Games / Your move / Area and density

Area and density

Read the situation and the numbers it starts from, then pick the change you would make. Every option was run, so the answer comes from the measurement rather than from anyone's judgement, and after you choose you see what all of them did. Progress is stored in this browser.

SourceEach option in these situations is a run of the same design with one thing changed, and the table you see afterwards is what those runs produced. The answer is whichever run came out best on the measure the question names, which is not always the change that sounds most sensible.
All 2 situations in this kind, with their tables
  • Which of these leaves the least cell area?
    Loosen it to 33 percent: 723 · Leave it at the default: 716 · Pack it to 79 percent: 709 · Synthesise for speed instead of area: 870

    Fourteen square micrometres separate the loosest floorplan from the tightest, which is two percent, and the ranking is the opposite of what the knob sounds like it does: the loose run is the largest, because longer wires made repair work harder. Utilization sets how much empty space surrounds the cells, not how many cells there are, and all three floorplans reach the same 0.44 nanosecond floor. The fourth option is the only one that really moves the area, and it moves it the wrong way. Optimizing for delay gives 870 square micrometres from 382 instances, 21 percent more silicon out of a quarter fewer cells, because the ones it chose are much larger. It is also slower once placed and routed, at 0.57 against 0.44, and it stops closing. The lever that changes cell area is synthesis, and on this block it was already set the right way round.

  • Which setting gives the best timing?
    Leave the adder mapping off: 0.02 · Turn the adder mapping on: -0.13 · Turn it on and synthesise for speed: -0.21

    The comment was right. With the adders mapped the block is 30 percent larger, its floor goes from 0.44 nanoseconds to 0.59, and it stops closing. Synthesising for speed on top makes the timing worse again, at 0.67. The power is the number that should stop anyone: 7.41 milliwatts against 2.62, nearly three times, for a block doing the same arithmetic. These runs do not say why, only that a mapping meant to help arithmetic-heavy designs does the opposite on this one. Leaving it off is the only option that keeps what the block already had.