Re:Reverse-engineering the classic MK4116 16-kilobit DRAM chip
by kens on Sunday September 24, 2023 @05:52PM
(#37637543)
I looked into this: the 386SL has 855,000 transistors while the other 386 versions have 275,000 transistors. I updated the Wikipedia page, adding a reference to Intel's detailed "Microprocessor Quick Reference Guide", which has transistor counts for most of their chips. (I wish I had found this guide long ago.) https://www.intel.com/pressroom/kits/quickreffam.htm
Re:Reverse-engineering the classic MK4116 16-kilobit DRAM chip
by userbinator on Sunday September 24, 2023 @06:49PM
(#37637920)
That page you found is not 100% either - it claims the 8088 has only 64k addressable memory.
Likewise, I'm doubtful that a 386SL needs over 3x the transistors of the non-SL.
Re:Reverse-engineering the classic MK4116 16-kilobit DRAM chip
by kens on Sunday September 24, 2023 @07:10PM
(#37638069)
The 386SL adds a cache controller, memory controller, AT bus controller, and EMS 4.0 hardware, which is why it has more than three times the transistors. I checked multiple independent sources before posting, and they all said 855,000 transistors for the 386SL. (Sources from 1990s, so they're not parroting Wikipedia.) The cache controller has a (relatively) huge amount of tag RAM, which accounts for a lot of the additional transistors.
Re:Reverse-engineering the classic MK4116 16-kilobit DRAM chip
by naoru on Sunday September 24, 2023 @07:08PM
(#37638054)
Afaik 386SL was in fact not a 386, but a cutdown 486. This might explain the difference in transistor count.
Re:Reverse-engineering the classic MK4116 16-kilobit DRAM chip
by kens on Sunday September 24, 2023 @07:23PM
(#37638118)
No, if you look at the die, the 386SL is nothing like the 486. The 386SL more-or-less has a 386 inside it, taking up about 1/4 of the chip. See this floorplan diagram: http://www.bitsavers.org/components/intel/80386/240814-005_3...
275k for a 386. 1.2M for a 486.
(I just noticed the Wikipedia article on the 386 is wrong --- it gives both 275k and 855k, with the latter a citation to a set of presentation slides that doesn't even contain the numbers "855". Perhaps that's where the misinformation came from? But I strongly remember the 275k number from early Intel marketing material.)