Re: [casper] porting pink block map to 10.1

2008-09-25 Thread Henry Chen
Hi Glenn, I'm actually in the process of doing this partway for the biplex unscramblers. For large FFTs, the arbitrary reorders consume an insanely huge number of resources trying to get the mapping ROM. Since the biplex unscramble reorders use a known and easily-described reorder, I was just

Re: [casper] porting pink block map to 10.1

2008-09-25 Thread G Jones
Hi Henry, I haven't put much effort into this so far, so I will wait on yours. At first I was dubious of espresso (not the algorithm, just having to call external programs), but it does seem to work well. Unless there are liscensing issues, it seems like it would be easier to use espresso, since I

Re: [casper] porting pink block map to 10.1

2008-09-25 Thread Aaron Parsons
I would avoid hardcoding the case for biplex FFTs, if you can avoid it. It's a much better solution to get the general reorder block to work. The pink blocks did use espresso to do the logic reduction in reorder blocks, and that resulted in slow simulation. Once it was determined that ROMs used

Re: [casper] porting pink block map to 10.1

2008-09-25 Thread Henry Chen
For simpler logic, the logic reduction seems to work, but the casper_library FFT has always been rather bloated in comparison to the astro_library ones, and I think the unscrambler is the cause. I don't think the synthesizer is good enough to recognize

Re: [casper] porting pink block map to 10.1

2008-09-25 Thread G Jones
I just threw together a quick design which has two roms, one with ''use placement information turned on and one with it off, and also my port of the espresso map block. I'm going to test them with various maps and see how the implementations look. Any specific maps I should try? Glenn On Thu, Sep

Re: [casper] porting pink block map to 10.1

2008-09-25 Thread G Jones
Well that's interesting. I just ran this test with the map bit_rev(0:1023,10) and both distributed ROMs seem to have been implemented in their entirety, with no logic reduction. So clearly the synthesis is not optimizing well at all, even for such a simple map. The espresso map ended up as simply

Re: [casper] porting pink block map to 10.1

2008-09-25 Thread G Jones
Regarding simulation speed, it does take a while to generate a map of size 2^15, but the save state logic works well, and this only happens when the parameters are changed. Updating the design after initially setting the parameters does not take an appreciable amount of time. Simulating a map of