreaCosts
85
1
3
0
0
0
0
G4
G12 G124
4
4
12
12
12
12
12
MACSeq/MACStr
Cycles are Illegal
AreaCosts
85
1
3
0
0
0
0
ILLEGAL!
4
12
12
12
12
G124
4
4
12
12
12
12 12
G124
MACSeq/MACStr
Cycles are Illegal
AreaCosts
85
1
3
0
0
0
0
G124
4
4
12
12
12
12 12LEGAL!
4
12
12
12
12G124
MACSeq/MACStr
Local Phase
AreaCosts
85
1
3
0
0
0
0
G4
G12 G124
4
12
12
12
12
Returning To Global Phase
AreaCosts
85
1
3
G3
G124
Global Phase
AreaCosts
85
1
3
G3
G124
Global Phase
AreaCosts
85
1
3
G3
G124
MACSeq/MACStr
Global Phase
AreaCosts
85
1
3
G3
G124
3
33124124
124 124
124
124
G1234
MACSeq/MACStr
Global Phase
AreaCosts
85
1
3
G3
G124
3
33124124
124 124
124
124
0
0
0
0
G1234
MACSeq/MACStr
Local Phase
AreaCosts
85
1
3
0
0
0
0
G3
G124
3
33124124
124 124
124
124
G1234
Local Phase
AreaCosts
85
1
3
0
0
0
0
G3
G124 G1234
3
33124124
124 124
124
124
MACSeq/MACStr
Local Phase
AreaCosts
85
1
3
0
0
0
0
G3
G124 G1234
3
33124124
124 124
124
124
MACSeq/MACStr
Local Phase
AreaCosts
85
1
3
0
0
0
0
G3
G124 G1234
3124
124
124
124
MACSeq/MACStr
Local Phase
AreaCosts
85
1
3
0
0
0
0
G3
G124 G1234
3124
124
124
124
MACSeq/MACStr
Local Phase
AreaCosts
85
1
3
0
0
0
0
G3
G124 G1234
3124
124
124
124
Local Phase
AreaCosts
85
1
3
0
0
0
0
G3
G124 G1234
3124
124
124
124
MACSeq/MACStr
Local Phase
AreaCosts
85
1
3
0
0
0
0
G3
G124 G1234
3124
124
124
124
MACSeq/MACStr
Local Phase
AreaCosts
85
1
3
0
0
0
0
G3
G124 G1234
124
124
MACSeq/MACStr
124
Local Phase
AreaCosts
85
1
3
0
0
0
0
G3
G124 G1234
124
124
MACSeq/MACStr
124
Local Phase
AreaCosts
85
1
3
0
0
0
0
G3
G124 G1234
124
124
124
MACSeq/MACStr
Local Phase
AreaCosts
85
1
3
0
0
0
0
G3
G124 G1234
124
124
124
We’re Done
AreaCosts
85
1
3
G1 G2
G3 G4
G1234
We’re Done
AreaCosts
85
1
3
G1 G2
G3 G4
Area = 17 Area = 25
Area = 14 Area = 20
G1234 Area = 30
Total Area of DFGs = 76
G1234
VLIW Synthesis
Experimental Procedure
Custom Instr.Generation
Set of Patterns
Machine-SUIFCompiler
ConsolidationGraph
ConstructionAlgorithm
Consolidation Graph
EstimateArea
Pipeline Synthesis
Pipelined Datapath Synthesis
Compiler
Loop Bodies• 80-90% of Program Execution Time• Parallelism Exists Across Multiple
Iterations• Pipelined Datapath Yields Maximal
Throughput.
Data Flow Graph
Insert Registers& Muxes
Pipelined Datapath Synthesis
Gc
G1 G2 G3 G4
VLIW Datapath Synthesis
Compiler
Non-Loop Computations• Instruction-Level Parallelism• Similar to Latency-Constrained
Scheduling in High-Level Synthesis
Data Flow Graph
Benchmark Suite
MediaBench Benchmark Suite
Exp. Benchmark File/FunctionNum. Instrs.
Largest Instr. (Operations)
Avg. Ops per Instr.
1234
567891011
MesaPGPRasta
EpicJPEGJPEGJPEGMPEG2MPEG2Rasta
Rasta
blend.cidea.cmul_mdmd_md.c
collapse_pyrjpeg_fdct_ifastjpeg_idct_4x4jpeg_idct_2x2idct_col
FR4TR
Lqsolve.c
idct_row
61457
2158794
10
18864
917125
303725
5.53.23.03.0
4.47.05.93.17.2
20.07.5
Experimental Results
0
5000
10000
15000
20000
25000
Slic
es
1 2 3 4 5 6 7 8 9 10 11
Pipelined Datapath Area Estimates
Additive
CG/PBRS
XilinxE-1000 Area
Experimental Results
0
5000
10000
15000
20000
25000
Slic
es
1 2 3 4 5 6 7 8 9 10 11
VLIW Datapath Area Estimates
Additive
CG/PBRS
XilinxE-1000 Area
Summary
• Area Estimates Based on Resource Sharing
• 0-1 Knapsack Problem Formulation Does Allow for Resource Sharing Estimates
• Resource Sharing Algorithm
• PBRS applied to Data Flow Graphs
• Experimental Results
• ILP Overestimates Area Costs by as much as 374% and 582% for Pipelined and VLIW Datapaths
Related Documents
