The field of the invention is data processing, or, more specifically, methods and apparatus for operation of a multi-slice processor.
The development of the EDVAC computer system of 1948 is often cited as the beginning of the computer era. Since that time, computer systems have evolved into extremely complicated devices. Today's computers are much more sophisticated than early systems such as the EDVAC. Computer systems typically include a combination of hardware and software components, application programs, operating systems, processors, buses, memory, input/output devices, and so on. As advances in semiconductor processing and computer architecture push the performance of the computer higher and higher, more sophisticated computer software has evolved to take advantage of the higher performance of the hardware, resulting in computer systems today that are much more powerful than just a few years ago.
One area of computer system technology that has advanced is computer processors. As the number of computer systems in data centers and the number of mobile computing devices has increased, the need for more efficient computer processors has also increased. Speed of operation and power consumption are just two areas of computer processor technology that affect efficiency of computer processors.
Methods and apparatus for operation of a multi-slice processor are disclosed in this specification. Such a multi-slice processor includes a plurality of execution slices and a plurality of load/store slices, where the load/store slices are coupled to the execution slices via a results bus. Such a multi-slice processor may further include one or more instruction sequencing units. Operation of such a multi-slice processor includes: receiving, at a load/store slice from an instruction sequencing unit, a instruction to be issued; determining, at the load/store slice, a rejection condition for the instruction; and responsive to determining the rejection condition for the instruction, maintaining state information for the instruction in the load/store slice instead of notifying the instruction sequencing unit of a rejection of the instruction.
The foregoing and other objects, features and advantages of the invention will be apparent from the following more particular descriptions of exemplary embodiments of the invention as illustrated in the accompanying drawings wherein like reference numbers generally represent like parts of exemplary embodiments of the invention.
Exemplary methods and apparatus for operation of a multi-slice processor in accordance with the present invention are described with reference to the accompanying drawings, beginning with
The computer (152) of
The example computer processor (156) of
The example multi-slice processor (156) of
Although the multi-slice processor (156) in the example of
Stored in RAM (168) in the example computer (152) is a data processing application (102), a module of computer program instructions that when executed by the multi-slice processor (156) may provide any number of data processing tasks. Examples of such data processing applications may include a word processing application, a spreadsheet application, a database management application, a media library application, a web server application, and so on as will occur to readers of skill in the art. Also stored in RAM (168) is an operating system (154). Operating systems useful in computers configured for operation of a multi-slice processor according to embodiments of the present invention include UNIX™, Linux™, Microsoft Windows™, AIX™, IBM's z/OS™, and others as will occur to those of skill in the art. The operating system (154) and data processing application (102) in the example of
The computer (152) of
The example computer (152) of
The exemplary computer (152) of
The arrangement of computers and other devices making up the exemplary system illustrated in
For further explanation,
The multi-slice processor in the example of
The general purpose registers (206) are configured to store the youngest instruction targeting a particular logical register and the result of the execution of the instruction. A logical register is an abstraction of a physical register that enables out-of-order execution of instructions that target the same physical register.
When a younger instruction targeting the same particular logical register is received, the entry in the general purpose register is moved to the history buffer, and the entry in the general purpose register is replaced by the younger instruction. The history buffer (208) may be configured to store many instructions targeting the same logical register. That is, the general purpose register is generally configured to store a single, youngest instruction for each logical register while the history buffer may store many, non-youngest instructions for each logical register.
Each execution slice (204) of the multi-slice processor of
The arithmetic logic unit (212) depicted in the example of
The results bus (220) may be configured in a variety of manners and be of composed in a variety of sizes. In some instances, each execution slice may be configured to provide results on a single bus line of the results bus (220). In a similar manner, each load/store slice may be configured to provide results on a single bus line of the results bus (220). In such a configuration, a multi-slice processor with four processor slices may have a results bus with eight bus lines—four bus lines assigned to each of the four load/store slices and four bus lines assigned to each of the four execution slices. Each of the execution slices may be configured to snoop results on any of the bus lines of the results bus. In some embodiments, any instruction may be dispatched to a particular execution unit and then by issued to any other slice for performance. As such, any of the execution slices may be coupled to all of the bus lines to receive results from any other slice. Further, each load/store slice may be coupled to each bus line in order to receive an issue load/store instruction from any of the execution slices. Readers of skill in the art will recognize that many different configurations of the results bus may be implemented.
