
	Where results make sense

Topic: IBM Floating Point Architecture

Related Topics

IEEE 754

Floating point

Computer numbering formats

List of IBM products

IBM 360

EBCDIC

ES EVM

FS technology

Linux kernel

International Business Machines

FDA

GNU

Richard Stallman

Nagarjuna

Changi International Airport

In the News (Fri 11 Dec 09)

Northern Trust

Marvin Harrison

Peter Chernin

Gary Locke

Match Play

Penelope Cruz

Mickey Rourke

AR Rahman

Danny Boyle

Hugh Jackman

	Floating point - Wikipedia, the free encyclopedia
		This website can be used to calculate the floating point representation of a decimal number.
		Rounding errors: unlike the fixed-point counterpart, the application of dither in a floating point environment is nearly impossible.
		Floating point representation is more likely to be appropriate when proportional accuracy over a range of scales is needed.
	en.wikipedia.org /wiki/Floating_point (1277 words)

	Floating point -- Facts, Info, and Encyclopedia article (Site not responding. Last check: 2007-10-08)
		Rounding errors: unlike the fixed-point counterpart, the application of (An excited state of agitation) dither in a floating point environment is nearly impossible.
		Floating point arithmetic is not (additional info and facts about associative) associative.
		Floating point arithmetic is also not (additional info and facts about distributive) distributive.
	www.absoluteastronomy.com /encyclopedia/f/fl/floating_point.htm (1517 words)

	IBM Floating Point Architecture - Wikipedia, the free encyclopedia
		IBM System/360 computers, and subsequent machines based on that architecture (mainframes), support a hexadecimal floating-point format.
		Note that in this format the initial bit is not suppressed, and the radix point is set to the left of the mantissa in increments of 4 bits.
		The fraction is the part at the right of the radix point, filled with 0 on the right until we get all 24 bits.
	en.wikipedia.org /wiki/IBM_Floating_Point_Architecture (443 words)

	IBM POWER (Site not responding. Last check: 2007-10-08)
		IBM also is encouraging other developers and manufacturers to use the POWER architecture or any other derivative of it through the Power.org community.
		Floating point became a focus for the America Project, and IBM was able to use new algorithms developed in the early 1980s that could support 64-bit double-precision multiplies and divides in a single cycle.
		IBM complemented this with a complex instruction decoder which could be fetching one instruction, decoding another, and sending one to the ALU and FPU at the same time, resulting in one of the first superscalar CPU designs in use.
	www.worldhistory.com /wiki/I/IBM-POWER.htm (1158 words)

	Floating point unit - Unipedia (Site not responding. Last check: 2007-10-08)
		Typical operations are floating point arithmetic (such as addition and multiplication), but some systems may be capable of performing exponential or trigonometric calculations as well (such as square roots or cosines).
		In some computer architectures, floating point operations are handled completely separate from integer operations, with dedicated floating point registers and independent clocking schemes.
		Floating point addition and multiplication operations are typically pipelined, but more complicated operations, like division, may not be, and some systems may even have a dedicated floating point divider circuit.
	www.unipedia.info /FPU.html (357 words)

	Chapter 18, BCD and Floating Point
		A fixed point number is a number written in positional notation that contains a radix point (a period in the United States, or a comma in in Europe) that separates the integer from the fractional portion of a number.
		Floating point hardware increases the cost of the processor, so this capability is a waste if you do not use it.
		When floating point arithmetic is done in software, the programmer has the option of performing these tradeoffs to design a floating point format that is optimum for the application.
	www.geocities.com /mc_assemblers/Chapter_18.htm (3220 words)

	Glossary Search Results (Site not responding. Last check: 2007-10-08)
		When writing software, larger floating point precision takes more space to store, and may be slower depending on the hardware you are running on.
		Floating point performance matters a lot in games and complex data manipulations, thus the "pro" or "Geek" segment of the market that drives system buys and recommends components.
		In architectures where the processor interacts directly with main memory, the definition of a singular front side bus is less clear.
	www.geek.com /glossary/glossary_search.cgi?f (5730 words)

