Curtis, What I heard before joining Juniper was that they were quite happy that Cisco made this acquisition because they don't use TCAM and they thought Cisco wasted a lot of money on a suboptimal technology.
Irrespectively Yours, John > -----Original Message----- > From: Curtis Villamizar [mailto:[email protected]] > Sent: Friday, February 08, 2013 1:42 PM > To: John E Drake > Cc: Balaji venkat Venkataswami; Eric Osborne (eosborne); Shankar Raman; > [email protected] > Subject: Re: Power aware networks : Comments requested from routing > community > > > In message > <0182dea5604b3a44a2ee61f3ee3ed69e14515...@bl2prd0510mb349.namprd05.prod > .outlook.com> > John E Drake writes: > > > > http://patft.uspto.gov/netacgi/nph- > Parser?Sect1=3DPTO1&Sect2=3DHITOFF& > > d=3DP= > > > ALL&p=3D1&u=3D%2Fnetahtml%2FPTO%2Fsrchnum.htm&r=3D1&f=3DG&l=3D50&s1=3D > > 71625= > > 72.PN.&OS=3DPN/7162572&RS=3DPN/7162572 > > > > Irrespectively Yours, > > > > John > > > John, > > Thanks. A better TCAM. If anything the bashing of conventional TCAM > in the background reinforces what I said about TCAM being power pigs. > > There are many disadvantages with the conventional ternary CAM > structure, however. Since each cell contains two memory cells, and a > mask-and-compare circuit, implementation of a table of size > w.times.2.sup.n requires w.times.2.sup.n+1 memory elements, and > w.times.2.sup.n mask-and-compare circuits. Since every lookup in the > table requires the activation of all the cells, power consumption is > proportional to w.times.2.sup.n. For large values of n, the cost is > considerable, and the power consumption is prohibitive. > > I'm quite sure radix trie is still more power efficient. > > A 4 bit radix trie (16 entry tables doing four binary radix trie > operations at once) requires a maximum of 8 SRAM lookups, seldom more > than 6, and often 4 or less. This can be pipelined using separate SRAM > blocks per radix trie stage. Other highly creative lookup techniques > exist. > > Curtis _______________________________________________ rtgwg mailing list [email protected] https://www.ietf.org/mailman/listinfo/rtgwg
