The present invention pertains to communication. More particularly, the present invention relates to a method and apparatus for configurable posting points in a communication system.
In communication systems, how information is transferred from one point to another is important. Also of importance is the successful transfer of the information. Acknowledgement of receipt of the information communicated is often used to convey the successful or non-successful transfer of the information. Information may be in the form of packets, streams, reads, writes, etc.
How an acknowledgement is performed, if and when it is sent, as well as the point at which it is sent may affect system performance. For example, if an acknowledgement is only sent after the receiving end has completed the entire reception of what was transmitted, this may delay the transmitting device from sending additional information until the prior transmission is acknowledged. On the other hand, if the transmitter sends information without regard to whether the receiver has actually received the information may also present problems in the communication system.
The present invention is illustrated by way of example and not limitation in the figures of the accompanying drawings, in which like references indicate similar elements and in which:
A method and apparatus for configurable posting points in a communication system are described.
The present invention, in one embodiment, deals with the treatment of writes, packets, etc., in a communication system. Specifically, one embodiment of the present invention deals with the issue of when a write is considered complete and/or a packet is considered acknowledged. For convenience in describing the present invention, the discussion is restricted to writes, however one of ordinary skill in the art will appreciate that the techniques disclosed apply to packets, etc.
When an initiator (such as a processor) is connected directly to a target (such as a memory system), there is little ambiguity as to when a write is considered complete. The processor may send the write command and data to the memory, and the memory acknowledges the write command back to the processor. At this point the write data is substantially in memory and the processor has been told that the write has completed, so each party to the communication is in synchronization as to when the write occurred. This example is often referred to as a tight coupling between the processor and the memory.
When the coupling of initiators to targets is less tight, for example because the size of the system has grown and there is a communication system between the processor and the memory, the notion of a single point in time that a write is completed from all viewpoints in the system goes away. Different elements in the system may now see the write completion at different times.
This leads to the concept of posted and non-posted writes as illustrated in
The trade-off between posted and non-posted writes involves one of performance versus accuracy. With posted writes, completion is faster (from the viewpoint of the initiator), allowing, for example, buffers to be reused and computation to continue without having to wait. However, a down-side may be that there is no longer a uniform view of when writes complete for the entire system, which complicates issues, such as, error handling and global event ordering. Depending upon system requirements, either posted or non-posted writes may make sense.
In existing communication systems, the handling of writes is usually not at the discretion of the system designer, making it difficult to do a fine trade-off between performance and accuracy for writes. In one embodiment of the present invention, a communication system allows the handling of writes to be configured so as to give the system designer fine-grained control over the performance versus accuracy trade-off. In one embodiment of the present invention, the system designer may place posting points (the points at which write requests are posted) at any point along the way from the initiator to the target.
In existing systems, it is typical for the posting point to be either right at the initiator (for posted writes) or at the target (for non-posted writes). In these systems, the location of the posting point is a function of the design of the initiators or targets and the system designer does not get a choice over their placement.
Thus, in one embodiment of the present invention, the posting point may be placed at any point from the one extreme of a write posted at the initiator to the other extreme of the non-posted write. By providing this ability to place the posting point, the designer and/or user may make a performance versus accuracy tradeoff.
Now, from the viewpoint of the initiator and the target, the write may be considered to have varying degrees of posting and/or non-posting. For example, in the right-most example in
In one embodiment of the present invention, it is possible for the communication system to be configurable as to the location of posting points. Registers that are accessible from system software may control the posting point presence and location within the communication system. This allows system software to modify the configuration of the communication system while an application is executing, allowing it to tune the desired trade-off between performance and ordering preciseness at runtime. The posting point may be set as a static point or may be dynamically set. For example, during initial power up, a system may set various posting points and then not change them while the system is operating. These static posting points may be pre-determined and/or may be determined during the power up sequence (as for example, based upon external memory access speeds). Alternatively, the posting points may be adjusted while the system is operating. Yet another alternative is that the posting points may be determined at the time of system design and later fabricated into the system, for example, on an integrated circuit. In this “hardwired” or fabricated approach, no explicit communication or setup is required to configure a system after powering up. A combination of static and dynamic posting is also possible.
In one embodiment of the present invention,
For example, if a write burst consists of n requests (1, . . . , n , where 1 is the first and n is the last request), then for 1 through n-1 requests the initiator I 602 has a write 612 posted at 608 and receives back a response 614, the write continues via 616 and 618 to the target T 606. On the last request n, the initiator I 602 has a write 612 that continues via 616 and 618, is posted at 610 which is part of the target T 606, and receives back a response 620 from the target T 606.
