676:, its initial, relatively, lower power and cooling implementation was soon adapted to embedded applications, such as laser printer raster image processing. Acorn, in partnership with Apple Inc, and VLSI, creating ARM Ltd, in 1990, to share R&D costs and find new markets for the ISA, who in partnership with TI, GEC, Sharp, Nokia, Oracle and Digital would develop low-power and embedded RISC designs, and target those market segments, which at the time were niche. With the rise in mobile, automotive, streaming, smart device computing, ARM became the most widely used ISA, the company estimating almost half of all CPUs shipped in history have been ARM.
830:
following 13 contain an immediate value or uses only five of them to indicate a register for the second operand. A more complex example is the MIPS encoding, which used only 6 bits for the opcode, followed by two 5-bit registers. The remaining 16 bits could be used in two ways, one as a 16-bit immediate value, or as a 5-bit shift value (used only in shift operations, otherwise zero) and the remaining 6 bits as an extension on the opcode. In the case of register-to-register arithmetic operations, the opcode was 0 and the last 6 bits contained the actual code; those that used an immediate value used the normal opcode field at the front.
561:
601:
777:—clearly a CISC CPU because many of its instructions involve multiple memory accesses—has only 8 basic instructions and a few extended instructions. The term "reduced" in that phrase was intended to describe the fact that the amount of work any single instruction accomplishes is reduced—at most a single data memory cycle—compared to the "complex instructions" of CISC CPUs that may require dozens of data memory cycles in order to execute a single instruction.
983:, yet many CPU designs dedicated 16 or 32 bits to store them. This suggests that, to reduce the number of memory accesses, a fixed length machine could store constants in unused bits of the instruction word itself, so that they would be immediately ready when the CPU needs them (much like immediate addressing in a conventional design). This required small opcodes in order to leave room for a reasonably sized constant in a 32-bit instruction word.
810:
have an immediate combined with the opcode in a single memory word, although certain instructions like increment and decrement did this implicitly by using a different opcode. In contrast, a 32-bit machine has ample room to encode an immediate value, and doing so avoids the need to do a second memory read to pick up the value. This is why many RISC processors allow a 12- or 13-bit constant to be encoded directly into the instruction word.
68:
690:
22:
862:. Generally, these instructions expose a smaller number of registers and fewer bits for immediate values, and often use a two-operand format to eliminate one register number from instructions. A two-operand format in a system with 16 registers requires 8 bits for register numbers, leaving another 8 for an opcode or other uses. The
818:, in which case three registers numbers are needed. If the processor has 32 registers, each one requires a 5-bit number, for 15 bits. If one of these registers is replaced by an immediate, there is still lots of room to encode the two remaining registers and the opcode. Common instructions found in multi-word systems, like
661:. Many of these have since disappeared due to them often offering no competitive advantage over others of the same era. Those that remain are often used only in niche markets or as parts of other systems; of the designs from these traditional vendors, only SPARC and POWER have any significant remaining market.
525:, produced a functioning system in 1983, and could run simple programs by 1984. The MIPS approach emphasized an aggressive clock cycle and the use of the pipeline, making sure it could be run as "full" as possible. The MIPS system was followed by the MIPS-X and in 1984 Hennessy and his colleagues formed
768:
A common misunderstanding of the phrase "reduced instruction set computer" is that instructions are simply eliminated, resulting in a smaller set of instructions. In fact, over the years, RISC instruction sets have grown in size, and today many of them have a larger set of instructions than many CISC
748:
Confusion around the definition of RISC deriving from the formulation of the term, along with the tendency to opportunistically categorize processor architectures with relatively few instructions (or groups of instructions) as RISC architectures, led to attempts to define RISC as a design philosophy.
596:
In the early 1980s, significant uncertainties surrounded the RISC concept. One concern involved the use of memory; a single instruction from a traditional processor like the
Motorola 68k may be written out as perhaps a half dozen of the simpler RISC instructions. In theory, this could slow the system
349:
The telephone switch program was canceled in 1975, but by then the team had demonstrated that the same design would offer significant performance gains running just about any code. In simulations, they showed that a compiler tuned to use registers wherever possible would run code about three times as
813:
Assuming a 13-bit constant area, as is the case in the MIPS and RISC designs, another 19 bits are available for the instruction encoding. This leaves ample room to indicate both the opcode and one or two registers. Register-to-register operations, mostly math and logic, require enough bits to encode
435:
Patterson's early work pointed out an important problem with the traditional "more is better" approach; even those instructions that were critical to overall performance were being delayed by their trip through the microcode. If the microcode was removed, the programs would run faster. And since the
103:(CISC), a RISC computer might require more instructions (more code) in order to accomplish a task because the individual instructions are written in simpler code. The goal is to offset the need to process more instructions by increasing the speed of each instruction, in particular by implementing an
947:
of the CPU busy for the extra time normally needed to perform a branch. Nowadays the branch delay slot is considered an unfortunate side effect of a particular strategy for implementing some RISC designs, and modern RISC designs generally do away with it (such as PowerPC and more recent versions of
496:
and aggressive use of register windowing. In a traditional CPU, one has a small number of registers, and a program can use any register at any time. In a CPU with register windows, there are a huge number of registers, e.g., 128, but programs can only use a small number of them, e.g., eight, at any
458:
than a sequence of simpler operations doing the same thing. This was in part an effect of the fact that many designs were rushed, with little time to optimize or tune every instruction; only those used most often were optimized, and a sequence of those instructions could be faster than a less-tuned
419:
to help DEC's west-coast team improve the VAX microcode. Patterson was struck by the complexity of the coding process and concluded it was untenable. He first wrote a paper on ways to improve microcoding, but later changed his mind and decided microcode itself was the problem. With funding from the
1018:
instruction. All other instructions were limited to internal registers. This simplified many aspects of processor design: allowing instructions to be fixed-length, simplifying pipelines, and isolating the logic for dealing with the delay in completing a memory access (cache miss, etc.) to only two
809:
Some of this is possible only due to the contemporary move to 32-bit formats. For instance, in a typical program, over 30% of all the numeric constants are either 0 or 1, 95% will fit in one byte, and 99% in a 16-bit value. When computers were based on 8- or 16-bit words, it would be difficult to
628:
processor, directly based on the
Berkeley RISC-II system. The US government Committee on Innovations in Computing and Communications credits the acceptance of the viability of the RISC concept to the success of the SPARC system. The success of SPARC renewed interest within IBM, which released new
505:
designs of the era), RISC-I had only 32 instructions, and yet completely outperformed any other single-chip design, with estimated performance being higher than the VAX. They followed this up with the 40,760-transistor, 39-instruction RISC-II in 1983, which ran over three times as fast as RISC-I.
501:: The call simply moves the window "down" by eight, to the set of eight registers used by that procedure, and the return moves the window back. The Berkeley RISC project delivered the RISC-I processor in 1982. Consisting of only 44,420 transistors (compared with averages of about 100,000 in newer
959:
assembly coding, and that complex addressing modes take many cycles to perform due to the required additional memory accesses. It was argued that such functions would be better performed by sequences of simpler instructions if this could yield implementations small enough to leave room for many
829:
The original RISC-I format remains a canonical example of the concept. It uses 7 bits for the opcode and a 1-bit flag for conditional codes, the following 5 bits for the destination register, and the next five for the first operand. This leaves 14 bits, the first of which indicates whether the
341:
generally ignored the vast majority of the available instructions, especially orthogonal addressing modes. Instead, they selected the fastest version of any given instruction and then constructed small routines using it. This suggested that the majority of instructions could be removed without
488:
of them actually performed an operation like addition or subtraction. But when those operations did occur, they tended to be slow. This led to far more emphasis on the underlying arithmetic data unit, as opposed to previous designs where the majority of the chip was dedicated to control and
1097:
Outside of the desktop arena, however, the ARM RISC architecture is in widespread use in smartphones, tablets and many forms of embedded devices. While early RISC designs differed significantly from contemporary CISC designs, by 2000 the highest-performing CPUs in the RISC line were almost
994:
of any instruction; decreasing that cycle-time often accelerates the execution of other instructions. The focus on "reduced instructions" led to the resulting machine being called a "reduced instruction set computer" (RISC). The goal was to make instructions so simple that they could
833:
One drawback of 32-bit instructions is reduced code density, which is more adverse a characteristic in embedded computing than it is in the workstation and server markets RISC architectures were originally designed to serve. To address this problem, several architectures, such as
583:
ISA is fixed. The ISA is designed to be extensible from a barebones core sufficient for a small embedded processor to supercomputer and cloud computing use with standard and chip designer–defined extensions and coprocessors. It has been tested in silicon design with the ROCKET
932:, where the instruction stream and the data stream are conceptually separated; this means that modifying the memory where code is held might not have any effect on the instructions executed by the processor (because the CPU has a separate instruction and data
110:
The key operational concept of the RISC computer is that each instruction performs only one function (e.g. copy a value from memory to a register). The RISC computer usually has many (16 or 32) high-speed, general-purpose registers with a
350:
fast as traditional designs. Somewhat surprisingly, the same code would run about 50% faster even on existing machines due to the improved register use. In practice, their experimental PL/8 compiler, a slightly cut-down version of
789:
Another way of looking at the RISC/CISC debate is to consider what is exposed to the compiler. In a CISC processor, the hardware may internally use registers and flag bit in order to implement a single complex instruction such as
115:
in which the code for the register-register instructions (for performing arithmetic and tests) are separate from the instructions that access the main memory of the computer. The design of the CPU allows RISC computers few simple
936:), at least until a special synchronization instruction is issued; CISC processors that have separate instruction and data caches generally keep them synchronized automatically, for backwards compatibility with older processors.
295:(register+register, and register+immediate constant) and 74 operation codes, with the basic clock cycle being 10 times faster than the memory access time. Partly due to the optimized load–store architecture of the CDC 6600,
943:, an instruction space immediately following a jump or branch. The instruction in this space is executed, whether or not the branch is taken (in other words the effect of the branch is delayed). This instruction keeps the
436:
microcode ultimately took a complex instruction and broke it into steps, there was no reason the compiler couldn't do this instead. These studies suggested that, even with no other changes, one could make a chip with
960:
registers, reducing the number of slow memory accesses. In these simple designs, most instructions are of uniform length and similar structure, arithmetic operations are restricted to CPU registers and only separate
369:
in 1986, which turned out to be a commercial failure. Although the 801 did not see widespread use in its original form, it inspired many research projects, including ones at IBM that would eventually lead to the
548:
The goal of any instruction format should be: 1. simple decode, 2. simple decode, and 3. simple decode. Any attempts at improved code density at the expense of CPU performance should be ridiculed at every
632:
By the later 1980s, the new RISC designs were easily outperforming all traditional designs by a wide margin. At that point, all of the other vendors began RISC efforts of their own. Among these were the
1505:, and designed to be extended with instructions for networking, I/O, and data processing. A specification for a 64-bit superscalar design, "Rocket", is available for download. It is implemented in the
1031:
Some CPUs have been specifically designed to have a very small set of instructions—but these designs are very different from classic RISC designs, so they have been given other names such as
826:, which reduce the number of words that have to be read before performing the instruction, are unnecessary in RISC as they can be accomplished with a single register and the immediate value 1.
806:
Most RISC architectures have fixed-length instructions and a simple encoding, which simplifies fetch, decode, and issue logic considerably. This is among the main goals of the RISC approach.
478:
which can significantly improve subroutine performance although at the cost of some complexity. They also noticed that the majority of mathematical instructions were simple assignments; only
885:
Single-cycle operation, described as "the rapid execution of simple functions that dominate a computer's instruction stream", thus seeking to deliver an average throughput approaching one
1046:-based platforms remain the dominant processor architecture. However, this may change, as ARM-based processors are being developed for higher performance systems. Manufacturers including
333:
The design was based on a study of IBM's extensive collection of statistics gathered from their customers. This demonstrated that code in high-performance settings made extensive use of
428:
effort. The
Program, practically unknown today, led to a huge number of advances in chip design, fabrication, and even computer graphics. Considering a variety of programs from their
299:
says that it can be considered a forerunner of modern RISC systems, although a number of other technical barriers needed to be overcome for the development of a modern RISC system.
