1. LoGPC: Modeling Network Contention in Message-Passing Programs
Csaba Andras Moritz
Matthew I. Frank
Laboratory for Computer Science
Massachusetts Institute of Technology
2/16/2019 Andras

2. Introduction
LogP, LogGP are great models to capture first order system costs
Our new model LoGPC extends LogP and LogGP capturing pipelining and network contention
Results preview: 3 applications, 50-76% contention found
2/16/2019 Andras

3. Motivation - why do we care?
Regular, tightly synchronized communication patterns successfully modeled with LogP, LogGP.
Important classes of applications have irregular comm patterns, are not tightly synchronized or using large messsages.
2/16/2019 Andras

4. Outline of presentation
LoGPC methodology
Contention-free models: LogP, LogGP
Pipelining model
Network contention model
Applications
This presentation is organized as follows:
First we introduce the three models on top of which we define an optimization process for finding optimized grain and balance in Raw systems. We exemplify by showing some aspects in this process for the Jacobi 2D
Finally we end with conclusions and recomendations for Raw systems
2/16/2019 Andras

5. LoGPC framework (optional) Platform Network Interfacing Pipelining
model
Communication
layer
Contention
free models
(optional)
Performance signature
Contention
models
Network
Application
Application
performance
2/16/2019 Andras

6. Short messages: LogP (Culler et al)
4 parameters:
L = Latency
O = Overheads
g = gap minimum time interval consecutive sends and receives
P = Processors g g
Osend L
Orec
2/16/2019 Andras

7. Long messages: LogGP (Alexandrov et al)
Sender
k bytes message
A new parameter introduced:
Receiver
G = Gap per byte for long messg. L G Os Or
(k-1)G
2/16/2019 Andras

8. LoGPC framework (optional) free models Platform: Comm.layer:
Application
Platform:
Network Interface
Contention
models
Pipelining
model
Comm.layer:
free models
Interconnection
Network
performance
(optional)
2/16/2019 Andras

9. Pipelining model Network Interface - Alewife MEMORY NETWORK PROCESSOR
Data
Cache
bus
IRQ
DMA1
DMA2
INPUT Q
OUTPUT Q
IPI in
IPI out
CONTROLLER
2/16/2019 Andras

10. Pipelining model Sender ... Receiver (k-1)G o dma interrupt L
Memory transfer
Network transfer
....
2/16/2019 Andras

11. LoGPC framework (optional) Application Contention model Platform
Network
Interface
Pipelining
Communication
layer
free models
Interconnection
performance
Performance signature
(optional)
2/16/2019 Andras

12. Network contention model
Performance signature {L,o,G}
(Active Messages - MIT-Alewife)
Application specific:
inter message time,
average distance
Contention
model
network dimension,
network distance
Contention delay per message
Application
Performance
2/16/2019 Andras

13. Contention per message: Cn
Start with open network model by Agarwal for expressing contention per message:
Cn= network contention
L = network latency
L + Cn
2/16/2019 Andras

14. Contention delay per message: Cn
Close the model, P customer system
Apply Little’s equation,
solve for m Pm
... P T0
T0: inter-message time
P: processors
m: message rate
Cn: contention delay
L : network latency
L + Cn
2/16/2019 Andras

15. LoGPC step-by-step Extract com. signature {L,o,G}
Estimate inter message time(s) based on application comm pattern(s) {T0}.
Estimate application locality ( = average message distance )
Use contention-model for contention delay per message {Cn}.
Estimate runtime based on critical path
2/16/2019 Andras

16. Applications: All-to-all remap
Measured
LoGPC
No contention
2/16/2019 Andras

17. Diamond DAG used in DNA chain comparison Random mapping Measured LoGPC
Perfect mapping
Measured
LogGP = LoGPC
2/16/2019 Andras

18. Em3d - hot-spot elimination
propagation of electromagnetic waves in solids
asynchronous communication pattern with bulk transfer
LoGPC used to eliminate performance bugs
we improved performance 20% reducing contention by up to 70%.
Synch
Communication
Synch
Comp
2/16/2019 Andras

19. Summary We found network contention significant
all-to-all remap: 50%
Diamond DAG: up to 56%
EM3D:up to 70% (averall performance 20%)
LoGPC: Simple way to evaluate how much locality matters for an application.
LoGPC: Simple way to evaluate if network contention is significant for an application.
We used applications that are parallel.
We can observe a following division of resources: 25% memory, 75 % processing and communication
The cost-performance optimal Raw configuration is the following:
We also used theframeowrk to compare designs with different assumptions.
We used DRAM inside a tile and a simple 2 byte FIFO router we obtained better preformance for the same cost.
2/16/2019 Andras