US20070204139A1 - Compact linked-list-based multi-threaded instruction graduation buffer - Google Patents

Compact linked-list-based multi-threaded instruction graduation buffer Download PDF

Info

Publication number
US20070204139A1
US20070204139A1 US11362763 US36276306A US2007204139A1 US 20070204139 A1 US20070204139 A1 US 20070204139A1 US 11362763 US11362763 US 11362763 US 36276306 A US36276306 A US 36276306A US 2007204139 A1 US2007204139 A1 US 2007204139A1
Authority
US
Grant status
Application
Patent type
Prior art keywords
buffer
linked
instruction
graduation
identification
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Abandoned
Application number
US11362763
Inventor
Kjeld Svendsen
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Arm Finance Overseas Ltd
Original Assignee
MIPS Technologies Inc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/30Arrangements for executing machine instructions, e.g. instruction decode
    • G06F9/38Concurrent instruction execution, e.g. pipeline, look ahead
    • G06F9/3836Instruction issuing, e.g. dynamic instruction scheduling, out of order instruction execution
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/30Arrangements for executing machine instructions, e.g. instruction decode
    • G06F9/30098Register arrangements
    • G06F9/30105Register structure
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/30Arrangements for executing machine instructions, e.g. instruction decode
    • G06F9/38Concurrent instruction execution, e.g. pipeline, look ahead
    • G06F9/3836Instruction issuing, e.g. dynamic instruction scheduling, out of order instruction execution
    • G06F9/3838Dependency mechanisms, e.g. register scoreboarding
    • G06F9/384Register renaming
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/30Arrangements for executing machine instructions, e.g. instruction decode
    • G06F9/38Concurrent instruction execution, e.g. pipeline, look ahead
    • G06F9/3836Instruction issuing, e.g. dynamic instruction scheduling, out of order instruction execution
    • G06F9/3851Instruction issuing, e.g. dynamic instruction scheduling, out of order instruction execution from multiple instruction streams, e.g. multistreaming
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/30Arrangements for executing machine instructions, e.g. instruction decode
    • G06F9/38Concurrent instruction execution, e.g. pipeline, look ahead
    • G06F9/3867Concurrent instruction execution, e.g. pipeline, look ahead using instruction pipelines

Abstract

A processor and instruction graduation unit for a processor. In one embodiment, a processor or instruction graduation unit according to the present invention includes a linked-list-based multi-threaded graduation buffer and a graduation controller. The graduation buffer stores identification values generated by an instruction decode and dispatch unit of the processor as part of one or more linked-list data structures. Each linked-list data structure formed is associated with a particular program thread running on the processor. The number of linked-list data structures formed is variable and related to the number of program threads running on the processor. The graduation controller includes linked-list head identification registers and linked-list tail identification registers that facilitate reading and writing identifications values to linked-list data structures associated with particular program threads. The linked-list head identification registers determine which executed instruction result or results are next to be written to a register file.

