Transmeta Astro Processor
simpl3x writes "Apparently, Transmeta's next generation processor was demonstrated to some folks the other day at Comdex. Tom's Hardware was at the demo and they had this to say: "The new Transmeta Astro was faster in every demo that we saw than the Pentium 4m 1.8GHz chip that was in the Sony GRX." Cnet had some information on the processor also . I just ordered a tablet to play with, though I ordered the Fujitsu which has a P3m (the Compaq has a bad screen according to the reviews). I certainly wish that something like this were available, and i do hope that the manufacturing goes smoothly. Mo options, mo better."
Do you have any references on the large amount of system RAM you mentioned is needed for code morphing ? I find it hard to believe that 1) you need that amount of memory for instruction translation and 2) that a hardware device using that much memory to emulate a CPU (at CPU clock speeds) can be too efficient both in terms of performance and heat dissipation.
Although chips are getting faster and faster people seem to forget that most people dont use a laptop as a portable supercomputer. The average user is gonna write papers and browse the web or soem kind of business application ... not that they wont do other things, but the fact is a laptop was never meant to replace the desktop market. Transmeta not only gives intel competetion, but they assure the consumer that intel will have to do at least a little innovation to make their product worthy. A chip that is fast enough for non video games and has an extended battery life compared to ther brands is a good thing. It is what the goal of laptop makers should be. gaming on a laptop is teh niche market, and thats what alienware computers are for.
Choosing the lesser of two evils is a choice for evil.
Support for new instruction set extensions like SSE or MMX could be added with a simple firmware upgrade. A new code-morphing frontend could turn the Crusoe from an x86-compatible chip to a PowerPC, MIPS, or SPARC-compatible chip in seconds
This turs out to be much more difficult than it first appears. There are a number of low-level architectural features - especially in the memory interface, but elsewhere too - that are very difficult to emulate if you've built a processor using different assumptions. This means that while you might be able to emulate a PPC/MIPS/SPARC on a Crusoe - or even on a PC - by dynamically recompiling code, the only architecture that would perform well would be one with a good match to your actual hardware. The original Crusoe chips were designed from the start to emulate Intel processors, and this new chip is presumably in the same boat.
Not that I really doubt Transmeta, but a closed system running benchmarks? Who is to say that they weren't running a P4 and not an Astro? And what do they mean by faster than a 1.8 GHZ mobile Intel chip? Faster than what? Some weird benchmark devised by some marketing department that no one has access to? Whithout specs, this whole thing is a wash.