Milan Dvorak
Tradecope
dvorak@netcope.com
Low-latency solution for algorithmic and high frequency trading
• European vendor of FPGA-based network solutions
• Formerly FPGA department of Invea-Tech
• First to introduce 100GE NIC (PCI-E form factor)
 Vast experience with FPGA technology since 2002
 Xilinx Alliance program partner
 PCI-SIG® member company
• Primary focus
 Low-latency electronic trading
 High-speed packet capture
 Smart traffic filtering
 FPGA firmware development kit
Company introduction
• An ideal algorithmic trading platform
 Handles all communication with an exchange transparently
to the user
 User simply injects specific trading strategy and initiate
trading
• Requirements
 Exchange/protocol independent
 Minimal technical knowledge required to write trading
strategies
 Flexible (new message types, protocol changes…)
 Low latency, high speed, (first come first serve)
Challenge
• Programmable hardware
 Flexibility of software
 New functionality does not require hardware modifications
 Performance of hardware
 Massive parallelism (tenths of parallel CPU-like single thread
computations)
 Deterministic, cycle accurate
 Low latency (measure in ns)
• Drawbacks
 Hardware designer expertise required
 Longer time to market compared to software
 Hardware development from scratch is generally expensive
FPGA technology
• FPGA based low latency trading solution
 Pre-built blocks for communication with an exchange
 FIX/FAST and binary
market data protocols
 Full order book,
aggregated level book
 Order sessions
management (FIX,
ArcaDirect, OUCH, …)
 User trading strategy
in C/C++ (optional)
 Latency optimized API
Tradecope
• Minimal tick-to-trade latency in HW:
 Processing pipeline completely in FPGA hardware
 Wire-to-wire sub-microsecond latency
 Significantly Improved hit-rate
• Flexibility
 One piece of hardware communicates with multiple
exchanges, supporting various protocols
 All major US exchanges supported
 New markets support ready within few weeks
• Easy to use
 User just takes care about trading strategy
 No need for FPGA specialist to harness its power
Tradecope – key features
• Pre-trade risk check in Tradecope
 Limits for price and size
 Limited number of orders
in time
• Custom risk checks
 Written in C/C++
 Fully customizable by user
• Monitoring in SW
 Every order passed to user
 Order generation can be
disabled from SW
Risk checks
• FPGA connected as bump-in-the-wire
 Risk-check is running transparently to the user
 FPGA can drop packets and report back to the trading
system
 Low additional latency (less than 1usec)
 Parallel processing – multiple risk checks at once
Transparent risk-check
FPGA
Risk check
Trading system Exchange
Netcope Technologies a.s.
U Vodárny 2965/2
616 00 Brno, Czech Republic
www.netcope.com
Accelerating your success
Contacts
Milan Dvorak
dvorak@netcope.com
+420 511 205 378

EXTENT-2015 Tradecope Presentation

  • 1.
    Milan Dvorak Tradecope dvorak@netcope.com Low-latency solutionfor algorithmic and high frequency trading
  • 2.
    • European vendorof FPGA-based network solutions • Formerly FPGA department of Invea-Tech • First to introduce 100GE NIC (PCI-E form factor)  Vast experience with FPGA technology since 2002  Xilinx Alliance program partner  PCI-SIG® member company • Primary focus  Low-latency electronic trading  High-speed packet capture  Smart traffic filtering  FPGA firmware development kit Company introduction
  • 3.
    • An idealalgorithmic trading platform  Handles all communication with an exchange transparently to the user  User simply injects specific trading strategy and initiate trading • Requirements  Exchange/protocol independent  Minimal technical knowledge required to write trading strategies  Flexible (new message types, protocol changes…)  Low latency, high speed, (first come first serve) Challenge
  • 4.
    • Programmable hardware Flexibility of software  New functionality does not require hardware modifications  Performance of hardware  Massive parallelism (tenths of parallel CPU-like single thread computations)  Deterministic, cycle accurate  Low latency (measure in ns) • Drawbacks  Hardware designer expertise required  Longer time to market compared to software  Hardware development from scratch is generally expensive FPGA technology
  • 5.
    • FPGA basedlow latency trading solution  Pre-built blocks for communication with an exchange  FIX/FAST and binary market data protocols  Full order book, aggregated level book  Order sessions management (FIX, ArcaDirect, OUCH, …)  User trading strategy in C/C++ (optional)  Latency optimized API Tradecope
  • 6.
    • Minimal tick-to-tradelatency in HW:  Processing pipeline completely in FPGA hardware  Wire-to-wire sub-microsecond latency  Significantly Improved hit-rate • Flexibility  One piece of hardware communicates with multiple exchanges, supporting various protocols  All major US exchanges supported  New markets support ready within few weeks • Easy to use  User just takes care about trading strategy  No need for FPGA specialist to harness its power Tradecope – key features
  • 7.
    • Pre-trade riskcheck in Tradecope  Limits for price and size  Limited number of orders in time • Custom risk checks  Written in C/C++  Fully customizable by user • Monitoring in SW  Every order passed to user  Order generation can be disabled from SW Risk checks
  • 8.
    • FPGA connectedas bump-in-the-wire  Risk-check is running transparently to the user  FPGA can drop packets and report back to the trading system  Low additional latency (less than 1usec)  Parallel processing – multiple risk checks at once Transparent risk-check FPGA Risk check Trading system Exchange
  • 9.
    Netcope Technologies a.s. UVodárny 2965/2 616 00 Brno, Czech Republic www.netcope.com Accelerating your success Contacts Milan Dvorak dvorak@netcope.com +420 511 205 378