Description

    FIELD OF THE INVENTION
  • The present invention relates generally to processors and more particularly to processors having an out-of-order execution pipeline.
  • BACKGROUND OF THE INVENTION
  • Reduced Instruction Set Computer (RISC) processors are well known. RISC processors have instructions that facilitate the use of a technique known as pipelining. Pipelining enables a processor to work on different steps of an instruction at the same time and thereby take advantage of parallelism that exists among the steps needed to execute an instruction. As a result, a processor can execute more instructions in a shorter period of time. Additionally, modern Complex Instruction Set Computer (CISC) processors often translate their instructions into micro-operations (i.e., instructions similar to those of a RISC processor) prior to execution to facilitate pipelining.
  • Many pipelined processors, especially those used in the embedded market, are relatively simple single-threaded in-order machines. As a result, they are subject to control, structural, and data hazard stalls. More complex processors are typically multi-threaded processors that have out-of-order execution pipelines. These more complex processors schedule execution of instructions around hazards that would stall an in-order machine.
  • A conventional multi-threaded out-of-order processor has multiple dedicated buffers that are used to reorder instructions executed out-of-order so that each instruction graduates (i.e., writes its result to a general purpose register file and/or other memory) in program order. For example, a conventional N-threaded out-of-order processor has N dedicated buffers for ensuring instructions graduate in program order; one buffer for each thread that can be run on the processor. A shortcoming of this approach, for example, is that it requires a significant amount of integrated circuit chip area to implement N separate buffers. This approach can also degrade performance in some designs when only a single program thread is running on a multi-threaded processor, for example, if each of the N buffers is limited in size in order to reduce the overall area of the N buffers.
  • What is needed is a processor that overcomes the limitations noted above.
  • BRIEF SUMMARY OF THE INVENTION
  • The present invention provides a processor, an instruction graduation unit for a processor, and applications thereof. In one embodiment, a processor or an instruction graduation unit according to the present invention includes a linked-list-based multi-threaded graduation buffer and a graduation controller.
  • The graduation buffer is used to temporarily store identification values generated by an instruction decode and dispatch unit of the processor. The identification values specify buffer registers used to temporarily store executed instruction results until the results are written to a register file. The identification values generated by the instruction decode and dispatch unit are stored in the graduation buffer and form part of one or more linked-list data structures. Each linked-list data structure formed is associated with a particular program thread running on the processor. Accordingly, the number of linked-list data structures formed is variable and related to the number of program threads running on the processor.
  • The graduation controller is coupled to the graduation buffer and includes both linked-list head identification registers and linked-list tail identification registers. The linked-list head identification registers and the linked-list tail identification registers facilitate reading and writing identifications values generated by the instruction decode and dispatch unit of the processor to a linked-list data structure associated with a particular program thread. The linked-list head identification registers determine which executed instruction result or results are next to be written to the register file.
  • Further embodiments, features, and advantages of the present invention, as well as the structure and operation of the various embodiments of the present invention, are described in detail below with reference to the accompanying drawings.
  • BRIEF DESCRIPTION OF THE DRAWINGS/FIGURES
  • The accompanying drawings, which are incorporated herein and form a part of the specification, illustrate the present invention and, together with the description, further serve to explain the principles of the invention and to enable a person skilled in the pertinent art to make and use the invention.
  • FIG. 1 is a diagram of a processor according to an embodiment of the present invention.
  • FIG. 2 is a more detailed diagram of the processor of FIG. 1.
  • FIG. 3 is a diagram of a first embodiment of a graduation buffer and a graduation controller according to the present invention.
  • FIG. 4 is a simplified diagram of the graduation buffer and the graduation controller of FIG. 3.
  • FIG. 5 is a first table illustrating operation of the graduation buffer and the graduation controller of FIG. 3.
  • FIG. 6 is a second table illustrating operation of the graduation buffer and the graduation controller of FIG. 3.
  • FIG. 7 is a diagram of a second embodiment of a graduation buffer and a graduation controller according to the present invention.
  • FIG. 8 is a simplified diagram of the graduation buffer and the graduation controller of FIG. 7.
  • FIG. 9 is a first table illustrating operation of the graduation buffer and the graduation controller of FIG. 7.
  • FIG. 10 is a second table illustrating operation of the graduation buffer and the graduation controller of FIG. 7.
  • The present invention is described with reference to the accompanying drawings. The drawing in which an element first appears is typically indicated by the leftmost digit or digits in the corresponding reference number.
  • DETAILED DESCRIPTION OF THE INVENTION
  • The present invention provides a processor, an instruction graduation unit for a processor, and applications thereof. In the detailed description of the invention that follows, references to “one embodiment”, “an embodiment”, “an example embodiment”, etc., indicate that the embodiment described may include a particular feature, structure, or characteristic, but every embodiment may not necessarily include the particular feature, structure, or characteristic. Moreover, such phrases are not necessarily referring to the same embodiment. Further, when a particular feature, structure, or characteristic is described in connection with an embodiment, it is submitted that it is within the knowledge of one skilled in the art to effect such feature, structure, or characteristic in connection with other embodiments whether or not explicitly described.
  • FIG. 1 illustrates an example processor 100 according to an embodiment of the present invention. As shown in FIG. 1, processor 100 includes an instruction fetch unit 102, an instruction cache 104, an instruction decode and dispatch unit 106, one or more instruction execution unit(s) 108, a data cache 110, an instruction graduation unit 112, a register file 114, and a bus interface unit 116. Processor 100 is capable of implementing multi-threading. As used herein, multi-threading refers to an ability of an operating system and a processor to execute different parts of a program, called threads, simultaneously.
  • Instruction fetch unit 102 retrieves instructions from instruction cache 104 and provides instructions to instruction decode and dispatch unit 106. Instructions are retrieved in program order, for example, for one or more program threads. In one embodiment, instruction fetch unit 102 includes logic for recoding compressed format instructions to a format that can be decoded and executed by processor 100. In one embodiment, instruction fetch unit 102 includes an instruction buffer that enables instruction fetch unit 102 to hold multiple instructions for multiple program threads, which are ready for decoding, and to issue more than one instruction at a time to instruction decode and dispatch unit 106.
  • Instruction cache 104 is an on-chip memory array organized as a direct associative or multi-way set associative cache such as, for example, a 2-way set associative cache, a 4-way set associative cache, an 8-way set associative cache, et cetera. In one embodiment, instruction cache 104 is virtually indexed and physically tagged, thereby allowing virtual-to-physical address translations to occur in parallel with cache accesses. Instruction cache 104 interfaces with instruction fetch unit 102.
  • Instruction decode and dispatch unit 106 receives one or more instructions at a time from instruction fetch unit 102 and decodes them prior to execution. In one embodiment, instruction decode and dispatch unit 106 receives at least one instruction for each program thread being implemented during a particular clock cycle. As described herein, the number of program threads being implemented at any given point in time is variable. Decoded instructions are stored in a decoded instruction buffer and issued to instruction execution unit(s) 108, for example, after it is determined that selected operands are available. Instructions can be dispatched from instruction decode and dispatch unit 106 to instruction execution unit(s) 108 out of program order.
  • Instruction execution unit(s) 108 execute instructions dispatched by instruction decode and dispatch unit 106. In one embodiment, at least one instruction execution unit 108 implements a load-store (RISC) architecture with single-cycle arithmetic logic unit operations (e.g., logical, shift, add, subtract, etc.). Other instruction execution unit(s) 108 can include, for example, a floating point unit, a multiple-divide unit and/or other special purpose co-processing units. In embodiments having multiple instruction execution units 108, one or more of the units can be implemented, for example, to operate in parallel. Instruction execution unit(s) 108 interface with data cache 110, register file 114, and a results buffer (not shown).
  • Data cache 110 is an on-chip memory array. Data cache 110 is preferably virtually indexed and physically tagged. Data cache 110 interfaces with instruction execution unit(s) 108.
  • Register file 114 represents a plurality of general purpose registers, which are visible to a programmer. Each general purpose register is a 32-bit or a 64-bit register, for example, used for logical and/or mathematical operations and address calculations. In one embodiment, register file 114 is part of instruction execution unit(s) 108. Optionally, one or more additional register file sets (not shown), such as shadow register file sets, can be included to minimize content switching overhead, for example, during interrupt and/or exception processing.
  • Bus interface unit 116 controls external interface signals for processor 100. In one embodiment, bus interface unit 116 includes a collapsing write buffer used to merge write-through transactions and gather writes from uncached stores. Processor 100 can include other features, and thus it is not limited to having just the specific features described herein.
  • FIG. 2 is a more detailed diagram of processor 100. As illustrated in FIG. 2, processor 100 performs four basic functions: instruction fetch; instruction decode and dispatch; instruction execution; and instruction graduation. These four basic functions are illustrative and not intended to limit the present invention.
  • Instruction fetch (represented in FIG. 1 by instruction fetch unit 102) begins when a PC selector 202 selects amongst a variety of program counter values and determines a value that is used to fetch an instruction from instruction cache 104. In one embodiment, the program counter value selected is the program counter value of a new program thread, the next sequential program counter value for an existing program thread, or a redirect program counter value associated with a branch instruction or a jump instruction. After each instruction is fetched, PC selector 202 selects a new value for the next instruction to be fetched.
  • During instruction fetch, tags associated with an instruction to be fetched from instruction cache 104 are checked. In one embodiment, the tags contain precode bits for each instruction indicating instruction type. If these precode bits indicate that an instruction is a control transfer instruction, a branch history table is accessed and used to determine whether the control transfer instruction is likely to branch or likely not to branch.
  • In one embodiment, any compressed-format instructions that are fetched are recoded by an optional instruction recoder 204 into a format that can be decoded and executed by processor 100. For example, in one embodiment in which processor 100 implements both 16-bit instructions and 32-bit instructions, any 16-bit compressed-format instructions are recoded by instruction recoder 204 to form instructions having 32 bits. In another embodiment, instruction recoder 204 recodes both 16-bit instructions and 32-bit instructions to a format having more than 32 bits.
  • After optional recoding, instructions are written to an instruction buffer 206. In one embodiment, this stage can be bypassed and instructions can be dispatched directly to instruction decoder 208.
  • Instruction decode and dispatch (represented in FIG. 1 by instruction decode and dispatch unit 106) begins, for example, when one or more instructions are received from instruction buffer 206 and decoded by an instruction decoder 208. In one embodiment, following resolution of a branch misprediction, the ability to receive instructions from instruction buffer 206 may be temporarily halted until selected instructions residing within the instruction execution portion and/or instruction graduation portion of processor 100 are purged.
  • In parallel with instruction decoding, operands are renamed. Register renaming map(s) located within instruction identification (ID) generator and operand renamer 210 are updated and used to determine whether required source operands are available, for example, in register file 114 and/or a results buffer 218. A register renaming map is a structure that holds the mapping information between programmer visible architectural registers and internal physical registers of processor 100. Register renaming map(s) indicate whether data is available and where data is available. As will be understood by persons skilled in the relevant arts given the description herein, register renaming is used to remove instruction output dependencies and to ensure that there is a single producer of a given register in processor 100 at any given time. Source registers are renamed so that data is obtained from a producer at the earliest opportunity instead of waiting for the processor's architectural state to be updated. In parallel with instruction decoding, instruction ID generator and operand renamer 210 generates and assigns an instruction ID tag to each instruction. An instruction ID tag assigned to an instruction is used, for example, to determine the program order of the instruction relative to other instructions. In one embodiment, each instruction ID tag is a thread-specific sequentially generated value that uniquely determines the program order of instructions. The instruction ID tags can be used to facilitate graduating instructions in program order, which were executed out of program order.