	IBM 704 - TheBestLinks.com - Computer, Floating point, Lisp programming language, Operand, ... (Site not responding. Last check: 2007-10-08)
		The IBM 704, the first mass-produced computer with floating point arithmetic hardware, was introduced by IBM in April, 1956.
		The 704 was significantly improved over the IBM 701 in terms of architecture as well as implementation, and was not compatible with its predecessor.
		IBM stated that the device was capable of executing up to 40,000 instructions per second.
	www.thebestlinks.com /IBM_704.html (364 words)

	CMOS floating-point unit for the S/390 Parallel Enterprise Server G4
		As shown in Figure 2, the first cycle consists of comparing the A and B register exponents to determine which operand is the smaller of the two, and conditionally swapping the fractions so that the smaller operand proceeds to be conditionally complemented and aligned by the exponent difference.
		In all architectures there could be cancellation of the most significant bits for an effective subtract operation which changes the location of the most significant bit.
		The algorithm was first used in the IBM System/360* Model 91 [17], but since then has not been implemented on S/390 mainframes, except for one low-end mainframe [4].
	www.research.ibm.com /journal/rd/414/schwarz.html (7457 words)

	Floating-point Formats
		Since older architectures did not retain guard bits between operations, and since the presence of guard bits can lead to the results of a calculation being affected by whether or not intermediate results are kept in registers, the option of disabling these guard bits is provided.
		However, if round on load, truncate on store, is specified, then when a floating point register is loaded with a value, the less significant portion of the register which is not filled by the input value is only loaded with zeroes when the input value is zero; otherwise, it is filled with 1000...0000.
		Note that in the case of 32-bit floating point numbers, a temporary format of 64 bits in size is not inherently necessary; 19 bits of the exponent will not be used, but are present in the temporary format because most of them are required to represent the numeric range available in the 64-bit format.
	www.quadibloc.com /arch/ar0505.htm (4465 words)

	Java theory and practice: Where's your point?
		An IEEE floating point number dedicates 1 bit to the sign of the number, 8 bits to the exponent, and 23 bits to the mantissa, or fractional part.
		Floating point numbers are best reserved for values such as measurements, whose values are fundamentally inexact to begin with.
		Floating point and decimal numbers are not nearly as well-behaved as integers, and you cannot assume that floating point calculations that "should" have integer or exact results actually do.
	www-128.ibm.com /developerworks/java/library/j-jtp0114 (1834 words)

	System/360 - TheBestLinks.com - IBM 360, Apollo program, Avionics, April 7, ... (Site not responding. Last check: 2007-10-08)
		Unlike past practice, IBM created an entire line of computers (or CPUs) from small to large, low to high performance, all (with two exceptions) running the same command set.
		The 44 (1966) was a variant aimed at the mid-range scientific market with hardware floating point, but an otherwise limited instruction set.
		Being somewhat uncertain of the reliability and availability of the then new monolithic integrated circuits, IBM chose instead to design custom hybrid integrated circuits using discrete flip chip mounted glass encapsulated transistors and diodes with silk screened resistors on a ceramic substrate, then either encapsulated in plastic or covered with a metal lid.
	www.thebestlinks.com /IBM_360.html (1021 words)

	IBM Journal of Research and Development: IBM eServer z990 floating-point unit, The (Site not responding. Last check: 2007-10-08)
		The floating-point unit (FPU) of the IBM z990 eServer(TM) is the first one in an IBM mainframe with a fused multiply-add dataflow.
		Both the HFP and BFP architectures are already implemented in hardware in the 1998 IBM zSeries G5 processor [7], but a hexadecimal dataflow is used.
		In the PowerPC Architecture, only RR instructions are possible, which allows the addition of tags to the operands in the register files, making it possible to recognize denormalized numbers.
	www.findarticles.com /p/articles/mi_qa3751/is_200405/ai_n9388219 (1478 words)

