US20040158691A1 - Loop handling for single instruction multiple datapath processor architectures - Google Patents
Loop handling for single instruction multiple datapath processor architectures Download PDFInfo
- Publication number
- US20040158691A1 US20040158691A1 US10/770,787 US77078704A US2004158691A1 US 20040158691 A1 US20040158691 A1 US 20040158691A1 US 77078704 A US77078704 A US 77078704A US 2004158691 A1 US2004158691 A1 US 2004158691A1
- Authority
- US
- United States
- Prior art keywords
- datapaths
- array
- loop
- total number
- loop passes
- 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
Links
- 238000000034 method Methods 0.000 claims abstract description 38
- 238000012545 processing Methods 0.000 claims abstract description 38
- 238000012360 testing method Methods 0.000 description 4
- 238000013459 approach Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/30—Arrangements for executing machine instructions, e.g. instruction decode
- G06F9/34—Addressing or accessing the instruction operand or the result ; Formation of operand address; Addressing modes
- G06F9/345—Addressing or accessing the instruction operand or the result ; Formation of operand address; Addressing modes of multiple operands or results
- G06F9/3455—Addressing or accessing the instruction operand or the result ; Formation of operand address; Addressing modes of multiple operands or results using stride
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F15/00—Digital computers in general; Data processing equipment in general
- G06F15/76—Architectures of general purpose stored program computers
- G06F15/80—Architectures of general purpose stored program computers comprising an array of processing units with common control, e.g. single instruction multiple data processors
- G06F15/8007—Architectures of general purpose stored program computers comprising an array of processing units with common control, e.g. single instruction multiple data processors single instruction multiple data [SIMD] multiprocessors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/30—Arrangements for executing machine instructions, e.g. instruction decode
- G06F9/32—Address formation of the next instruction, e.g. by incrementing the instruction counter
- G06F9/322—Address formation of the next instruction, e.g. by incrementing the instruction counter for non-sequential address
- G06F9/325—Address formation of the next instruction, e.g. by incrementing the instruction counter for non-sequential address for loops, e.g. loop detection or loop counter
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/30—Arrangements for executing machine instructions, e.g. instruction decode
- G06F9/34—Addressing or accessing the instruction operand or the result ; Formation of operand address; Addressing modes
- G06F9/345—Addressing or accessing the instruction operand or the result ; Formation of operand address; Addressing modes of multiple operands or results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/30—Arrangements for executing machine instructions, e.g. instruction decode
- G06F9/38—Concurrent instruction execution, e.g. pipeline, look ahead
- G06F9/3885—Concurrent instruction execution, e.g. pipeline, look ahead using a plurality of independent parallel functional units
Definitions
- This invention relates to loop handling operations over an array of data items in a single instruction multiple datapath (SIMD) processor architecture.
- SIMD single instruction multiple datapath
- a SIMD processor is a parallel processor array architecture wherein multiple datapaths are controlled by a single instruction. Each datapath handles one data item at a given time.
- the data items in an eight data item array would be processed in each of the four datapaths in two passes of a loop operation.
- the allocation between datapaths and data items may vary, but in one approach, in a first pass the first data item in the array is processed by a first datapath, a second data item in the array is processed by a second datapath, a third data item is processed by a third datapath, and a fourth data item is processed by a fourth datapath. In a second pass, a fifth data item is processed by the first datapath, a sixth data item is processed by the second datapath, a seventh data item is processed by the third datapath, and an eighth data item is processed by the fourth datapath.
- One way of avoiding such erroneous overwriting is to force the size of the array, i.e., the number of data items contained within the array, to be an integer multiple of the number of datapaths.
- Such an approach assumes that programmers have a priori control of how data items are allocated in the array, which they may not always have.
- each datapath in a SIMD processor has an associated processor enable bit that controls whether a datapath is enabled or disabled. This allows a datapath to be disabled when, e.g., the datapath would otherwise overrun the array.
- the invention features a method of controlling whether to enable one of a plurality of processor datapaths in a SIMD processor that are operating on data elements in an array, including determining whether to enable the datapath based on information about parameters of the SIMD processor and the array, and a processing state of the datapaths relative to the data items in the array.
- the information includes an allocation between the data items and a memory, a total number of parallel loop passes in a loop processing operation being performed by the datapaths, a size of the array, and a number of datapaths (i.e., how many datapaths there are in the SIMD processor).
- the processing state is a number of remaining parallel passes of the datapaths in the loop processing operation.
- the allocation between the data items and the memory may be unity-stride, contiguous or striped-stride.
- the invention features a computer instruction including a loop handling instruction that specifies the enabling of one of a plurality of processor datapaths during processing an array of data items.
- the instruction includes a parallel count field that specifies the number of remaining parallel loop passes to process the array, and a serial count field that specifies the number of serial loop passes to process the array.
- the invention features a processor including a register file and an arithmetic logic unit coupled to the register file, and a program control store that stores a loop handling instruction that causes the processor to enable one of a plurality of processor datapaths during processing of an array of data.
- Embodiments of various aspects of the invention may have, one or more of the following advantages.
- Datapaths may be disabled without having prior knowledge of the number of data items in the array.
- the method is readily extensible to a variety of memory allocation schemes.
- the loop handling instruction saves instruction memory because the many operations needed to determine whether to enable or disable a datapath may be specified with a simple and powerful single instruction that also saves register space.
- the loop handling instruction saves a programmer from having to force the number of data items in the array of data items to be an integer multiple of the number of datapaths.
- FIG. 1 is a block diagram of a single instruction multiple datapath (SIMD) processor.
- SIMD single instruction multiple datapath
- FIG. 2 shows a table of how thirty data items in an array are handled by a SIMD processor having four datapaths during loop processing in a unity stride allocation of memory.
- FIG. 3 shows the syntax of a loop handling instruction.
- FIG. 4 shows a table of how thirty data items in an array are handled by a SIMD processor having four datapaths during loop processing in a contiguous stride allocation of memory.
- FIG. 5 shows the syntax of a loop handling instruction combined with a loop branch.
- FIG. 6 is a flow diagram of a process of controlling the enabling of datapaths in a SIMD processor during loop processing.
- a single instruction multiple datapath (SIMD) processor 10 includes an instruction cache 12 , control logic 14 , a serial datapath, and a number of parallel datapaths labeled 18 a , 18 b , 18 c , 18 , . . . 18 n .
- the parallel datapaths 18 write to a memory 20 .
- Each of the datapaths 18 has an associated processor enable (PE) bit 22 .
- PE processor enable
- parallel datapath 18 a is associated with a PE bit 22 a
- parallel datapath 18 b is associated with a PE bit 22 b
- so forth When a PE bit is enabled, its associated parallel datapath is enabled and data items may be written by that parallel datapath.
- PE bit 22 a For example, if PE bit 22 a is enabled, data items may be written by parallel datapath 18 a ; if PE bit 22 b is enabled, data items may be written by parallel datapath 18 b . If PE bit 22 n is enabled, data items may be written by parallel datapath 18 n . When a PE bit is disabled, its associated parallel datapath is disabled and data items may not be written by that parallel datapath.
- control logic 14 fetches an instruction from the instruction cache 12 .
- the instruction is fed to the serial datapath 16 that provides the instruction to the datapaths 18 .
- Each of the datapaths 18 are read together and written together unless the processor enable bit is disabled for a particular datapath.
- One or more of the datapaths 18 may need to be disabled during a loop processing operation of an array of data items to avoid an unused datapath from overrunning the end of the array and erroneously writing over another data structure in memory. Rather than manually having to determine when during the loop processing operation to enable and disable datapaths, this determination may be made on the fly during the loop processing operation, based on information about parameters of the SIMD processor and the array, and the processing state of the datapaths relative to the data items in the array.
- This information includes: (1) the total number of parallel loop passes occurring in the loop processing operation, (2) the number of loop passes that would execute in a serial datapath design (which indicates the size of the array), (3) the number of remaining parallel passes occurring in the loop processing operation, (4) the memory allocation used to allocate data items of the array among the datapaths, and (5) the number of parallel datapaths. Instructions that enable or disable a processor enable bit for a datapath (thereby enabling or disabling the datapath) during loop processing based on this information are provided.
- NDP datapaths
- FIG. 2 a table illustrating how thirty data items numbered 0 to 29 in an array are handled by a SIMD processor having four datapaths labeled DP 0 , DP 1 , DP 2 and DP 3 , respectively, during loop processing in a unity stride memory allocation is shown.
- eight parallel loop passes are executed.
- data items 0 , 1 , 2 , and 3 are handled by datapaths 0 , 1 , 2 , and 3 .
- data items 4 , 5 , 6 and 7 are handled by datapaths 0 , 1 , 2 , and 3 .
- parallel loop pass 8 parallel loop pass 8 , data items 28 and 30 and handled by datapaths 0 and 1 while datapaths 2 and 3 must be disabled to avoid overrunning the array and writing over other data stored in memory.
