@oe1cxw @folknology Any ideas on the good #ice40 compression method with compact decompression library for ARM host?
-
-
Replying to @wavedrom @folknology
Simple experiment with huffman coded RLE for zero bits: http://svn.clifford.at/handicraft/2016/ice40compr/ …pic.twitter.com/uJ0SmnAosG
2 replies 0 retweets 3 likes -
what percentage of gates were used?
2 replies 0 retweets 1 like -
Replying to @folknology @wavedrom
This example is an approximately half-full (hx8k) FPGA:pic.twitter.com/xUlcbYmU1o
1 reply 1 retweet 4 likes -
That shows (predictably) the limitations of RLE quite clearly, maybe other methods can improve with higher gate counts..
1 reply 0 retweets 0 likes -
Replying to @folknology @wavedrom
J1a is pretty much as tight as it gets (hx1k). Still 33% space savings. ("gzip -9" achieves 42% space savings.)pic.twitter.com/7rTHUssgT7
2 replies 0 retweets 3 likes -
Replying to @oe1cxw @folknology
I think some form of RLE is a good start. 33% vs 42% gzip -9 is impressive. What 7Z /RAR gives you on J1a bitstream?
1 reply 0 retweets 1 like
you can try it yourself. I checked in the example .bin files: http://svn.clifford.at/handicraft/2016/ice40compr/ …
-
-
Replying to @oe1cxw @folknology
I guess, bitstream data is not byte aligned, is it?
1 reply 0 retweets 0 likes -
Replying to @wavedrom @folknology
correct, it is not. (bitstream, not bytestream ;)
1 reply 0 retweets 0 likes - Show replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.