	IBM Research \| IBM Research \| The Cell architecture
		IBM Research participated throughout the development, implementation and software enablement of the architecture, ensuring the timely and efficient application of novel ideas and technology into a product that solves real challenges.
		Floating point data types automatically support a wide dynamic data range and saturation, so no additional data conditioning is required.
		IBM Research grew its partnership in the development of the broadband processor architecture beyond its initial definition.
	domino.research.ibm.com /comm/research.nsf/pages/r.arch.innovation.html (1819 words)

	The IBM 701
		The first unit was installed in 1952 at IBM Headquarters in New York City, replacing the SSEC.
		The 701's vacuum tubes were collected into "pluggable units", a concept introduced with IBM's 604 Electronic Calculating Punch in 1948, which simplified troubleshooting and service of machines that had hundreds or thousands of tubes.
		The 36-bit architecture was adopted by Digital Equipment Corporation for its PDP-6 and PDP-10 computers from 1964 to 1988 and by other manufacturers including Honeywell and Sperry; the Sperry/UNIVAC 1100 survives to this day [2001] as the Unisys Clearpath IX and IE series.
	www.columbia.edu /acis/history/701.html (802 words)

	The S/390 G5 floating-point unit
		The microprocessor chip is fabricated in IBM CMOS 6X technology, with a device size of 0.25 µm as drawn and 0.15 µm effective length.
		The new S/390 architecture [2] defines a superset of the union of the IEEE 754 standard and the S/390 hexadecimal format.
		IBM S/390 mainframes are more reliable than PCs and workstations, and this tradition is continued with the G5 microprocessor.
	www.research.ibm.com /journal/rd/435/schwarz.html (7160 words)

	ipedia.com: IBM Floating Point Architecture Article (Site not responding. Last check: 2007-10-08)
		IBM System/360 computers, and subsequent machines based on that architecture, support a hexadecimal floating-point format.
		Note that in this format the initial bit is not suppressed, and the radix point is set to the left of the mantissa.
		Again the tricky part is moving the mantissa since IBM always puts the radix just left of the mantissa.
	www.ipedia.com /ibm_floating_point_architecture.html (411 words)

	IBM Research \| IBM Research \| Computer Architecture: Publications
		This is a jointly funded research partnership between IBM and the Lawrence Livermore National Laboratory as part of the United States Department of Energy ASCI Advanced Architecture Research Program.
		An analytical theory is presented that shows two opposing architectural parameters affect the optimal pipeline length: the degree of instruction level parallelism (superscalar) decreases the optimal pipeline length, while the lack of pipeline stalls increases the optimal pipeline length.
		Thus, the original architecture is implemented using dynamic compilation, a process we refer to as DAISY (Dynamically Architected Instruction Set from Yorktown).
	domino.research.ibm.com /comm/research.nsf/pages/r.arch.papers.html (825 words)

	POWER4 System Microarchitecture
		Several years ago, we set out to design a new microprocessor that would insure we would leverage IBM strengths across many different disciplines to deliver a server that would redefine what was meant by the term server.
		Additionally, dual fixed point execution units, a branch execution unit and an execution unit to perform logical operations on the condition register exist.
		At that point, if the predictions were found to be correct, the branch instructions are simply completed like all other instructions.
	www-1.ibm.com /servers/eserver/pseries/hardware/whitepapers/power4.html (1871 words)

	Floating point unit at opensource encyclopedia (Site not responding. Last check: 2007-10-08)
		Floating Point Unit uses and addresses new media technologies with a special emphasis on distance performance and...
		The floating point unit is integrated into all processors from the 486DX on (this does not include the...
		An FPU (floating point unit), also known as a numeric coprocessor, is a microprocessor or special circuitry in a more general microprocessor that manipulates numbers more quickly than the basic microprocessor your computer uses.
	www.springknow.com /FPU.html (602 words)

	Architecture of the World Wide Web, Volume One
		An architectural principle is a fundamental rule that applies to a large number of situations and variables.
		The problem with aliases is that if half of the neighborhood points to one URI for a given resource, and the other half points to a second, different URI for that same resource, the neighborhood is divided.
		If a vocabulary has no extensibility points (that is, if it does not allow elements or attributes from foreign namespaces or have a mechanism for dealing with unrecognized names from the same namespace), it may be absolutely necessary to change the namespace name.
	www.w3.org /2001/tag/webarch (14496 words)