- the table in FIG. 2 illustrates why this type of memory allocation is referred to as unity-stride.
- the “stride” between data items being processed in each of the parallel datapaths in any given parallel loop pass is one. That is, the difference between any two data items being processed by parallel datapaths in a parallel loop pass is one (or unity).
- a loop processor enable instruction 30 includes a field C representing the number of remaining parallel loop passes during a loop processing operation, and a field L representing the overall number of passes needed to service all the data items in an array in a serial machine architecture.
- the instruction 30 includes a memory allocation designation x.
- PE [i, j] represents the state of the processor enable bit for datapath i during parallel loop pass j.
- the total number of parallel loop passes is determined by dividing the total number of serial loop passes by the number of datapaths, and rounding the result up to the next integer.
- the total number of parallel loop passes equals 30/4, which rounded up to the next integer produces 8.
- a processor enable bit associated with a datapath index i representing the datapath and a data item j, that is, PE [i, j], is enabled if the total number of parallel loop passes minus the number of remaining parallel loop passes, all multiplied by the total number of datapaths plus the datapath index, is less than the total number of serial loop passes.
- SIMD processor 10 may use a contiguous stride memory allocation.
- FIG. 4 a table illustrating how thirty data items ( 0 to 29 ) in an array are handled by SIMD processor 10 having four datapaths (DP 0 -DP 3 ) and implementing a contiguous stride memory allocation is shown.
- eight parallel passes are executed.
- data items 0 , 8 , 16 and 24 are handled by datapaths 0 , 1 , 2 and 3 , respectively.
- parallel loop pass 2 data items 1 , 9 , 17 and 25 are handled by datapaths 0 , 1 , 2 and 3 .
- a pattern arises.
- parallel loop passes 7 and 8 datapath 3 needs to be disabled to avoid writing over memory beyond the end of the thirty data items in the array. All other datapaths are enabled in every pass.
- the contiguous-stride memory allocation is useful when neighboring data items are used when working on a particular data item. For example, if datapath 0 is processing data item 4 in parallel loop pass 5 , it already has data item 3 from parallel loop pass 4 and will be using data item 5 on the next parallel loop pass. This memory allocation is called contiguous stride allocation because each datapath is accessing a contiguous region of the array.
- the total number of parallel loop passes needed to process the array of data items is determined by dividing the total number of serial loop passes by the number of datapaths and rounding the result up to the next integer.
- the total number of parallel loop passes equals 30/4, rounded up to 8.
- An interleaved memory system permits many memory accesses to be done at once.
- the stride value may be selected to be an odd number. Selecting the stride to be an odd number spreads the addresses evenly among M banks if M is a power of two, since any odd number and any power of two are mutually prime. In the case of a 30 element array, the stride would be 9, not 8 as with the contiguous allocation. Datapath 0 would correspond to array elements 0 to 8 , datapath 1 would be associated with array elements 9 to 17 , and datapath 2 would correspond to elements 18 to 26 , and datapath 3 would be assigned to elements 26 to 29 . Datapath 3 would be turned off for the last six elements, i.e., array elements 30 to 35 . This memory allocation is referred to as a striped-stride memory allocation.
- the number of parallel loop passes needed to process an array of data items in a striped-stride memory allocation scheme is determined by dividing the total number of serial datapaths by the number of datapaths and rounding the result up to the next odd integer.
- the loop processor enable instruction is shown combined with a loop branch instruction 70 .
- This combined instruction 70 will set the processor enable bit, as described previously, according to the memory allocation scheme, the overall number of parallel loop passes and the number of remaining parallel loop passes, and test if the number of remaining parallel loop passes equals zero. If the number of remaining passes greater than zero, the branch is performed (i.e., “go to PC+displacement”), to perform the next pass of the loop operation. Otherwise, the loop is exited, and processing continues. In either case, the number of remaining parallel loop passes is decremented and the loop processing operation continues.
- a process 100 of controlling the enabling of a datapath in a SIMD processor during loop processing determines 102 the number of serial loop passes to service all of the data items in an array. The process determines 104 the number of remaining parallel loop passes to service the array. The process then tests 106 whether the memory allocation scheme is a unity stride allocation. If the memory allocation is a unity stride allocation, the processor enable bit for the datapath servicing the data item is enabled 108 if the total number of parallel loop passes minus the number of remaining parallel loop passes, all multiplied by the total number of datapaths plus the datapath index, is less than the total number of serial loop passes.
- the process tests 110 whether the memory allocation scheme is a contiguous stride allocation. If the memory allocation is a contiguous stride allocation, the processor enable bit for the datapath servicing the data item is enabled 112 if the total number of parallel loop passes multiplied by the datapath index plus the total number of parallel loop passes minus the number of remaining parallel loop passes is less than the total number of serial loop passes.
- the process tests 114 whether the memory allocation scheme is a striped stride allocation. If the memory allocation is a striped stride allocation, the processor enable bit for the datapath servicing the data item is enabled 116 if the total number of parallel loop passes times the datapath index plus the total number of parallel loop passes minus the number of remaining parallel loop passes is less than the total number of serial loop passes.
Abstract
A method of controlling the enabling of processor datapaths in a SIMD processor during a loop processing operation is described. The information used by the method includes an allocation between the data items and a memory, a size of the array, and a number of remaining parallel passes of the datapaths in the loop processing operation. A computer instruction is also provided, which includes a loop handling instruction that specifies the enabling of one of a plurality of processor datapaths during processing an array of data items. The instruction includes a count field that specifies the number of remaining parallel loop passes to process the array and a count field that specifies the number of serial loop passes to process the array. Different instructions can be used to handle different allocations of passes to parallel datapaths. The instruction also uses information about the total number of datapaths.
Description
- This invention relates to loop handling operations over an array of data items in a single instruction multiple datapath (SIMD) processor architecture.
- Parallel processing is an efficient way of processing an array of data items. A SIMD processor is a parallel processor array architecture wherein multiple datapaths are controlled by a single instruction. Each datapath handles one data item at a given time. In a simple example, in a SIMD processor having four datapaths, the data items in an eight data item array would be processed in each of the four datapaths in two passes of a loop operation. The allocation between datapaths and data items may vary, but in one approach, in a first pass the first data item in the array is processed by a first datapath, a second data item in the array is processed by a second datapath, a third data item is processed by a third datapath, and a fourth data item is processed by a fourth datapath. In a second pass, a fifth data item is processed by the first datapath, a sixth data item is processed by the second datapath, a seventh data item is processed by the third datapath, and an eighth data item is processed by the fourth datapath.
- Problems may occur when the number of data items in the array is not an integer multiple of the number of datapaths. For example, modifying the simple example above so that there are four datapaths and an array having seven data items, during the second pass, the fourth datapath does not have an element in the eighth item of the array to process. As a result, the fourth datapath may erroneously write over some other data structure in memory, unless the fourth datapath is disabled during the second pass.
- One way of avoiding such erroneous overwriting is to force the size of the array, i.e., the number of data items contained within the array, to be an integer multiple of the number of datapaths. Such an approach assumes that programmers have a priori control of how data items are allocated in the array, which they may not always have.
- Typically, each datapath in a SIMD processor has an associated processor enable bit that controls whether a datapath is enabled or disabled. This allows a datapath to be disabled when, e.g., the datapath would otherwise overrun the array.
- In a general aspect, the invention features a method of controlling whether to enable one of a plurality of processor datapaths in a SIMD processor that are operating on data elements in an array, including determining whether to enable the datapath based on information about parameters of the SIMD processor and the array, and a processing state of the datapaths relative to the data items in the array.
- In a preferred embodiment, the information includes an allocation between the data items and a memory, a total number of parallel loop passes in a loop processing operation being performed by the datapaths, a size of the array, and a number of datapaths (i.e., how many datapaths there are in the SIMD processor). The processing state is a number of remaining parallel passes of the datapaths in the loop processing operation.
- The allocation between the data items and the memory may be unity-stride, contiguous or striped-stride.
- In another aspect, the invention features a computer instruction including a loop handling instruction that specifies the enabling of one of a plurality of processor datapaths during processing an array of data items.
- In a preferred embodiment, the instruction includes a parallel count field that specifies the number of remaining parallel loop passes to process the array, and a serial count field that specifies the number of serial loop passes to process the array.
- In another aspect, the invention features a processor including a register file and an arithmetic logic unit coupled to the register file, and a program control store that stores a loop handling instruction that causes the processor to enable one of a plurality of processor datapaths during processing of an array of data.
- Embodiments of various aspects of the invention may have, one or more of the following advantages.
- Datapaths may be disabled without having prior knowledge of the number of data items in the array.
- The method is readily extensible to a variety of memory allocation schemes.
- The loop handling instruction saves instruction memory because the many operations needed to determine whether to enable or disable a datapath may be specified with a simple and powerful single instruction that also saves register space.
- The loop handling instruction saves a programmer from having to force the number of data items in the array of data items to be an integer multiple of the number of datapaths.