1606:
ARM DesignStart, in 2018 ARM, in partnership with FPGA supplier Xilinx, started to offer free access to some of ARM's IP, including FPGA specification for some older CPU cores.
668:
has been the most widely adopted RISC ISA, initially intended to deliver higher performance desktop computing, at low cost, and in a restricted thermal package, such as in the
968:
instructions access memory. These properties enable a better balancing of pipeline stages than before, making RISC pipelines significantly more efficient and allowing higher
382:
By the late 1970s, the 801 had become well-known in the industry. This coincided with new fabrication techniques that were allowing more complex chips to come to market. The
986:
Since many real-world programs spend most of their time executing simple operations, some researchers decided to focus on making those operations as fast as possible. The
979:
summed up many of these, demonstrating that processors often had oversized immediates. For instance, he showed that 98% of all the constants in a program would fit in 13
579:, has been under development at the University of California, Berkeley, for research purposes and as a free alternative to proprietary ISAs. As of 2014, version 2 of the
474:
calls and returns, and it seemed there was the potential to improve overall performance by speeding these calls. This led the
Berkeley design to select a method known as
3264:
955:
designs around 1975 include the observations that the memory-restricted compilers of the time were often unable to take advantage of features intended to facilitate
390:(68k) had 68,000. These newer designs generally used their newfound complexity to expand the instruction set to make it more orthogonal. Most, like the 68k, used
4914:
1066:-based devices in 2017 as part of its partnership with Qualcomm. These devices will support Windows applications compiled for 32-bit x86 via an x86 processor
620:
in some of their computers. In the meantime, the
Berkeley effort had become so well known that it eventually became the name for the entire concept. In 1987
2277:
753:
A RISC processor has an instruction set that is designed for efficient execution by a pipelined processor and for code generation by an optimizing compiler.
322:. To reach their goal of switching 1 million calls per hour (300 per second) they calculated that the CPU required performance on the order of 12 million
553:
Competition between RISC and conventional CISC approaches was also the subject of theoretical analysis in the early 1980s, leading, for example, to the
209:
began offering systems designed according to RISC or RISC-like principles in the early 1980s. Few of these designs began by using RISC microprocessors.
1333:, a small core integer instruction set, and an experimental "Compressed" ISA for code density and designed for standard and special-purpose extensions.
1150:
dominates the market for low-power and low-cost embedded systems (typically 200–1800 MHz in 2014). It is used in a number of systems such as most
597:
down as it spent more time fetching instructions from memory. But by the mid-1980s, the concepts had matured enough to be seen as commercially viable.
707:
470:
The
Berkeley work also turned up a number of additional points. Among these was the fact that programs spent a significant amount of time performing
866:
also follows this pattern, albeit having evolved in the opposite direction, having added longer 32-bit instructions to an original 16-bit encoding.
127:
project in the late 1970s, but these were not immediately put into use. Designers in
California picked up the 801 concepts in two seminal projects,
3886:
3453:
5025:
4208:
1597:, in 2010, the Berkeley RISC version 5, specification, tool chain, and brand, were made available, free of charge, for non-commercial purposes.
3030:
4727:
2223:
361:
in 1981, which stood for 'Research OPD Micro
Processor'. This CPU was designed for "mini" tasks, and found use in peripheral interfaces and
3205:
40:
4005:
3608:
878:
dedicated to the core logic which originally allowed designers to increase the size of the register set and increase internal parallelism.
337:, and that they often ran out of them. This suggested that additional registers would improve performance. Additionally, they noticed that
2451:
1010:
Later, it was noted that one of the most significant characteristics of RISC processors was that external memory was only accessible by a
4884:
4450:
4267:
3341:
Apple has officially announced that it will be switching from Intel processors to its own ARM-based, A-series chips in its Mac computers.
1007:. This contrasted with CISC designs whose "crucial arithmetic operations and register transfers" were considered difficult to pipeline.
5238:
794:, but hide those details from the compiler. The internal operations of a RISC processor are "exposed to the compiler", leading to the
4230:
3076:
99:
designed to simplify the individual instructions given to the computer to accomplish tasks. Compared to the instructions given to a
4879:
318:
and completed in 1980. The 801 developed out of an effort to build a 24-bit high-speed processor to use as the basis for a digital
3354:
3008:
268:
A number of systems, going back to the 1960s, have been credited as the first RISC architecture, partly based on their use of the
4951:
2817:
1142:
By the beginning of the 21st century, the majority of low-end and mobile systems relied on RISC architectures. Examples include:
2860:
Colwell, Robert P.; Hitchcock III, Charles Y.; Jensen, E. Douglas; Sprunt, H. M. Brinkley; Kollar, Charles P. (September 1985).
1733:
Colwell, Robert P.; Hitchcock III, Charles Y.; Jensen, E. Douglas; Sprunt, H. M. Brinkley; Kollar, Charles P. (September 1985).
1058:
in 2017 to produce an ARM-based supercomputer. On the desktop, Microsoft announced that it planned to support the PC version of
5822:
5233:
4704:
540:
The overall philosophy of the RISC concept was widely understood by the second half of the 1980s, and led the designers of the
1829:
432:
variant, the
Berkeley team found, as had IBM, that most programs made no use of the large variety of instructions in the 68k.
3406:
2716:
2135:
394:
to do this, reading instructions and re-implementing them as a sequence of simpler internal instructions. In the 68k, a full
2982:
1639:
for their contributions to the invention, development, and implementation of reduced instruction set computer (RISC) chips.
5648:
4772:
4035:
3879:
1684:
1624:
408:
346:
to be shorter, freeing up bits in the instruction word which could then be used to select among a larger set of registers.
273:
3274:
3054:
5658:
4799:
1766:
342:
affecting the resulting code. These two conclusions worked in concert; removing instructions would allow the instruction
3926:
1352:
416:
3519:
4966:
4794:
4767:
4146:
3170:
2931:
2761:
2519:
2376:
2164:
2105:
2071:
1983:
1927:
1603:, in 2015, a project to offer clean room implementations of the, patent expired, Hitachi SuperH RISC ISA was started.
729:
554:
502:
454:
It was also discovered that, on microcoded implementations of certain architectures, complex operations tended to be
3531:
5781:
5344:
4237:
4198:
4117:
4082:
3601:
2261:
1036:
1032:
100:
31:
1042:
RISC architectures have traditionally had few successes in the desktop PC and commodity server markets, where the
5756:
5653:
5054:
4961:
4762:
3983:
3872:
3131:
1636:
1373:
315:
4782:
4501:
3936:
2965:
1894:
1717:
711:
429:
2861:
5817:
4956:
4804:
4777:
4638:
4252:
4213:
4070:
1506:
1498:
1476:
629:
RISC systems by 1990 and by 1995 RISC processors were the foundation of a $ 15 billion server industry.
975:
Yet another impetus of both RISC and other designs came from practical measurements on real-world programs.
892:
Uniform instruction format, using single word with the opcode in the same bit positions for simpler decoding
159:. As the projects matured, many similar designs, produced in the mid-to-late 1980s and early 1990s, such as
5393:
5155:
4631:
4592:
4247:
4242:
4176:
3988:
3297:
1663:
1658:
572:
3102:
2736:
5020:
4717:
4415:
4112:
3594:
2587:
2292:
1763:
Proceedings of the 1992 ACM/SIGAPP Symposium on
Applied computing: technological challenges of the 1990's
1734:
782:
269:
112:
3586:
3323:
2919:
5670:
5317:
4734:
4225:
4193:
3963:
3951:
3931:
2005:
1789:
1632:
1151:
859:
839:
2428:
2408:
609:
5761:
5724:
5714:
4102:
3560:
1559:, for part of 2019 the specifications were free to use, royalty free, for registered MIPS developers.
917:
900:
654:
1919:
529:
to produce the design commercially. The venture resulted in a new architecture that was also called
450:
Skipping this extra level of interpretation appears to enhance performance while reducing chip size.
5776:
5183:
5119:
5096:
4946:
4908:
4744:
4694:
4689:
4166:
4060:
3968:
2309:
896:
2700:
2561:
2535:
2227:
1975:
1886:
5729:
5512:
5406:
5370:
5287:
5271:
5113:
4902:
4861:
4849:
4712:
4626:
4547:
4312:
3973:
3916:
3671:
3209:
2341:
2038:
1513:
1147:
814:
the two or three registers being used. Most processors use the three-operand format, of the form
700:
665:
323:
160:
3576:
3145:
2511:
1090:
processor, were released in November 2020. Macs with Apple silicon can run x86-64 binaries with
5535:
5507:
5417:
5382:
5131:
5125:
5107:
4841:
4835:
4739:
4643:
4534:
4473:
4335:
3978:
3845:
2633:
2304:
1837:
1448:
1127:
1123:
1115:
886:
493:
371:
257:
148:
3160:
2127:
2063:
459:
instruction performing an equivalent operation as that sequence. One infamous example was the
5709:
5618:
5364:
5076:
4894:
4653:
4621:
4579:
4491:
4292:
4107:
4097:
4087:
4077:
4047:
4030:
3895:
1648:
1494:
1472:
1348:
1330:
1265:
1245:
944:
526:
96:
59:
2692:
2503:
2119:
2055:
1967:
1912:
1878:
899:
can be used equally as source/destination in all instructions, simplifying compiler design (
612:
appeared in April 1985, MIPS R2000 appeared in January 1986, followed shortly thereafter by
5739:
5675:
5261:
4983:
4873:
4820:
4352:
4065:
3921:
3903:
3792:
3676:
1852:
1565:, in 2005, Sun released its Ultra Sparc documentation and specifications, under the GPLv2.
1534:
1257:
929:
921:
560:
534:
497:
one time. A program that limits itself to eight registers per procedure can make very fast
104:
1054:
have released server processors based on the ARM architecture. ARM further partnered with
769:
CPUs. Some RISC processors such as the PowerPC have instruction sets as large as the CISC
8:
5786:
5771:
5591:
5442:
5424:
5388:
5376:
5030:
4977:
4754:
4670:
4552:
4407:
4302:
4161:
3710:
3572:
2693:
2266:. 8th annual symposium on Computer Architecture. Minneapolis, MN, USA. pp. 443–457.
1968:
1879:
1742:
1538:
1520:
series processor used for various services on the AWS platform. ARM was also used in the
1403:
1261:
1063:
976:
514:
2673:
2654:
2614:
588:, which is also available as an open-source processor generator in the CHISEL language.
5643:
5635:
5487:
5462:
5266:
5141:
4665:
4606:
4486:
4218:
3946:
3736:
2881:
2798:
2474:
2322:
1430:
1372:
based on the ARM architecture for its lineup of desktop and laptop computers since its
1187:
1078:
desktop and laptop computers from Intel processors to internally developed ARM64-based
1071:
362:
334:
202:
198:
187:
179:
3432:
2835:
1945:
Assembly Language Programming for the Control Data 6000 Series and the Cyber 70 Series
1455:
were and are used in many of IBM's supercomputers, mid-range servers and workstations.
874:
For any given level of general performance, a RISC chip will typically have far fewer
5596:
5563:
5479:
5411:
5312:
5302:
5292:
5223:
5218:
5213:
5136:
5065:
4971:
4931:
4564:
4514:
4464:
4440:
4322:
4262:
4257:
4139:
4055:
3695:
3359:
3166:
2961:
2955:
2927:
2757:
2712:
2515:
2504:
2372:
2160:
2131:
2120:
2101:
2067:
2056:
1979:
1948:
1923:
1890:
1713:
1556:
1416:
1387:
1237:
1131:
843:
530:
136:
36:
2802:
2478:
2326:
5766:
5699:
5685:
5540:
5447:
5401:
5208:
5203:
5198:
5193:
5188:
5178:
5048:
5015:
4926:
4921:
4830:
4682:
4677:
4660:
4648:
4587:
4151:
4129:
4015:
3993:
3911:
3821:
3564:
3187:
2885:
2873:
2790:
2704:
2466:
2314:
2267:
2020:
1770:
1705:
1620:
1502:
1434:
1420:
1241:
1191:
1079:
743:
669:
621:
585:
522:
319:
307:
84:
72:
2181:
1106:
RISC architectures are now used across a range of platforms, from smartphones and
906:
Simple addressing modes with complex addressing performed by instruction sequences
446:
fewer transistors that would run faster. In the original RISC-I paper they noted:
5680:
5665:
5613:
5517:
5492:
5329:
5322:
5173:
5168:
5163:
5102:
5010:
5000:
4722:
4557:
4509:
4272:
4156:
4124:
4025:
4020:
3941:
3666:
3454:"Arm Expands Design Possibilities with Free Cortex-M Processors for Xilinx FPGAs"
2751:
2470:
1794:
1484:
1458:
1203:
1107:
969:
613:
475:
357:
A 32-bit version of the 801 was eventually produced in a single-chip form as the
292:
213:
206:
120:
and predictable instruction times that simplify design of the system as a whole.