  • Each decoded instruction is assigned a results buffer identification value or tag by a results buffer allocater 212. The results buffer identification value determines the location in results buffer 218 where instruction execution unit(s) 108 can write calculated results for an instruction. In one embodiment, the assignment of results buffer identification values are accomplished using a free list. The free list contains as many entries as the number of entries in results buffer 218. The free list can be implemented, for example, using a bitmap. A first bit of the bitmap can be used to indicate whether the results buffer entry is either available (e.g., if the bit has a value of one) or unavailable (e.g., if the bit has a value of zero).
  • As described in more detail below, assigned results buffer identification values are written into a graduation buffer 224. In one embodiment, results buffer completion bits associated with newly renamed instructions are reset/cleared to indicate incomplete results. As instructions complete execution, their corresponding results buffer completion bits are set, thereby enabling the instructions to graduate and release their associated results buffer identification values. In one embodiment, control logic (not shown) ensures that one program thread does not consume more than its share of results buffer entries.
  • Decoded instructions are written to a decoded instruction buffer 214. An instruction dispatcher 216 selects instructions residing in decoded instruction buffer 214 for dispatch to execution unit(s) 108. In embodiments, instructions can be dispatched for execution out of program order. In one embodiment, instructions are selected and dispatched, for example, based on their age (ID tags) assuming that their operands are determined to be ready.
  • Instruction execution unit(s) 108 execute instructions as they are dispatched. During execution, operand data is obtained as appropriate from data cache 110, register file 114, and/or results buffer 218. A result calculated by instruction execution unit(s) 108 for a particular instruction is written to a location/entry of results buffer 218 specified by the instruction's associated results buffer identification value.
  • Instruction graduation (represented in FIG. 1 by instruction graduation unit 112) is controlled by a graduation controller 220. Graduation controller 220 graduates instructions in accordance with the results buffer identification values stored in graduation buffer 224. When an instruction graduates, its associated result is transferred from results buffer 218 to register file 114. In conjunction with instruction graduation, graduation controller 220 updates, for example, the free list of results buffer allocater 212 to indicate a change in availability status of the graduating instruction's assigned results buffer identification value.
  • FIG. 3 is a diagram of a graduation controller 220 a and a graduation buffer 224 a according to a embodiment present invention. In this embodiment, a single instruction is identified for graduation by graduation controller 220 during each instruction graduation cycle.
  • Graduation controller 220 a includes a plurality of 2-to-1 multiplexers 302, a plurality of registers 304, and an N-to-1 multiplexer 306. Graduation controller 220 a also includes a plurality of registers 308 and an N-to-1 multiplexer 310. Graduation buffer 224 a stores one or more linked-list data structures, each one being associated with a particular program thread that is running on processor 100. Each of the linked-list data structures has an associated head identification (ID) value and an associated tail ID value.
  • As shown in FIG. 3, each of the 2-to-1 multiplexers 302 is coupled to results buffer allocater 212 (see FIG. 2) and a read data bus of graduation buffer 224 a. The outputs of 2-to-1 multiplexers 302 are coupled to the inputs of registers 304. Each register 304 stores a head ID value that is associated with a particular linked-list data structure for a program thread. The output of each register 304 is coupled to N-to-1 multiplexer 306. The output of N-to-1 multiplexer 306 is coupled to a read address bus of graduation buffer 224 a and to results buffer 218. Results buffer allocater 212 is also coupled to a write data bus of graduation buffer 224 a and to the input of each register 308. Each register 308 stores a tail ID value that is associated with a particular linked-list data structure for a program thread. The output of each register 308 is coupled to N-to-1 multiplexer 310. The output of N-to-1 multiplexer 310 is coupled to a write address bus of graduation buffer 224 a.
  • In an embodiment, graduation controller 220 a operates as follows. Results buffer allocater 212 assigns (allocates) a results buffer ID value (new ID) to an instruction being decoded by instruction decoder 208. This new ID is provided to the inputs of 2-to-1 multiplexers 302, a write data bus of graduation buffer 224 a, and the inputs of registers 308. This new ID is stored by the appropriate thread tail ID register 308 and, if appropriate, thread head ID register 304. For example, if a first new ID value (e.g., buffer ID 0) is allocated by results buffer allocater 212 for an instruction associated with program thread 1, and if graduation buffer 224 a currently does not store any ID values associated with program thread 1, the new ID value is stored by thread head ID register 304 b and thread tail ID register 308 b. If a second new ID value (e.g., buffer ID 5) associated with program thread 1 is then allocated before the instruction associated with the first new ID graduates, the second new ID value (buffer ID 5) is written to a memory location 312 (i.e., a memory location linked to buffer ID 0). Register 308 b is accordingly updated to store the second new ID (buffer ID 5) and point to the tail of the linked-list data structure formed for program thread 1.
  • As shown in FIG. 3, graduation buffer 224 a also stores a linked list data structure for program thread 0 and a linked list data structure for program thread N. The linked-list data structure stored for program thread 0 is {(6-7), (7-9)}. The linked-list data structure stored for program thread N is {(10-N), N−1)}.
  • When an instruction graduates, the appropriate thread head ID register 304 is updated to point to the new head value of the linked-list data structure stored. For example, assume that the next instruction to graduate is an instruction associated with program thread 0. As can be seen by looking a thread head ID register 304 a, the calculated result for this instruction is stored in results buffer entry 6. Thus, when the thread selection value provided to N-to-1 multiplexer 306 selects thread 0, the output of N-to-1 multiplexer 306 will be 6. This value (i.e., 6) is placed on the read address bus of graduation buffer 224 a, and the associated next ID value (i.e., 7) is provided by the read data bus of graduation buffer 224 a to an input of 2-to-1 multiplexer 302 a and stored by thread 0 head ID register 304 a. In a similar manner, if the next instruction to graduate is an instruction associated with program thread N, register 304 n will be updated to store the next ID value (i.e., 1) associated with buffer ID N.
  • As described herein, the total number of program threads running on processor 100 at any given time is variable from one up to a maximum number of threads (e.g., N) supported by processor 100. The number of graduation buffer entries that can be allocated to a particular program thread is independent of the number of threads that can run on processor 100. For example, a single thread can be allocated all of the graduation buffer entries to achieve a maximum single-threaded performance. This point is further illustrated by FIG. 4.
  • FIG. 4 illustrates the relationship between results buffer allocater 212, results buffer 218, and graduation buffer 224 a according to an embodiment of the present invention. It also shows the type of information stored by these components. In the example depicted in FIG. 4, only a single program thread is running on processor 100. Since only a single program thread (e.g., program thread 0) is running on processor 100, the control logic required to support multiple program threads (shown in FIG. 3) is not shown for purposes of clarity.
  • As shown in FIG. 4, results buffer allocater 212 has allocated six results buffer entries to store the results of six instructions belonging to program thread 0. Results buffer entry 6 (represented as Buffer ID 6) has been assigned to an instruction having instruction ID 0. Results buffer entries 0, 5, 7, 10, and N have been assigned to instructions having instruction IDs 1, 2, 3, 4, and 5, respectively. As illustrated by these values, results buffer allocater 212 assigns the entries of results buffer 218 independently of program threads (i.e., there is no limitation regarding with entries of results buffer 218 can be assigned to an instruction based on the program thread to which the instruction belongs.)
  • In the example of FIG. 4, graduation buffer 224 a stores a single linked-list data structure associated with program thread 0. The elements of the linked-list data structure are (6, 0), (0, 5), (5, 7), (7, 10), and (10, N). The head ID value of the linked-list data structure (6) is stored in register 304 a. The tail ID value of the linked-list data structure (N) is stored in register 308 a. The next instruction to graduate is instruction ID 0, whose calculated resultant value (A) is stored in buffer entry 6 of results buffer 218. Upon graduation of instruction ID 0, the value A stored in buffer entry 6 will be written to a general purpose register of register file 114. Buffer entry 6 will then become available to be assigned/allocated to a new instruction by results buffer allocater 212.
  • Results buffer 218 in FIG. 4 is shown storing a plurality of values. For example, as noted above, buffer entry 6 stores the value A. Buffer entries 0, 5, 7, 10, and N are shown storing values B, C, D, E, and F, respectively. In one embodiment, whether or not the stored values are valid is determine, for example, by a valid bit stored with each entry of results buffer 218. However, bits used to determine whether an entry is valid or not valid need not be store in results buffer 218. Other means for determining whether an entry is valid or not valid can also be used.
  • FIG. 5 depicts a Table 1 that further illustrates operation of processor 100. In the embodiment represented by FIG. 5, processor 100 includes the graduation controller 220 a and the graduation buffer 224 a shown, for example, in FIG. 3. As noted in FIG. 5, Table 1 depicts an example ten-cycle clock-by-clock progress of buffer entry allocations and graduation of values stored in results buffer 218 for a case in which processor 100 is executing a single program thread.
  • In clock cycle 1 of Table 1, results buffer allocater 212 of instruction decode and dispatch unit 106 allocates entry 0 of results buffer 218 to a first instruction of a program thread, for example, program thread 0. It is assumed for this example that this is the only buffer entry currently allocated to an instruction belonging to program thread 0. Accordingly, their is no associated linked-list data structure presently stored in graduation buffer 224 a for program thread 0, and the thread head ID register and the thread tail ID register do not yet contain valid values. The allocated buffer entry ID 0 is provided to graduation controller 220 a as the New ID shown, for example, in FIG. 4.
  • In clock cycle 2 of Table 1, as shown by arrows, graduation controller 220 a updates the thread head ID register 304 and the thread tail ID register 308 with the buffer entry ID value 0 (i.e., the New ID) allocated by results buffer allocater 212 during clock cycle 1. In clock cycle 2, as shown in FIG. 5, results buffer allocater 212 allocates buffer entry 5 to a second instruction of program thread 0. This value (5) is provided to graduation controller 220 a as illustrated, for example, in FIG. 4. The value 5 is stored in the next ID entry of buffer ID 0, which is the write address specified by the value stored in tail ID register 308, during clock cycle 3.
  • In clock cycle 3 of Table 1, results buffer allocater 212 allocates buffer entry 7 to a third instruction of program thread 0. As shown in FIG. 5 by arrows, the value 7 is stored in the next ID entry of buffer ID 5, which is the write address specified by the value stored in tail ID register 308, during clock cycle 4. As noted above, in clock cycle 3, graduation controller 220 a stores the value 5 in the next ID entry of buffer ID 0 (see, e.g., location 312 of graduation buffer 224 a in FIG. 3). Graduation controller 220 a also updates thread tail ID register 308 to contain the value 5. As no instruction has yet graduated, the value of thread head ID register 304 remains unchanged.
  • In clock cycle 4 of Table 1, results buffer allocater 212 allocates buffer entry 10 to a fourth instruction of program thread 0. Graduation controller 220 a updates thread tail ID register 308 to contain the value 7, which was allocated by results buffer allocater 212 in clock cycle 3. In clock cycle 4, the result stored in entry 0 of results buffer 218 is graduated by instruction graduation unit 112. As shown by arrows in FIG. 5, during clock cycle 5, the value 5 stored in the Next ID entry of Buffer ID 0 of graduation buffer 224 a will be used to update head ID register 304 a.
  • In clock cycle 5 of Table 1, results buffer allocater 212 does not allocate any buffer entry to a new instruction. This situation might arise, for example, due to a branch misprediction that resulted in a processing pipeline purge. During this clock cycle, graduation controller 220 a stores the value 10 in the next ID entry of buffer ID 7 of graduation buffer 224 a. As noted above, because an instruction was graduated in the previous clock cycle, graduation controller 220 a updates thread head ID register 304 to contain the new head value of the linked-list data structure (i.e., the value 5 that identifies the next instruction to be graduated by instruction graduation unit 112). Graduation controller 220 a also updates thread tail ID register 308 to contain the value 10, which was allocated during clock cycle 4. In clock cycle 5, the result stored in entry 5 of results buffer 218 is graduated.
  • In clock cycle 6 of Table 1, the result stored in entry 7 of results buffer 218 graduates. To reflect the fact that an instruction graduated during clock cycle 5, graduation controller 220 a updates thread head ID register 304 to contain the value 7 (i.e., the next to graduate).
  • In clock cycle 7 of Table 1, the result stored in entry 10 of results buffer 218 graduates. In this clock cycle, graduation controller 220 a updates thread head ID register 304 to contain the value 10 (i.e., the next to graduate).
  • In clock cycle 8 of Table 1, no activity takes place.
  • In clock cycle 9 of Table 1, results buffer allocater 212 of instruction decode and dispatch unit 106 allocates entry N of results buffer 218 to a fifth instruction of program thread 0. This value (N) is provided to graduation controller 220 a and used to update thread head ID register 304 and thread tail ID register 308 in clock cycle 10.
  • In clock cycle 10 of Table 1, graduation controller 220 a updates thread head ID register 304 and thread tail ID register 308 with the buffer entry ID value N allocated by results buffer allocater 212 during clock cycle 9.
  • FIG. 6 depicts a Table 2 that further illustrates the operation of graduation controller 220 a. As noted in FIG. 6, Table 2 is a thread head ID and thread tail ID update logic table. This logic table provides implementation information regarding graduation controller 220 a to persons skilled in the relevant art(s).
