R2000
Early 32-bit RISC microprocessor chipset from MIPS
MIPS Computer Systems launched the R2000 in May 1986 as a pioneering 32-bit reduced instruction set computer. This multi-chip module powered early workstations and embedded systems, establishing the MIPS architecture in commercial computing.
- Launched in May 1986 as an early commercial RISC chip
- Uses a multi-chip design with separate FPU and write buffers
- Contains 110,000 transistors on an 80 mm2 die
- Licensed to multiple foundries including Toshiba and LSI Logic
- Powered workstations from SGI and DEC
What it is
The R2000 is a 32-bit central processing unit that brought reduced instruction set computing to the mass market. MIPS Computer Systems designed this chipset, which debuted in May 1986. It stands out as one of the earliest commercial RISC products, arriving just after the IBM RT PC. The design splits tasks across multiple chips to handle integer math, floating point operations, and memory writes efficiently. This approach allowed it to compete with complex instruction set rivals like the Intel 80386 and Motorola 68020.
How it came about
MIPS Computer Systems created the R2000 to prove that simplified instructions could deliver high performance. Prime Computer became the first confirmed buyer. Early sales required customers to purchase the entire chipset mounted on a specific circuit board to guarantee signal timing. By 1987, other system builders felt confident enough to integrate the chips into their own custom designs. This shift helped spread the technology to various workstation manufacturers and embedded device makers.
Inside the chip
The system relies on three main components. The R2000 chip handles integer instructions using a short pipeline and manages external static random access memory caches. A separate R2010 chip processes floating point math with its own registers and longer pipeline. Four R2020 chips act as write buffers, queuing up to four pending memory writes so the main processor does not stall. This structure enables one instruction completion per cycle when cache data is available, outperforming many contemporaries that needed multiple cycles per task.
How it was made
MIPS operated as a fabless company, meaning it designed the chips but did not manufacture them. Initial production used a 2.0 micrometre double-metal complementary metal oxide semiconductor process at Sierra Semiconductor and Toshiba. Each die held 110,000 transistors and covered 80 square millimetres. In late 1987, MIPS licensed the design to Integrated Device Technology, LSI Logic, and Performance Semiconductor. LSI marketed its version as the LR2000, while Performance Semiconductor produced a faster 0.8 micrometre variant called the PR2000.
Where it went
Workstations from Silicon Graphics and Digital Equipment Corporation utilized this processor. The DECstation 2100 and SGI IRIS 4D are notable examples. Ardent Computer and Northern Telecom also adopted the technology. Beyond high-end computing, the improved R2000A found a home in embedded roles, such as controlling printers. Its efficiency made it suitable for devices requiring reliable integer processing without the overhead of complex instruction decoding.
Versions and family
The initial release offered speeds of 8.3, 12.5, and 15 megahertz. An enhanced model, the R2000A, arrived in 1988 with clock rates of 12.5 and 16.67 megahertz. This update paired the R2000A integer unit with the R2010A floating point accelerator. The R3000 succeeded the entire family in 1988, keeping the same architectural principles but implementing them on faster silicon. The R2000 lineage established the foundation for subsequent MIPS processors.
Why it matters
This chipset helped validate reduced instruction set computing as a viable alternative to dominant complex architectures. It appeared alongside other early RISC efforts like SPARC and PA-RISC. By delivering high instruction throughput through simple pipelines and external caching, it influenced how engineers balanced processor speed with memory latency. The licensing model allowed multiple manufacturers to produce compatible parts, expanding the ecosystem.
Questions people ask about R2000
What makes the R2000 different from other CPUs of its time?
It uses a reduced instruction set architecture with a simple pipeline. Instead of one large chip, it splits tasks across multiple components for integer math, floating point operations, and memory buffering.
Who manufactured the R2000 chips?
MIPS designed the chip but did not make it. Sierra Semiconductor and Toshiba produced the initial versions. Later, Integrated Device Technology, LSI Logic, and Performance Semiconductor also fabricated the design.
What was the clock speed of the original R2000?
The initial models ran at 8.3, 12.5, or 15 megahertz. An improved version called the R2000A later offered speeds of 12.5 and 16.67 megahertz.
Good reading and sources
The facts on this page come from the Wikipedia article "R2000 microprocessor", written by its contributors and used under the CC BY-SA 4.0 licence, and from its Wikidata record (CC0). EveryChip rewrote the text in its own words, with AI assistance, and compares every page with the article to make sure no passage is copied. It may be reused under the same CC BY-SA 4.0 licence with a link back.
It may contain mistakes, and figures change over time. Nothing here is investment or buying advice. If something is wrong, tell us. Last refreshed 2026-11-14.
Like R2000
All CPUs and microprocessors
🇺🇸 United StatesI386
First 32-bit x86 microprocessor by IntelCPU · x86 · 1985
More from MIPS Computer Systems
All of them
🇺🇸 United StatesMotorola 68000
A 16/32-bit CISC microprocessor introduced by Motorola in 1979CPU · 68k · 1979