117:
2924:
Proceedings of the Conference Held at Computer Graphics 87, London, October 1987
492:
The resulting Berkeley RISC was based on gaining performance through the use of
354:, consistently produced code that ran much faster on their existing mainframes.
171:, created central processing units that increased the commercial utility of the
5791:
5625:
5608:
5601:
5497:
5354:
5091:
5005:
4936:
4519:
4481:
4430:
4425:
4420:
4134:
3958:
3831:
3802:
3658:
3556:
2778:
1758:
1653:
1584:
1308:
1183:
1075:
770:
650:
510:
498:
387:
327:
241:
147:
eventually produced RISC designs based on further work on the 801 concept, the
2723:
the main goal was not to reduce the number of instructions, but the complexity
2429:"The RISC-V Instruction Set Manual, Volume I: Base User-Level ISA version 2.0"
600:
5811:
5586:
5502:
4542:
4524:
4317:
4010:
3690:
3642:
3637:
3544:
3269:
2295:; Ditzel, D. R. (1980). "The case for the reduced instruction set computer".
2152:
1952:
1628:
1541:
since they are relatively simple to implement, which makes them suitable for
1521:
1369:
1326:
1271:
1249:
1222:
1179:
1111:
1083:
569:
518:
425:
296:
277:
253:
183:
132:
128:
123:
The conceptual developments of the RISC computer architecture began with the
4445:
2877:
2794:
2708:
5796:
5734:
5550:
5527:
5339:
5060:
3998:
3779:
3686:
2638:
1616:
1594:
1517:
1207:
1199:
421:
288:
194:
3561:"Yet Another Post of the Old RISC Post [unchanged from last time]"
3478:
2349:. Advanced Course on VLSI Architecture. University of Bristol. CSD-82-106.
2318:
2271:
1774:
1552:, an open instruction set and micro-architecture first introduced in 2000.
5581:
5545:
5256:
5228:
5086:
4941:
3864:
3797:
3774:
3616:
2983:"Microsoft unveils new ARM server designs, threatening Intel's dominance"
2905:
2200:
1286:
1253:
1195:
1167:
638:
217:
175:
80:
3496:
3226:
2872:(9). The Institute of Electrical and Electronics Engineers, Inc.: 8–19.
2753:
Embedded Computing: A VLIW Approach to Architecture, Compilers and Tools
2449:
2024:
1881:
Embedded Computing: A VLIW Approach to Architecture, Compilers and Tools
1380:
processors, and the first such computers were released in November 2020.
5467:
5457:
5452:
5434:
5334:
5307:
4569:
4402:
4372:
4092:
3816:
3812:
3749:
3568:
3381:
2678:
PDP-8 Collection, The University Of Iowa Department of Computer Science
1365:
1359:
1175:
1159:
1059:
987:
940:
875:
714: in this section. Unsourced material may be challenged and removed.
646:
642:
580:
471:
412:
233:
229:
3214:
the line between RISC and CISC has been growing fuzzier over the years
2450:
Garnsey, Elizabeth; Lorenzoni, Gianni; Ferriani, Simone (March 2008).
1600:
673:
5558:
5555:
5297:
4367:
4345:
3807:
3769:
3753:
3705:
3077:"Microsoft is bringing Windows desktop apps to mobile ARM processors"
1810:
1735:"Instruction Sets and Beyond: Computers, Complexity, and Controversy"
1588:
1580:
1562:
1468:
1452:
1383:
1344:
1304:
1290:
1098:
indistinguishable from the highest-performing CPUs in the CISC line.
1091:
933:
910:
847:
795:
634:
391:
383:
366:
326:(MIPS), compared to their fastest mainframe machine of the time, the
237:
221:
168:
156:
3835:
2862:"Instruction Sets and Beyond: Computers, Complexity and Controversy"
2427:
Waterman, Andrew; Lee, Yunsup; Patterson, David A.; Asanovi, Krste.
1516:
currently in use by cloud providers for servers. One example is the
863:
689:
67:
5573:
4392:
3853:
3700:
3681:
3661:
3407:"Wave Computing Shutters MIPS Open Programme with Immediate Effect"
3328:
3032:
AMD's first ARM-based processor, the Opteron A1100, is finally here
2431:. University of California, Berkeley. Technical Report EECS-2014-54
1549:
1226:
1214:
1171:
1087:
1067:
1051:
939:
Many early RISC designs also shared the characteristic of having a
855:
358:
338:
284:
225:
2452:"Speciation through entrepreneurial spin-off: The Acorn-ARM story"
4382:
4340:
3849:
3840:
3741:
3632:
3009:"Cavium Unveils ThunderX2 Plans, Reports ARM Traction is Growing"
2100:
by Committee on Innovations in Computing and Communications 1999
1545:
implementations and prototyping, for instance. Examples include:
1524:
chip to create Fugaku, the world's fastest supercomputer in 2020.
1462:
1438:
1399:
1312:
1294:
658:
617:
311:
280:
project, although somewhat similar concepts had appeared before.
164:
152:
124:
2859:
1732:
990:
of a CPU is limited by the time it takes to execute the slowest
4397:
4362:
4327:
3826:
3746:
3726:
3717:
2098:
Funding a Revolution: Government Support for Computing Research
2058:
Processor architecture: from dataflow to superscalar and beyond
1490:
1480:
1395:
1391:
1322:
1298:
1275:
1155:
1119:
1047:
851:
835:
576:
541:
343:
249:
245:
3479:"Recipients of the Charles Stark Draper Prize for Engineering"
2122:
Processor design: system-on-chip computing for ASICs and FPGAs
1710:
Computer Architecture: Pipelined and Parallel Processor Design
608:
Commercial RISC designs began to emerge in the mid-1980s. The
107:, which may be simpler to achieve given simpler instructions.
4855:
4387:
4357:
3787:
3784:
3731:
1853:"Japan's Fugaku gains title as world's fastest supercomputer"
1572:
1426:
1377:
1230:
774:
625:
140:
3055:"Cray to Deliver ARM-Powered Supercomputer to UK Consortium"
1410:
1019:
instructions. This led to RISC designs being referred to as
5719:
4867:
4787:
4377:
3721:
3713:
2750:
Fisher, Joseph A.; Faraboschi, Paolo; Young, Cliff (2005).
1877:
Fisher, Joseph A.; Faraboschi, Paolo; Young, Cliff (2005).
1571:, an open source, radiation-tolerant implementation of the
1568:
1542:
1279:
1163:
1055:
914:
365:
on later IBM computers. It was also used as the CPU in the
351:
172:
55:
Processor executing one instruction in minimal clock cycles
1798:. Vol. 9, no. 12. McGraw-Hill. pp. 191–206.
4307:
4297:
2691:
Dandamudi, Sivarama P. (2005). "Ch. 3: RISC Principles".
1914:
Milestones in computer science and information technology
1444:
1316:
1282:
1218:
1043:
980:
460:
144:
3580:
Nth re-posting of CISC vs RISC (or what is RISC, really)
1465:, also known as HP-PA (discontinued at the end of 2008).
679:
3355:"Microsoft to launch a new ARM-based Surface this fall"
3324:"Apple starts its two-year transition to ARM this week"
2426:
1830:"Inside Technology — The Frantic Search for More Speed"
2695:
Guide to RISC Processors for Programmers and Engineers
1970:
Numerical Linear Algebra on High-Performance Computers
75:
UltraSPARC processor is a type of RISC microprocessor.
3126:
3124:
2777:
Alexander, W. Gregg; Wortman, David (November 1975).
2749:
2528:
1876:
1497:, and the integer core extended with floating point,
749:
One attempt to do so was expressed as the following:
291:
in 1964 used a load–store architecture with only two
3219:
3069:
2779:"Static and Dynamic Characteristics of XPL Programs"
2579:
1026:
2906:"Microprocessors From the Programmer's Perspective"
2613:Esponda, Margarita; Rojas, Ra'ul (September 1991).
1493:, the fifth Berkeley RISC ISA, with 64- or 128-bit
1347:computers from 1994, when they began a switch from
404:of the transistors were used for this microcoding.
212:The varieties of RISC processor design include the
3121:
2615:"Section 2: The confusion around the RISC concept"
2287:
2285:
2255:
2253:
2251:
2249:
2247:
2245:
2243:
2241:
2239:
2237:
1911:
1575:V8 instruction set (targeting space applications).
377:
2054:Ĺ ilc, Jurij; RobiÄŤ, Borut; Ungerer, Theo (1999).
2004:Cocke, John; Markstein, Victoria (January 1990).
1712:. Jones & Bartlett Learning. pp. 54–56.
5809:
2776:
2053:
1808:
1528:
1475:, workstations, servers and supercomputers from
386:of 1976 had 8,000 transistors, whereas the 1979
135:. These were commercialized in the 1980s as the
2339:
2291:
2282:
2263:RISC I: A Reduced Instruction Set VLSI Computer
2259:
2234:
1726:
1343:IBM's PowerPC architecture was used in Apple's
1337:
928:RISC designs are also more likely to feature a
3382:"ARM Processor - AWS Graviton Processor - AWS"
2619:The RISC Concept — A Survey of Implementations
2260:Patterson, David A.; Sequin, Carlo H. (1981).
2150:
2003:
881:Other features of RISC architectures include:
798:'Relegate Interesting Stuff to the Compiler'.
657:, and, slightly later, the IBM/Apple/Motorola
3880:
3602:
3148:(Press release). Apple Inc. 12 November 2020.
3134:(Press release). Apple Inc. 10 November 2020.
2490:the first silicon was run on April 26th 1985.
2340:Sequin, Carlo; Patterson, David (July 1982).
2182:"Design Philosophy Behind Motorola's MC68000"
1821:
1802:
1682:
1307:, used in a variety of products ranging from
1137:
1074:. Apple announced they will transition their
763:
509:As the RISC project began to become known in
244:, the MIPS architecture, PA-RISC, Power ISA,
3497:"Charles Stark Draper Prize for Engineering"
3433:"Branding Guidelines – RISC-V International"
3298:"Review: The ARM-powered Samsung Chromebook"
2953:
2911:
2612:
2562:"Arm searches for growth beyond smartphones"
1999:
1997:
1995:
1683:Chen, Crystal; Novick, Greg; Shimano, Kirk.
1101:
4885:Computer performance by orders of magnitude
3295:
2853:
2410:Code Density Concerns for New Architectures
1781:
1423:(ceased making MIPS-based systems in 2006).
1386:uses Qualcomm ARM-based processors for its
58:"RISC" redirects here. For other uses, see
3894:
3887:
3873:
3609:
3595:
2954:Dowd, Kevin; Loukides, Michael K. (1993).
1811:"Histoire de l'Informatique et d'Internet"
1750:
1591:with extensions for video and 3D graphics.
1533:RISC architectures have become popular in
951:Some aspects attributed to the first RISC-
858:, have an optional short, feature-reduced
263:
3321:
3250:
3162:Schaum's Outline of Computer Architecture
2690:
2390:
2388:
2308:
2218:
2216:
2214:
2198:
2093:
2091:
2089:
2087:
2085:
2083:
2006:"The evolution of RISC technology at IBM"
1992:
1700:
1698:
1411:Workstations, servers, and supercomputers
730:Learn how and when to remove this message
521:project grew out of a graduate course by
252:, and SPARC. RISC processors are used in
3206:"A History of Apple's Operating Systems"
3165:. McGraw Hill Professional. p. 96.
3132:"Introducing the next generation of Mac"
2917:
2362:
2360:
2358:
2356:
1965:
1942:
1903:
1315:open-source microcontroller platform to
1072:translates 32-bit x86 code to ARM64 code
599:
559:
66:
3262:
3052:
3006:
2980:
2926:. Online Publications. pp. 83–91.