  • FIG. 7 is a diagram of a graduation controller 220 b and a graduation buffer 224 b in accordance with another embodiment of the present invention. In this embodiment, two instructions (or their resulting values stored in results buffer 218) are identified for graduation by graduation controller 220 b during each instruction graduation cycle.
  • As shown in FIG. 7, graduation controller 220 b includes a plurality of thread head ID units 701 and a plurality of thread tail ID units 703. The number of thread head ID units 701 and the number of thread tail ID units 703 is a design choice. Each thread head ID unit 701 is capable of holding two head ID values (head ID-0 and head ID-1). Each thread tail ID unit 703 is capable of holding two tail ID values (tail ID-0 and tail ID-1). The inputs to graduation controller 220 b include a new ID-0 value and a new-ID-1 value generated, for example, by results buffer allocater 212.
  • The head ID units 701 each include a multiplexer 702 and a register 704 that select and store a head ID-0 value. This head ID-0 value is provided to an N-to-1 multiplexer 720 a. The head ID units 701 also each include a multiplexer 706 and a register 708 that select and store a head ID-1 value. This head ID-1 value is provided to an N-to-1 multiplexer 720 b. The interconnections of these components is illustrated in FIG. 7.
  • The tail ID units 703 each include a multiplexer 712 and a register 714 that select and store a tail ID-0 value. This tail ID-0 value is provided to an N-to-1 multiplexer 722 a. The tail ID units 703 also each include a multiplexer 716 and a register 718 that select and store a tail ID-1 value. This tail ID-1 value is provided to an N-to-1 multiplexer 722 b. The interconnections of these components is also illustrated in FIG. 7.
  • As shown in FIG. 7, graduation buffer 224 b includes a plurality of data and address buses. These buses are used to store and to retrieve linked-list data used to determine the order in which instructions are graduated by instruction graduation unit 112. The connections of these buses to graduation controller 220 b and the a new ID-0 value and a new-ID-1 value generated, for example, by results buffer allocater 212 are shown in FIG. 7.
  • In an embodiment, graduation controller 220 b operates as follows. Results buffer allocater 212 assigns (allocates) one or two results buffer ID values (new ID-0 and new ID-1) to one or two instructions of a program thread, respectively, during decoding by instruction decoder 208. The new ID-0 value and the new ID-1 values are processed by the thread tail ID unit 703 associated with the program thread and used, if appropriate, to add one or two new elements to a linked-list data structure residing within graduation buffer 224 b. If the new ID value(s) are associated with a program thread for which there is no current linked-list data structure stored within graduation buffer 224 b, the new ID value(s) are processed and stored by the appropriate register(s) 704 and 708 of a thread head ID unit 701. When one or two instructions of a program thread are graduated, the head ID unit associated with the program thread is updated to store the value(s) of the next instruction(s) of the program thread to be graduated.
  • To better understand the operation of graduation controller 220 b and graduation buffer 224 b, an example in which only a single program thread is running on processor 100 is provided below. This example is described with reference to FIGS. 8 and 9.
  • FIG. 8 is a simplified diagram of graduation controller 220 b and graduation buffer 224 b. FIG. 8 represents an example implementation in which only a single program thread (thread-0) is running on processor 100. In particular, FIG. 8 depicts the state of graduation controller 220 b and graduation buffer 224 b for clock cycle 5 of Table 3 (see FIG. 9). Since only a single program thread is running on processor 100 in this example, the control logic required to support multiple program threads (shown in FIG. 7) is not depicted for purposes of clarity.
  • As can be seen in FIG. 8, graduation controller 220 b and graduation buffer 224 b store elements of a linked-list data structure associated with program thread-0. The head of the linked-list data structure (results buffer entry 10) is stored in head ID-0 register 704 a. The second element of the linked-list data structure (results buffer entry 12) is stored in head ID-1 register 708 a. The tail value of the linked-list data structure (results buffer entry 15) is stored in tail ID-1 register 718 a. The next to the last element of the linked-list data structure (results buffer entry 12) is stored in tail ID-0 register 714 a. Based on this information, one can discern that the elements of the linked-list data structure are (10, 12) and (12, 15).
  • In the next clock cycle, if both the results stored in results buffer entry 10 and results buffer entry 12 graduate, and no new results buffer entry is allocated to an instruction belonging to program thread 0, the value 15 will be read from graduation buffer 224 b and stored in head ID-0 register 704 a. Because no valid value is stored in graduation buffer 224 b for buffer ID 12, the value stored by head ID-1 register 708 a will be treated as invalid. The value 15 stored by tail ID-1 register 718 a will be transferred to tail ID-0 register 714 a. The value stored by tail ID-1 register 718 a will be treated as invalid.
  • In the next clock cycle, if only the result stored in results buffer entry 10 is graduated, and no new results buffer entry is allocated to an instruction belonging to program thread 0, the value 12 stored by head ID-1 register 708 a will be transferred to head ID-0 register 704 a, and the value 15 will be read from graduation buffer 224 b and stored in head ID-1 register 708 a. Because no valid value is stored in graduation buffer 224 b for buffer ID 12, the value stored by head ID-1 register 708 a will be treated as invalid. The value 15 stored by tail ID-1 register 718 a will be transferred to tail ID-0 register 714 a. The value stored by tail ID-1 register 718 a will be treated as invalid.
  • A more detailed explanation of the operation of graduation controller 220 b and graduation buffer 224 b is illustrated by Table 3 of FIG. 9.
  • FIG. 9 depicts a Table 3 that further illustrates the operation of graduation controller 220 b and graduation buffer 224 b. As noted in FIG. 9, Table 3 depicts an example eight-cycle clock-by-clock progress of buffer entry allocation and graduation of values stored in results buffer 218, for a case in which processor 100 is executing a single program thread.
  • In clock cycle 1 of Table 3, results buffer allocater 212 of instruction decode and dispatch unit 106 allocates entry 0 of results buffer 218 to a first instruction of a program thread, for example, program thread 0. This allocated buffer entry ID (e.g., New ID-0 shown in FIG. 8) is provided to graduation controller 220 b. It is assumed for this example that this is the only buffer entry currently allocated to program thread 0. Thus, their is no associated linked-list data structure presently stored by graduation controller 220 b and graduation buffer 224 a for program thread 0, and the thread head ID unit 701 a and the thread tail ID unit 703 a do not yet contain valid values.
  • In clock cycle 2 of Table 3, as shown by arrows, graduation controller 220 b updates thread head ID-0 register 704 a and thread tail ID-0 register 714 a with buffer entry ID value 0, which was allocated by results buffer allocater 212 during clock cycle 1. As shown in FIG. 9, in clock cycle 2, results buffer allocater 212 allocates buffer entry 5 to a second instruction of program thread 0 and buffer entry 7 to a third instruction of program thread 0. These values, as shown by arrows in FIG. 9, are used to update head ID-1 register 708 a, tail ID-0 register 714 a, and tail ID-1 register 718 a in clock cycle 3. No instructions are graduated during this clock cycle.
  • In clock cycle 3 of Table 3, results buffer allocater 212 allocates buffer entry 10 to a fourth instruction of program thread 0 and buffer entry 12 to a fifth instruction of program thread 0. During this clock cycle, graduation controller 220 b stores the value 7 in the next ID entry of buffer ID 0 of graduation buffer 224 b, which was the address pointed to by tail ID-0 register 714 a during the previous clock cycle. Graduation controller 220 b updates head ID-1 register 708 a and thread tail ID-0 register 714 a to contain the value 5. Tail ID-1 register 718 a is updated to hold the value 7. In clock cycle 3, the results stored in entries 0 and 5 of results buffer 218 are graduated by instruction graduation unit 112.
  • In clock cycle 4 of Table 3, results buffer allocater 212 allocates buffer entry 15 to a sixth instruction of program thread 0. During this clock cycle, graduation controller 220 b stores the values 10 and 12 in the next ID entries of buffer IDs 5 and 7, respectively, of graduation buffer 224 b. Graduation controller 220 b updates head ID-0 register 704 a to contain the value 7 read from buffer ID entry 0 of graduation buffer 224 b. Graduation controller 220 b also updates head ID-1 register 708 a and thread tail ID-0 register 714 a to contain the value 10, and thread tail ID-1 register 718 a to contain the value 12. In clock cycle 4, the result stored in entry 7 of results buffer 218 is graduated by instruction graduation unit 112.
  • In clock cycle 5 of Table 3, results buffer allocater 212 allocates buffer entry 21 to a seventh instruction of program thread 0 and buffer entry 22 to an eight instruction of program thread 0. During this clock cycle, graduation controller 220 b stores the value 15 in the next ID entry of buffer ID 10 of graduation buffer 224 b. Graduation controller 220 b updates head ID-0 register 704 a to contain the value 10 read from head ID-1 register 708 a. Graduation controller 220 b updates head ID-1 register 708 a to contain the value 12 read from buffer ID entry 7. Graduation controller 220 b updates tail ID-0 register 714 a to contain the value 12 read from tail ID-1 register 718 a. Graduation controller 220 b updates tail ID-1 register 718 a to contain the value 15 provided by results buffer allocater 212 as a new ID-0 value during clock cycle 4. In clock cycle 5, the results stored in entries 10 and 12 of results buffer 218 are graduated by instruction graduation unit 112. It is this logic state of graduation controller 220 b and graduation buffer 224 b that is depicted in FIG. 8.
  • In clock cycle 6 of Table 3, results buffer allocater 212 allocates buffer entry N to a ninth instruction of program thread 0. As shown by arrows in FIG. 9, the value N is stored in the next ID entry of buffer ID 21, which is the write address specified by the value stored in tail ID-0 register 714 a, during clock cycle 7. In clock cycle 6, graduation controller 220 b updates head ID-0 register 704 a to contain the value 15 read from buffer ID entry 10. Graduation controller 220 b updates head ID-1 register 708 a and tail ID-0 register 714 a to contain the value 21 allocated by results buffer allocater 212 in clock cycle 5. Graduation controller 220 b updates tail ID-1 register 718 a to contain the value 22 provided by results buffer allocater 212 as a new ID-1 value in clock cycle 5. In clock cycle 6, the instruction result stored in entry 15 of results buffer 218 is graduated by instruction graduation unit 112.
  • In clock cycle 7 of Table 3, graduation controller 220 b updates head ID-0 register 704 a to contain the value 21. Graduation controller 220 b updates head ID-1 register 708 a and tail ID-0 register 714 a to contain the value 22. Graduation controller 220 b updates tail ID-1 register 718 a to contain the value N. During this clock cycle, the results stored in entries 21 and 22 of results buffer 218 are graduated by instruction graduation unit 112.
  • In clock cycle 8 of Table 3, graduation controller 220 b updates head ID-0 register 704 a and tail ID-0 register 714 a to contain the value N. In this clock cycle, the instruction result stored in entry N of results buffer 218 is graduated by instruction graduation unit 112.
  • FIG. 10 depicts a Table 4 that also illustrates the operation of graduation controller 220 b. As noted in FIG. 10, Table 4 is an example thread head ID and thread tail ID update logic table. This logic table provides example state and implementation information regarding the various inputs and outputs of graduation controller 220 b. For purposes of brevity and clarity, only a few of the row entries are shown in Table 4. A Person skilled in the relevant art(s) will be able to populate all of the row entries of Table 4 given the description of the present invention provided herein.
  • While various embodiments of the present invention have been described above, it should be understood that they have been presented by way of example, and not limitation. It will be apparent to persons skilled in the relevant computer arts that various changes in form and detail can be made therein without departing from the spirit and scope of the invention. Furthermore, it should be appreciated that the detailed description of the present invention provided herein, and not the summary and abstract sections, is intended to be used to interpret the claims. The summary and abstract sections may set forth one or more but not all exemplary embodiments of the present invention as contemplated by the inventors.
  • For example, in addition to implementations using hardware (e.g., within or coupled to a Central Processing Unit (“CPU”), microprocessor, microcontroller, digital signal processor, processor core, System on Chip (“SOC”), or any other programmable or electronic device), implementations may also be embodied in software (e.g., computer readable code, program code, instructions and/or data disposed in any form, such as source, object or machine language) disposed, for example, in a computer usable (e.g., readable) medium configured to store the software. Such software can enable, for example, the function, fabrication, modeling, simulation, description, and/or testing of the apparatus and methods described herein. For example, this can be accomplished through the use of general programming languages (e.g., C, C++), GDSII databases, hardware description languages (HDL) including Verilog HDL, VHDL, SystemC Register Transfer Level (RTL) and so on, or other available programs, databases, and/or circuit (i.e., schematic) capture tools. Such software can be disposed in any known computer usable medium including semiconductor, magnetic disk, optical disk (e.g., CD-ROM, DVD-ROM, etc.) and as a computer data signal embodied in a computer usable (e.g., readable) transmission medium (e.g., carrier wave or any other medium including digital, optical, or analog-based medium). As such, the software can be transmitted over communication networks including the Internet and intranets.
  • It is understood that the apparatus and method embodiments described herein may be included in a semiconductor intellectual property core, such as a microprocessor core (e.g., embodied in HDL) and transformed to hardware in the production of integrated circuits. Additionally, the apparatus and methods described herein may be embodied as a combination of hardware and software. Thus, the present invention should not be limited by any of the above-described exemplary embodiments, but should be defined only in accordance with the following claims and their equivalence.