The multi-slice processor in the example of
The example multi-slice processor of
During the flush and recovery operation, in prior art processors, the dispatcher was configured to halt dispatch of new instructions to an execution slice. Such instructions may be considered either target or source instructions. A target instruction is an instruction that targets a logical register for storage of result data. A source instruction by contrast has, as its source, a logical register. A target instruction, when executed, will result in data stored in an entry of a register file while a source instruction utilizes such data as a source for executing the instruction. A source instruction, while utilizing one logical register as its source, may also target another logical register for storage of the results of instruction. That is, with respect to one logical register, an instruction may be considered a source instruction and with respect to another logical register, the same instruction may be considered a target instruction.
The multi-slice processor in the example of
In some cases, a load/store unit receiving an issued instruction, such as a load/store slice, may not yet be able to handle the instruction, and the instruction sequencing unit (240) may keep the instruction queued until such time as the load/store slice may handle the instruction. After the instruction is issued, the instruction sequencing unit (240) may track progress of the instruction based at least in part on signals received from a load/store slice.
For further explanation,
In previous systems, if a load/store unit received an instruction from an instruction sequencing unit, and the load/store unit was unable to handle the instruction for some reason, then the load/store unit would notify the instruction sequencing unit that the instruction was being rejected and the load/store unit would discard information related to the rejected instruction. In which case, the instruction sequencing unit would continue maintaining information to track and maintain the rejected instruction until the instruction is resent to the load/store unit. An instruction may be rejected for a variety of reasons, including an address miss in an address translation cache, a set prediction miss, data cache banking collisions, an overload of the load miss queue (308), among other possible rejection conditions.
The load/store slice (222a), by contrast to the above previous system, is configured to determine a rejection condition for an instruction received from an instruction sequencing unit, however, the load/store slice (222a), instead of sending a reject signal to the instruction sequencing unit, maintains tracking and handling of the instruction—including information usable to relaunch or reissue the instruction—until the rejection condition is resolved. Further, an entry in the load reorder queue (304) or the store reorder queue (306) may be configured to maintain information for tracking an instruction that would otherwise have been rejected and removed from the load reorder queue (304). For example, if the load/store slice (222a) determines that a rejection condition exists for a given load or store instruction, then logic within the load/store slice may notify the load reorder queue (304) or the store reorder queue (306) to place the instruction in a sleep state for a given number of cycles, or to place the instruction in a sleep state until notified to awaken, or to immediately reissue the instruction, among other notifications to perform other operations.
In this way, the load/store slice (222a) may save cycles that would otherwise be lost if the instruction were rejected to the instruction sequencing unit because the load/store slice (222a) may more efficiently and quickly reissue the instruction when the rejection condition is resolved in addition to more quickly detecting resolution of a rejection condition than an instruction sequencing unit. For example, if the load/store slice (222a) determines that an instruction that is in a sleep state may be reissued in response to determining that one or more rejection conditions have been resolved preventing the instruction from completing, then the load/store store slice may notify the load reorder queue (304) or the store reorder queue (306) to relaunch or reissue the instruction immediately or after some number of cycles. The number of cycles may depend upon a type of rejection condition or upon other factors affecting reissue or relaunch of the instruction. In this example, the load reorder queue (304) or the store reorder queue (306) may reissue or relaunch an instruction by providing the load/store access queue (224) with information to reissue the instruction, where the load reorder queue (304) or the store reorder queue (306) may communicate with the load/store access queue (224) along line (314) and may provide data for reissuing or relaunching the instruction along line (313).