2815:
2652:
2606:
2406:
2333:
2179:
2013:IBM Journal of Research and Development
1966:Dongarra, Jack J.; et al. (1987).
1870:
1787:
869:
5810:
3555:
3489:
3265:"Apple shifting from PowerPC to Intel"
3158:
2585:
2501:
2385:
2297:ACM SIGARCH Computer Architecture News
2211:
2111:
2080:
2043:(Technical report). IBM. January 1987.
1909:
1827:
1756:
1695:
1325:, the current iteration of Berkeley's
1086:; the first such computers, using the
591:
272:approach. The term RISC was coined by
3868:
3590:
3352:
3188:"CISC, RISC, and DSP Microprocessors"
3185:
2834:Staff, Embedded (24 September 2003).
2833:
2734:
2394:
2353:
2159:. Gulf Professional. pp. 252–4.
2117:
1704:
801:
758:Michael Slater, Microprocessor Report
680:Characteristics and design philosophy
4856:Floating-point operations per second
3471:
3053:Feldman, Michael (18 January 2017).
2621:. Freie Universitat Berlin. B-91-12.
2366:
1353:transitioned to Intel x86 processors
999:be pipelined, in order to achieve a
712:adding citations to reliable sources
683:
15:
2343:Design and Implementation of RISC I
1767:Association for Computing Machinery
1362:use ARM-based platforms since 2012.
1122:list as of November 2020, and
773:, for example; conversely, the DEC
310:views the first RISC system as the
13:
3542:
3353:Smith, Chris (16 September 2020).
2634:"RISC vs. CISC: the Post-RISC Era"
2631:
1947:. Algorithmics Press. p. 12.
1765:. SAC '92. Kansas City, Missouri:
1759:"An overview of RISC architecture"
1757:Aletan, Samuel O. (1 April 1992).
903:registers are often kept separate)
848:Power Variable Length Encoding ISA
604:Acorn ARM Evaluation System (1985)
417:University of California, Berkeley
14:
5834:
3511:
3227:"Top 500 The List: November 2020"
3203:
2671:
2510:. Taylor & Francis. pp.
2157:Readings in computer architecture
1918:. Greenwood Publishing. pp.
1094:, an x86-64 to ARM64 translator.
1027:Comparison to other architectures
889:for any single instruction stream
555:iron law of processor performance
5782:Semiconductor device fabrication
3618:Reduced instruction set computer
3322:DeAngelis, Marc (22 June 2020).
3103:"How x86 emulation works on ARM"
2199:Patterson, David (30 May 2018).
1828:Manuel, Tom (3 September 1987).
1278:, originally in wide use in the
1240:line (at one point used in many
1037:transport triggered architecture
1033:minimal instruction set computer
688:
624:began shipping systems with the
197:market, companies that included
101:complex instruction set computer
89:reduced instruction set computer
32:Complex instruction set computer
20:
5757:History of general-purpose CPUs
3984:Nondeterministic Turing machine
3446:
3425:
3399:
3374:
3346:
3315:
3289:
3256:
3244:
3197:
3179:
3152:
3138:
3095:
3046:
3023:
3000:
2981:Vincent, James (9 March 2017).
2974:
2947:
2899:
2827:
2809:
2770:
2743:
2728:
2684:
2665:
2646:
2625:
2554:
2495:
2443:
2420:
2407:Weaver, Vincent; McKee, Sally.
2400:
2192:
2173:
2144:
2047:
2031:
1959:
1936:
1788:Markoff, John (November 1984).
1637:National Academy of Engineering
1351:processors, to 2005, when they
1134:, the next three on that list.
1110:to some of the world's fastest
823:
819:
815:
791:
699:needs additional citations for
378:Berkeley RISC and Stanford MIPS
330:, which performed at 3.5 MIPS.
3937:Deterministic finite automaton
3035:, ExtremeTech, 14 January 2016
2816:Soares, JoĂŁo; Rocha, Ricardo.
2735:Walls, Colin (18 April 2016).
2369:The MIPS-X RISC microprocessor
1845:
1841:. McGraw-Hill. pp. 59–62.
1676:
1487:(HP)(discontinued as of 2007).
1213:IBM's PowerPC was used in the
216:processor, the DEC Alpha, the
1:
5823:Instruction set architectures
4728:Simultaneous and heterogenous
3007:Russell, John (31 May 2016).
2674:"Doug Jones's DEC PDP-8 FAQs"
2586:Slater, Michael (June 1990).
2371:. Springer. pp. xix–xx.
2040:IBM System/370 System Summary
1669:
1529:Open source, standard, or use
1507:European Processor Initiative
1477:Digital Equipment Corporation
1329:RISC ISA, with 32- or 64-bit
1311:handheld controllers and the
513:, a similar project began at
46:Proposed since December 2023.
5412:Integrated memory controller
5394:Translation lookaside buffer
4593:Memory dependence prediction
4036:Random-access stored program
3989:Probabilistic Turing machine
3538:. Stanford University. 2000.
3526:. Stanford University. 2000.
3159:Carter, Nicholas P. (2002).
2818:"Encoding MIPS Instructions"
2659:Australian Personal Computer
2653:Borrett, Lloyd (June 1991).
2471:10.1016/j.respol.2007.11.006
2180:Starnes, Thomas (May 1983).
1809:Boursin de l'Arc, Philippe.
1664:One-instruction set computer
1659:No instruction set computing
1338:Desktop and laptop computers
1293:, now developed and sold by
674:Super Computer League tables
573:instruction set architecture
564:RISC-V prototype chip (2013)
544:to put it this way in 1987:
220:, the ARM architecture, the
7:
4868:Synaptic updates per second
3296:Vaughan-Nichols, Steven J.
2836:"ARM Thumb Instruction Set"
2224:"Example: Berkeley RISC II"
1642:
1370:inhouse-designed processors
1244:computers) was used in the
29:It has been suggested that
10:
5839:
5272:Heterogeneous architecture
4194:Orthogonal instruction set
3964:Alternating Turing machine
3952:Quantum cellular automaton
3186:Jones, Douglas L. (2000).
2957:High Performance Computing
2918:Sweetman, Dominic (1987).
1633:Charles Stark Draper Prize
1154:-based systems, the Apple
1138:Low-end and mobile systems
860:compressed instruction set
764:Instruction set philosophy
741:
302:
57:
5762:Microprocessor chronology
5749:
5725:Dynamic frequency scaling
5698:
5634:
5572:
5526:
5478:
5433:
5353:
5280:
5249:
5154:
5075:
5039:
4993:
4893:
4880:Cache performance metrics
4819:
4753:
4703:
4614:
4605:
4578:
4533:
4500:
4472:
4463:
4283:
4186:
4175:
4046:
3902:
3762:
3651:
3625:
2536:"Olivetti buys RISC card"
2506:Computer science handbook
2502:Tucker, Allen B. (2004).
2155:; Sohi, Gurindar (1999).
1910:Reilly, Edwin D. (2003).
1610:
1102:Use of RISC architectures
897:general-purpose registers
672:, while featuring in the
314:design, begun in 1975 by
5777:Hardware security module
5120:Digital signal processor
5097:Graphics processing unit
4909:Graphics processing unit
3386:Amazon Web Services, Inc
2756:. Elsevier. p. 57.
2632:Stokes, Jon "Hannibal".
2542:. August 1988. p. 7
1943:Grishman, Ralph (1974).
1790:"New Chips — RISC Chips"
786:is sometimes preferred.
424:, Patterson started the
190:, and similar products.
5730:Dynamic voltage scaling
5513:Memory address register
5407:Branch target predictor
5371:Address generation unit
5114:Physics processing unit
4903:Central processing unit
4862:Transactions per second
4850:Instructions per second
4773:Array processing (SIMT)
3917:Stored-program computer
3146:"macOS Big Sur is here"
2908:by Andrew Schulman 1990
2878:10.1109/MC.1985.1663000
2795:10.1109/C-M.1975.218804
2709:10.1007/0-387-27446-4_3
783:load–store architecture
324:instructions per second
264:History and development
113:load–store architecture
5536:Hardwired control unit
5418:Memory management unit
5383:Memory management unit
5132:Secure cryptoprocessor
5126:Tensor Processing Unit
5108:Vision processing unit
4842:Cycles per instruction
4836:Instructions per cycle
4783:Associative processing
4474:Instruction pipelining
3896:Processor technologies
2920:"The RISC Workstation"
1746:. IEEE. pp. 8–19.
1535:open source processors
1473:single-board computers
1449:IBM POWER architecture
1402:PCs with an ARM-based
761:
605:
565:
551:
452:
372:IBM POWER architecture
149:IBM POWER architecture
76:
5619:Sum-addressed decoder
5365:Arithmetic logic unit
4492:Classic RISC pipeline
4446:Epiphany architecture
4293:Motorola 68000 series
3263:Bennett, Amy (2005).
2699:. Springer. pp.
2319:10.1145/641914.641917
2272:10.1145/285930.285981
2126:. Springer. pp.
2062:. Springer. pp.
1775:10.1145/143559.143570
1649:Classic RISC pipeline
1635:by the United States
1349:Motorola 68000 family
1266:Linksys WRT54G series
1118:, the fastest on the
887:instruction per cycle
751:
742:Further information:
603:
563:
546:
527:MIPS Computer Systems
448:
97:computer architecture
70:
60:RISC (disambiguation)
5818:Classes of computers
5740:Performance per watt
5318:replacement policies
4984:Package on a package
4874:Performance per watt
4778:Pipelined processing
4548:Tomasulo's algorithm
4353:Clipper architecture
4209:Application-specific
3922:Finite-state machine
3620:(RISC) architectures
3559:(5 September 2000).
2118:Nurmi, Jari (2007).
1885:. Elsevier. p.
1539:soft microprocessors
1262:residential gateways
1258:PlayStation Portable
930:Harvard memory model
922:binary-coded decimal
870:Hardware utilization
708:improve this article
535:R2000 microprocessor
105:instruction pipeline
39:into this article. (
5772:Digital electronics
5425:Instruction decoder
5377:Floating-point unit
5031:Soft microprocessor
4978:System in a package
4553:Reservation station
4083:Transport-triggered
3543:Savard, John J. G.
3277:on 13 November 2020
2367:Chow, Paul (1989).
2153:Jouppi, Norman Paul
2151:Hill, Mark Donald;
2025:10.1147/rd.341.0004
1404:Qualcomm Snapdragon
1260:game consoles, and
1064:Qualcomm Snapdragon
592:Commercial breakout
515:Stanford University
363:channel controllers
335:processor registers
180:embedded processors
5644:Integrated circuit
5488:Processor register
5142:Baseband processor
4487:Operand forwarding
3947:Cellular automaton
3413:. 15 November 2019
3253:, pp. 121–123
2672:Jones, Douglas W.
2655:"RISC versus CISC"
2188:. p. Photo 1.
1769:. pp. 11–20.
1625:David A. Patterson
1190:devices, Nintendo
802:Instruction format
606:
568:Since 2010, a new
566:
422:DARPA VLSI Program
203:Pyramid Technology
199:Celerity Computing
77:
5805:
5804:
5694:
5693:
5313:Instruction cache
5303:Scratchpad memory
5150:
5149:
5137:Network processor
5066:Network on a chip
5021:Ultra-low-voltage
4972:Multi-chip module
4815:
4814:
4601:
4600:
4588:Branch prediction
4565:Register renaming
4459:
4458:
4441:VISC architecture
4263:Quantum computing
4258:VISC architecture
4140:Secondary storage
4056:Microarchitecture
4016:Register machines
3862:
3861:
3536:RISC Architecture
3524:RISC Architecture
3360:Boy Genius Report
3212:on 3 April 2020.
3109:. 23 October 2023
3083:. 8 December 2016
2718:978-0-387-21017-9
2137:978-1-4020-5529-4
1706:Flynn, Michael J.
1689:RISC Architecture
1631:were awarded the
1583:, an open source
1557:MIPS architecture
1503:vector processing
1132:Sunway TaihuLight
970:clock frequencies
948:SPARC and MIPS).