Claims (24)

1. A processor, comprising:
a results buffer having a plurality of registers, each register for temporarily storing a result of an executed instruction prior to the result being written to a register file;
a results buffer allocater that generates identification values, wherein each identification value identifies a register of the results buffer in which an executed instruction's result can be temporarily stored; and
a graduation buffer having a plurality of registers, wherein identification values generated by the results buffer allocater are temporarily stored as part of a linked-list data structure.
2. The processor of claim 1, wherein identification values generated by the results buffer allocater are temporarily stored as part of a plurality of linked-list data structures, each linked-list data structure being associated with a particular program thread.
3. The processor of claim 1, further comprising:
a graduation controller, coupled to the graduation buffer, that includes a linked-list head identification register and a linked-list tail identification register.
4. The processor of claim 3, wherein the graduation controller includes a plurality of linked-list head identification registers and a plurality of linked-list tail identification registers.
5. The processor of claim 1, further comprising:
a graduation controller, coupled to the graduation buffer, that includes
a plurality of linked-list head identification units each having a first linked-list head identification register and a second linked-list head identification register, and
a plurality of linked-list tail identification units each having a first linked-list tail identification register and a second linked-list tail identification register.
6. The processor of claim 1, wherein the graduation controller specifies a plurality of results to be written to the register file in a particular clock cycle of the processor.
7. An instruction graduation unit for a processor, comprising:
a graduation buffer having a plurality of registers, wherein identification values generated by an instruction decode and dispatch unit of a processor are temporarily stored as part of a linked-list data structure; and
a graduation controller, coupled to the graduation buffer, that includes a linked-list head identification register and a linked-list tail identification register.
8. The instruction graduation unit of claim 7, wherein identification values generated by the instruction decode and dispatch unit are temporarily stored as part of a plurality of linked-list data structures, each linked-list data structure being associated with a particular program thread.
9. The instruction graduation unit of claim 7, wherein the graduation controller includes a plurality of linked-list head identification registers and a plurality of linked-list tail identification registers.
10. The instruction graduation unit of claim 7, wherein the graduation controller specifies a plurality of results to be written from a results buffer to a register file in a particular clock cycle of a processor.
11. A computer readable storage medium comprising a processor embodied in software, the processor comprising:
a results buffer having a plurality of registers, each register for temporarily storing a result of an executed instruction prior to the result being written to a register file;
a results buffer allocater that generates identification values, wherein each identification value identifies a register of the results buffer in which an executed instruction's result can be temporarily stored; and
a graduation buffer having a plurality of registers, wherein identification values generated by the results buffer allocater are temporarily stored as part of a linked-list data structure.
12. The computer readable storage medium of claim 11, wherein identification values generated by the results buffer allocater are temporarily stored as part of a plurality of linked-list data structures, each linked-list data structure being associated with a particular program thread.
13. The computer readable storage medium of claim 11, wherein the processor further comprises:
a graduation controller, coupled to the graduation buffer, that includes a linked-list head identification register and a linked-list tail identification register.
14. The computer readable storage medium of claim 13, wherein the graduation controller includes a plurality of linked-list head identification registers and a plurality of linked-list tail identification registers.
15. The computer readable storage medium of claim 11, wherein the graduation controller specifies a plurality of results to be written to the register file in a particular clock cycle of the processor.
16. The computer readable storage medium of claim 11, wherein the processor is embodied in hardware description language software.
17. The computer readable storage medium of claim 16, wherein the processor core is embodied in one of Verilog hardware description language software and VHDL hardware description language software.
18. A computer readable storage medium comprising an instruction graduation unit for a processor embodied in software, the instruction graduation unit comprising:
a graduation buffer having a plurality of registers, wherein identification values generated by an instruction decode and dispatch unit of a processor are temporarily stored as part of a linked-list data structure; and
a graduation controller, coupled to the graduation buffer, that includes a linked-list head identification register and a linked-list tail identification register.
19. The computer readable storage medium of claim 18, wherein identification values generated by the instruction decode and dispatch unit are temporarily stored as part of a plurality of linked-list data structures, each linked-list data structure being associated with a particular program thread.
20. The computer readable storage medium of claim 19, wherein the graduation controller includes a plurality of linked-list head identification registers and a plurality of linked-list tail identification registers.
21. The computer readable storage medium of claim 18, wherein the graduation controller specifies a plurality of results to be written from a results buffer to a register file in a particular clock cycle of a processor.
22. The computer readable storage medium of claim 18, wherein the instruction graduation unit is embodied in hardware description language software.
23. A method for controlling the order in which instruction results are written to a register file of a processor, the method comprising:
assigning a first identification value to a first instruction of a program thread, a second identification value to a second instruction of the program thread, and a third identification value to a third instruction of the program thread, wherein the first identification value specifies where in a first buffer of a processor a result of the first instruction is to be written by an execution unit of the processor, the second identification value specifies where in the first buffer a result of the second instruction is to be written by the execution unit, and the third identification value specifies where in the first buffer a result of the third instruction is to be written by the execution unit;
writing the first identification value to a first register of a second buffer of the processor, the second identification value to a second register of the second buffer, and the third identification value to a third register of the second buffer, wherein the first identification value, the second identification value, and the third identification value form part of a linked-list data structure; and
writing results stored in the first buffer to a register file of the processor in an order determined by the values that form the linked-list data structure.
24. The method of claim 23, further comprising:
assigning a fourth identification value to a first instruction of a second program thread, a fifth identification value to a second instruction of the second program thread, and a sixth identification value to a third instruction of the second program thread, wherein the fourth identification value specifies where in the first buffer of t processor a result of the first instruction of the second program thread is to be written by the execution unit of the processor, the fifth identification value specifies where in the first buffer a result of the second instruction of the second program thread is to be written by the execution unit, and the sixth identification value specifies where in the first buffer a result of the third instruction of the second program thread is to be written by the execution unit;
writing the fourth identification value to a fourth register of the second buffer of the processor, the fifth identification value to a fifth register of the second buffer, and the sixth identification value to a sixth register of the second buffer, wherein the fourth identification value, the fifth identification value, and the sixth identification value form part of a second linked-list data structure; and
writing results stored in the first buffer, for instructions belonging to the second program thread, to the register file of the processor in an order determined by the values that form the second linked-list data structure.
US11362763 2006-02-28 2006-02-28 Compact linked-list-based multi-threaded instruction graduation buffer Abandoned US20070204139A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US11362763 US20070204139A1 (en) 2006-02-28 2006-02-28 Compact linked-list-based multi-threaded instruction graduation buffer