- Other features and advantages of the invention will be apparent from the following detailed description and drawings, and from the claims.
- FIG. 1 is a block diagram of a single instruction multiple datapath (SIMD) processor.
- FIG. 2 shows a table of how thirty data items in an array are handled by a SIMD processor having four datapaths during loop processing in a unity stride allocation of memory.
- FIG. 3 shows the syntax of a loop handling instruction.
- FIG. 4 shows a table of how thirty data items in an array are handled by a SIMD processor having four datapaths during loop processing in a contiguous stride allocation of memory.
- FIG. 5 shows the syntax of a loop handling instruction combined with a loop branch.
- FIG. 6 is a flow diagram of a process of controlling the enabling of datapaths in a SIMD processor during loop processing.
- Like reference symbols in the various drawings indicate like elements.
- Referring to FIG. 1, a single instruction multiple datapath (SIMD)
processor 10 includes aninstruction cache 12,control logic 14, a serial datapath, and a number of parallel datapaths labeled 18 a, 18 b, 18 c, 18, . . . 18 n. Theparallel datapaths 18 write to amemory 20. Each of thedatapaths 18 has an associated processor enable (PE)bit 22. Specifically,parallel datapath 18 a is associated with aPE bit 22 a,parallel datapath 18 b is associated with aPE bit 22 b, and so forth. When a PE bit is enabled, its associated parallel datapath is enabled and data items may be written by that parallel datapath. For example, ifPE bit 22 a is enabled, data items may be written byparallel datapath 18 a; ifPE bit 22 b is enabled, data items may be written byparallel datapath 18 b. IfPE bit 22 n is enabled, data items may be written byparallel datapath 18 n. When a PE bit is disabled, its associated parallel datapath is disabled and data items may not be written by that parallel datapath. - In operation, the
control logic 14 fetches an instruction from theinstruction cache 12. The instruction is fed to theserial datapath 16 that provides the instruction to thedatapaths 18. Each of thedatapaths 18 are read together and written together unless the processor enable bit is disabled for a particular datapath. - One or more of the
datapaths 18 may need to be disabled during a loop processing operation of an array of data items to avoid an unused datapath from overrunning the end of the array and erroneously writing over another data structure in memory. Rather than manually having to determine when during the loop processing operation to enable and disable datapaths, this determination may be made on the fly during the loop processing operation, based on information about parameters of the SIMD processor and the array, and the processing state of the datapaths relative to the data items in the array. This information includes: (1) the total number of parallel loop passes occurring in the loop processing operation, (2) the number of loop passes that would execute in a serial datapath design (which indicates the size of the array), (3) the number of remaining parallel passes occurring in the loop processing operation, (4) the memory allocation used to allocate data items of the array among the datapaths, and (5) the number of parallel datapaths. Instructions that enable or disable a processor enable bit for a datapath (thereby enabling or disabling the datapath) during loop processing based on this information are provided. - There are many ways to allocate memory for processing of an array of data items in a SIMD processor. The simplest memory allocation is where each one of a number of datapaths (NDP) takes the NDPth iteration of the loop. This type of memory allocation is called “unity stride.”
- Referring to FIG. 2, for example, a table illustrating how thirty data items numbered0 to 29 in an array are handled by a SIMD processor having four datapaths labeled DP0, DP1, DP2 and DP3, respectively, during loop processing in a unity stride memory allocation is shown. In order to process the array, eight parallel loop passes are executed. In a
parallel loop pass 1,data items datapaths parallel loop pass 2,data items datapaths parallel loop pass 8,data items datapaths 0 and 1 whiledatapaths - The table in FIG. 2 illustrates why this type of memory allocation is referred to as unity-stride. The “stride” between data items being processed in each of the parallel datapaths in any given parallel loop pass is one. That is, the difference between any two data items being processed by parallel datapaths in a parallel loop pass is one (or unity).
- In the unity stride allocation, as the number of data items are being processed a pattern emerges. Specifically, the pattern illustrates that only two datapaths in a final parallel loop pass need to be disabled. (Obviously, the pattern illustrated in FIG. 2 is trivial; as the number of datapaths and the array size are increased, the pattern becomes more complex, but is discernible in time.) From a knowledge of the pattern, the total number of loop passes that would execute in a serial machine (which indicates the size of the array), the number of remaining parallel loop passes, and the number of datapaths, an instruction is provided to determine whether a particular datapath should be disabled during a particular parallel loop pass.
- Referring to FIG. 3, a loop processor enable
instruction 30 includes a field C representing the number of remaining parallel loop passes during a loop processing operation, and a field L representing the overall number of passes needed to service all the data items in an array in a serial machine architecture. Theinstruction 30 includes a memory allocation designation x. In the example described with reference to FIG. 2, the memory allocation designation x would refer to a unity-stride memory allocation, i.e., U, and L=30 since there are thirty data items that would require thirty loop passes in a serial machine architecture. PE [i, j] represents the state of the processor enable bit for datapath i during parallel loop pass j. - For the unity-stride example described in reference to FIG. 2, the total number of parallel loop passes is determined by dividing the total number of serial loop passes by the number of datapaths, and rounding the result up to the next integer. Thus, in the example the total number of parallel loop passes equals 30/4, which rounded up to the next integer produces 8.
- Using the knowledge gained from the pattern present in the unity-stride example and the values of C and L, a processor enable bit associated with a datapath index i representing the datapath and a data item j, that is, PE [i, j], is enabled if the total number of parallel loop passes minus the number of remaining parallel loop passes, all multiplied by the total number of datapaths plus the datapath index, is less than the total number of serial loop passes.
- Alternatively,
SIMD processor 10 may use a contiguous stride memory allocation. Referring to FIG. 4, a table illustrating how thirty data items (0 to 29) in an array are handled bySIMD processor 10 having four datapaths (DP0-DP3) and implementing a contiguous stride memory allocation is shown. In order to process all thirty data items in the array, eight parallel passes are executed. In aparallel loop pass 1,data items datapaths parallel loop pass 2,data items datapaths datapath 3 needs to be disabled to avoid writing over memory beyond the end of the thirty data items in the array. All other datapaths are enabled in every pass. - The contiguous-stride memory allocation is useful when neighboring data items are used when working on a particular data item. For example, if datapath0 is processing
data item 4 inparallel loop pass 5, it already hasdata item 3 fromparallel loop pass 4 and will be usingdata item 5 on the next parallel loop pass. This memory allocation is called contiguous stride allocation because each datapath is accessing a contiguous region of the array. - In the contiguous stride memory allocation, a pattern emerges to suggest that a single datapath needs to be disabled during executions of, in this example, the last two parallel loop passes. Referring again to FIG. 3, a memory allocation designation x=CONT represents a contiguous-stride memory allocation scheme. For the example described with reference to FIG. 4, the total number of parallel loop passes needed to process the array of data items is determined by dividing the total number of serial loop passes by the number of datapaths and rounding the result up to the next integer. Thus, in the example, the total number of parallel loop passes equals 30/4, rounded up to 8.
- From the contiguous-stride memory allocation pattern and the values of C and L, a processor enable bit associated with a datapath index i and a data item j, that is, PE [i, j], is enabled if the total number of parallel loop passes multiplied by the datapath index plus the total number of parallel loop passes minus the number of remaining parallel loop passes is less than the total number of serial loop passes.
- An interleaved memory system permits many memory accesses to be done at once. The number of memory banks M in an interleaved memory system is generally a power of two, since that allows the memory bank selection to be made using the lowest address bits. If the stride in a read or write instruction is also a power of two, the memory interleaving will not help, since all the addresses will try to access the same memory bank. For example, if M=4 and the stride is also four, the addresses for the read or write would be 0, 4, 8, and so forth, and they would all have to be handled by bank0;
banks - To avoid having all of the data items processed in the same memory bank, the stride value may be selected to be an odd number. Selecting the stride to be an odd number spreads the addresses evenly among M banks if M is a power of two, since any odd number and any power of two are mutually prime. In the case of a 30 element array, the stride would be 9, not 8 as with the contiguous allocation. Datapath0 would correspond to array elements 0 to 8,
datapath 1 would be associated witharray elements 9 to 17, anddatapath 2 would correspond toelements 18 to 26, anddatapath 3 would be assigned toelements 26 to 29.Datapath 3 would be turned off for the last six elements, i.e.,array elements 30 to 35. This memory allocation is referred to as a striped-stride memory allocation. - The number of parallel loop passes needed to process an array of data items in a striped-stride memory allocation scheme is determined by dividing the total number of serial datapaths by the number of datapaths and rounding the result up to the next odd integer.
- Referring again to FIG. 3, a memory designation x=S represents striped-stride allocation. A processor enable bit associated with a datapath i and a data item j, that is, PE [i, j], is enabled if the total number of parallel loop passes times the datapath index plus the total number of parallel loop passes minus the number of remaining parallel loop passes is less than the total number of serial loop passes.
