The Rise of the Vortex86: Embedded x86 Processors
Back in 1998 a fabless CPU company introduced the Rise mP6 x86 CPU running at 166MHz Later versions ran at up to 233MHz and were Performance Rated at a somewhat generous PR300. Rise was a bit late to the party of desktop x86 designs, and had somewhat lackluster performance. In the 90s they had to compete with Intel, AMD, IDT, and IBM/Cyrix. VIA, who later bought IDTs Centaur (Winchip) division, as well as Cyrix from National Semiconductor was an investor in Rise, as they were wanting an entry into the CPU market as well. The mP6 used 16K of L1 cache and an 8 stage pipeline capable of executing 3 integer instructions per clock cycle. This at a time when most CPUs had 32K or even 64K of L1 cache, and better branch prediction crippled the mP6. It was used in set-top boxes and other low power type applications. Rise licensed the core to ST Microelectronics who used it in set-top SoCs.
By 1999 Rise was losing money and losing sales. In most areas this would have been the end, Rise would be a foot note in history (a smaller one then they are). However SiS, known for their value chipsets and budget graphics cores, bought what remained of Rise and the mP6 core. SiS wanted to develop an embedded CPU out of the mP6, and having a lack of experience took a while to make it happen. In late 2001 they had what they wanted. The SiS 550 was at its core a 200MHz mP6 but now integrated audio, video and IDE controller all at 2/3 the power requirements of the original.
The SiS550 found a home in several Thin Clients made by Neoware as well as various internet appliances.
We wrote about the SiS550 series many years ago here.
DM&P (aka Jan Yin Chan Electronics) eventually took over the design from SiS. It is DM&P who took the lowly mP6 design into the powerful embedded CPU it is today. The pipeline was reduced to 6 stages, and onboard 256k L2 cache was added. The L1 cache was doubled to 32K, and the clock speed was increased to a rather quick 1GHz.
The Vortex86DX is a fully capable x86 processor. It is perfect for very small PC applications and embedded designs where x86 code is required. The PMX-1000 can run at up to 1GHz and adds IDE support, graphics, and HD-Audio (much like the original SiS550.
While technically an embedded CPU the PMX-1000 is fully capable of running Windows and other x86 programs. eBox (part of DM&P) makes many small form factor, fanless, and sealed PCs based on it. It runs on a rather small 2.2Watts at 800MHz, a third the power, and 4 times the speed of the original Rise mP6.
Processor | Date | MHz | Pipelines | L1 | L2 | Process | Watts |
mP6 | 1998 | 200 | 8 | 16K | – | 0.25u | 7 |
SiS 550
Vortex86 |
2001 | 200 | 8 | 16K | – | 0.18u | 4 |
Vortex86SX | 2007 | 300 | 6 | 32K | – | 0.13u | 1 |
Vortex86DX
Vortex86MX |
2008 | 1000 | 6 | 32K | 256K | 0.09u | 2 |
The original Rise mP6 design is going on 12 years old and is still in wide use. While most CPUs have switched to a RISC like design internally. the mP6, and its Vortex86 variants retain the in-order CISC architecture of the 1990’s, and for what it does, thats just fine. Thanks to DMP Electronics for donating the Vortex86DX and PMX-1000!
December 29th, 2010 at 6:39 am
As far as I know, Vortex86DX/MX/SX is completely different from Vortex86, (which is SiS55x/Rise mP6 – that is a fact). For one thing – MSTI PSX 300 (aka Vortex86SX) lacks FPU, and it doesn’t sound very realistic to me that DM&P would find itself in year 2007 redesigning ready-to-use SiS55x in such a bizarre way. 🙂
The real story is that in 1995 ICOP (a company somehow connected with the DM&P) launches its M6117D, which is roughly a ALi M6117C whis an IDE interface and some minor upgrades. ALi was a well-known i386 motherboard chipset producer and had i386 license from Acer (“ALi” stands for Acer Laboratories inc.). So, ALi M1217 chipset for i386 was used to build M6117 series SoC. It is even reported that Nvidia is still producing it (they now own ULi, what was a division of ALi once).
What stands behind latest MSTI PDX processors I do not know for sure. I know, that somewhere around 1997 ICOP reported its first 486-compatible 75mhz SoC design, which is said to be “SGS-Thomson STPC Client 5×86 processor with FPU unit”, and that thing I believe had a core of ‘1995 Cyrix 5×86 “M1” core, a product of Cyrix-STMicroelectronics cooperation (those were even available under STM’s own brand – “It’s ST 5×86”). In 2000 ICOP launched the 6033/6034 and 6066/6067 board designs, build on a ZFx86 from ZF Microsolutions. The CPU part of this SoC is discribed “Cyrix 586 FP DX 486/133mhz”, obviously makes it nothing more than a late version of a Cx5x86 (notably, only Cyrix produced its Cx5x86-133, when IBM didn’t and on STM you could barely find any info about their 5×86 line), and also gives a bit more proof to a “STPC” origin. Keep in mind that Vortex86SX cannot run WinXP because it lacks CMPXCHG8B istruction, indicating it is still a 486-compatible, not a P5! And to think Vortex86DX/MX actually can run XP…
Now it is a bit sad, because what you brought to light is a very interesting story, which is taking place on a backstreets of x86 timeline! If you have a good contact with DM&P, can you make this whole picture more clear?
If you have any questions on my little research here, contact me – a48178249 at gmail.com . I also own myself a DM&P Vortex86 machine if it could help somehow.
And sorry for my English – I had no practice in years…