941:branch delay slot
856:Adapteva Epiphany
740:
739:
732:
53:
52:
48:
5830:
5767:Processor design
5659:Power management
5541:Instruction unit
5402:Branch predictor
5351:
5350:
5049:System on a chip
4991:
4990:
4831:Transistor count
4755:Flynn's taxonomy
4612:
4611:
4470:
4469:
4273:Addressing modes
4184:
4183:
4130:Memory hierarchy
3994:Hypercomputation
3912:Abstract machine
3889:
3882:
3875:
3866:
3865:
3611:
3604:
3597:
3588:
3587:
3582:
3552:
3545:"Not Quite RISC"
3539:
3527:
3505:
3504:
3493:
3487:
3486:
3475:
3469:
3468:
3466:
3464:
3450:
3444:
3443:
3441:
3439:
3429:
3423:
3422:
3420:
3418:
3403:
3397:
3396:
3394:
3392:
3378:
3372:
3371:
3369:
3367:
3350:
3344:
3343:
3338:
3336:
3319:
3313:
3312:
3310:
3308:
3293:
3287:
3286:
3284:
3282:
3273:. Archived from
3260:
3254:
3248:
3242:
3241:
3239:
3237:
3223:
3217:
3216:
3208:. Archived from
3201:
3195:
3194:
3192:
3183:
3177:
3176:
3156:
3150:
3149:
3142:
3136:
3135:
3128:
3119:
3118:
3116:
3114:
3099:
3093:
3092:
3090:
3088:
3073:
3067:
3066:
3064:
3062:
3050:
3044:
3043:
3042:
3040:
3027:
3021:
3020:
3018:
3016:
3004:
2998:
2997:
2995:
2993:
2978:
2972:
2971:
2951:
2945:
2944:
2942:
2940:
2915:
2909:
2903:
2897:
2896:
2894:
2892:
2857:
2851:
2850:
2848:
2846:
2831:
2825:
2824:
2822:
2813:
2807:
2806:
2774:
2768:
2767:
2747:
2741:
2740:
2732:
2726:
2725:
2698:
2688:
2682:
2681:
2669:
2663:
2662:
2650:
2644:
2643:
2629:
2623:
2622:
2610:
2604:
2603:
2601:
2599:
2594:. pp. 96–95
2583:
2577:
2576:
2574:
2572:
2558:
2552:
2551:
2549:
2547:
2532:
2526:
2525:
2509:
2499:
2493:
2492:
2487:
2485:
2456:
2447:
2441:
2440:
2438:
2436:
2424:
2418:
2417:
2415:
2404:
2398:
2397:, pp. 52–53
2392:
2383:
2382:
2364:
2351:
2350:
2348:
2337:
2331:
2330:
2312:
2293:Patterson, D. A.
2289:
2280:
2275:
2257:
2232:
2231:
2230:on 13 June 2022.
2226:. Archived from
2220:
2209:
2208:
2196:
2190:
2189:
2177:
2171:
2170:
2148:
2142:
2141:
2125:
2115:
2109:
2095:
2078:
2077:
2061:
2051:
2045:
2044:
2035:
2029:
2028:
2010:
2001:
1990:
1989:
1973:
1963:
1957:
1956:
1940:
1934:
1933:
1917:
1907:
1901:
1900:
1884:
1874:
1868:
1867:
1865:
1863:
1849:
1843:
1842:
1834:
1825:
1819:
1818:
1815:boursinp.free.fr
1806:
1800:
1799:
1785:
1779:
1778:
1754:
1748:
1747:
1739:
1730:
1724:
1723:
1702:
1693:
1692:
1680:
1629:Sophie M. Wilson
1621:John L. Hennessy
1514:ARM architecture
1435:Sun Microsystems
1421:Silicon Graphics
1233:gaming consoles.
1192:Game Boy Advance
1148:ARM architecture
1108:tablet computers
1005:high frequencies
977:Andrew Tanenbaum
913:in hardware (no
825:
821:
817:
793:
759:
744:Processor design
735:
728:
724:
721:
715:
692:
684:
670:Acorn Archimedes
666:ARM architecture
622:Sun Microsystems
575:(ISA), Berkeley
523:John L. Hennessy
487:
486:
482:
476:register windows
466:
445:
444:
440:
403:
402:
398:
320:telephone switch
308:Michael J. Flynn
293:addressing modes
118:addressing modes
85:computer science
73:Sun Microsystems
44:
24:
23:
16:
5838:
5837:
5833:
5832:
5831:
5829:
5828:
5827:
5808:
5807:
5806:
5801:
5787:Tick–tock model
5745:
5701:
5690:
5630:
5614:Address decoder
5568:
5522:
5518:Program counter
5493:Status register
5474:
5429:
5389:Load–store unit
5356:
5349:
5276:
5245:
5146:
5103:Image processor
5078:
5071:
5041:
5035:
5011:Microcontroller
5001:Embedded system
4989:
4889:
4822:
4811:
4749:
4699:
4597:
4574:
4558:Re-order buffer
4529:
4510:Data dependency
4496:
4455:
4285:
4279:
4178:
4177:Instruction set
4171:
4157:Multiprocessing
4125:Cache hierarchy
4118:Register/memory
4042:
3942:Queue automaton
3898:
3893:
3863:
3858:
3758:
3647:
3621:
3615:
3585:
3557:Mashey, John R.
3530:
3520:"RISC vs. CISC"
3518:
3514:
3509:
3508:
3495:
3494:
3490:
3477:
3476:
3472:
3462:
3460:
3452:
3451:
3447:
3437:
3435:
3431:
3430:
3426:
3416:
3414:
3405:
3404:
3400:
3390:
3388:
3380:
3379:
3375:
3365:
3363:
3351:
3347:
3334:
3332:
3320:
3316:
3306:
3304:
3294:
3290:
3280:
3278:
3261:
3257:
3249:
3245:
3235:
3233:
3225:
3224:
3220:
3202:
3198:
3190:
3184:
3180:
3173:
3157:
3153:
3144:
3143:
3139:
3130:
3129:
3122:
3112:
3110:
3101:
3100:
3096:
3086:
3084:
3075:
3074:
3070:
3060:
3058:
3051:
3047:
3038:
3036:
3029:
3028:
3024:
3014:
3012:
3005:
3001:
2991:
2989:
2979:
2975:
2968:
2952:
2948:
2938:
2936:
2934:
2916:
2912:
2904:
2900:
2890:
2888:
2858:
2854:
2844:
2842:
2832:
2828:
2820:
2814:
2810:
2775:
2771:
2764:
2748:
2744:
2737:"CISC and RISC"
2733:
2729:
2719:
2689:
2685:
2670:
2666:
2651:
2647:
2630:
2626:
2611:
2607:
2597:
2595:
2588:"What is RISC?"
2584:
2580:
2570:
2568:
2560:
2559:
2555:
2545:
2543:
2534:
2533:
2529:
2522:
2500:
2496:
2483:
2481:
2459:Research Policy
2454:
2448:
2444:
2434:
2432:
2425:
2421:
2413:
2405:
2401:
2393:
2386:
2379:
2365:
2354:
2346:
2338:
2334:
2290:
2283:
2258:
2235:
2222:
2221:
2212:
2201:"RISCy History"
2197:
2193:
2178:
2174:
2167:
2149:
2145:
2138:
2116:
2112:
2096:
2081:
2074:
2052:
2048:
2037:
2036:
2032:
2008:
2002:
1993:
1986:
1964:
1960:
1941:
1937:
1930:
1908:
1904:
1897:
1875:
1871:
1861:
1859:
1851:
1850:
1846:
1832:
1826:
1822:
1807:
1803:
1786:
1782:
1755:
1751:
1737:
1731:
1727:
1720:
1703:
1696:
1681:
1677:
1672:
1645:
1613:
1601:SuperH - J Core
1531:
1485:Hewlett-Packard
1459:Hewlett-Packard
1451:, PowerPC, and
1413:
1340:
1186:/ Windows CE),
1140:
1104:
1029:
1023:architectures.
872:
804:
766:
760:
757:
746:
736:
725:
719:
716:
705:
693:
682:
614:Hewlett-Packard
594:
499:procedure calls
484:
480:
479:
464:
442:
438:
437:
409:David Patterson
400:
396:
395:
380:
305:
274:David Patterson
266:
207:Ridge Computers
63:
56:
49:
25:
21:
12:
11:
5:
5836:
5826:
5825:
5820:
5803:
5802:
5800:
5799:
5794:
5792:Pin grid array
5789:
5784:
5779:
5774:
5769:
5764:
5759:
5753:
5751:
5747:
5746:
5744:
5743:
5737:
5732:
5727:
5722:
5717:
5712:
5706:
5704:
5696:
5695:
5692:
5691:
5689:
5688:
5683:
5678:
5673:
5668:
5663:
5662:
5661:
5656:
5651:
5640:
5638:
5632:
5631:
5629:
5628:
5626:Barrel shifter
5623:
5622:
5621:
5616:
5609:Binary decoder
5606:
5605:
5604:
5594:
5589:
5584:
5578:
5576:
5570:
5569:
5567:
5566:
5561:
5553:
5548:
5543:
5538:
5532:
5530:
5524:
5523:
5521:
5520:
5515:
5510:
5505:
5500:
5498:Stack register
5495:
5490:
5484:
5482:
5476:
5475:
5473:
5472:
5471:
5470:
5465:
5455:
5450:
5445:
5439:
5437:
5431:
5430:
5428:
5427:
5422:
5421:
5420:
5409:
5404:
5399:
5398:
5397:
5391:
5380:
5374:
5368:
5361:
5359:
5348:
5347:
5342:
5337:
5332:
5327:
5326:
5325:
5320:
5315:
5310:
5305:
5300:
5290:
5284:
5282:
5278:
5277:
5275:
5274:
5269:
5264:
5259:
5253:
5251:
5247:
5246:
5244:
5243:
5242:
5241:
5231:
5226:
5221:
5216:
5211:
5206:
5201:
5196:
5191:
5186:
5181:
5176:
5171:
5166:
5160:
5158:
5152:
5151:
5148:
5147:
5145:
5144:
5139:
5134:
5129:
5123:
5117:
5111:
5105:
5100:
5094:
5092:AI accelerator
5089:
5083:
5081:
5073:
5072:
5070:
5069:
5063:
5058:
5055:Multiprocessor
5052:
5045:
5043:
5037:
5036:
5034:
5033:
5028:
5023:
5018:
5013:
5008:
5006:Microprocessor
5003:
4997:
4995:
4994:By application
4988:
4987:
4981:
4975:
4969:
4964:
4959:
4954:
4949:
4944:
4939:
4937:Tile processor
4934:
4929:
4924:
4919:
4918:
4917:
4906:
4899:
4897:
4891:
4890:
4888:
4887:
4882:
4877:
4871:
4865:
4859:
4853:
4847:
4846:
4845:
4833:
4827:
4825:
4817:
4816:
4813:
4812:
4810:
4809:
4808:
4807:
4797:
4792:
4791:
4790:
4785:
4780:
4775:
4765:
4759:
4757:
4751:
4750:
4748:
4747:
4742:
4737:
4732:
4731:
4730:
4725:
4723:Hyperthreading
4715:
4709:
4707:
4705:Multithreading
4701:
4700:
4698:
4697:
4692:
4687:
4686:
4685:
4675:
4674:
4673:
4668:
4658:
4657:
4656:
4651:
4641:
4636:
4635:
4634:
4629:
4618:
4616:
4609:
4603:
4602:
4599:
4598:
4596:
4595:
4590:
4584:
4582:
4576:
4575:
4573:
4572:
4567:
4562:
4561:
4560:
4555:
4545:
4539:
4537:
4531:
4530:
4528:
4527:
4522:
4517:
4512:
4506:
4504:
4498:
4497:
4495:
4494:
4489:
4484:
4482:Pipeline stall
4478:
4476:
4467:
4461:
4460:
4457:
4456:
4454:
4453:
4448:
4443:
4438:
4435:
4434:
4433:
4431:z/Architecture
4428:
4423:
4418:
4410:
4405:
4400:
4395:
4390:
4385:
4380:
4375:
4370:
4365:
4360:
4355:
4350:
4349:
4348:
4343:
4338:
4330:
4325:
4320:
4315:
4310:
4305:
4300:
4295:
4289:
4287:
4281:
4280:
4278:
4277:
4276:
4275:
4265:
4260:
4255:
4250:
4245:
4240:
4235:
4234:
4233:
4223:
4222:
4221:
4211:
4206:
4201:
4196:
4190:
4188:
4181:
4173:
4172:
4170:
4169:
4164:
4159:
4154:
4149:
4144:
4143:
4142:
4137:
4135:Virtual memory
4127:
4122:
4121:
4120:
4115:
4110:
4105:
4095:
4090:
4085:
4080:
4075:
4074:
4073:
4063:
4058:
4052:
4050:
4044:
4043:
4041:
4040:
4039:
4038:
4033:
4028:
4023:
4013:
4008:
4003:
4002:
4001:
3996:
3991:
3986:
3981:
3976:
3971:
3966:
3959:Turing machine
3956:
3955:
3954:
3949:
3944:
3939:
3934:
3929:
3919:
3914:
3908:
3906:
3900:
3899:
3892:
3891:
3884:
3877:
3869:
3860:
3859:
3857:
3856:
3843:
3838:
3832:Motorola 88000
3829:
3824:
3819:
3810:
3805:
3800:
3795:
3790:
3782:
3777:
3772:
3766:
3764:
3760:
3759:
3757:
3756:
3744:
3739:
3734:
3729:
3724:
3708:
3703:
3698:
3693:
3684:
3679:
3674:
3669:
3664:
3659:Analog Devices
3655:
3653:
3649:
3648:
3646:
3645:
3640:
3635:
3629:
3627:
3623:
3622:
3614:
3613:
3606:
3599:
3591:
3584:
3583:
3553:
3540:
3532:"What is RISC"
3528:
3515:
3513:
3512:External links
3510:
3507:
3506:
3488:
3470:
3445:
3424:
3398:
3373:
3345:
3314:
3288:
3255:
3251:Dandamudi 2005
3243:
3218:
3196:
3178:
3171:
3151:
3137:
3120:
3107:Microsoft Docs
3094:
3068:
3045:
3022:
2999:
2973:
2966:
2946:
2932:
2910:
2898:
2852:
2826:
2808:
2769:
2762:
2742:
2727:
2717:
2683:
2664:
2645:
2624:
2605:
2578:
2553:
2527:
2520:
2494:
2465:(2): 210–224.