- Referring to FIG. 5, the loop processor enable instruction is shown combined with a
loop branch instruction 70. This combinedinstruction 70 will set the processor enable bit, as described previously, according to the memory allocation scheme, the overall number of parallel loop passes and the number of remaining parallel loop passes, and test if the number of remaining parallel loop passes equals zero. If the number of remaining passes greater than zero, the branch is performed (i.e., “go to PC+displacement”), to perform the next pass of the loop operation. Otherwise, the loop is exited, and processing continues. In either case, the number of remaining parallel loop passes is decremented and the loop processing operation continues. - Referring to FIG. 6, a
process 100 of controlling the enabling of a datapath in a SIMD processor during loop processing determines 102 the number of serial loop passes to service all of the data items in an array. The process determines 104 the number of remaining parallel loop passes to service the array. The process then tests 106 whether the memory allocation scheme is a unity stride allocation. If the memory allocation is a unity stride allocation, the processor enable bit for the datapath servicing the data item is enabled 108 if the total number of parallel loop passes minus the number of remaining parallel loop passes, all multiplied by the total number of datapaths plus the datapath index, is less than the total number of serial loop passes. - If the memory allocated is not unity stride, the process tests110 whether the memory allocation scheme is a contiguous stride allocation. If the memory allocation is a contiguous stride allocation, the processor enable bit for the datapath servicing the data item is enabled 112 if the total number of parallel loop passes multiplied by the datapath index plus the total number of parallel loop passes minus the number of remaining parallel loop passes is less than the total number of serial loop passes.
- Finally, if the memory allocation is neither unity stride nor contiguous, the process tests114 whether the memory allocation scheme is a striped stride allocation. If the memory allocation is a striped stride allocation, the processor enable bit for the datapath servicing the data item is enabled 116 if the total number of parallel loop passes times the datapath index plus the total number of parallel loop passes minus the number of remaining parallel loop passes is less than the total number of serial loop passes.
- A number of embodiments of the invention have been described. Nevertheless, it will be understood that various modifications may be made without departing from the spirit and scope of the invention. For example, for processing larger numbers of data items, a lookup table could be utilized until a time at which a pattern develops according to the memory allocation scheme employed. Once the pattern develops, the enabling of datapaths is determined by the method herein described. Accordingly, other embodiments are within the scope of the following claims.
Claims (20)
1. A method of controlling whether to enable one of a plurality of processor datapaths in a SIMD processor that are operating on data elements in an array, comprising:
determining whether to enable the datapath based on information about parameters of the SIMD processor and the array, and a processing state of the datapaths relative to the data items in the array.
2. The method of claim 1 wherein the information includes an allocation between the data items and a memory.
3. The method of claim 2 wherein the information includes whether the allocation is unity-stride, contiguous, or striped stride.
4. The method of claim 1 wherein the information includes a total number of parallel loop passes in a loop processing operation being performed by the datapaths.
5. The method of claim 1 wherein the information indicates a size of the array.
6. The method of claim 1 wherein the processing state is a number of remaining parallel loop passes in the loop processing operation.
7. The method of claim 1 wherein the information includes a number of said processor datapaths.
8. The method of claim 1 wherein the information includes an allocation between the data items and a memory, a total number of parallel loop passes in a loop processing operation being performed by the datapaths, a size of the array, a number of remaining parallel passes of the datapaths in the loop processing operation, and a number of said processor datapaths.
9. The method of claim 8 wherein the allocation between the data items and the memory is a unity-stride.
10. The method of claim 9 wherein the total number of loop passes is determined by dividing a total number of serial loop passes by the total number of datapaths implemented and rounded up to a next integer.
11. The method of claim 10 wherein enabling comprises:
determining whether the total number of parallel loop passes minus the number of remaining loop passes multiplied by the total number of datapaths implemented plus a datapath number is less than the total number of serial loop passes.
12. The method of claim 8 wherein the allocation between the data items and the memory is a contiguous stride.
13. The method of claim 12 wherein the total number of parallel loop passes is determined by dividing the total number of serial loop passes by the number of datapaths and rounded up to a next integer.
14. The method of claim 13 wherein enabling comprises:
determining whether the total number of parallel loop passes multiplied by a datapath number plus the total number of parallel loop passes minus a number of remaining parallel loop passes is less than the total number of serial loop passes.
15. The method of claim 8 wherein the allocation is a striped stride.
16. The method of claim 15 wherein enabling comprises:
determining whether the total number of parallel loop passes times a datapath number plus the total number of parallel loop passes minus a number of remaining parallel loop passes is less than the total number of serial loop passes.
17. A computer instruction comprising:
a loop handling instruction that specifies the enabling of one of a plurality of processor datapaths during processing an array of data items.
18. The instruction of claim 17 further comprising:
a parallel count field that specifies the number of remaining parallel loop passes to process the array.
19. The instruction of claim 17 further comprising:
a serial count field that specifies the number of serial loop passes to process the array.
20. A processor comprising:
a register file;
an arithmetic logic unit coupled to the register file and a program control store that stores a loop handling instruction that causes the processor to enable one of a plurality of processor datapaths during processing of an array of data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US10/770,787 US20040158691A1 (en) | 2000-11-13 | 2004-02-03 | Loop handling for single instruction multiple datapath processor architectures |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US09/711,556 US6732253B1 (en) | 2000-11-13 | 2000-11-13 | Loop handling for single instruction multiple datapath processor architectures |
US10/770,787 US20040158691A1 (en) | 2000-11-13 | 2004-02-03 | Loop handling for single instruction multiple datapath processor architectures |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US09/711,556 Continuation US6732253B1 (en) | 2000-11-13 | 2000-11-13 | Loop handling for single instruction multiple datapath processor architectures |
Publications (1)
Publication Number | Publication Date |
---|---|
US20040158691A1 true US20040158691A1 (en) | 2004-08-12 |
Family
ID=24858560
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US09/711,556 Expired - Fee Related US6732253B1 (en) | 2000-11-13 | 2000-11-13 | Loop handling for single instruction multiple datapath processor architectures |
US10/770,787 Abandoned US20040158691A1 (en) | 2000-11-13 | 2004-02-03 | Loop handling for single instruction multiple datapath processor architectures |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US09/711,556 Expired - Fee Related US6732253B1 (en) | 2000-11-13 | 2000-11-13 | Loop handling for single instruction multiple datapath processor architectures |
Country Status (8)
Country | Link |
---|---|
US (2) | US6732253B1 (en) |
JP (1) | JP2004513455A (en) |
KR (1) | KR20030072354A (en) |
CN (1) | CN1484786A (en) |
AU (1) | AU2002234101A1 (en) |
DE (1) | DE10196879T5 (en) |
TW (1) | TW563063B (en) |
WO (1) | WO2002039271A1 (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060080071A1 (en) * | 2000-06-20 | 2006-04-13 | International Business Machines Cor | Method, apparatus and computer program product for network design and analysis |
WO2006044978A2 (en) * | 2004-10-20 | 2006-04-27 | Intel Corporation | Looping instructions for a single instruction, multiple data execution engine |
US20070169061A1 (en) * | 2003-12-15 | 2007-07-19 | Bera Rajendra K | Run-Time Parallelization of Loops in Computer Programs Using Bit Vectors |
US20080127152A1 (en) * | 1999-12-01 | 2008-05-29 | Rajendra Kumar Bera | Compiler optimisation of source code by determination and utilization of the equivalence of algebraic expressions in the source code |
