 | This articleneeds additional citations forverification. Please helpimprove this article byadding citations to reliable sources. Unsourced material may be challenged and removed. Find sources: "Motorola 68040" – news ·newspapers ·books ·scholar ·JSTOR(May 2023) (Learn how and when to remove this message) |
| General information | |
|---|---|
| Launched | 1990 |
| Designed by | Motorola |
| Performance | |
| Max.CPUclock rate | 25 MHz to 40 MHz |
| Data width | 32 bits |
| Address width | 32 bits |
| Cache | |
| L1cache | 4096 bytes each for instruction and data with independent MMU and TLB[1] |
| Architecture and classification | |
| Instruction set | Motorola 68000 series |
| Physical specifications | |
| Transistors |
|
| Package | |
| Products, models, variants | |
| Variant |
|
| History | |
| Predecessor | Motorola 68030 |
| Successor | Motorola 68060 |
TheMotorola 68040 ("sixty-eight-oh-forty") is a32-bit microprocessor in theMotorola 68000 series, released in 1990.[2] It is the successor to the68030 and is followed by the68060, skipping the 68050. In keeping with general Motorola naming, the 68040 is often referred to as simply the '040 (pronouncedoh-four-oh oroh-forty).
The 68040 was the first680x0 family member with an on-chipFloating-Point Unit (FPU). It thus included all of the functionality that previously required external chips, namely the FPU andMemory Management Unit (MMU), which was added in the 68030. It also had split instruction and data caches of 4kilobytes each. It was fullypipelined, with six stages.[3]
Versions of the 68040 were created for specific market segments, including the68LC040, which removed the FPU, and the68EC040, which removed both the FPU and MMU. Motorola had intended the EC variant for embedded use, but embedded processors during the 68040's time did not need the power of the 68040, so EC variants of the 68020 and 68030 continued to be common in designs.
Motorola produced several speed grades. The 16 MHz and 20 MHz parts were never qualified (XC designation) and used as prototyping samples. 25 MHz and 33 MHz grades featured across the whole line, but until around 2000 the 40 MHz grade was only for the "full" 68040. A planned 50 MHz grade was canceled after it exceeded thethermal design envelope.
InApple Macintosh computers, the 68040 was introduced in theMacintosh Quadra, which was named for the chip. The fastest 68040 processor was clocked at 40 MHz and it was used only in theQuadra 840AV. The more expensive models in the (short-lived)Macintosh Centris line also used the 68040, while the cheaper Quadra, Centris,Performa, and some late-modelLC used the68LC040.
The 68040 was also used in otherpersonal computers, such as theAmiga 4000 andAmiga 4000T, as well as a number ofworkstations,Alpha Microsystems servers, theHP 9000/400 series,NCR Corporation's TOWER 32/750, 32/825 and 32/850,[4]Apollo Computer'sDN5500,[5] and later versions of theNeXT computer.
The 68040 processor is used in theflight management computers (FMC) aboard manyBoeing 737 aircraft, including allNext Generation andMAX models.[6]
The 68040 ran into the transistor budget limit early in design. While the MMU did not take many transistors—indeed, having it on the same die as the CPU actually saved on transistors—the FPU certainly did. Motorola's68882 external FPU was known as a very high performance unit and Motorola did not wish to risk integrators using the "LC" version with a 68882 instead of the more profitable full "RC" unit. (For information on Motorola's multiprocessing model with the 680x0 series, seeMotorola 68020.) The FPU in the 68040 was incapable of IEEEtranscendental functions, which had been supported by both the 68881 and 68882 and were used by the popular fractal generating software of the time and little else. The Motorola floating-point support package (FPSP) emulated these instructions in software under interrupt. As this was an exception handler, heavy use of the transcendental functions caused severe performance penalties.
Heat was always a problem throughout the 68040's life. While it delivered over four times the per-clock performance of the 68020 and 68030, the chip's complexity and power requirements came from a large die and large caches. This affected the scaling of the processor and it was never able to run with a clock rate exceeding 40 MHz. A 50 MHz variant was planned, but canceled.Overclocking enthusiasts reported success reaching 50 MHz using a 100 MHz oscillator instead of an 80 MHz part and the then novel technique of adding oversized heat sinks with fans.
The 68040 offered the same features as theIntel 80486, but on a clock-for-clock basis could significantly outperform the Intel chip in integer and floating-point instructions.[7][8] However, the 80486 had the ability to be clocked significantly faster without suffering from overheating problems, and also quickly spawned a mobile derivative for laptops. Newer-generationIntel 80486-based PC laptops were introduced in 1992, resulting in the 100-series PowerBook being stuck with the aging68030 which were no longer competitive, and Apple was unable to ship a 68040-equipped PowerBook until thePowerBook Duo 280 andPowerBook 500 series in 1994.[9][10]
The68EC040 is a version of the Motorola 68040 microprocessor, intended for embedded controllers (EC). It differs from the 68040 in that it has neither an FPU nor an MMU. This makes it less expensive and it draws less power. The 68EC040 was used in Cisco switchSupervisor Engine I that is the heart of models 2900, 2948G, 2980G, 4000, 4500, 5000, 5500, 6000, 6500 and 7600.
The68LC040 is alow cost version of the Motorola 68040microprocessor with no FPU. This makes it less expensive and it draws less power. Although the CPU now fits into a feature chart more like the Motorola 68030, it continues to include the 68040'scaches andpipeline and is thus significantly faster than the 68030.
Somemask revisions of the 68LC040 contained abug that prevents the chip from operating correctly when a software FPUemulator is used. According to Motorola's errata,[11] any chip with a mask set 2E71M or later does not contain the bug. This new mask was introduced in mid-1995 and converted the 68LC040 chip to MC status.[12]
The buggy revisions are typically found in 68LC040-basedApple Macintosh computers. Chips with mask set 2E23G (as used in the LC 475) have been confirmed to be faulty. The fault relates to pending writes being lost when the F-line exception is triggered.[13] The 68040 cannot update its microcode in the manner of modern x86 chips. This means that the only way to use software that requires floating-point functionality is to replace the buggy 68LC040 with a later revision, or a full 68040.
| Variant | MMU | FPU |
|---|---|---|
| 68040 | Yes | Yes |
| 68LC040 | Yes | No |
| 68EC040 | No | No |
| CPUclock rate | 25, 33, 40 MHz |
| Production process | staticCMOS0.8 μm,0.65 μm, Freescale0.57 μm |
| Chip carrier | 179 ceramicPGA and 184QFP |
| Address bus | 32 bit |
| Data bus | 32 bit |
| Instruction set | CISC |
| Transistors | ~1,200,000 |