So far, we have made use of the terms initiator and target. They define the end points for the communication: the initiator is the source of the request, and the target is where the write is ultimately performed. There may, however, be several other elements in the communication chain between the initiator and the target. In
The parameter writeresp_enable can be ON or OFF and controls the presence of a response for writes. With writeresp_enable OFF (as illustrated in
When the parameter writeresp_enable is ON, the writechoice_enable parameter can be used to turn ON and OFF the ability for the master to explicitly communicate whether posted or non-posted write semantics are desired. When writechoice_enable is OFF (as illustrated in
With writechoice_enable ON (as illustrated in
Thus what has been disclosed is a communication system and method with configurable posting points.
Referring back to
Referring back to
For purposes of discussing and understanding the invention, it is to be understood that various terms are used by those knowledgeable in the art to describe techniques and approaches. Furthermore, in the description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the present invention. It will be evident, however, to one of ordinary skill in the art that the present invention may be practiced without these specific details. In some instances, well-known structures and devices are shown in block diagram form, rather than in detail, in order to avoid obscuring the present invention. These embodiments are described in sufficient detail to enable those of ordinary skill in the art to practice the invention, and it is to be understood that other embodiments may be utilized and that logical, mechanical, electrical, and other changes may be made without departing from the scope of the present invention.
Some portions of the description may be presented in terms of algorithms and symbolic representations of operations on, for example, data bits within a computer memory. These algorithmic descriptions and representations are the means used by those of ordinary skill in the data processing arts to most effectively convey the substance of their work to others of ordinary skill in the art. An algorithm is here, and generally, conceived to be a self-consistent sequence of acts leading to a desired result. The acts are those requiring physical manipulations of physical quantities. Usually, though not necessarily, these quantities take the form of electrical, magnetic, or optical signals capable of being stored, transferred, combined, compared, and otherwise manipulated. It has proven convenient at times, principally for reasons of common usage, to refer to these signals as bits, values, elements, symbols, characters, terms, numbers, or the like.
It should be borne in mind, however, that all of these and similar terms are to be associated with the appropriate physical quantities and are merely convenient labels applied to these quantities. Unless specifically stated otherwise as apparent from the discussion, it is appreciated that throughout the description, discussions utilizing terms such as “processing” or “computing” or “calculating” or “determining” or “communicating” or “displaying” or the like, can refer to the action and processes of a computer system, or an electronic device, that manipulates and transforms data represented as physical (electronic) quantities within the electronic device or computer system's registers and memories into other data similarly represented as physical quantities within the electronic device and/or computer system memories or registers or other such information storage, transmission, or display devices.
The present invention can be implemented by an apparatus for performing the operations herein. This apparatus may be specially constructed for the required purposes, or it may comprise a general-purpose computer, selectively activated or reconfigured by a computer program stored in the computer. Such a computer program may be stored in a computer readable storage medium, such as, but not limited to, any type of disk including floppy disks, hard disks, optical disks, compact disk-read only memories (CD-ROMs), digital versatile disk (DVD), and magnetic-optical disks, read-only memories (ROMs), random access memories (RAMs), electrically programmable read-only memories (EPROM)s, electrically erasable programmable read-only memories (EEPROMs), FLASH memories, magnetic or optical cards, etc., or any type of media suitable for storing electronic instructions either local to the computer or remote to the computer.
The algorithms and displays presented herein are not inherently related to any particular computer or other apparatus. Various general purpose systems may be used with programs in accordance with the teachings herein, or it may prove convenient to construct more specialized apparatus to perform the required method. For example, any of the methods according to the present invention can be implemented in hard-wired circuitry, by programming a general-purpose processor, or by any combination of hardware and software. One of ordinary skill in the art will immediately appreciate that the invention can be practiced with computer system configurations other than those described, including hand-held devices, multiprocessor systems, microprocessor-based or programmable consumer electronics, digital signal processing (DSP) devices, set top boxes, network PCs, minicomputers, mainframe computers, and the like. The invention can also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. This communications network is not limited by size, and may range from, for example, on-chip communications to WANs such as the Internet.
The methods of the invention may be implemented using computer software. If written in a programming language conforming to a recognized standard, sequences of instructions designed to implement the methods can be compiled for execution on a variety of hardware platforms and for interface to a variety of operating systems. It will be appreciated that a variety of programming languages may be used to implement the teachings of the invention as described herein. Furthermore, it is common in the art to speak of software, in one form or another (e.g., program, procedure, application, driver, . . . ), as taking an action or causing a result. Such expressions are merely a shorthand way of saying that execution of the software by a computer causes the processor of the computer to perform an action or produce a result.