US20110099352A1 (en) * | 2009-10-23 | 2011-04-28 | Mindspeed Technologies, Inc. | Automatic control of multiple arithmetic/logic SIMD units |
US7996671B2 (en) | 2003-11-17 | 2011-08-09 | Bluerisc Inc. | Security of program executables and microprocessors based on compiler-architecture interaction |
US8607209B2 (en) | 2004-02-04 | 2013-12-10 | Bluerisc Inc. | Energy-focused compiler-assisted branch prediction |
US9069938B2 (en) | 2006-11-03 | 2015-06-30 | Bluerisc, Inc. | Securing microprocessors against information leakage and physical tampering |
US9235393B2 (en) | 2002-07-09 | 2016-01-12 | Iii Holdings 2, Llc | Statically speculative compilation and execution |
US9569186B2 (en) | 2003-10-29 | 2017-02-14 | Iii Holdings 2, Llc | Energy-focused re-compilation of executables and hardware mechanisms based on compiler-architecture interaction and compiler-inserted control |
Families Citing this family (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1346279A1 (en) * | 2000-12-07 | 2003-09-24 | Koninklijke Philips Electronics N.V. | Digital signal processing apparatus |
GB2382672B (en) * | 2001-10-31 | 2005-10-05 | Alphamosaic Ltd | Repeated instruction execution |
DE10206830B4 (en) * | 2002-02-18 | 2004-10-14 | Systemonic Ag | Method and arrangement for merging data from parallel data paths |
US7903555B2 (en) * | 2003-12-17 | 2011-03-08 | Intel Corporation | Packet tracing |
US7937557B2 (en) | 2004-03-16 | 2011-05-03 | Vns Portfolio Llc | System and method for intercommunication between computers in an array |
US8190809B2 (en) * | 2004-11-23 | 2012-05-29 | Efficient Memory Technology | Shunted interleave for accessing plural memory banks, particularly those having partially accessed cells containing data for cache lines |
WO2006057949A2 (en) * | 2004-11-23 | 2006-06-01 | Efficient Memory Technology | Method and apparatus of multiple abbreviations of interleaved addressing of paged memories and intelligent memory banks therefor |
US7904695B2 (en) * | 2006-02-16 | 2011-03-08 | Vns Portfolio Llc | Asynchronous power saving computer |
US7966481B2 (en) | 2006-02-16 | 2011-06-21 | Vns Portfolio Llc | Computer system and method for executing port communications without interrupting the receiving computer |
US7904615B2 (en) | 2006-02-16 | 2011-03-08 | Vns Portfolio Llc | Asynchronous computer communication |
US7913069B2 (en) * | 2006-02-16 | 2011-03-22 | Vns Portfolio Llc | Processor and method for executing a program loop within an instruction word |
US20070294181A1 (en) * | 2006-05-22 | 2007-12-20 | Saurabh Chheda | Flexible digital rights management with secure snippets |
US7493475B2 (en) * | 2006-11-15 | 2009-02-17 | Stmicroelectronics, Inc. | Instruction vector-mode processing in multi-lane processor by multiplex switch replicating instruction in one lane to select others along with updated operand address |
US20080154379A1 (en) * | 2006-12-22 | 2008-06-26 | Musculoskeletal Transplant Foundation | Interbody fusion hybrid graft |
GB2486485B (en) * | 2010-12-16 | 2012-12-19 | Imagination Tech Ltd | Method and apparatus for scheduling the issue of instructions in a microprocessor using multiple phases of execution |
KR20120074762A (en) * | 2010-12-28 | 2012-07-06 | 삼성전자주식회사 | Computing apparatus and method based on reconfigurable simd architecture |
CN103491315A (en) * | 2013-08-09 | 2014-01-01 | 北京中传视讯科技有限公司 | Video data processing method, video data processing device and electronic device comprising video data processing device |
US20150100758A1 (en) * | 2013-10-03 | 2015-04-09 | Advanced Micro Devices, Inc. | Data processor and method of lane realignment |
KR102202575B1 (en) * | 2013-12-31 | 2021-01-13 | 삼성전자주식회사 | Memory management method and apparatus |
KR102332523B1 (en) | 2014-12-24 | 2021-11-29 | 삼성전자주식회사 | Apparatus and method for execution processing |
Citations (68)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4101960A (en) * | 1977-03-29 | 1978-07-18 | Burroughs Corporation | Scientific processor |
US4138720A (en) * | 1977-04-04 | 1979-02-06 | Burroughs Corporation | Time-shared, multi-phase memory accessing system |
US4181942A (en) * | 1978-03-31 | 1980-01-01 | International Business Machines Corporation | Program branching method and apparatus |
US4410939A (en) * | 1979-07-17 | 1983-10-18 | Matsushita Electric Industrial Co. Ltd. | System for program interrupt processing with quasi-stack of register-sets |
US4434461A (en) * | 1980-09-15 | 1984-02-28 | Motorola, Inc. | Microprocessor with duplicate registers for processing interrupts |
US4435758A (en) * | 1980-03-10 | 1984-03-06 | International Business Machines Corporation | Method for conditional branch execution in SIMD vector processors |
US4592013A (en) * | 1981-08-21 | 1986-05-27 | International Business Machines Corp. | Method and device for addressing a memory |
US4604695A (en) * | 1983-09-30 | 1986-08-05 | Honeywell Information Systems Inc. | Nibble and word addressable memory arrangement |
US4679140A (en) * | 1983-12-23 | 1987-07-07 | Hitachi, Ltd. | Data processor with control of the significant bit lengths of general purpose registers |
US4773038A (en) * | 1986-02-24 | 1988-09-20 | Thinking Machines Corporation | Method of simulating additional processors in a SIMD parallel processor array |
US4992933A (en) * | 1986-10-27 | 1991-02-12 | International Business Machines Corporation | SIMD array processor with global instruction control and reprogrammable instruction decoders |
US5021993A (en) * | 1987-03-31 | 1991-06-04 | Kabushiki Kaisha Toshiba | Device for saving and restoring register information |
US5038282A (en) * | 1988-05-11 | 1991-08-06 | Massachusetts Institute Of Technology | Synchronous processor with simultaneous instruction processing and data transfer |
US5045995A (en) * | 1985-06-24 | 1991-09-03 | Vicom Systems, Inc. | Selective operation of processing elements in a single instruction multiple data stream (SIMD) computer system |
US5111389A (en) * | 1987-10-29 | 1992-05-05 | International Business Machines Corporation | Aperiodic mapping system using power-of-two stride access to interleaved devices |
US5121498A (en) * | 1988-05-11 | 1992-06-09 | Massachusetts Institute Of Technology | Translator for translating source code for selective unrolling of loops in the source code |
US5136697A (en) * | 1989-06-06 | 1992-08-04 | Advanced Micro Devices, Inc. | System for reducing delay for execution subsequent to correctly predicted branch instruction using fetch information stored with each block of instructions in cache |
US5193202A (en) * | 1990-05-29 | 1993-03-09 | Wavetracer, Inc. | Processor array with relocated operand physical address generator capable of data transfer to distant physical processor for each virtual processor while simulating dimensionally larger array processor |
US5224214A (en) * | 1990-04-12 | 1993-06-29 | Digital Equipment Corp. | BuIffet for gathering write requests and resolving read conflicts by matching read and write requests |
US5230079A (en) * | 1986-09-18 | 1993-07-20 | Digital Equipment Corporation | Massively parallel array processing system with processors selectively accessing memory module locations using address in microword or in address register |
US5276895A (en) * | 1986-09-18 | 1994-01-04 | Digital Equipment Corporation | Massively parallel array processing system |
US5361367A (en) * | 1991-06-10 | 1994-11-01 | The United States Of America As Represented By The Administrator Of The National Aeronautics And Space Administration | Highly parallel reconfigurable computer architecture for robotic computation having plural processor cells each having right and left ensembles of plural processors |
US5430854A (en) * | 1991-10-24 | 1995-07-04 | Intel Corp | Simd with selective idling of individual processors based on stored conditional flags, and with consensus among all flags used for conditional branching |
US5479324A (en) * | 1993-12-17 | 1995-12-26 | Barry; James E. | Illuminated gas tank or shell |
US5497478A (en) * | 1991-03-20 | 1996-03-05 | Hewlett-Packard Company | Memory access system and method modifying a memory interleaving scheme so that data can be read in any sequence without inserting wait cycles |
US5524223A (en) * | 1994-01-31 | 1996-06-04 | Motorola, Inc. | Instruction accelerator for processing loop instructions with address generator using multiple stored increment values |
US5542074A (en) * | 1992-10-22 | 1996-07-30 | Maspar Computer Corporation | Parallel processor system with highly flexible local control capability, including selective inversion of instruction signal and control of bit shift amount |
US5551039A (en) * | 1992-02-03 | 1996-08-27 | Thinking Machines Corporation | Compiling a source code vector instruction by generating a subgrid loop for iteratively processing array elements by plural processing elements |
US5555386A (en) * | 1992-11-26 | 1996-09-10 | Sharp Kabushiki Kaisha | Data flow processor with variable logic connection between processors in a system |
US5590283A (en) * | 1990-10-03 | 1996-12-31 | Thinking Machines Corporation | Parallel computer system with physically separate tree networks for data and control messages |