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US11362763 US20070204139A1 (en) 2006-02-28 2006-02-28 Compact linked-list-based multi-threaded instruction graduation buffer
US14494167 US9851975B2 (en) 2006-02-28 2014-09-23 Compact linked-list-based multi-threaded instruction graduation buffer
US15842398 US20180107486A1 (en) 2006-02-28 2017-12-14 Compact linked-list-based multi-threaded instruction graduation buffer

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US14494167 Continuation US9851975B2 (en) 2006-02-28 2014-09-23 Compact linked-list-based multi-threaded instruction graduation buffer

Publications (1)

Publication Number Publication Date
US20070204139A1 true true US20070204139A1 (en) 2007-08-30

Family

ID=38445410

Family Applications (3)

Application Number Title Priority Date Filing Date
US11362763 Abandoned US20070204139A1 (en) 2006-02-28 2006-02-28 Compact linked-list-based multi-threaded instruction graduation buffer
US14494167 Active 2026-09-09 US9851975B2 (en) 2006-02-28 2014-09-23 Compact linked-list-based multi-threaded instruction graduation buffer
US15842398 Pending US20180107486A1 (en) 2006-02-28 2017-12-14 Compact linked-list-based multi-threaded instruction graduation buffer

Family Applications After (2)

Application Number Title Priority Date Filing Date
US14494167 Active 2026-09-09 US9851975B2 (en) 2006-02-28 2014-09-23 Compact linked-list-based multi-threaded instruction graduation buffer
US15842398 Pending US20180107486A1 (en) 2006-02-28 2017-12-14 Compact linked-list-based multi-threaded instruction graduation buffer

Country Status (1)

Country Link
US (3) US20070204139A1 (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2492457A (en) * 2011-06-29 2013-01-02 Ibm Predicting out of order instruction level parallelism of threads in a multi-threaded processor
CN104572020A (en) * 2014-12-31 2015-04-29 中国电子科技集团公司第三十八研究所 Register file paged expansion device and achievement method thereof
US9851975B2 (en) 2006-02-28 2017-12-26 Arm Finance Overseas Limited Compact linked-list-based multi-threaded instruction graduation buffer