It is to be understood that various terms and techniques are used by those knowledgeable in the art to describe communications, protocols, applications, implementations, mechanisms, etc. One such technique is the description of an implementation of a technique in terms of an algorithm or mathematical expression. That is, while the technique may be, for example, implemented as executing code on a computer, the expression of that technique may be more aptly and succinctly conveyed and communicated as a formula, algorithm, or mathematical expression. Thus, one of ordinary skill in the art would recognize a block denoting A+B=C as an additive function whose implementation in hardware and/or software would take two inputs (A and B) and produce a summation output (C). Thus, the use of formula, algorithm, or mathematical expression as descriptions is to be understood as having a physical embodiment in at least hardware and/or software (such as a computer system in which the techniques of the present invention may be practiced as well as implemented as an embodiment).
A machine-readable medium is understood to include any mechanism for storing or transmitting information in a form readable by a machine (e.g., a computer). For example, a machine-readable medium includes read only memory (ROM); random access memory (RAM); magnetic disk storage media; optical storage media; flash memory devices; electrical, optical, acoustical, or other form of propagated signals (e.g., carrier waves, infrared signals, digital signals, etc.); etc.
Thus, a communication system and method with configurable posting points have been described.
Number | Name | Date | Kind |
---|---|---|---|
5923860 | Olarig | Jul 1999 | A |
5948089 | Wingard et al. | Sep 1999 | A |
5987541 | Hewitt | Nov 1999 | A |
6034542 | Ridgeway | Mar 2000 | A |
6041400 | Ozcelik et al. | Mar 2000 | A |
6061730 | Billings | May 2000 | A |
6122664 | Boukobza et al. | Sep 2000 | A |
6182183 | Wingard et al. | Jan 2001 | B1 |
6253243 | Spencer | Jun 2001 | B1 |
6330225 | Weber et al. | Dec 2001 | B1 |
6336138 | Caswell et al. | Jan 2002 | B1 |
6539225 | Lee | Mar 2003 | B1 |
6549516 | Albert et al. | Apr 2003 | B1 |
6571286 | Fisher et al. | May 2003 | B2 |
6578117 | Weber | Jun 2003 | B2 |
6654798 | Skibinski et al. | Nov 2003 | B1 |
6671724 | Pandya et al. | Dec 2003 | B1 |
6683474 | Ebert et al. | Jan 2004 | B2 |
6718416 | Self et al. | Apr 2004 | B1 |
6721793 | Corless | Apr 2004 | B1 |
6725313 | Wingard et al. | Apr 2004 | B1 |
6766406 | Gasperini et al. | Jul 2004 | B1 |
6775719 | Leitner et al. | Aug 2004 | B1 |
6785256 | O'Neill | Aug 2004 | B2 |
6785753 | Weber et al. | Aug 2004 | B2 |
6795857 | Leung et al. | Sep 2004 | B1 |
6804738 | Weber | Oct 2004 | B2 |
6804757 | Weber | Oct 2004 | B2 |
6816814 | Ebert et al. | Nov 2004 | B2 |
6831916 | Parthasarathy et al. | Dec 2004 | B1 |
6880133 | Meyer et al. | Apr 2005 | B2 |
6948004 | Gasbarro et al. | Sep 2005 | B2 |
6961834 | Weber | Nov 2005 | B2 |
6976106 | Tomlinson et al. | Dec 2005 | B2 |
20020046260 | Day, II | Apr 2002 | A1 |
20020138287 | Chen et al. | Sep 2002 | A1 |
20020138615 | Schmeling | Sep 2002 | A1 |
20020141401 | Albert et al. | Oct 2002 | A1 |
20020143653 | DiLena et al. | Oct 2002 | A1 |
20020169854 | Tarnoff | Nov 2002 | A1 |
20020184300 | Schmeling et al. | Dec 2002 | A1 |
20030018738 | Boylan et al. | Jan 2003 | A1 |
20030069960 | Symons et al. | Apr 2003 | A1 |
20030074520 | Weber | Apr 2003 | A1 |
20030126192 | Magnussen | Jul 2003 | A1 |
20030158994 | Moy | Aug 2003 | A1 |
20030167144 | Wang et al. | Sep 2003 | A1 |
20030208566 | Weber et al. | Nov 2003 | A1 |
20040015961 | Chefalas et al. | Jan 2004 | A1 |
Number | Date | Country |
---|---|---|
1 376 932 | Jan 2004 | EP |
03 72 8644 | Aug 2005 | EP |
WO 9534153 | Dec 1995 | WO |
WO 9963727 | Dec 1999 | WO |
WO 0213024 | Feb 2002 | WO |
Number | Date | Country | |
---|---|---|---|
20030208553 A1 | Nov 2003 | US |