1. Packing and Placement Dr. Philip Brisk Department of Computer Science and Engineering University of California, Riverside CS 223

2. Packing Example (Homogeneous)

3. Packing Example (Heterogeneous) Netlist Architecture Packing Solution

4. Architecture Description and Packing for Logic Blocks with Hierarchy, Modes, and Complex Interconnect Jason Luu, Jason Anderson, and Jonathan Rose International Symposium on FPGAs, 2011

5. AA-Pack 6.0 Algorithm Pick the un-packed mapped LUT with the largest number of attached nets p – Netlist block ; B partially filled logic cluster nets(p, B) – number of shared nets between p and B ext(p, B) – number of pins on p ’s nets residing on netlist blocks NOT packed into B packed(p) – number of pins on p ’s nets residing on netlist blocks packed into logic clusters OTHER than B num_pins(p) – number of used pins on p (normalizes affinities across netlist blocks with varying numbers of used pins

6. Legality Challenges Handle complex logic clusters with hierarchy – Fracturable LUTs – Carry chains – Hard logic circuits Routability – Sparse crossbar intra-cluster routing

7. Hierarchical Cluster Example Strategy: Pack each netlist block into the smallest primitive that can accommodate it Algorithm: Search the tree bottom-up, from right to left

8. Ensuring Routability Basic Check: Does packing the netlist block into the cluster exceed I/O pin availability? Routability: Build routing graph and run a routing algorithm to determine legality – Routing algorithm details will be discussed next week

9. Limitations Focus is area optimization, not timing Architectural limitations – (Fracturable) LUT-based logic blocks – Fracturable arithmetic blocks (e.g., multipliers) – Memories with reconfigurable aspect ratios (not discussed) Mapping assumptions – Different block types cannot accommodate the same netlist block In reality, could pack a flip-flop into either a LUT- or multiplier- based block

10. Toward Interconnect-Adaptive Packing for FPGAs Jason Luu, Jason Anderson, and Jonathan Rose International Symposium on FPGAs, 2014

11. AA-Pack 7.0 Calling the router repeatedly during packing is computationally expensive – Speculative Packing: avoid unnecessary calls to the router – Interconnect-Aware Pin Counting: Quickly find unroutable instances based on pin demand Pre-packing: Support inflexible routing structures – E.g., carry chains Other bells and whistles – Accurate timing model – Best-fit placement – Better support for high-fanout nets

12. Speculative Packing FPGA 2011 Implementation – Call the router to check legality each time a new block is packed into the cluster FPGA 2014 Implementation – Fill the logic block to capacity, then call the router If a legal route is found, we’re done Otherwise, re-pack the block using the FPGA 2011 approach – Works because the common case is that a legal route is found

13. Interconnect-Aware Pin Counting Partition I/O pins into classes based on interconnect structure When each netlist block is packed, check the demand for each pin class Reject the block if demand exceeds supply for any pin class

14. Example

15. Properties and Limitations An optimistic filter – Cases that fail are not routable – Cases that pass may or may not be routable Sparse interconnect is approximated as fully connected Does not account for situations where a net routes through a sub- cluster without connecting to any primitives in that subcluster Internal feedback/feedforward connections within a logic cluster are discovered before packing and accounted for during pin counting Gives a pass/fail answer – Does not help to guide future candidate selection

16. Pre-packing Inflexible routing structures – Incorrect grouping or placement of netlist blocks may fail routing – The architect enumerates “pack patterns” to describe each structure – Before packing, identify netlist sub-graphs that match “pack patterns” Group them together and match them to logic cluster primitives that match the “pack pattern” Pack Patterns Multiply-add Registered multiply Registered add Registered multiply-add

17. Experiments

18. Results

19. Timing-Driven Placement for FPGAs Alexander (Sandy) Marquardt, Vaughn Betz, and Jonathan Rose International Symposium on FPGAs, 2000

20. Placement

21. Simulated Annealing

22. VPlace (Pre-dates this paper) Strategy: Minimize interconnect overhead

23. Timing Analysis For a placed and routed net How much delay can we add to a net before it becomes critical?

24. T-VPlace (This Paper) Optimize Timing + Wiring Complexity Delay approximation – FPGAs are uniform – Store delays (Δx, Δy) in a ROM Model a two-terminal net with source at (x source, y source ) and target at (x source + Δx, y source + Δy) Reduce the allowable move distance over time α is the fraction of attempted moves that were accepted at the previous temperature

25. Timing Cost and Objective Sum the timing costs of all source-sink pairs Heavily weight critical nets Maximum delay of all nets in the circuit

26. Default value is 10 Annealing Schedule Number of moves to perform at each temperature Vary the temperature as the algorithm progresses Termination criteria α is the fraction of attempted moves that were accepted at the old temperature T old

27. VPlace vs. T-VPlace

28. Improving Simulated Annealing- Based FPGA Placement with Directed Moves Kristofer Vorwerk, Andrew Kennings, and Jonathan W. Greene IEEE Transactions on CAD 28(2): 179-192 (2009)

29. Motivation: an annealer may spend significant time revisiting previously explored states before it finds the lowest cost state – Coax the annealer into exploring neighbor states that are more likely to yield an improvement

30. Simple “Moves” (T-Vplace) Randomly select a cell – Move a cell to an unoccupied target location – Swap the location of two cells Location selection – Random shrinking window α is the fraction of attempted moves that were accepted at the previous temperature

31. Heuristics to Determine Source Cells Random – VPR Graph coloring – Color the netlist before placement – Chose up to 15 non-adjacent (same color) cells at a time Priority list – Randomly choose among the 25% worst placed cells Position (details to follow) Timing cost of paths

32. Heuristics to Determine Target Locations Random – VPR Linear assignment – Details omitted Median placement and variants – Details on the next slide Priority list

33. Median Placement Compute bounding boxes for all nets omitting source pins – Take x and y minimums and maximums Put points into vectors and sort Define a rectangle by the median and median+1 entries in each vector Randomly select a new target location within the rectangle

34. Cell Rippling Nearest empty location to B Rippling directions are chosen randomly

35. Quality Factor of a Move p i is the probability that the move is accepted Use previous annealing iteration to determine the probabilities empirically P prev (i) is P(i) from the previous iteration

36. Results 4 BLEs per cluster 8 BLEs per cluster

37. Improving FPGA Placement with Dynamically Adaptive Stochastic Tunneling Mingjie Lin and John Wawryznek IEEE Transactions on CAD 29(12): 1858-1869 (2010)

38. Simulated Annealing (Conceptual) Stochastic Tunneling

39. Simulated Annealing Weaknesses Sensitivity to parameters – Quite a few – Interactions between them not understood Freezing problem – Unable to escape local minima – Prevalent at low temperatures where bad moves are accepted with a very low probability

40. Acceptance Criteria for Bad Moves Simulated Annealing Stochastic Tunneling “Energy” of the best solution found so far Continually adjusted as better solutions are found “Energy” of the current solution being evaluated Tunneling parameter

41. Stochastic Tunneling (Conceptual)

42. Stochastic Tunneling Pseudocode

43. Results Averages: 10.17 9.54 8.86 89.44 87.72 92.06422.5 488.5 363.7