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2017134651A1 (en) * 2016-02-01 2017-08-10 Shapedo Ltd. Comparing and merging complex data structures
US10083127B2 (en) 2016-08-22 2018-09-25 HGST Netherlands B.V. Self-ordering buffer

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6721874B1 (en) * 2000-10-12 2004-04-13 International Business Machines Corporation Method and system for dynamically shared completion table supporting multiple threads in a processing system
US20040210743A1 (en) * 2003-04-21 2004-10-21 International Business Machines Corporation Dynamically shared group completion table between multiple threads
US6931639B1 (en) * 2000-08-24 2005-08-16 International Business Machines Corporation Method for implementing a variable-partitioned queue for simultaneous multithreaded processors

Family Cites Families (70)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5109520A (en) 1985-02-19 1992-04-28 Tektronix, Inc. Image frame buffer access speedup by providing multiple buffer controllers each containing command FIFO buffers
US5021945A (en) 1985-10-31 1991-06-04 Mcc Development, Ltd. Parallel processor system for processing natural concurrencies and method therefor
US5781753A (en) 1989-02-24 1998-07-14 Advanced Micro Devices, Inc. Semi-autonomous RISC pipelines for overlapped execution of RISC-like instructions within the multiple superscalar execution units of a processor having distributed pipeline control for speculative and out-of-order execution of complex instructions
US5091851A (en) 1989-07-19 1992-02-25 Hewlett-Packard Company Fast multiple-word accesses from a multi-way set-associative cache memory
US5440749A (en) 1989-08-03 1995-08-08 Nanotronics Corporation High performance, low cost microprocessor architecture
EP0461923B1 (en) 1990-06-15 1997-10-01 Compaq Computer Corporation True least recently used replacement apparatus
EP0871108B1 (en) 1991-03-11 2000-09-13 MIPS Technologies, Inc. Backward-compatible computer architecture with extended word size and address space
US5961629A (en) 1991-07-08 1999-10-05 Seiko Epson Corporation High performance, superscalar-based computer system with out-of-order instruction execution
US5493667A (en) 1993-02-09 1996-02-20 Intel Corporation Apparatus and method for an instruction cache locking scheme
US6079014A (en) 1993-12-02 2000-06-20 Intel Corporation Processor that redirects an instruction fetch pipeline immediately upon detection of a mispredicted branch while committing prior instructions to an architectural state
US5740402A (en) 1993-12-15 1998-04-14 Silicon Graphics, Inc. Conflict resolution in interleaved memory systems with multiple parallel accesses
US5526504A (en) 1993-12-15 1996-06-11 Silicon Graphics, Inc. Variable page size translation lookaside buffer
US5510934A (en) 1993-12-15 1996-04-23 Silicon Graphics, Inc. Memory system including local and global caches for storing floating point and integer data
US5493523A (en) 1993-12-15 1996-02-20 Silicon Graphics, Inc. Mechanism and method for integer divide involving pre-alignment of the divisor relative to the dividend
US5604909A (en) 1993-12-15 1997-02-18 Silicon Graphics Computer Systems, Inc. Apparatus for processing instructions in a computing system
US5537538A (en) 1993-12-15 1996-07-16 Silicon Graphics, Inc. Debug mode for a superscalar RISC processor
US5572704A (en) 1993-12-15 1996-11-05 Silicon Graphics, Inc. System and method for controlling split-level caches in a multi-processor system including data loss and deadlock prevention schemes
US6393550B1 (en) 1993-12-30 2002-05-21 Intel Corporation Method and apparatus for pipeline streamlining where resources are immediate or certainly retired
US5452426A (en) 1994-01-04 1995-09-19 Intel Corporation Coordinating speculative and committed state register source data and immediate source data in a processor
US5606683A (en) 1994-01-28 1997-02-25 Quantum Effect Design, Inc. Structure and method for virtual-to-physical address translation in a translation lookaside buffer
US5586278A (en) 1994-03-01 1996-12-17 Intel Corporation Method and apparatus for state recovery following branch misprediction in an out-of-order microprocessor
WO1996012231A1 (en) 1994-10-14 1996-04-25 Silicon Graphics, Inc. A translation buffer for detecting and preventing conflicting virtual addresses from being stored therein
WO1996012229A1 (en) 1994-10-14 1996-04-25 Silicon Graphics, Inc. Indexing and multiplexing of interleaved cache memory arrays
WO1996012228A1 (en) 1994-10-14 1996-04-25 Silicon Graphics, Inc. Redundant mapping tables
US6216200B1 (en) 1994-10-14 2001-04-10 Mips Technologies, Inc. Address queue
US5625789A (en) 1994-10-24 1997-04-29 International Business Machines Corporation Apparatus for source operand dependendency analyses register renaming and rapid pipeline recovery in a microprocessor that issues and executes multiple instructions out-of-order in a single cycle
US5675758A (en) 1994-11-15 1997-10-07 Advanced Micro Devices, Inc. Processor having primary integer execution unit and supplemental integer execution unit for performing out-of-order add and move operations
US5546545A (en) 1994-12-09 1996-08-13 International Business Machines Corporation Rotating priority selection logic circuit
US5675759A (en) 1995-03-03 1997-10-07 Shebanow; Michael C. Method and apparatus for register management using issue sequence prior physical register and register association validity information
US5732242A (en) 1995-03-24 1998-03-24 Silicon Graphics, Inc. Consistently specifying way destinations through prefetching hints
JPH0991136A (en) 1995-09-25 1997-04-04 Toshiba Corp Signal processor
US5764999A (en) 1995-10-10 1998-06-09 Cyrix Corporation Enhanced system management mode with nesting
US5670898A (en) 1995-11-22 1997-09-23 Silicon Graphics, Inc. Low-power, compact digital logic topology that facilitates large fan-in and high-speed circuit performance
US5734881A (en) 1995-12-15 1998-03-31 Cyrix Corporation Detecting short branches in a prefetch buffer using target location information in a branch target cache
US5799165A (en) 1996-01-26 1998-08-25 Advanced Micro Devices, Inc. Out-of-order processing that removes an issued operation from an execution pipeline upon determining that the operation would cause a lengthy pipeline delay
US6108769A (en) 1996-05-17 2000-08-22 Advanced Micro Devices, Inc. Dependency table for reducing dependency checking hardware
GB2317469B (en) 1996-09-23 2001-02-21 Advanced Risc Mach Ltd Data processing system register control
US5966734A (en) 1996-10-18 1999-10-12 Samsung Electronics Co., Ltd. Resizable and relocatable memory scratch pad as a cache slice
US5802386A (en) 1996-11-19 1998-09-01 International Business Machines Corporation Latency-based scheduling of instructions in a superscalar processor
US5909572A (en) 1996-12-02 1999-06-01 Compaq Computer Corp. System and method for conditionally moving an operand from a source register to a destination register
US5864341A (en) 1996-12-09 1999-01-26 International Business Machines Corporation Instruction dispatch unit and method for dynamically classifying and issuing instructions to execution units with non-uniform forwarding
US5974535A (en) 1997-05-09 1999-10-26 International Business Machines Corporation Method and system in data processing system of permitting concurrent processing of instructions of a particular type
US6044478A (en) 1997-05-30 2000-03-28 National Semiconductor Corporation Cache with finely granular locked-down regions
US6076159A (en) 1997-09-12 2000-06-13 Siemens Aktiengesellschaft Execution of a loop instructing in a loop pipeline after detection of a first occurrence of the loop instruction in an integer pipeline
US6085315A (en) 1997-09-12 2000-07-04 Siemens Aktiengesellschaft Data processing device with loop pipeline
US6223278B1 (en) 1998-11-05 2001-04-24 Intel Corporation Method and apparatus for floating point (FP) status word handling in an out-of-order (000) Processor Pipeline
US6308252B1 (en) 1999-02-04 2001-10-23 Kabushiki Kaisha Toshiba Processor method and apparatus for performing single operand operation and multiple parallel operand operation
US6473837B1 (en) 1999-05-18 2002-10-29 Advanced Micro Devices, Inc. Snoop resynchronization mechanism to preserve read ordering
US7401205B1 (en) 1999-08-13 2008-07-15 Mips Technologies, Inc. High performance RISC instruction set digital signal processor having circular buffer and looping controls
US6546477B1 (en) 1999-09-20 2003-04-08 Texas Instruments Incorporated Memory management in embedded systems with dynamic object instantiation
US6446197B1 (en) 1999-10-01 2002-09-03 Hitachi, Ltd. Two modes for executing branch instructions of different lengths and use of branch control instruction and register set loaded with target instructions
US6430655B1 (en) 2000-01-31 2002-08-06 Mips Technologies, Inc. Scratchpad RAM memory accessible in parallel to a primary cache
US20010052053A1 (en) 2000-02-08 2001-12-13 Mario Nemirovsky Stream processing unit for a multi-streaming processor
US6557127B1 (en) 2000-02-28 2003-04-29 Cadence Design Systems, Inc. Method and apparatus for testing multi-port memories
US6915395B1 (en) 2000-05-03 2005-07-05 Sun Microsystems, Inc. Active address content addressable memory
US6757817B1 (en) 2000-05-19 2004-06-29 Intel Corporation Apparatus having a cache and a loop buffer
US7502876B1 (en) 2000-06-23 2009-03-10 Mips Technologies, Inc. Background memory manager that determines if data structures fits in memory with memory state transactions map
US6505285B1 (en) 2000-06-26 2003-01-07 Ncr Corporation Scratch segment subsystem for a parallel processing database system
US7032226B1 (en) 2000-06-30 2006-04-18 Mips Technologies, Inc. Methods and apparatus for managing a buffer of events in the background
US6760835B1 (en) 2000-11-22 2004-07-06 Lsi Logic Corporation Instruction branch mispredict streaming
EP1229338B1 (en) 2001-01-31 2005-11-09 STMicroelectronics S.r.l. A test access port (TAP) management method and system
US7055021B2 (en) 2002-02-05 2006-05-30 Sun Microsystems, Inc. Out-of-order processor that reduces mis-speculation using a replay scoreboard
US6836833B1 (en) 2002-10-22 2004-12-28 Mips Technologies, Inc. Apparatus and method for discovering a scratch pad memory configuration
US20040128483A1 (en) 2002-12-31 2004-07-01 Intel Corporation Fuser renamer apparatus, systems, and methods
US7159103B2 (en) 2003-03-24 2007-01-02 Infineon Technologies Ag Zero-overhead loop operation in microprocessor having instruction buffer
US7418575B2 (en) 2003-07-29 2008-08-26 Stretch, Inc. Long instruction word processing with instruction extensions
US20060095732A1 (en) 2004-08-30 2006-05-04 Tran Thang M Processes, circuits, devices, and systems for scoreboard and other processor improvements
US20070204139A1 (en) 2006-02-28 2007-08-30 Mips Technologies, Inc. Compact linked-list-based multi-threaded instruction graduation buffer
US7370178B1 (en) 2006-07-14 2008-05-06 Mips Technologies, Inc. Method for latest producer tracking in an out-of-order processor, and applications thereof
US20080016326A1 (en) 2006-07-14 2008-01-17 Mips Technologies, Inc. Latest producer tracking in an out-of-order processor, and applications thereof