Another improvement that results from the load/store slice (222a) maintaining an instruction if a rejection condition is determined is that the load/store slice (222a) uses fewer resources, such as logic and circuitry for latches and other components, to maintain the instruction than an instruction sequencing unit. In other words, given that the instruction sequencing unit may rely on the load/store slice (222a) in handling the instruction to completion, the instruction sequencing unit may free resources once the instruction is provided to the load/store slice (222a).
Further, the instruction sequencing unit (240), based at least in part on communications with the load/store slice (222a), may determine when and whether to wake instructions that may be dependent on a current instruction being handled by the load/store slice (222a). Therefore, if the load/store slice (222a) determines that a rejection condition exists, the load/store slice (222a) delays a notification to the instruction sequencing unit (240) to awaken dependent instructions to prevent the instruction sequencing unit (240) from issuing dependent instructions that are subsequently unable to finish due to lack of availability of results from a current instruction. In this way, the instruction sequencing unit (240) may avoid wasting execution cycles reissuing dependent instructions that are unable to finish.
For example, the load/store slice (222a) may communicate with the instruction sequencing unit (240) through the generation of signals indicating, at different points in handling a load instruction, that a load instruction is to be reissued or that data for a load instruction is valid. In some cases, in response to the instruction sequencing unit (240) receiving a signal from the load/store slice (222a) that a given instruction is to be reissued, the instruction sequencing unit (240) may awaken instructions dependent upon the given instruction with the expectation that the given instruction, after being reissued, is going to finish and provide valid data.
The load/store slice (222a) may also retrieve data from any tier of a memory hierarchy, beginning with a local data cache (232), and extending as far down in the hierarchy as needed to find requested data. The requested data, when received, may be provided to general purpose registers, virtual registers, or to some other destination. The received data may also be stored in a data cache (232) for subsequent access. The load/store slice (222a) may also manage translations of effective addresses to real addresses to communicate with different levels of memory hierarchy.
A store reorder queue (306) may include entries for tracking the cache operations for sequential consistency and may reissue operations into the load/store pipeline for execution independent of an execution slice.
A load miss queue (308) may issue requests for data to one or more data storage devices of a multi-tiered memory hierarchy, where a request for data may correspond to a load instruction for the data.
Responsive to the data being returned along the line (302) to the load/store slice (222a), the data may be delivered to a destination such as the results bus (220 of
A load reorder queue (304) may track execution of cache operations issued to the load/store slice (222a) and includes entries for tracking cache operations for sequential consistency, among other attributes. The load reorder queue (304) may also reissue operations into the load/store pipeline for execution, which provides operation that is independent of the execution slices.
For further explanation,
The method of
During normal operation, a load operation may access data already stored in a data cache and the load operation finishes without being reissued. However, under some conditions, the load/store slice (222a) may determine that an instruction is to be reissued or rejected—where an instruction may be reissued immediately, or after some number of cycles dependent upon a rejection condition for the instruction being resolved. While it is often the case that a reissued instruction may complete, if a reissued instruction does not complete, sending a signal to the instruction sequencing unit (240) may result in instructions dependent upon the reissued instruction being awakened prematurely. Similarly, under some conditions, a store instruction may be unable to be performed.
The method of
The method of
Further, maintaining the state information may include storing, for example, within an entry of the load reorder queue (304) or store reorder queue (306), information that may be used to reissue or relaunch the instruction after a notification is received to awaken due to a rejection condition being resolved, or due to a rejection condition being expected to resolve within a quantity of cycles.
For example, an entry may store, or maintain, information previously held to handle instructions so that a reissued instruction appears identical or similar to the instruction as originally received from an instruction sequencing unit. For example, an entry may store, or maintain, instruction operation codes, or opcodes, effective address information to determine which bytes in a cacheline are involved in an instruction, an ITAG, which may be used for ordering instructions, a real address, which may describe a cacheline address used by lower tiers of memory, and various control bits, among other information. Further, the entry may store, or maintain, a set of wait states corresponding to different rejection conditions, where this information may be a basis for awakening instructions in response to corresponding rejection conditions being resolved.
