News
IndustryTSMC’s grip on advanced chipmaking will face competitionIndustryCadence joins European Chip Design Platform to support semiconductor startups and SMEsMaking chipsMarc Hijink on ASML’s Culture, Supply Chain, and GeopoliticsProcessorsIntel's post-Nova Lake CPUs take shape as Razor Lake desktop and laptop variants surfaceAI chipsHow Google’s New AI Chip Software Helps It Battle NvidiaIndiaMore IC Packaging Plants Emerge In IndiaIndustryUS Tightens China AI Chip Access as Nvidia, TSMC and Semiconductor Stocks SlideDesignAxelera AI moves into HPC with TitaniaMaking chipsChinese envoy says chip equipment export curbs threaten EU-China trade thawIndiaSEMICON India 2026 Day 2 Sees 25 MoUs, Strategic Collaborations Across Semiconductor Value ChainIndustryTSMC’s grip on advanced chipmaking will face competitionIndustryCadence joins European Chip Design Platform to support semiconductor startups and SMEsMaking chipsMarc Hijink on ASML’s Culture, Supply Chain, and GeopoliticsProcessorsIntel's post-Nova Lake CPUs take shape as Razor Lake desktop and laptop variants surfaceAI chipsHow Google’s New AI Chip Software Helps It Battle NvidiaIndiaMore IC Packaging Plants Emerge In IndiaIndustryUS Tightens China AI Chip Access as Nvidia, TSMC and Semiconductor Stocks SlideDesignAxelera AI moves into HPC with TitaniaMaking chipsChinese envoy says chip equipment export curbs threaten EU-China trade thawIndiaSEMICON India 2026 Day 2 Sees 25 MoUs, Strategic Collaborations Across Semiconductor Value Chain
EveryChip
CPU HP PA-RISC 7300

PA-7100

HP microprocessor with on-die floating-point unit

Photo: Konstantin Lanzet (with permission), CC BY-SA 3.0, via Wikimedia Commons

Hewlett-Packard released the PA-7100 in early 1992 as a PA-RISC 1.1 microprocessor. It was the first in its family to place the floating-point unit on the same silicon die as the main processor, running at speeds up to 100 MHz for workstations and servers.

Share on WhatsApp

  • First PA-RISC chip with on-die floating-point unit
  • Fabricated using HP 0.8 μm CMOS26B process
  • Operated at clock speeds from 33 to 100 MHz
  • Used in HP 9000 workstations and Stratus servers

What it is

The PA-7100 is a central processing unit created by Hewlett-Packard. It follows the PA-RISC 1.1 instruction set architecture. Launched in early 1992, this chip marked a significant step for HP because it combined the main processor logic and the floating-point unit onto a single piece of silicon. This integration helped reduce size and complexity compared to earlier designs that kept these functions separate. The chip targeted high-performance computing tasks in professional workstations and server environments, competing against other RISC processors of the era such as the DEC Alpha.

How it came about

HP developed the PA-7100 to succeed the PA-7000 chipset, known internally as PCX-S. The earlier design required two separate chips for integer processing and floating-point math. By merging these into one die, HP aimed to improve performance and efficiency. The project resulted in the Thunderbird code name and the PCX-T product identifier. Fabrication took place at HP facilities in Corvallis, Oregon, and Fort Collins, Colorado. The chip entered the market in 1992, positioning HP strongly in the workstation sector before the release of faster successors like the PA-7150 in 1994.

Inside the chip

This microprocessor implements the PA-RISC 1.1 architecture. Its most notable feature is the inclusion of the floating-point unit on the same die as the integer core. This on-die integration reduces latency for mathematical operations. The chip contains 850,000 transistors and measures 14.3 by 14.3 millimetres. It operates at clock speeds between 33 and 100 MHz. The design uses a 0.8 micrometre complementary metal–oxide–semiconductor process called CMOS26B. A copper-tungsten heat spreader helps manage thermal output within its 504-pin ceramic package.

How it was made

Hewlett-Packard manufactured the PA-7100 in-house using their CMOS26B process. This technology node features a minimum feature size of 0.8 micrometres. The fabrication occurred at two specific plants: one in Corvallis, Oregon, and another in Fort Collins, Colorado. The final component is housed in a 504-pin ceramic pin grid array package. To assist with cooling, the package includes a copper-tungsten heat spreader. The total silicon area for the die is approximately 204.49 square millimetres, containing 850,000 transistors.

PA-7100
A drawing made by EveryChip from what this page says. It is a diagram, not a picture of the real chip.

Where it went

The primary customers for this chip were HP itself and Stratus Computer. HP installed the PA-7100 in its HP 9000 series of workstations. Stratus used it in Continuum fault-tolerant servers, which require high reliability. Samsung also produced workstations based on this processor, running the HP-UX operating system under license from HP. These systems served engineers, scientists, and enterprise users who needed robust computing power for technical applications and server duties during the early 1990s.

Versions and family

The PA-7100 served as the foundation for several related chips. The PA-7150 arrived in 1994 as an improved version, reaching 125 MHz through better circuit design while using the same manufacturing process. The PA-7100LC and PA-7200 also derived their architecture from the original PA-7100 design. These variants allowed HP to extend the lifespan of the PA-RISC 1.1 platform across different performance tiers and market segments without redesigning the core instruction set support.

Why it matters

The PA-7100 established a new standard for HP’s RISC lineup by integrating floating-point hardware directly onto the processor die. This move simplified system board design and likely improved computational throughput for scientific and engineering software. It competed directly with the Digital Equipment Corporation Alpha 21064 in the workstation and server markets. The success of this integration paved the way for subsequent PA-RISC chips, ensuring HP remained a key player in high-end computing hardware throughout the 1990s.

Questions people ask about PA-7100

What makes the PA-7100 different from its predecessor?

The PA-7100 integrates the floating-point unit on the same silicon die as the main processor. Its predecessor, the PA-7000, used a chipset approach where the microprocessor and floating-point unit were separate components.

Which companies used the PA-7100 in their products?

Hewlett-Packard used it in HP 9000 workstations. Stratus Computer included it in Continuum fault-tolerant servers. Samsung also built workstations based on the chip using licensed HP technology and software.

What was the manufacturing process for this chip?

HP fabricated the PA-7100 using its internal CMOS26B process. This was a 0.8 micrometre complementary metal–oxide–semiconductor technology. Production took place at facilities in Corvallis, Oregon, and Fort Collins, Colorado.

Good reading and sources

Where this page comes from

The facts on this page come from the Wikipedia article "PA-7100", 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.

Photo credits on this page

The small pictures above come from Wikimedia Commons under free licences. Some are cropped to fit.

The weekly digest

Every Monday: the chip of the day, new pages on EveryChip, and the conferences and anniversaries of the week ahead.