US5590356A (en) * | 1994-08-23 | 1996-12-31 | Massachusetts Institute Of Technology | Mesh parallel computer architecture apparatus and associated methods |
US5604913A (en) * | 1993-08-10 | 1997-02-18 | Fujitsu Limited | Vector processor having a mask register used for performing nested conditional instructions |
US5608886A (en) * | 1994-08-31 | 1997-03-04 | Exponential Technology, Inc. | Block-based branch prediction using a target finder array storing target sub-addresses |
US5638533A (en) * | 1995-10-12 | 1997-06-10 | Lsi Logic Corporation | Method and apparatus for providing data to a parallel processing array |
US5659778A (en) * | 1992-02-03 | 1997-08-19 | Tm Patents, L.P. | System and method of mapping an array to processing elements |
US5659722A (en) * | 1994-04-28 | 1997-08-19 | International Business Machines Corporation | Multiple condition code branching system in a multi-processor environment |
US5666519A (en) * | 1994-03-08 | 1997-09-09 | Digital Equipment Corporation | Method and apparatus for detecting and executing cross-domain calls in a computer system |
US5684973A (en) * | 1993-03-11 | 1997-11-04 | Data General Corporation | Expandable memory system and method for interleaving addresses among memory banks of different speeds and sizes |
US5696958A (en) * | 1993-01-11 | 1997-12-09 | Silicon Graphics, Inc. | Method and apparatus for reducing delays following the execution of a branch instruction in an instruction pipeline |
US5727229A (en) * | 1996-02-05 | 1998-03-10 | Motorola, Inc. | Method and apparatus for moving data in a parallel processor |
US5737572A (en) * | 1995-06-06 | 1998-04-07 | Apple Computer, Inc. | Bank selection logic for memory controllers |
US5758176A (en) * | 1994-09-28 | 1998-05-26 | International Business Machines Corporation | Method and system for providing a single-instruction, multiple-data execution unit for performing single-instruction, multiple-data operations within a superscalar data processing system |
US5758112A (en) * | 1994-10-14 | 1998-05-26 | Silicon Graphics, Inc. | Pipeline processor with enhanced method and apparatus for restoring register-renaming information in the event of a branch misprediction |
US5778241A (en) * | 1994-05-05 | 1998-07-07 | Rockwell International Corporation | Space vector data path |
US5805915A (en) * | 1992-05-22 | 1998-09-08 | International Business Machines Corporation | SIMIMD array processing system |
US5822606A (en) * | 1996-01-11 | 1998-10-13 | Morton; Steven G. | DSP having a plurality of like processors controlled in parallel by an instruction word, and a control processor also controlled by the instruction word |
US5848290A (en) * | 1995-03-09 | 1998-12-08 | Sharp Kabushiki Kaisha | Data driven information processor |
US5870581A (en) * | 1996-12-20 | 1999-02-09 | Oak Technology, Inc. | Method and apparatus for performing concurrent write operations to a single-write-input register file and an accumulator register |
US5872987A (en) * | 1992-08-07 | 1999-02-16 | Thinking Machines Corporation | Massively parallel computer including auxiliary vector processor |
US5924117A (en) * | 1996-12-16 | 1999-07-13 | International Business Machines Corporation | Multi-ported and interleaved cache memory supporting multiple simultaneous accesses thereto |
US5933650A (en) * | 1997-10-09 | 1999-08-03 | Mips Technologies, Inc. | Alignment and ordering of vector elements for single instruction multiple data processing |
US5946222A (en) * | 1996-12-20 | 1999-08-31 | Oak Technology, Inc. | Method and apparatus for performing a masked byte addition operation |
US5991857A (en) * | 1993-12-23 | 1999-11-23 | Nokia Mobile Phones Limited | Interleaving and de-interleaving of data in telecommunications |
US6049330A (en) * | 1997-08-28 | 2000-04-11 | Oak Technology, Inc. | Method and apparatus for optimizing storage of compressed images in memory |
US6052703A (en) * | 1998-05-12 | 2000-04-18 | Oak Technology, Inc. | Method and apparatus for determining discrete cosine transforms using matrix multiplication and modified booth encoding |
US6067609A (en) * | 1998-04-09 | 2000-05-23 | Teranex, Inc. | Pattern generation and shift plane operations for a mesh connected computer |
US6076158A (en) * | 1990-06-29 | 2000-06-13 | Digital Equipment Corporation | Branch prediction in high-performance processor |
US6121905A (en) * | 1998-05-11 | 2000-09-19 | Oak Technology, Inc. | Method and apparatus for decoding JPEG symbols |
US6130631A (en) * | 1998-05-11 | 2000-10-10 | Oak Technology, Inc. | Method and apparatus utilizing a simplified content-addressable memory for JPEG decoding |
US6175892B1 (en) * | 1998-06-19 | 2001-01-16 | Hitachi America. Ltd. | Registers and methods for accessing registers for use in a single instruction multiple data system |
US6216223B1 (en) * | 1998-01-12 | 2001-04-10 | Billions Of Operations Per Second, Inc. | Methods and apparatus to dynamically reconfigure the instruction pipeline of an indirect very long instruction word scalable processor |
US6282623B1 (en) * | 2000-02-04 | 2001-08-28 | Motorola Inc. | Method for digital signal processing, DSP, mobile communication and audi o-device |
US6282628B1 (en) * | 1999-02-24 | 2001-08-28 | International Business Machines Corporation | Method and system for a result code for a single-instruction multiple-data predicate compare operation |
US6292879B1 (en) * | 1995-10-25 | 2001-09-18 | Anthony S. Fong | Method and apparatus to specify access control list and cache enabling and cache coherency requirement enabling on individual operands of an instruction of a computer |
US6404439B1 (en) * | 1997-03-11 | 2002-06-11 | Sony Corporation | SIMD control parallel processor with simplified configuration |
US6452864B1 (en) * | 2000-01-31 | 2002-09-17 | Stmicroelectonics S.R.L. | Interleaved memory device for sequential access synchronous reading with simplified address counters |
US6473339B2 (en) * | 2000-03-02 | 2002-10-29 | Stmicroelectronics S.R.L. | Redundancy architecture for an interleaved memory |
US6487651B1 (en) * | 1999-10-26 | 2002-11-26 | Assabet Ventures | MIMD arrangement of SIMD machines |
Family Cites Families (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
GB2177526B (en) | 1985-06-24 | 1990-02-14 | Pixar | Selective operation of processing elements in a single instruction, multiple data stream (simd)computer system |
US4896258A (en) | 1985-07-04 | 1990-01-23 | Hitachi, Ltd. | Data processor provided with instructions which refer to both tagged and tagless data |
GB2201015B (en) | 1987-02-10 | 1990-10-10 | Univ Southampton | Parallel processor array and array element |
US5157785A (en) | 1990-05-29 | 1992-10-20 | Wavetracer, Inc. | Process cell for an n-dimensional processor array having a single input element with 2n data inputs, memory, and full function arithmetic logic unit |
US5361363A (en) | 1990-10-03 | 1994-11-01 | Thinking Machines Corporation | Input/output system for parallel computer for performing parallel file transfers between selected number of input/output devices and another selected number of processing nodes |
US5479624A (en) | 1992-10-14 | 1995-12-26 | Lee Research, Inc. | High-performance interleaved memory system comprising a prime number of memory modules |
GB2273377A (en) * | 1992-12-11 | 1994-06-15 | Hughes Aircraft Co | Multiple masks for array processors |
US5590352A (en) | 1994-04-26 | 1996-12-31 | Advanced Micro Devices, Inc. | Dependency checking and forwarding of variable width operands |
WO1998043168A1 (en) | 1997-03-21 | 1998-10-01 | International Business Machines Corporation | Address mapping for system memory |
JPH10289305A (en) | 1997-04-11 | 1998-10-27 | Mitsubishi Electric Corp | Image processing device and its method |
WO1999014685A1 (en) | 1997-09-16 | 1999-03-25 | Hitachi, Ltd. | Data processor and data processing system |
JPH11272546A (en) | 1998-03-23 | 1999-10-08 | Nec Corp | Variable length register device |
JP2002007359A (en) | 2000-06-21 | 2002-01-11 | Sony Corp | Method and device for parallel processing simd control |
-
2000
- 2000-11-13 US US09/711,556 patent/US6732253B1/en not_active Expired - Fee Related
-
2001
- 2001-11-09 TW TW090127898A patent/TW563063B/en not_active IP Right Cessation
- 2001-11-09 CN CNA018216390A patent/CN1484786A/en active Pending
- 2001-11-09 JP JP2002541527A patent/JP2004513455A/en active Pending
- 2001-11-09 WO PCT/US2001/050029 patent/WO2002039271A1/en active Application Filing
- 2001-11-09 AU AU2002234101A patent/AU2002234101A1/en not_active Abandoned
- 2001-11-09 KR KR10-2003-7006484A patent/KR20030072354A/en not_active Application Discontinuation
- 2001-11-09 DE DE10196879T patent/DE10196879T5/en not_active Withdrawn
-
2004
- 2004-02-03 US US10/770,787 patent/US20040158691A1/en not_active Abandoned
Patent Citations (70)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4101960A (en) * | 1977-03-29 | 1978-07-18 | Burroughs Corporation | Scientific processor |
US4138720A (en) * | 1977-04-04 | 1979-02-06 | Burroughs Corporation | Time-shared, multi-phase memory accessing system |
US4181942A (en) * | 1978-03-31 | 1980-01-01 | International Business Machines Corporation | Program branching method and apparatus |
US4410939A (en) * | 1979-07-17 | 1983-10-18 | Matsushita Electric Industrial Co. Ltd. | System for program interrupt processing with quasi-stack of register-sets |