The load reorder queue (304) and the store reorder queue (306) are further configured to, in response to being notified to place an instruction into a sleep state, not send any signal or notification to the instruction sequencing unit that provided the instruction to prevent the instruction sequencing unit from prematurely awakening any instructions dependent on the instruction being placed into a sleep state.
For example, in response to the instruction sequencing unit (240) receiving a signal on the results bus (220) indicating that an instruction is being reissued, the instruction sequencing unit (240) may awaken instructions dependent on the reissued instruction in anticipation that a data valid signal is to follow, which would allow the dependent instructions to execute properly. However, if the load/store slice (222a) delays sending a signal that an instruction is being reissued, the instruction sequencing unit (240) does not awaken instructions dependent upon the reissued instruction, thereby avoiding cancelation of dependent instructions awakened for a reissued instruction that does not complete upon reissue, which prevents wasting execution cycles recovering from canceling the dependent instructions.
In this way, the load/store slice (222a) relieves the instruction sequencing unit from expending any resources tracking an instruction once the instruction sequencing unit provides the instruction to the load/store slice (222a) because the instruction sequencing unit relies on the load/store slice (222a) to handle the instruction to completion whether or not the load/store slice (222a) determines or identifies any rejection conditions that would have otherwise required the instruction sequencing unit to maintain status information for the instruction.
For further explanation,
The method of
The method of
Determining (502) that the rejection condition for the instruction has resolved or is pending resolution may be carried out by the load/store slice (222a) determining that one or more of the conditions on which a rejection of the instruction may be based, as determined at (404), has been resolved or is expected to be resolved within some quantity of cycles. For example, the load/store slice (222a) may determine resolution of rejection conditions including: the data cache being unable to currently read a requested data address, a translation mechanism being unable to translate the requested data address, a load/miss queue being too busy to handle the instruction request, a detected hazard with other load or store instructions, waiting for a store forward to complete, among other possible conditions for rejecting an instruction.
The load/store slice (222a) may further determine, based on a type of rejection, a quantity of cycles within which a resolution of a rejection condition is expected to resolve, and notify the load reorder queue (304) or the store reorder queue (306).
Reissuing (504) the instruction (452) from within the load/store slice (222a) may be carried out by the load/store slice (222a) notifying either the load reorder queue (304) or the store reorder queue (306) to awaken an instruction previously placed in a sleep state or to awaken after passage, the lapse of, a quantity of cycles. In response to receiving a signal to awaken, the load reorder queue (304) or the store reorder queue (306) may signal (552) the load/store access queue (224) along line (314) to reissue or relaunch an instruction.
Further, the load/store slice (222a) may determine an order in which to awaken multiple instructions that are in a sleep state awaiting resolution of rejection conditions. In other words, while instructions arrive at the load/store slice (222a) in an order determined by an instruction sequencing unit, the load/store slice (222a) may reorder instructions such that any effect of the completed, reordered instructions, is consistent with the order in which the instructions were received from the instruction sequencing unit. For example, the load/store slice (222a) may determine awakening priorities based on at least in part on an age of an instruction, a measure of nearness to completion for the instruction, or according to an instruction that may take advantage of carry data forwarding.
Notifying (506) the instruction sequencing unit (240) that the instruction is being reissued may be carried out by the load reorder queue (304) or the store reorder queue (306) generating a signal (554) notifying the instruction sequencing unit (240) along line (312) to the results bus (220)—where the signal (554) may indicate to the instruction sequencing unit (240) an identification of a reissue signal, and an ITAG identifying the instruction being reissued.
Further, the load/store slice (222a) may propagate a signal to the instruction sequencing unit (240) indicating that the data requested by the load instruction, identifiable by an ITAG, is on a results bus and is valid, where the instruction sequencing unit (240) receives the signal and corresponds the signal with an indication that the data is valid and on the results bus (220).