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6931639B1 (en) * 2000-08-24 2005-08-16 International Business Machines Corporation Method for implementing a variable-partitioned queue for simultaneous multithreaded processors
US6721874B1 (en) * 2000-10-12 2004-04-13 International Business Machines Corporation Method and system for dynamically shared completion table supporting multiple threads in a processing system
US20040210743A1 (en) * 2003-04-21 2004-10-21 International Business Machines Corporation Dynamically shared group completion table between multiple threads

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9851975B2 (en) 2006-02-28 2017-12-26 Arm Finance Overseas Limited Compact linked-list-based multi-threaded instruction graduation buffer
GB2492457A (en) * 2011-06-29 2013-01-02 Ibm Predicting out of order instruction level parallelism of threads in a multi-threaded processor
US9652243B2 (en) 2011-06-29 2017-05-16 International Business Machines Corporation Predicting out-of-order instruction level parallelism of threads in a multi-threaded processor
CN104572020A (en) * 2014-12-31 2015-04-29 中国电子科技集团公司第三十八研究所 Register file paged expansion device and achievement method thereof

Also Published As

Publication number Publication date Type
US20150012730A1 (en) 2015-01-08 application
US20180107486A1 (en) 2018-04-19 application
US9851975B2 (en) 2017-12-26 grant

Similar Documents

Publication Publication Date Title
US5226130A (en) Method and apparatus for store-into-instruction-stream detection and maintaining branch prediction cache consistency
US5907860A (en) System and method of retiring store data from a write buffer
US6826704B1 (en) Microprocessor employing a performance throttling mechanism for power management
US6192465B1 (en) Using multiple decoders and a reorder queue to decode instructions out of order
US5471598A (en) Data dependency detection and handling in a microprocessor with write buffer
US6279105B1 (en) Pipelined two-cycle branch target address cache
US5721857A (en) Method and apparatus for saving the effective address of floating point memory operations in an out-of-order microprocessor
US6038645A (en) Microprocessor circuits, systems, and methods using a combined writeback queue and victim cache
US5913049A (en) Multi-stream complex instruction set microprocessor
US5546597A (en) Ready selection of data dependent instructions using multi-cycle cams in a processor performing out-of-order instruction execution
US5778220A (en) Method and apparatus for disabling interrupts in a highly pipelined processor
US6021485A (en) Forwarding store instruction result to load instruction with reduced stall or flushing by effective/real data address bytes matching
US5632023A (en) Superscalar microprocessor including flag operand renaming and forwarding apparatus
US6349382B1 (en) System for store forwarding assigning load and store instructions to groups and reorder queues to keep track of program order
US5974523A (en) Mechanism for efficiently overlapping multiple operand types in a microprocessor
US6219773B1 (en) System and method of retiring misaligned write operands from a write buffer
US5911057A (en) Superscalar microprocessor having combined register and memory renaming circuits, systems, and methods
US5627985A (en) Speculative and committed resource files in an out-of-order processor
US5913054A (en) Method and system for processing a multiple-register instruction that permit multiple data words to be written in a single processor cycle
US6138230A (en) Processor with multiple execution pipelines using pipe stage state information to control independent movement of instructions between pipe stages of an execution pipeline
US5615385A (en) Method and apparatus for zero extension and bit shifting to preserve register parameters in a microprocessor utilizing register renaming
US20140380023A1 (en) Dependence-based replay suppression
US5630149A (en) Pipelined processor with register renaming hardware to accommodate multiple size registers
US20100332803A1 (en) Processor and control method for processor
US20150095627A1 (en) Two level re-order buffer

Legal Events

Date Code Title Description
AS Assignment

Owner name: MIPS TECHNOLOGIES, INC., CALIFORNIA

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:SVENDSEN, KJELD;REEL/FRAME:017643/0318

Effective date: 20060228

AS Assignment

Owner name: JEFFERIES FINANCE LLC, AS COLLATERAL AGENT, NEW YO

Free format text: SECURITY AGREEMENT;ASSIGNOR:MIPS TECHNOLOGIES, INC.;REEL/FRAME:019744/0001

Effective date: 20070824

Owner name: JEFFERIES FINANCE LLC, AS COLLATERAL AGENT,NEW YOR

Free format text: SECURITY AGREEMENT;ASSIGNOR:MIPS TECHNOLOGIES, INC.;REEL/FRAME:019744/0001

Effective date: 20070824

AS Assignment

Owner name: MIPS TECHNOLOGIES, INC., CALIFORNIA

Free format text: RELEASE BY SECURED PARTY;ASSIGNOR:JEFFERIES FINANCE LLC, AS COLLATERAL AGENT;REEL/FRAME:021985/0015

Effective date: 20081205

Owner name: MIPS TECHNOLOGIES, INC.,CALIFORNIA

Free format text: RELEASE BY SECURED PARTY;ASSIGNOR:JEFFERIES FINANCE LLC, AS COLLATERAL AGENT;REEL/FRAME:021985/0015

Effective date: 20081205

AS Assignment

Owner name: BRIDGE CROSSING, LLC, NEW JERSEY

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:MIPS TECHNOLOGIES, INC.;REEL/FRAME:030202/0440

Effective date: 20130206

AS Assignment

Owner name: ARM FINANCE OVERSEAS LIMITED, GREAT BRITAIN

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:BRIDGE CROSSING, LLC;REEL/FRAME:033074/0058

Effective date: 20140131