2442:
2419:
2399:
2384:
2377:
2352:
2332:
2310:10.1.1.68.9623
2281:
2233:
2210:
2191:
2172:
2165:
2143:
2136:
2110:
2079:
2072:
2046:
2030:
1991:
1984:
1958:
1935:
1928:
1902:
1895:
1869:
1844:
1820:
1801:
1780:
1749:
1725:
1718:
1694:
1674:
1673:
1671:
1668:
1667:
1666:
1661:
1656:
1654:Microprocessor
1651:
1644:
1641:
1612:
1609:
1608:
1607:
1604:
1598:
1592:
1578:
1577:
1576:
1560:
1553:
1530:
1527:
1526:
1525:
1510:
1495:address spaces
1488:
1466:
1456:
1442:
1424:
1412:
1409:
1408:
1407:
1398:have released
1381:
1363:
1356:
1339:
1336:
1335:
1334:
1331:address spaces
1320:
1302:
1269:
1234:
1211:
1184:Windows Mobile
1139:
1136:
1112:supercomputers
1103:
1100:
1028:
1025:
1003:throughput at
926:
925:
924:, for example)
907:
904:
901:floating-point
893:
890:
871:
868:
803:
800:
771:IBM System/370
765:
762:
755:
738:
737:
696:
694:
687:
681:
678:
651:Motorola 88000
593:
590:
517:in 1981. This
511:Silicon Valley
411:was sent on a
388:Motorola 68000
379:
376:
304:
301:
265:
262:
256:, such as the
254:supercomputers
242:Motorola 88000
54:
51:
50:
28:
26:
19:
9:
6:
4:
3:
2:
5835:
5824:
5821:
5819:
5816:
5815:
5813:
5798:
5795:
5793:
5790:
5788:
5785:
5783:
5780:
5778:
5775:
5773:
5770:
5768:
5765:
5763:
5760:
5758:
5755:
5754:
5752:
5748:
5741:
5738:
5736:
5733:
5731:
5728:
5726:
5723:
5721:
5718:
5716:
5713:
5711:
5708:
5707:
5705:
5703:
5697:
5687:
5684:
5682:
5679:
5677:
5674:
5672:
5669:
5667:
5664:
5660:
5657:
5655:
5652:
5650:
5647:
5646:
5645:
5642:
5641:
5639:
5637:
5633:
5627:
5624:
5620:
5617:
5615:
5612:
5611:
5610:
5607:
5603:
5600:
5599:
5598:
5595:
5593:
5590:
5588:
5587:Demultiplexer
5585:
5583:
5580:
5579:
5577:
5575:
5571:
5565:
5562:
5560:
5557:
5554:
5552:
5549:
5547:
5544:
5542:
5539:
5537:
5534:
5533:
5531:
5529:
5525:
5519:
5516:
5514:
5511:
5509:
5508:Memory buffer
5506:
5504:
5503:Register file
5501:
5499:
5496:
5494:
5491:
5489:
5486:
5485:
5483:
5481:
5477:
5469:
5466:
5464:
5461:
5460:
5459:
5456:
5454:
5451:
5449:
5446:
5444:
5443:Combinational
5441:
5440:
5438:
5436:
5432:
5426:
5423:
5419:
5416:
5415:
5413:
5410:
5408:
5405:
5403:
5400:
5395:
5392:
5390:
5387:
5386:
5384:
5381:
5378:
5375:
5372:
5369:
5366:
5363:
5362:
5360:
5358:
5352:
5346:
5343:
5341:
5338:
5336:
5333:
5331:
5328:
5324:
5321:
5319:
5316:
5314:
5311:
5309:
5306:
5304:
5301:
5299:
5296:
5295:
5294:
5291:
5289:
5286:
5285:
5283:
5279:
5273:
5270:
5268:
5265:
5263:
5260:
5258:
5255:
5254:
5252:
5248:
5240:
5237:
5236:
5235:
5232:
5230:
5227:
5225:
5222:
5220:
5217:
5215:
5212:
5210:
5207:
5205:
5202:
5200:
5197:
5195:
5192:
5190:
5187:
5185:
5182:
5180:
5177:
5175:
5172:
5170:
5167:
5165:
5162:
5161:
5159:
5157:
5153:
5143:
5140:
5138:
5135:
5133:
5130:
5127:
5124:
5121:
5118:
5115:
5112:
5109:
5106:
5104:
5101:
5098:
5095:
5093:
5090:
5088:
5085:
5084:
5082:
5080:
5074:
5067:
5064:
5062:
5059:
5056:
5053:
5050:
5047:
5046:
5044:
5038:
5032:
5029:
5027:
5024:
5022:
5019:
5017:
5014:
5012:
5009:
5007:
5004:
5002:
4999:
4998:
4996:
4992:
4985:
4982:
4979:
4976:
4973:
4970:
4968:
4965:
4963:
4960:
4958:
4955:
4953:
4950:
4948:
4945:
4943:
4940:
4938:
4935:
4933:
4930:
4928:
4925:
4923:
4920:
4916:
4913:
4912:
4910:
4907:
4904:
4901:
4900:
4898:
4896:
4892:
4886:
4883:
4881:
4878:
4875:
4872:
4869:
4866:
4863:
4860:
4857:
4854:
4851:
4848:
4843:
4840:
4839:
4837:
4834:
4832:
4829:
4828:
4826:
4824:
4818:
4806:
4803:
4802:
4801:
4798:
4796:
4793:
4789:
4786:
4784:
4781:
4779:
4776:
4774:
4771:
4770:
4769:
4766:
4764:
4761:
4760:
4758:
4756:
4752:
4746:
4743:
4741:
4738:
4736:
4733:
4729:
4726:
4724:
4721:
4720:
4719:
4716:
4714:
4711:
4710:
4708:
4706:
4702:
4696:
4693:
4691:
4688:
4684:
4681:
4680:
4679:
4676:
4672:
4669:
4667:
4664:
4663:
4662:
4659:
4655:
4652:
4650:
4647:
4646:
4645:
4642:
4640:
4637:
4633:
4630:
4628:
4625:
4624:
4623:
4620:
4619:
4617:
4613:
4610:
4608:
4604:
4594:
4591:
4589:
4586:
4585:
4583:
4581:
4577:
4571:
4568:
4566:
4563:
4559:
4556:
4554:
4551:
4550:
4549:
4546:
4544:
4543:Scoreboarding
4541:
4540:
4538:
4536:
4532:
4526:
4525:False sharing
4523:
4521:
4518:
4516:
4513:
4511:
4508:
4507:
4505:
4503:
4499:
4493:
4490:
4488:
4485:
4483:
4480:
4479:
4477:
4475:
4471:
4468:
4466:
4462:
4452:
4449:
4447:
4444:
4442:
4439:
4436:
4432:
4429:
4427:
4424:
4422:
4419:
4417:
4414:
4413:
4411:
4409:
4406:
4404:
4401:
4399:
4396:
4394:
4391:
4389:
4386:
4384:
4381:
4379:
4376:
4374:
4371:
4369:
4366:
4364:
4361:
4359:
4356:
4354:
4351:
4347:
4344:
4342:
4339:
4337:
4334:
4333:
4331:
4329:
4326:
4324:
4321:
4319:
4318:Stanford MIPS
4316:
4314:
4311:
4309:
4306:
4304:
4301:
4299:
4296:
4294:
4291:
4290:
4288:
4282:
4274:
4271:
4270:
4269:
4266:
4264:
4261:
4259:
4256:
4254:
4251:
4249:
4246:
4244:
4241:
4239:
4236:
4232:
4229:
4228:
4227:
4224:
4220:
4217:
4216:
4215:
4212:
4210:
4207:
4205:
4202:
4200:
4197:
4195:
4192:
4191:
4189:
4185:
4182:
4180:
4179:architectures
4174:
4168:
4165:
4163:
4160:
4158:
4155:
4153:
4150:
4148:
4147:Heterogeneous
4145:
4141:
4138:
4136:
4133:
4132:
4131:
4128:
4126:
4123:
4119:
4116:
4114:
4111:
4109:
4106:
4104:
4101:
4100:
4099:
4098:Memory access
4096:
4094:
4091:
4089:
4086:
4084:
4081:
4079:
4076:
4072:
4069:
4068:
4067:
4064:
4062:
4059:
4057:
4054:
4053:
4051:
4049:
4045:
4037:
4034:
4032:
4031:Random-access
4029:
4027:
4024:
4022:
4019:
4018:
4017:
4014:
4012:
4011:Stack machine
4009:
4007:
4004:
4000:
3997:
3995:
3992:
3990:
3987:
3985:
3982:
3980:
3977:
3975:
3972:
3970:
3967:
3965:
3962:
3961:
3960:
3957:
3953:
3950:
3948:
3945:
3943:
3940:
3938:
3935:
3933:
3930:
3928:
3927:with datapath
3925:
3924:
3923:
3920:
3918:
3915:
3913:
3910:
3909:
3907:
3905:
3901:
3897:
3890:
3885:
3883:
3878:
3876:
3871:
3870:
3867:
3855:
3851:
3847:
3844:
3842:
3839:
3837:
3833:
3830:
3828:
3825:
3823:
3820:
3818:
3814:
3811:
3809:
3806:
3804:
3801:
3799:
3796:
3794:
3791:
3789:
3786:
3783:
3781:
3778:
3776:
3773:
3771:
3768:
3767:
3765:
3761:
3755:
3751:
3748:
3745:
3743:
3740:
3738:
3735:
3733:
3730:
3728:
3725:
3723:
3719:
3715:
3712:
3709:
3707:
3704:
3702:
3699:
3697:
3694:
3692:
3691:LatticeMico32
3688:
3685:
3683:
3680:
3678:
3675:
3673:
3670:
3668:
3665:
3663:
3660:
3657:
3656:
3654:
3650:
3644:
3643:Stanford MIPS
3641:
3639:
3638:Berkeley RISC
3636:
3634:
3631:
3630:
3628:
3624:
3619:
3612:
3607:
3605:
3600:
3598:
3593:
3592:
3589:
3581:
3577:
3574:
3570:
3566:
3562:
3558:
3554:
3550:
3546:
3541:
3537:
3533:
3529:
3525:
3521:
3517:
3516:
3502:
3498:
3492:
3484:
3480:
3474:
3459:
3455:
3449:
3434:
3428:
3412:
3408:
3402:
3387:
3383:
3377:
3362:
3361:
3356:
3349:
3342:
3331:
3330:
3325:
3318:
3303:
3299:
3292:
3276:
3272:
3271:
3270:Computerworld
3266:
3259:
3252:
3247:
3232:
3228:
3222:
3215:
3211:
3207:
3204:Singh, Amit.