	Search Results for floating-point - Encyclopædia Britannica
		In the early 1950s John Backus convinced his managers at IBM to let him put together a team to design a language and write a compiler for it.
		He had a machine in mind: the IBM 704, which had built-in...
		The southernmost point of the Chilean mainland in Punta Arenas.
	www.britannica.com /search?query=floating-point&submit=Find&source=MWTAB (483 words)

	Apple and IBM Introduce the PowerPC G5 Processor
		The next generation PowerPC architecture is based on a completely new execution core that features massively parallel computation for an unprecedented 215 in-flight instructions, full symmetric multi-processing, two double precision floating point units and an optimized Velocity Engine™.
		IBM is a recognized innovator in the chip industry, having been first with advances like more power-efficient copper wiring in place of aluminum, faster silicon-on-insulator (SOI) and silicon germanium transistors, and improved low-k dielectric insulation between chip wires.
		IBM Microelectronics is a key contributor to IBM’s role as the world's premier information technology supplier.
	www.apple.com /pr/library/2003/jun/23joint.html (793 words)

	DCE 1.1: Remote Procedure Call - Transfer Syntax NDR
		The IBM architecture defines short and long floating-point formats for single-precision and double-precision floating-point values, respectively.
		If the input and output octet streams pertaining to one remote procedure call contain several pointers that point to the same thing, the first of these pointers to be transmitted is considered primary and the others are considered aliases.
		The scope of aliasing for a pointer extends to all streams transmitted in the service of one remote procedure call; that is, any inputs in the request that initiates the call, and any outputs in the response to the call.
	www.opengroup.org /onlinepubs/9629399/chap14.htm (5852 words)

	Floating point (Site not responding. Last check: 2007-10-08)
		A few machines offer larger sizes; Intel FPUs suchas the Intel 8087 (and itsdescendants integrated into the x86 architecture) offer 80 bit floating point numbers forintermediate results, and several systems offer 128 bit floating-point, generally implemented in software.
		Arithmetic using the floating point number system has two important properties that differ from those of arithmetic using realnumbers.
		Notable exceptions include IBM Mainframes, which have both hexadecimal and IEEE 754 data types, andCray vector machines, where the T90 series had an IEEE version, but the SV1 still uses Cray floating-point format.
	www.therfcc.org /floating-point-37401.html (1198 words)

	Ars Technica: Inside the IBM PowerPC 970, Part II - Page 1 - (5/2003) (Site not responding. Last check: 2007-10-08)
		Introduction to Part II The present article is the second installment in a two-part series on IBM's upcoming PowerPC 970.
		The first article in the series is available here, and prior to that I wrote a brief preview of the 970 that's available at this link.
		This article is as much theirs as it is mine, since we've all been poring over this chip as a group since it was first announced.
	arstechnica.com /cpu/03q1/ppc970/ppc970-0.html (356 words)

	IBM 7090/94 Architecture Home Page
		The IBM 7090/94 series was the most popular family of large second-generation transistorized mainframe computers and was designed for "large-scale scientific and technological applications".
		By 1965, over 300 IBM 7090/94 systems had been installed with an average purchase price of about $3-million (most were rented from IBM for about $70,000 per month or for about $450,000 per month in today's money as adjusted for inflation).
		In low-end installations, IBM 1401(s) would typically be used to read cards and transfer the information for input to the 7090/94 from magnetic tapes.
	www.frobenius.com /7090.htm (1041 words)

	Apple - PowerPC G5 - Architecture (Site not responding. Last check: 2007-10-08)
		The G5’s execution core is derived from IBM’s POWER architecture: two double-precision floating-point units, advanced branch prediction logic and a high-bandwidth frontside bus.
		To that superscalar, superpipelined execution core, Apple and IBM added the Velocity Engine, so software that optimizes vector math routines will run on the Power Mac G5 without modification.
		The PowerPC architecture was designed from the get-go for both 32- and 64-bit processing.
	www.apple.com /g5processor/architecture.html (647 words)

Try your search on: Qwika (all wikis)