US4435758A (en) * | 1980-03-10 | 1984-03-06 | International Business Machines Corporation | Method for conditional branch execution in SIMD vector processors |
US4434461A (en) * | 1980-09-15 | 1984-02-28 | Motorola, Inc. | Microprocessor with duplicate registers for processing interrupts |
US4592013A (en) * | 1981-08-21 | 1986-05-27 | International Business Machines Corp. | Method and device for addressing a memory |
US4604695A (en) * | 1983-09-30 | 1986-08-05 | Honeywell Information Systems Inc. | Nibble and word addressable memory arrangement |
US4679140A (en) * | 1983-12-23 | 1987-07-07 | Hitachi, Ltd. | Data processor with control of the significant bit lengths of general purpose registers |
US5045995A (en) * | 1985-06-24 | 1991-09-03 | Vicom Systems, Inc. | Selective operation of processing elements in a single instruction multiple data stream (SIMD) computer system |
US4773038A (en) * | 1986-02-24 | 1988-09-20 | Thinking Machines Corporation | Method of simulating additional processors in a SIMD parallel processor array |
US5230079A (en) * | 1986-09-18 | 1993-07-20 | Digital Equipment Corporation | Massively parallel array processing system with processors selectively accessing memory module locations using address in microword or in address register |
US5276895A (en) * | 1986-09-18 | 1994-01-04 | Digital Equipment Corporation | Massively parallel array processing system |
US4992933A (en) * | 1986-10-27 | 1991-02-12 | International Business Machines Corporation | SIMD array processor with global instruction control and reprogrammable instruction decoders |
US5021993A (en) * | 1987-03-31 | 1991-06-04 | Kabushiki Kaisha Toshiba | Device for saving and restoring register information |
US5111389A (en) * | 1987-10-29 | 1992-05-05 | International Business Machines Corporation | Aperiodic mapping system using power-of-two stride access to interleaved devices |
US5038282A (en) * | 1988-05-11 | 1991-08-06 | Massachusetts Institute Of Technology | Synchronous processor with simultaneous instruction processing and data transfer |
US5121498A (en) * | 1988-05-11 | 1992-06-09 | Massachusetts Institute Of Technology | Translator for translating source code for selective unrolling of loops in the source code |
US5136697A (en) * | 1989-06-06 | 1992-08-04 | Advanced Micro Devices, Inc. | System for reducing delay for execution subsequent to correctly predicted branch instruction using fetch information stored with each block of instructions in cache |
US5224214A (en) * | 1990-04-12 | 1993-06-29 | Digital Equipment Corp. | BuIffet for gathering write requests and resolving read conflicts by matching read and write requests |
US5193202A (en) * | 1990-05-29 | 1993-03-09 | Wavetracer, Inc. | Processor array with relocated operand physical address generator capable of data transfer to distant physical processor for each virtual processor while simulating dimensionally larger array processor |
US6076158A (en) * | 1990-06-29 | 2000-06-13 | Digital Equipment Corporation | Branch prediction in high-performance processor |
US5590283A (en) * | 1990-10-03 | 1996-12-31 | Thinking Machines Corporation | Parallel computer system with physically separate tree networks for data and control messages |
US5497478A (en) * | 1991-03-20 | 1996-03-05 | Hewlett-Packard Company | Memory access system and method modifying a memory interleaving scheme so that data can be read in any sequence without inserting wait cycles |
US5361367A (en) * | 1991-06-10 | 1994-11-01 | The United States Of America As Represented By The Administrator Of The National Aeronautics And Space Administration | Highly parallel reconfigurable computer architecture for robotic computation having plural processor cells each having right and left ensembles of plural processors |
US5430854A (en) * | 1991-10-24 | 1995-07-04 | Intel Corp | Simd with selective idling of individual processors based on stored conditional flags, and with consensus among all flags used for conditional branching |
US5659778A (en) * | 1992-02-03 | 1997-08-19 | Tm Patents, L.P. | System and method of mapping an array to processing elements |
US5551039A (en) * | 1992-02-03 | 1996-08-27 | Thinking Machines Corporation | Compiling a source code vector instruction by generating a subgrid loop for iteratively processing array elements by plural processing elements |
US5805915A (en) * | 1992-05-22 | 1998-09-08 | International Business Machines Corporation | SIMIMD array processing system |
US5872987A (en) * | 1992-08-07 | 1999-02-16 | Thinking Machines Corporation | Massively parallel computer including auxiliary vector processor |
US5542074A (en) * | 1992-10-22 | 1996-07-30 | Maspar Computer Corporation | Parallel processor system with highly flexible local control capability, including selective inversion of instruction signal and control of bit shift amount |
US5555386A (en) * | 1992-11-26 | 1996-09-10 | Sharp Kabushiki Kaisha | Data flow processor with variable logic connection between processors in a system |
US5696958A (en) * | 1993-01-11 | 1997-12-09 | Silicon Graphics, Inc. | Method and apparatus for reducing delays following the execution of a branch instruction in an instruction pipeline |
US5684973A (en) * | 1993-03-11 | 1997-11-04 | Data General Corporation | Expandable memory system and method for interleaving addresses among memory banks of different speeds and sizes |
US5604913A (en) * | 1993-08-10 | 1997-02-18 | Fujitsu Limited | Vector processor having a mask register used for performing nested conditional instructions |
US5479324A (en) * | 1993-12-17 | 1995-12-26 | Barry; James E. | Illuminated gas tank or shell |
US5991857A (en) * | 1993-12-23 | 1999-11-23 | Nokia Mobile Phones Limited | Interleaving and de-interleaving of data in telecommunications |
US5524223A (en) * | 1994-01-31 | 1996-06-04 | Motorola, Inc. | Instruction accelerator for processing loop instructions with address generator using multiple stored increment values |
US5666519A (en) * | 1994-03-08 | 1997-09-09 | Digital Equipment Corporation | Method and apparatus for detecting and executing cross-domain calls in a computer system |
US5659722A (en) * | 1994-04-28 | 1997-08-19 | International Business Machines Corporation | Multiple condition code branching system in a multi-processor environment |
US5778241A (en) * | 1994-05-05 | 1998-07-07 | Rockwell International Corporation | Space vector data path |
US5590356A (en) * | 1994-08-23 | 1996-12-31 | Massachusetts Institute Of Technology | Mesh parallel computer architecture apparatus and associated methods |
US5752068A (en) * | 1994-08-23 | 1998-05-12 | Massachusetts Institute Of Technology | Mesh parallel computer architecture apparatus and associated methods |
US5608886A (en) * | 1994-08-31 | 1997-03-04 | Exponential Technology, Inc. | Block-based branch prediction using a target finder array storing target sub-addresses |
US5758176A (en) * | 1994-09-28 | 1998-05-26 | International Business Machines Corporation | Method and system for providing a single-instruction, multiple-data execution unit for performing single-instruction, multiple-data operations within a superscalar data processing system |
US5758112A (en) * | 1994-10-14 | 1998-05-26 | Silicon Graphics, Inc. | Pipeline processor with enhanced method and apparatus for restoring register-renaming information in the event of a branch misprediction |
US5848290A (en) * | 1995-03-09 | 1998-12-08 | Sharp Kabushiki Kaisha | Data driven information processor |
US5737572A (en) * | 1995-06-06 | 1998-04-07 | Apple Computer, Inc. | Bank selection logic for memory controllers |
US5638533A (en) * | 1995-10-12 | 1997-06-10 | Lsi Logic Corporation | Method and apparatus for providing data to a parallel processing array |
US6292879B1 (en) * | 1995-10-25 | 2001-09-18 | Anthony S. Fong | Method and apparatus to specify access control list and cache enabling and cache coherency requirement enabling on individual operands of an instruction of a computer |
US5822606A (en) * | 1996-01-11 | 1998-10-13 | Morton; Steven G. | DSP having a plurality of like processors controlled in parallel by an instruction word, and a control processor also controlled by the instruction word |
US5727229A (en) * | 1996-02-05 | 1998-03-10 | Motorola, Inc. | Method and apparatus for moving data in a parallel processor |
US5924117A (en) * | 1996-12-16 | 1999-07-13 | International Business Machines Corporation | Multi-ported and interleaved cache memory supporting multiple simultaneous accesses thereto |
US5870581A (en) * | 1996-12-20 | 1999-02-09 | Oak Technology, Inc. | Method and apparatus for performing concurrent write operations to a single-write-input register file and an accumulator register |
US5946222A (en) * | 1996-12-20 | 1999-08-31 | Oak Technology, Inc. | Method and apparatus for performing a masked byte addition operation |
US6404439B1 (en) * | 1997-03-11 | 2002-06-11 | Sony Corporation | SIMD control parallel processor with simplified configuration |
US6049330A (en) * | 1997-08-28 | 2000-04-11 | Oak Technology, Inc. | Method and apparatus for optimizing storage of compressed images in memory |
US6211864B1 (en) * | 1997-08-28 | 2001-04-03 | Oak Technology, Inc. | Method and apparatus for optimizing storage of compressed images in memory |