3200:
3189:
3182:
3174:
3172:0-07-136207-X
3168:
3164:
3163:
3155:
3147:
3141:
3133:
3127:
3125:
3108:
3104:
3098:
3082:
3078:
3072:
3056:
3049:
3034:
3033:
3026:
3010:
3003:
2988:
2984:
2977:
2969:
2963:
2959:
2958:
2950:
2935:
2933:0-86353-092-3
2929:
2925:
2921:
2914:
2907:
2902:
2887:
2883:
2879:
2875:
2871:
2867:
2863:
2856:
2841:
2837:
2830:
2819:
2812:
2804:
2800:
2796:
2792:
2789:(11): 41–48.
2788:
2784:
2783:IEEE Computer
2780:
2773:
2765:
2763:9781558607668
2759:
2755:
2754:
2746:
2738:
2731:
2724:
2720:
2714:
2710:
2706:
2702:
2697:
2696:
2687:
2679:
2675:
2668:
2660:
2656:
2649:
2641:
2640:
2635:
2628:
2620:
2616:
2609:
2593:
2589:
2582:
2567:
2563:
2557:
2541:
2537:
2531:
2523:
2521:1-58488-360-X
2517:
2513:
2508:
2507:
2498:
2491:
2480:
2476:
2472:
2468:
2464:
2460:
2453:
2446:
2430:
2423:
2412:
2411:
2403:
2396:
2391:
2389:
2380:
2378:0-7923-9045-8
2374:
2370:
2363:
2361:
2359:
2357:
2345:
2344:
2336:
2328:
2324:
2320:
2316:
2311:
2306:
2302:
2298:
2294:
2288:
2286:
2279:
2273:
2269:
2265:
2264:
2256:
2254:
2252:
2250:
2248:
2246:
2244:
2242:
2240:
2238:
2229:
2225:
2219:
2217:
2215:
2206:
2202:
2195:
2187:
2183:
2176:
2168:
2166:1-55860-539-8
2162:
2158:
2154:
2147:
2139:
2133:
2129:
2124:
2123:
2114:
2107:
2106:0-309-06278-0
2103:
2099:
2094:
2092:
2090:
2088:
2086:
2084:
2075:
2073:3-540-64798-8
2069:
2065:
2060:
2059:
2050:
2042:
2041:
2034:
2026:
2022:
2018:
2014:
2007:
2000:
1998:
1996:
1987:
1985:0-89871-428-1
1981:
1977:
1972:
1971:
1962:
1954:
1950:
1946:
1939:
1931:
1929:1-57356-521-0
1925:
1921:
1916:
1915:
1906:
1898:
1892:
1888:
1883:
1882:
1873:
1858:
1854:
1848:
1840:
1839:
1831:
1824:
1816:
1812:
1805:
1797:
1796:
1791:
1784:
1776:
1772:
1768:
1764:
1760:
1753:
1745:
1744:
1736:
1729:
1721:
1715:
1711:
1707:
1701:
1699:
1690:
1686:
1679:
1675:
1665:
1662:
1660:
1657:
1655:
1652:
1650:
1647:
1646:
1640:
1638:
1634:
1630:
1626:
1622:
1618:
1605:
1602:
1599:
1596:
1593:
1590:
1587:based on the
1586:
1582:
1579:
1574:
1570:
1567:
1566:
1564:
1561:
1558:
1554:
1551:
1548:
1547:
1546:
1544:
1540:
1536:
1523:
1522:Fujitsu A64FX
1519:
1515:
1511:
1508:
1504:
1500:
1496:
1492:
1489:
1486:
1482:
1478:
1474:
1470:
1467:
1464:
1460:
1457:
1454:
1450:
1446:
1443:
1440:
1436:
1432:
1428:
1425:
1422:
1418:
1415:
1414:
1405:
1401:
1397:
1393:
1389:
1385:
1382:
1379:
1375:
1371:
1367:
1364:
1361:
1357:
1354:
1350:
1346:
1342:
1341:
1332:
1328:
1327:open standard
1324:
1321:
1318:
1314:
1310:
1306:
1303:
1300:
1296:
1292:
1288:
1284:
1281:
1277:
1273:
1270:
1267:
1263:
1259:
1255:
1251:
1250:PlayStation 2
1247:
1243:
1239:
1235:
1232:
1228:
1224:
1223:PlayStation 3
1220:
1216:
1212:
1209:
1205:
1201:
1197:
1193:
1189:
1185:
1181:
1180:Windows Phone
1177:
1173:
1169:
1165:
1161:
1157:
1153:
1149:
1145:
1144:
1143:
1135:
1133:
1129:
1125:
1121:
1117:
1113:
1109:
1099:
1095:
1093:
1089:
1085:
1084:Apple silicon
1081:
1077:
1073:
1069:
1065:
1061:
1057:
1053:
1049:
1045:
1040:
1038:
1034:
1024:
1022:
1017:
1013:
1008:
1006:
1002:
998:
993:
992:sub-operation
989:
984:
982:
978:
973:
971:
967:
963:
958:
954:
949:
946:
942:
937:
935:
931:
923:
919:
916:
912:
908:
905:
902:
898:
894:
891:
888:
884:
883:
882:
879:
877:
867:
865:
861:
857:
853:
849:
845:
841:
837:
831:
827:
811:
807:
799:
797:
787:
785:
784:
778:
776:
772:
754:
750:
745:
734:
731:
723:
713:
709:
703:
702:
697:This section
695:
691:
686:
685:
677:
675:
671:
667:
662:
660:
656:
652:
648:
644:
640:
636:
630:
627:
623:
619:
615:
611:
602:
598:
589:
587:
582:
578:
574:
571:
570:open standard
562:
558:
556:
550:
545:
543:
538:
536:
532:
528:
524:
520:
516:
512:
507:
504:
500:
495:
490:
477:
473:
468:
467:instruction.
462:
457:
451:
447:
433:
431:
427:
426:Berkeley RISC
423:
418:
414:
410:
405:
393:
389:
385:
375:
373:
368:
364:
360:
355:
353:
347:
345:
340:
336:
331:
329:
325:
321:
317:
313:
309:
300:
298:
297:Jack Dongarra
294:
290:
286:
281:
279:
278:Berkeley RISC
275:
271:
261:
259:
255:
251:
247:
243:
239:
235:
231:
227:
223:
219:
215:
210:
208:
204:
200:
196:
191:
189:
185:
184:laser printer
181:
177:
174:
170:
166:
162:
158:
154:
150:
146:
142:
138:
134:
133:Berkeley RISC
130:
129:Stanford MIPS
126:
121:
119:
114:
108:
106:
102:
98:
94:
90:
86:
82:
74:
69:
65:
61:
47:
42:
38:
34:
33:
27:
18:
17:
5797:Chip carrier
5735:Clock gating
5654:Mixed-signal
5551:Write buffer
5528:Control unit
5340:Clock signal
5079:accelerators
5061:Cypress PSoC
4718:Simultaneous
4535:Out-of-order
4203:
4167:Neuromorphic
4048:Architecture
4006:Belt machine
3999:Zeno machine
3932:Hierarchical
3780:Apollo PRISM
3763:Discontinued
3687:LatticeMico8
3617:
3579:
3548:
3535:
3523:
3500:
3491:
3482:
3473:
3461:. Retrieved
3458:Arm Newsroom
3457:
3448:
3436:. Retrieved
3427:
3415:. Retrieved
3410:
3401:
3389:. Retrieved
3385:
3376:
3364:. Retrieved
3358:
3348:
3340:
3333:. Retrieved
3327:
3317:
3305:. Retrieved
3301:
3291:
3279:. Retrieved
3275:the original
3268:
3258:
3246:
3234:. Retrieved
3230:
3221:
3213:
3210:the original
3199:
3181:
3161:
3154:
3140:
3111:. Retrieved
3106:
3097:
3085:. Retrieved
3080:
3071:
3059:. Retrieved
3057:. Top500.org
3048:
3037:, retrieved
3031:
3025:
3013:. Retrieved
3002:
2990:. Retrieved
2986:
2976:
2960:. O'Reilly.
2956:
2949:
2937:. Retrieved
2923:
2913:
2901:
2889:. Retrieved
2869:
2865:
2855:
2843:. Retrieved
2840:Embedded.com
2839:
2829:
2811:
2786:
2782:
2772:
2752:
2745:
2730:
2722:
2694:
2686:
2677:
2667:
2658:
2648:
2639:Ars Technica
2637:
2627:
2618:
2608:
2596:. Retrieved
2591:
2581:
2569:. Retrieved
2565:
2556:
2544:. Retrieved
2539:
2530:
2505:
2497:
2489:
2482:. Retrieved
2462:
2458:
2445:
2433:. Retrieved
2422:
2416:. ICCD 2009.
2409:
2402:
2368:
2342:
2335:
2303:(6): 25–33.
2300:
2296:
2262:
2228:the original
2204:
2194:
2185:
2175:
2156:
2146:
2121:
2113:
2097:
2057:
2049:
2039:
2033:
2016:
2012:
1969:
1961:
1944:
1938:
1913:
1905:
1880:
1872:
1860:. Retrieved
1856:
1847:
1836:
1823:
1814:
1804:
1793:
1783:
1762:
1752:
1741:
1728:
1709:
1688:
1685:"Pipelining"
1678:
1617:Steve Furber
1614:
1532:
1518:AWS Graviton
1483:and finally
1433:(previously
1208:Raspberry Pi
1178:, Microsoft
1141:
1105:
1096:
1041:
1030:
1020:
1015:
1011:
1009:
1004:
1001:single clock
1000:
996:
991:
985:
974:
965:
961:
956:
952:
950:
938:
927:
880:
873:
832:
828:
812:
808:
805:
788:
781:
779:
767:
752:
747:
726:
717:
706:Please help
701:verification
698:
663:
631:
607:
595:
567:
552:
549:opportunity.
547:
539:
508:
491:
469:
455:
453:
449:
434:
406:
381:
356:
348:
332:
306:
289:Seymour Cray
287:designed by
282:
267:
211:
195:minicomputer
192:
122:
109:
92:
88:
78:
64:
45:
30:
5582:Multiplexer
5546:Data buffer
5257:Single-core
5229:bit slicing
5087:Coprocessor
4942:Coprocessor
4823:performance
4745:Cooperative
4735:Speculative
4695:Distributed
4654:Superscalar
4639:Instruction
4607:Parallelism
4580:Speculative
4412:System/3x0
4284:Instruction
4061:Von Neumann
3974:Post–Turing
3775:AMD Am29000
2019:(1): 4–11.
1974:. pp.
1838:Electronics
1360:chromebooks
1254:Nintendo 64
1246:PlayStation
1168:Apple Watch
1050:, AMD, and
876:transistors
792:STRING MOVE
639:AMD Am29000
489:microcode.
218:AMD Am29000
176:workstation
81:electronics
5812:Categories
5702:management
5597:Multiplier
5458:Logic gate
5448:Sequential
5355:Functional
5335:Clock rate
5308:Data cache
5281:Components
5262:Multi-core
5250:Core count
4740:Preemptive
4644:Pipelining
4627:Bit-serial
4570:Wide-issue
4515:Structural
4437:Tilera ISA
4403:MicroBlaze
4373:ETRAX CRIS
4268:Comparison
4113:Load–store
4093:Endianness
3813:Intel i860
3750:MicroBlaze
3113:27 October
3087:8 December
3011:. HPC Wire
2967:1565920325
2592:IEEE Micro
2566:www.ft.com
2540:Acorn User
2395:Nurmi 2007
2205:AM SIGARCH
1896:1558607668
1719:0867202041
1670:References
1509:processor.
1471:, used in
1374:transition
1160:iPod Touch
1060:Windows 10
1035:(MISC) or
1021:load–store
988:clock rate
911:data types
854:, and the
720:March 2012
643:Intel i860
610:Acorn ARM1
581:user space
494:pipelining
472:subroutine
413:sabbatical
316:John Cocke
270:load–store
234:Intel i960
230:Intel i860
5636:Circuitry
5556:Microcode
5480:Registers
5323:coherence
5298:CPU cache
5156:Word size
4821:Processor
4465:Execution
4368:DEC Alpha
4346:Power ISA
4162:Cognitive
3969:Universal
3808:DEC PRISM
3754:PicoBlaze
3706:Power ISA
3569:comp.arch
3565:Newsgroup
3549:Computers
3391:9 January
3335:24 August
3281:24 August
3236:2 January
3081:The Verge
3039:14 August
2987:The Verge
2305:CiteSeerX
1953:425963232
1589:Power ISA
1581:Libre-SOC
1563:OpenSPARC
1453:Power ISA
1384:Microsoft
1345:Macintosh
1305:Atmel AVR
1291:Dreamcast
1283:Super 32X
1092:Rosetta 2
840:ARM thumb
816:A = B + C
796:backronym
780:The term
655:IBM POWER
635:DEC Alpha
537:in 1985.
415:from the
407:In 1979,
392:microcode
384:Zilog Z80
367:IBM RT PC
339:compilers
238:LoongArch
222:Atmel AVR
157:Power ISA
143:systems.
5574:Datapath
5267:Manycore
5239:variable
5077:Hardware
4713:Temporal
4393:OpenRISC
4088:Cellular
4078:Dataflow
4071:modified
3701:OpenRISC
3682:eSi-RISC
3662:Blackfin
3366:20 March
3329:Engadget
3307:28 April
2939:26 March
2891:25 March
2866:Computer
2803:39685209
2598:20 March
2479:73520408
2327:12034303
2108:page 239
1743:Computer
1708:(1995).
1643:See also
1615:In 2022
1550:OpenRISC
1227:Xbox 360
1215:GameCube
1182:(former
1172:Apple TV
1114:such as
1088:Apple M1
1068:emulator
1052:Qualcomm
850:(2006),
846:(2004),
842:(1994),
838:(1992),
756:—
533:and the
430:BSD Unix
359:IBM ROMP
285:CDC 6600
226:Blackfin
5750:Related
5681:Quantum
5671:Digital
5666:Boolean
5564:Counter
5463:Quantum
5224:512-bit
5219:256-bit
5214:128-bit
5057:(MPSoC)
5042:on chip
5040:Systems
4858:(FLOPS)
4671:Process
4520:Control
4502:Hazards
4388:Itanium
4383:Unicore
4341:PowerPC
4066:Harvard
4026:Pointer
4021:Counter
3979:Quantum
3850:PowerPC
3841:PA-RISC
3793:Clipper
3742:Unicore
3711:Renesas
3633:IBM 801
3626:Origins
3573:Usenet:
3567::
3501:nae.edu
3483:nae.edu
3463:23 June
3438:23 June
3417:23 June
3411:AB Open
3231:TOP 500
3015:8 March
2886:7306378
2845:23 June
2571:23 June
2435:1 March
1862:24 June
1499:atomics
1479:, then
1463:PA-RISC
1439:Fujitsu
1437:), and
1400:Windows
1388:Surface
1313:Arduino
1297:as the
1295:Renesas
1272:Hitachi
1152:Android
1082:called
1039:(TTA).
953:labeled
844:MIPS16e
659:PowerPC
618:PA-RISC
483:⁄
441:⁄
399:⁄
344:opcodes
328:370/168
312:IBM 801
303:IBM 801
276:of the
193:In the
182:in the
178:and of
165:PA-RISC
153:PowerPC
125:IBM 801
95:) is a
41:Discuss
5686:Switch
5676:Analog
5414:(IMC)
5385:(MMU)
5234:others
5209:64-bit
5204:48-bit
5199:32-bit
5194:24-bit
5189:16-bit
5184:15-bit
5179:12-bit
5016:Mobile
4932:Stream
4927:Barrel
4922:Vector
4911:(GPU)
4870:(SUPS)
4838:(IPC)
4690:Memory
4683:Vector
4666:Thread
4649:Scalar
4451:Others
4398:RISC-V
4363:SuperH
4332:Power
4328:MIPS-X
4303:PDP-11
4152:Fabric
3904:Models
3836:M·CORE
3827:MIPS-X
3747:Xilinx
3737:Sunway
3727:RISC-V
3718:SuperH
3652:Active
3575:
3169:
3061:12 May
2992:12 May
2964:
2930:
2884:
2801:
2760:
2715:
2546:24 May
2518:
2484:2 June
2477:
2375:
2325:
2307:
2163:
2134:
2104:
2070:
1982:
1951:
1926:
1893:
1716:
1611:Awards
1595:RISC-V
1491:RISC-V
1481:Compaq
1431:Oracle
1396:Lenovo
1392:HP Inc
1390:line.
1323:RISC-V
1287:Saturn
1276:SuperH
1210:, etc.
1204:Switch
1170:, and
1156:iPhone
1130:, and
1128:Sierra
1124:Summit
1120:TOP500
1116:Fugaku
1048:Cavium
997:easily
957:manual
918:string
852:RISC-V
836:SuperH
577:RISC-V
542:MIPS-X
456:slower
258:Fugaku
250:SuperH
246:RISC-V
205:, and
188:router
186:, the
167:, and
155:, and
37:merged
5742:(PPW)
5700:Power
5592:Adder
5468:Array
5435:Logic
5396:(TLB)
5379:(FPU)
5373:(AGU)
5367:(ALU)
5357:units
5293:Cache
5174:8-bit
5169:4-bit
5164:1-bit
5128:(TPU)
5122:(DSP)
5116:(PPU)
5110:(VPU)
5099:(GPU)
5068:(NoC)
5051:(SoC)
4986:(PoP)
4980:(SiP)
4974:(MCM)
4915:GPGPU
4905:(CPU)
4895:Types
4876:(PPW)
4864:(TPS)
4852:(IPS)
4844:(CPI)
4615:Level
4426:S/390
4421:S/370
4416:S/360
4358:SPARC
4336:POWER
4219:TRIPS
4187:Types
3846:POWER
3803:CRISP
3788:AVR32
3785:Atmel
3770:Alpha
3732:SPARC
3302:ZDNet
3191:(PDF)
2882:S2CID
2821:(PDF)
2799:S2CID
2703:–44.
2475:S2CID
2455:(PDF)
2414:(PDF)
2347:(PDF)
2323:S2CID
2130:–43.
2009:(PDF)
1857:RIKEN
1833:(PDF)
1738:(PDF)
1573:SPARC
1555:Open
1469:Alpha
1429:, by
1427:SPARC
1419:, by
1378:Intel
1376:from
1368:uses
1366:Apple
1358:Some
1319:cars.
1264:like
1231:Wii U
1070:that
1016:store
966:store
934:cache
775:PDP-8
626:SPARC
465:INDEX
169:Alpha
141:SPARC
5720:ACPI
5453:Glue
5345:FIFO
5288:Core
5026:ASIP
4967:CPLD
4962:FPOA
4957:FPGA
4952:ASIC
4805:SPMD
4800:MIMD
4795:MISD
4788:SWAR
4768:SIMD
4763:SISD
4678:Data
4661:Task
4632:Word
4378:M32R
4323:MIPS
4286:sets
4253:ZISC
4248:NISC
4243:OISC
4238:MISC
4231:EPIC
4226:VLIW
4214:EDGE
4204:RISC
4199:CISC
4108:HUMA
4103:NUMA
3854:ROMP
3822:META
3817:i960
3798:CR16
3722:V850
3714:M32R
3696:MIPS
3465:2024
3440:2024
3419:2024
3393:2024
3368:2023
3337:2020
3309:2021
3283:2020
3238:2021
3167:ISBN
3115:2023
3089:2016
3063:2017
3041:2016
3017:2017
2994:2017
2962:ISBN
2941:2024
2928:ISBN
2893:2023
2847:2024
2758:ISBN
2713:ISBN
2600:2023
2573:2024
2548:2021
2516:ISBN
2514:–6.
2486:2011
2437:2022
2373:ISBN
2186:Byte
2161:ISBN
2132:ISBN
2102:ISBN
2068:ISBN
1980:ISBN
1949:OCLC
1924:ISBN
1891:ISBN
1864:2020
1795:Byte
1714:ISBN
1627:and
1569:LEON
1543:FPGA
1537:and
1512:The
1501:and
1417:MIPS
1394:and
1309:Xbox
1289:and
1280:Sega
1238:MIPS
1236:The
1229:and
1202:and
1176:Palm
1164:iPad
1146:The
1080:SoCs
1056:Cray
1012:load
981:bits
964:and
962:load
915:byte
909:Few
895:All
822:and
664:The
647:i960
645:and
531:MIPS
519:MIPS
503:CISC
352:PL/I
283:The
173:Unix
139:and
137:MIPS
131:and
93:RISC
87:, a
83:and
71:The
5715:APM
5710:PMU
5602:CPU
5559:ROM
5330:Bus
4947:PAL
4622:Bit
4408:LMC
4313:ARM
4308:x86
4298:VAX
3677:AVR
3672:ARM
3667:ARC
2874:doi
2791:doi
2705:doi
2512:100
2467:doi
2315:doi
2278:PDF
2276:As
2268:doi
2021:doi
1771:doi
1585:SoC
1461:'s
1447:'s
1445:IBM
1317:BMW
1299:SH4
1274:'s
1242:SGI
1219:Wii
1200:3DS
1188:RIM
1076:Mac
1062:on
1044:x86
1014:or
945:ALU
920:or
864:SH5
824:DEC
820:INC
710:by
616:'s
586:SoC
463:'s
461:VAX
214:ARC
161:ARM
145:IBM
79:In
35:be
5814::
5649:3D
3852:,
3848:,
3834:,
3815:,
3752:,
3720:,
3716:,
3689:,
3578:.
3571:.
3563:.
3547:.
3534:.
3522:.
3499:.
3481:.
3456:.
3409:.
3384:.
3357:.
3339:.
3326:.
3300:.
3267:.
3229:.
3123:^
3105:.
3079:.
2985:.
2922:.
2880:.
2870:18
2868:.
2864:.
2838:.
2797:.
2785:.
2781:.
2721:.
2711:.
2701:39
2676:.
2657:.
2636:.
2617:.
2590:.
2564:.
2538:.
2488:.
2473:.
2463:37
2461:.
2457:.
2387:^
2355:^
2321:.
2313:.
2299:.
2284:^
2236:^
2213:^
2203:.
2184:.
2128:40
2082:^
2066:.
2064:33
2017:34
2015:.
2011:.
1994:^
1978:.
1922:.
1920:50
1889:.
1887:55
1855:.
1835:.
1813:.
1792:.
1761:.
1740:.
1697:^
1687:.
1623:,
1619:,
1285:,
1256:,
1252:,
1248:,
1225:,
1221:,
1217:,
1206:,
1198:,
1196:DS
1194:,
1174:,
1166:,
1162:,
1158:,
1126:,
972:.
653:,
649:,
641:,
637:,
557:.
374:.
260:.
248:,
240:,
236:,
232:,
228:,
224:,
201:,
163:,
151:,
3888:e
3881:t
3874:v
3610:e
3603:t
3596:v
3551:.
3503:.
3485:.
3467:.
3442:.
3421:.
3395:.
3370:.
3311:.
3285:.
3240:.
3193:.
3175:.
3117:.
3091:.
3065:.
3019:.
2996:.
2970:.
2943:.
2895:.
2876::
2849:.
2823:.
2805:.
2793::
2787:8
2766:.
2739:.
2707::
2680:.
2661:.
2642:.
2602:.
2575:.
2550:.
2524:.
2469::
2439:.
2381:.
2329:.
2317::
2301:8
2274:.
2270::
2207:.
2169:.
2140:.
2076:.
2027:.
2023::
1988:.
1976:6
1955:.
1932:.
1899:.
1866:.
1817:.
1777:.
1773::
1722:.
1691:.
1441:.
1406:.
1355:.
1301:.
1268:.
733:)
727:(
722:)
718:(
704:.
485:3
481:1
443:3
439:1
401:3
397:1
91:(
62:.
43:)
Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.