Determining (508) an arrival of data for the instruction from a lower tier of memory into the data cache (232) on the load/store slice (222a) may be carried out by the load/store slice (222a) receiving an indication from a lower tier of memory that requested data is moving toward the data cache (232) and may be expected to be available at a given number of cycles. Such information may allow the load/store slice (222a) to awaken load instructions in time to make use of a carry data forward path.
Scheduling (510) the instruction to be issued such that the instruction may provide the data for the instruction to a destination without accessing the data cache (232) may be carried out by the load/store slice (222a) notifying the load reorder queue (304) to awaken a sleeping instruction in time so that the instruction may provide the data being received to a destination along a carry data forward path (310) without waiting for the requested data first being latched or stored in the data cache (232). In other words, the instruction makes use of the carry data forwarding technique described above with regard to
In this way, the load/store slice (222a) may awaken instructions at points in time a number of cycles from a current point so that the awakened and reissued instructions are not delayed in completing.
For further explanation,
The method of
The method of
Determining (602) if the instruction (452) is a load or a store may be carried out by the load/store slice (222a) determining whether an opcode for the instruction (452) received from the instruction sequencing unit matches a load operation or a store operation.
Providing (604), from the load/store access queue (224) to the load reorder queue (304), the instruction (452) may be carried out by the load/store access queue (224) propagating the instruction (452) through MUX (228) along line (316) to the load reorder queue (304).
Providing (606), from the load/store access queue (224) to the store reorder queue (304), the instruction (452) may be carried out by the load/store access queue (224) propagating the instruction (452) through MUX (228) along line (316) to the store reorder queue (306).
In this way, the load/store access queue (224) may route load and store instructions to corresponding queues for handling the instruction, where both the load reorder queue (304) and the store reorder queue (306) include entries that are configured to maintain information for maintaining instructions that are determined to be subject to rejection conditions such that the maintained information may be used to reawaken and reissue the instructions pending resolution of one or more rejection conditions.
The present invention may be a system, a method, and/or a computer program product. The computer program product may include a computer readable storage medium (or media) having computer readable program instructions thereon for causing a processor to carry out aspects of the present invention.
The computer readable storage medium can be a tangible device that can retain and store instructions for use by an instruction execution device. The computer readable storage medium may be, for example, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. A non-exhaustive list of more specific examples of the computer readable storage medium includes the following: a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanically encoded device such as punch-cards or raised structures in a groove having instructions recorded thereon, and any suitable combination of the foregoing. A computer readable storage medium, as used herein, is not to be construed as being transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission media (e.g., light pulses passing through a fiber-optic cable), or electrical signals transmitted through a wire.
Computer readable program instructions described herein can be downloaded to respective computing/processing devices from a computer readable storage medium or to an external computer or external storage device via a network, for example, the Internet, a local area network, a wide area network and/or a wireless network. The network may comprise copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. A network adapter card or network interface in each computing/processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium within the respective computing/processing device.
Computer readable program instructions for carrying out operations of the present invention may be assembler instructions, instruction-set-architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state-setting data, or either source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C++ or the like, and conventional procedural programming languages, such as the “C” programming language or similar programming languages. The computer readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider). In some embodiments, electronic circuitry including, for example, programmable logic circuitry, field-programmable gate arrays (FPGA), or programmable logic arrays (PLA) may execute the computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuitry, in order to perform aspects of the present invention.
Aspects of the present invention are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer readable program instructions.
These computer readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer readable program instructions may also be stored in a computer readable storage medium that can direct a computer, a programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer readable storage medium having instructions stored therein comprises an article of manufacture including instructions which implement aspects of the function/act specified in the flowchart and/or block diagram block or blocks.
The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process, such that the instructions which execute on the computer, other programmable apparatus, or other device implement the functions/acts specified in the flowchart and/or block diagram block or blocks.
The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts or carry out combinations of special purpose hardware and computer instructions.
It will be understood from the foregoing description that modifications and changes may be made in various embodiments of the present invention without departing from its true spirit. The descriptions in this specification are for purposes of illustration only and are not to be construed in a limiting sense. The scope of the present invention is limited only by the language of the following claims.