US5933650A (en) * | 1997-10-09 | 1999-08-03 | Mips Technologies, Inc. | Alignment and ordering of vector elements for single instruction multiple data processing |
US6216223B1 (en) * | 1998-01-12 | 2001-04-10 | Billions Of Operations Per Second, Inc. | Methods and apparatus to dynamically reconfigure the instruction pipeline of an indirect very long instruction word scalable processor |
US6067609A (en) * | 1998-04-09 | 2000-05-23 | Teranex, Inc. | Pattern generation and shift plane operations for a mesh connected computer |
US6121905A (en) * | 1998-05-11 | 2000-09-19 | Oak Technology, Inc. | Method and apparatus for decoding JPEG symbols |
US6130631A (en) * | 1998-05-11 | 2000-10-10 | Oak Technology, Inc. | Method and apparatus utilizing a simplified content-addressable memory for JPEG decoding |
US6052703A (en) * | 1998-05-12 | 2000-04-18 | Oak Technology, Inc. | Method and apparatus for determining discrete cosine transforms using matrix multiplication and modified booth encoding |
US6175892B1 (en) * | 1998-06-19 | 2001-01-16 | Hitachi America. Ltd. | Registers and methods for accessing registers for use in a single instruction multiple data system |
US6282628B1 (en) * | 1999-02-24 | 2001-08-28 | International Business Machines Corporation | Method and system for a result code for a single-instruction multiple-data predicate compare operation |
US6487651B1 (en) * | 1999-10-26 | 2002-11-26 | Assabet Ventures | MIMD arrangement of SIMD machines |
US6452864B1 (en) * | 2000-01-31 | 2002-09-17 | Stmicroelectonics S.R.L. | Interleaved memory device for sequential access synchronous reading with simplified address counters |
US6282623B1 (en) * | 2000-02-04 | 2001-08-28 | Motorola Inc. | Method for digital signal processing, DSP, mobile communication and audi o-device |
US6473339B2 (en) * | 2000-03-02 | 2002-10-29 | Stmicroelectronics S.R.L. | Redundancy architecture for an interleaved memory |
Cited By (27)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080127152A1 (en) * | 1999-12-01 | 2008-05-29 | Rajendra Kumar Bera | Compiler optimisation of source code by determination and utilization of the equivalence of algebraic expressions in the source code |
US8028280B2 (en) | 1999-12-01 | 2011-09-27 | International Business Machines Corporation | Compiler optimisation of source code by determination and utilization of the equivalence of algebraic expressions in the source code |
US8176108B2 (en) | 2000-06-20 | 2012-05-08 | International Business Machines Corporation | Method, apparatus and computer program product for network design and analysis |
US20060080071A1 (en) * | 2000-06-20 | 2006-04-13 | International Business Machines Cor | Method, apparatus and computer program product for network design and analysis |
US9235393B2 (en) | 2002-07-09 | 2016-01-12 | Iii Holdings 2, Llc | Statically speculative compilation and execution |
US10101978B2 (en) | 2002-07-09 | 2018-10-16 | Iii Holdings 2, Llc | Statically speculative compilation and execution |
US10248395B2 (en) | 2003-10-29 | 2019-04-02 | Iii Holdings 2, Llc | Energy-focused re-compilation of executables and hardware mechanisms based on compiler-architecture interaction and compiler-inserted control |
US9569186B2 (en) | 2003-10-29 | 2017-02-14 | Iii Holdings 2, Llc | Energy-focused re-compilation of executables and hardware mechanisms based on compiler-architecture interaction and compiler-inserted control |
US7996671B2 (en) | 2003-11-17 | 2011-08-09 | Bluerisc Inc. | Security of program executables and microprocessors based on compiler-architecture interaction |
US9582650B2 (en) | 2003-11-17 | 2017-02-28 | Bluerisc, Inc. | Security of program executables and microprocessors based on compiler-architecture interaction |
US20070169061A1 (en) * | 2003-12-15 | 2007-07-19 | Bera Rajendra K | Run-Time Parallelization of Loops in Computer Programs Using Bit Vectors |
US8028281B2 (en) * | 2003-12-15 | 2011-09-27 | International Business Machines Corporation | Run-Time parallelization of loops in computer programs using bit vectors |
US9697000B2 (en) | 2004-02-04 | 2017-07-04 | Iii Holdings 2, Llc | Energy-focused compiler-assisted branch prediction |
US10268480B2 (en) | 2004-02-04 | 2019-04-23 | Iii Holdings 2, Llc | Energy-focused compiler-assisted branch prediction |
US8607209B2 (en) | 2004-02-04 | 2013-12-10 | Bluerisc Inc. | Energy-focused compiler-assisted branch prediction |
US9244689B2 (en) | 2004-02-04 | 2016-01-26 | Iii Holdings 2, Llc | Energy-focused compiler-assisted branch prediction |
US20060101256A1 (en) * | 2004-10-20 | 2006-05-11 | Dwyer Michael K | Looping instructions for a single instruction, multiple data execution engine |
WO2006044978A3 (en) * | 2004-10-20 | 2006-12-07 | Intel Corp | Looping instructions for a single instruction, multiple data execution engine |
GB2433146A (en) * | 2004-10-20 | 2007-06-13 | Intel Corp | Looping instructions for a single instruction,multiple data execution engine |
WO2006044978A2 (en) * | 2004-10-20 | 2006-04-27 | Intel Corporation | Looping instructions for a single instruction, multiple data execution engine |
GB2433146B (en) * | 2004-10-20 | 2008-12-10 | Intel Corp | Looping instructions for a single instruction, multiple data execution engine |
US9940445B2 (en) | 2006-11-03 | 2018-04-10 | Bluerisc, Inc. | Securing microprocessors against information leakage and physical tampering |
US9069938B2 (en) | 2006-11-03 | 2015-06-30 | Bluerisc, Inc. | Securing microprocessors against information leakage and physical tampering |
US10430565B2 (en) | 2006-11-03 | 2019-10-01 | Bluerisc, Inc. | Securing microprocessors against information leakage and physical tampering |
US11163857B2 (en) | 2006-11-03 | 2021-11-02 | Bluerisc, Inc. | Securing microprocessors against information leakage and physical tampering |
US20110099352A1 (en) * | 2009-10-23 | 2011-04-28 | Mindspeed Technologies, Inc. | Automatic control of multiple arithmetic/logic SIMD units |
US9164770B2 (en) * | 2009-10-23 | 2015-10-20 | Mindspeed Technologies, Inc. | Automatic control of multiple arithmetic/logic SIMD units |
Also Published As
Publication number | Publication date |
---|---|
KR20030072354A (en) | 2003-09-13 |
JP2004513455A (en) | 2004-04-30 |
CN1484786A (en) | 2004-03-24 |
TW563063B (en) | 2003-11-21 |
DE10196879T5 (en) | 2004-04-15 |
US6732253B1 (en) | 2004-05-04 |
WO2002039271A1 (en) | 2002-05-16 |
AU2002234101A1 (en) | 2002-05-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US6732253B1 (en) | Loop handling for single instruction multiple datapath processor architectures | |
US6665790B1 (en) | Vector register file with arbitrary vector addressing | |
US6378041B2 (en) | Shared instruction cache for multiple processors | |
US6343356B1 (en) | Methods and apparatus for dynamic instruction controlled reconfiguration register file with extended precision | |
US6178482B1 (en) | Virtual register sets | |
JP2776132B2 (en) | Data processing system with static and dynamic masking of information in operands | |
JPH04172533A (en) | Electronic computer | |
US6256783B1 (en) | Object conversion apparatus, object conversion method and program storing medium | |
US5940876A (en) | Stride instruction for fetching data separated by a stride amount | |
US20040078554A1 (en) | Digital signal processor with cascaded SIMD organization | |
US6292845B1 (en) | Processing unit having independent execution units for parallel execution of instructions of different category with instructions having specific bits indicating instruction size and category respectively | |
EP0908812B1 (en) | Processor architecture scheme for implementing various addressing modes and method therefor | |
US6029241A (en) | Processor architecture scheme having multiple bank address override sources for supplying address values and method therefor | |
US5737625A (en) | Selectable processing registers and method | |
US5572700A (en) | Cache access controller and method for permitting caching of information in selected cache lines | |
EP0913766B1 (en) | Processor architecture scheme and instruction set for maximizing available opcodes and for implementing various addressing modes | |
US5179681A (en) | Method and apparatus for current window cache with switchable address and out cache registers | |
US5179682A (en) | Method and apparatus for improved current window cache with switchable address in, out, and local cache registers | |
US6886159B2 (en) | Computer system, virtual machine, runtime representation of object, storage media and program transmission apparatus | |
US6243798B1 (en) | Computer system for allowing a two word jump instruction to be executed in the same number of cycles as a single word jump instruction | |
EP0686922B1 (en) | Vector processing unit with reconfigurable data buffer | |
JPH0619710B2 (en) | Register control method | |
JPH04271432A (en) | Operand designating method and central arithmetic processing unit using this method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: ADG ACQUISITION CORP., MASSACHUSETTS Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:FINN, JR., MR. JOSEPH F.;REEL/FRAME:016976/0533 Effective date: 20050523 |
|
STCB | Information on status: application discontinuation |
Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION |