GB2402763A - Data access program instruction encoding - Google Patents
Data access program instruction encoding Download PDFInfo
- Publication number
- GB2402763A GB2402763A GB0313765A GB0313765A GB2402763A GB 2402763 A GB2402763 A GB 2402763A GB 0313765 A GB0313765 A GB 0313765A GB 0313765 A GB0313765 A GB 0313765A GB 2402763 A GB2402763 A GB 2402763A
- Authority
- GB
- United Kingdom
- Prior art keywords
- address value
- data access
- value
- address
- memory
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 19
- 230000004044 response Effects 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- PWPJGUXAGUPAHP-UHFFFAOYSA-N lufenuron Chemical compound C1=C(Cl)C(OC(F)(F)C(C(F)(F)F)F)=CC(Cl)=C1NC(=O)NC(=O)C1=C(F)C=CC=C1F PWPJGUXAGUPAHP-UHFFFAOYSA-N 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
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
- G06F9/30003—Arrangements for executing specific machine instructions
- G06F9/3004—Arrangements for executing specific machine instructions to perform operations on memory
- G06F9/30043—LOAD or STORE instructions; Clear instruction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
-
- 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
-
- 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
- G06F9/30145—Instruction analysis, e.g. decoding, instruction word fields
-
- 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
- G06F9/30145—Instruction analysis, e.g. decoding, instruction word fields
- G06F9/3016—Decoding the operand specifier, e.g. specifier format
-
- 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
- G06F9/30145—Instruction analysis, e.g. decoding, instruction word fields
- G06F9/3016—Decoding the operand specifier, e.g. specifier format
- G06F9/30167—Decoding the operand specifier, e.g. specifier format of immediate specifier, e.g. constants
-
- 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
-
- 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
- G06F9/355—Indexed addressing
Abstract
A data processing apparatus 2 is provided which is responsive to data access instructions to perform data access operations. These data access instructions have a first form utilising a 12-bit offset field but with a fixed addressing mode and a second form utilising a shorter 8-bit offset field but with an addressing mode specified within a manipulation mode control field of the data access instruction.
Description
DATAACCESS PROGRAM INSTRUCTION ENCODING
This invention relates to the field of data processing systems. More particularly, this invention relates to the encoding of data access program instructions for use in data processing systems.
It is known to provide data processing systems with data access instructions.
An example of such a class of program instructions is the LDR/LDRB/STR/STRB class of instructions of the ARM instruction set (see for example the ARM Architecture Reference Manual). These are a group of instructions that are orthogonally encoded with respect to each other, in the sense that they specify different main operations, but each main operation can use the same addressing modes or other sub-operations as all the others. The ARM instruction set is a 32-bit instruction set and the LDRILDRB/STR/STRB class of instructions contains 20 bits that affect the addressing mode calculation: 4 bits (bits[ 19:16]) to specify the base register; 13 bits (bit[25] and bits[11:0]) to specify either a 12-bit immediate offset (a first form of the instruction) or an index register and a shift (or rotate) to be applied to it (a second form of the instruction); and 3 bits (P = bit[24], U = bit[23], W = bit[21]) to specify the manipulation to be performed on the base register value and the offset.
Examples of the addressing modes that may be specified are offset addressing, pre- indexed addressing, post-indexed addressing and unprivileged post-indexed addressing. Such data access instructions provide considerable flexibility in the way that the data access operation may be specified. This helps to reduce the number of instructions required to transfer the desired data to or from memory thereby increasing speed and improving code density.
A common problem within data processing systems is that the encoding bit space available is a finite resource and competing demands are made upon this encoding bit space for different types of instructions which may be useful in different circumstances. It is often the case that the number of potentially useful instructions that might be provided exceeds the encoding bit space available within the processor architecture. Accordingly, measures which can improve the efficiency of use of the encoding bit space are strongly advantageous.
Viewed from one aspect the present invention provides apparatus for processing data, said apparatus comprising: a register bank having one or more registers operable to hold respective data values; a data access circuit operable to perform data access operations transferring one or more data values between said apparatus and addressed memory locations within a memory circuit; and an instruction decoder responsive to data access program instructions to control said data access circuit to perform respective data access operations, each of said data access program instructions including an address offset field that specifies an offset value and including a base register field that specifies a base address register within said register bank and specifying a manipulation to be performed upon said offset value and a base address value held in said base address register to form a memory address value to be accessed within said memory circuit upon execution of said data access program instruction; wherein said data access program instructions have: (i) a first form including an address offset field having a first address offset
field length; and
(ii) a second form including an address offset field having a second address offset field length, said first address offset field length being greater than said second address offset field length and said first form being capable of specifying a lesser number of possible manipulations to be performed upon said base address value and said offset value than said second form.
The invention recognises that in practice most programmers and compilers do not make uniform use of the large number of possibilities that may be provided by data access instructions which give large offset fields and a large number of manipulation mode selections. More particularly, as an example, low values of offsets are much more common than high values. Furthermore, simple offset addressing with the offset being added to the base register value is much more common than any other type of manipulation. It is unusual for two or more of the less common options to simultaneously appear, e.g. a large offset value and post-indexed addressing.
Statistical analysis of programs indicates that non-uniformity in the distributions of instruction types used is a general characteristic of programs and is not a characteristic of particular programmers or particular compilation strategies. The present invention both recognises and exploits this characteristic. In particular, the present invention provides data access program instructions having a first form including a long offset field and few address manipulation options (or just one) and a second form having a shorter offset field but a larger number of address manipulation options. Thus, the total amount of encoding bit space utilised by the data access instructions may be reduced whilst maintaining the availability of instructions directly providing the desired operations in the overwhelming majority of circumstances.
In preferred embodiments, said manipulation forms a modified address value by one out of: adding said offset value to said base address value; and subtracting said offset value from said base address value.
In preferred embodiments, said manipulation also allows at least one of the following options for a data access operation: using said base address value as said memory address value; using said modified address value as said memory address value; using said base address value and writing back said modified address value to said base address register as said memory address value; and using said modified address value and writing back said modified address value to said base address register as said memory address value.
In preferred embodiments, said apparatus can operate in a plurality of modes at least one of which is privileged and at least one of which is unprivileged, data accesses being marked either privileged or unprivileged to allow code to be given different levels of access to said memory circuit.
In preferred embodiments at least one fonm of said manipulation allows a memory access to be forced to be unprivileged regardless of the current mode.
It will be appreciated that the present technique trades off encoding bit space used to specify a manipulation to be applied in the addressing mode against encoding bit space used to specify an offset field. Particularly preferred embodiments are ones in which the first fonm of the instruction operates with a fixed manipulation which accordingly does not require a manipulation mode control field within the instruction and the second fonm of the instruction includes a manipulation mode control field specifying one of a plurality of different manipulations which may be used.
It will be appreciated that any manipulations that are available both in the first fonm of the instruction and in the second fonm of the instruction result in inefficient use of encoding bit space, since any data access operation that can be performed using such a manipulation in the second fonm of the instruction can equally well be perfonned using the same manipulation in the first form of the instruction. So in preferred embodiments, the sets of manipulations provided by said first fonn and said second fonm are disjoint.
Viewed from another aspect the present invention provides a method of processing data, said method comprising the steps of: holding data values within respective ones of one or more registers of a register bank, said register bank forming part of a data processing apparatus; perfonning data access operations with a data access circuit to transfer one or more data values between said data processing apparatus and addressed memory locations within a memory circuit; and in response to data access program instructions, controlling said data access circuit with an instruction decoder to perform respective data access operations, each of said data access program instructions including an address offset field that specifies an offset value and including a base register field that specifies a base address register within said register bank and specifying a manipulation to be performed upon said offset value and a base address value held in said base address register to form a memory address value to be accessed within said memory circuit upon execution of i said data access program instruction; wherein said data access program instructions have: (i) a first form including an address offset field having a first address offset
field length; and
(ii) a second form including an address offset field having a second address] offset field length, said first address offset field length being greater than said second address offset field length and said first form being capable of specifying a lesser number of possible manipulations to be performed upon said base address value and i said offset value than said second form.
Viewed from a further aspect the present invention provides a computer program product having a computer program operable to control a data processing apparatus, said computer program holding one or more data values for manipulation within respective ones of one or more registers of a register bank, and comprising: data access code operable to perform data access operations with a data access circuit to transfer one or more data values between said data processing apparatus and addressed memory locations within a memory circuit; wherein said data access code includes a plurality of data access program instructions, each of said data access program instructions including an address offset field that specifies an offset value and including a base register field that specifies a base address register within said register bank and specifying a manipulation to be performed upon said offset value and a base address value held in said base address register to form a memory address value to be accessed within said memory circuit upon execution of said data access program instruction; wherein said data access program instructions include at least one data access program instruction of each of: (i) a first form including an address offset field having a first address offset
field length; and
(ii) a second form including an address offset field having a second address offset field length, said first address offset field length being greater than said second address offset f eld length and said first form being capable of speci fying a lesser number of possible manipulations to be performed upon said base address value and i said offset value than said second form.
An embodiment of the invention will now be described, by way of example only, with reference to the accompanying drawings in which: i Figure I schematically illustrates a data processing apparatus utilising data access instructions; Figure 2 schematically illustrates a first form of a data access instruction; l 5 Figure 3 schematically illustrates a second form of a data access instruction; Figure 4 is a flow diagram schematically illustrating the operation of an instruction decoder in decoding data access instructions of the first form and of the second form; and Figure 5 is a diagram schematically illustrating the architecture of a general purpose computer which may implement program instructions in accordance with the above described techniques.
Figure I schematically illustrates a data processing apparatus 2 in the form of a processor core containing a register bank 4 having a plurality of program registers for storing respective data values, a multiplier 6, a shifter 8, an adder 10, an instruction i decoder 12, an instruction pipeline 14 and a load/store unit 16. It will be appreciated that the data processing apparatus 2 will typically contain many more circuit elements as will be familiar to those in this technical field, but these circuit elements have been omitted from Figure l for the sake of clarity. In operation program instructions are fetched from memory (not illustrated) into the instruction pipeline 14. When a program instruction reaches the decode stage in the instruction pipeline 14, it is decoded by the instruction decoder 12 which generates control signals applied to the data processing logic including the register bank 4, the multiplier 6, the shifter 8 and the adder 10 to perform a desired data processing operation. s
One type of program instruction which may be executed and to which the instruction decoder 12 is responsive is a data access instruction. Such a data access instruction specifies a load or a store operation to be performed by the load/store unit 16 to write data to or read from a specified address or sequence of addresses within the memory coupled to the data processing apparatus 2. The data values being accessed are either written to or read from respective registers within the register bank 4 m this load/store architecture type of data processing apparatus. However this is not an essential requirement.
As will be familiar from the type of data access instructions provided by the existing ARM instruction set these data access instructions can specify an immediate offset value and a manipulation mode to be used. The instruction decoder 12 is responsive to fields within the data access instruction specifying these parameters and passes these parameters on to the load/store unit 16 for action. A base register specifier field included in the data access instruction specifies one of the program registers within the register bank 4, which is read by the load/store unit 16 to obtain a base address value to be used in the data access operation. The memory address value used to access memory is formed from this base address value by the manipulation, which may for example consist of the addition of an offset value contained in an address offset field of the instruction. In this apparatus, respective data values that are transferred to or from memory are read from or written to the register bank 4 by the load/store unit 16.
Figure 2 schematically illustrates a first form of data access instruction. This instruction comprises two 16-bit halfwords. In this first form, bitted = 1 in halfword HW1 to indicate to the instruction decoder 12 that halfword HW2 contains a long 12- bit offset value field offsets 2 and that the instruction uses a fixed address manipulation, in which the zero-extended offset value is added to the base address value and the result is used as the memory address value for the data access.
The field Rn specifies the register which holds the base address value. The field Rd specifies the register which is to be either the source or the destination of the data access operation. Bits[15:9] of halfword HW1 specify that this instruction is a data access instruction, and bits[7:4] of halfword HW1 are an opcode field which specifies details of the data access to be performed: whether a load or a store is to be performed, the length of the data to be accessed in memory (e.g. an 8-bit byte, a 16-bit halfword or a 32-bit word), and in cases where a narrow data value is being loaded into a wider register, whether the value is to be zeroextended or sign-extended.
Figure 3 schematically illustrates a second form of data access instruction. In this second form, bitts] = 0 in halfword HW1 to indicate to the instruction decoder 12 l S that halfword HW2 contains a short 8bit offset value field offsets and also contains 3 bits P. U and W that specify the address manipulation to be used. The fields Rn and Rd. and bits[ 15:9] and bits[7:4] of halfword HW1 specify the same things as they do in Figure 2.
The U bit specifies whether the zero-extended offset value is to be added to or subtracted from the base address value to form a modified address value.
The P bit specifies whether the memory address value used for the data access is the base address value or the modified address value.
The W bit specifies whether the register which holds the base address value is left unchanged or has the modified address value written back to it.
In addition, when the P. U and W bits specify the address manipulation used by the first form (that is, the offset is added to the base address value, the modified address value is used for the data access, and the register which holds the base address value is left unchanged), the data access is marked as unprivileged regardless of whether the processor is in an unprivileged or privileged mode of operation. It will be appreciated that this combination of the P. U and W bits would otherwise be redundant, as the first form of the instruction makes the required data access operations available. s
It will be seen from the above that the first form of the data access instruction illustrated in Figure 2 provides a large offset field at the expense of a fixed address manipulation whereas the second form of the data access instruction as illustrated in Figure 3 provides a smaller offset field but does give a larger number of options for the address manipulation to be performed. It has been found that the combination of the data access instruction of the first form and the second form is particularly advantageous in providing good coverage to the type of data access operations which are desired whilst reducing the amount of encoding bit space used to specify these ' parameters. The encoding bit space saved may then be used for other purposes to I considerable advantage. The above encoding requires 13 bits to specify the offset and l the address manipulation (HWI [8] and HW2[ 11:0]), whereas a simple (P. U. W. offset 12) encoding as used in the ARM instruction set would require IS.
As an alternative encoding it is also possible to use: HWI[15:9] =lllllOOratherthanlllOlOlasshowninFigures2and3.
HW1[7] to distinguish the two forms of the instruction rather than HW1[8], and HW1[8,6:4] as the opcode field rather than HWI [7:4].
In Figure 3, HW2[11] = 1 rather than O as shown.
Figure 4 is a flow diagram schematically illustrating the processing operation performed by the instruction decoder 12. It will be appreciated that the sequential processing illustrated in Figure 4 may not in practice happen within the instruction decoder 12 wherein considerable parallelism may be employed. However, Figure 4 assists in providing an understanding of the decoding required and the operations performed. i At step 18 the instruction decoder identifies a data access instruction by the most significant seven bits of the first halfword HW1. If another type of instruction is identified then this is decoded at step 19. At step 20 the instruction decoder 12 examines bit [8] within the halfword HW1 to determine whether the data access instruction is one of the first form or one of the second form. If this bit [8] is equal to "1", then the data access instruction has the first form and processing proceeds to step 24 at which the opcode is decoded to determine further parameters associated with the data access instruction desired and the long 12-bit offset value is used with the fixed manipulation mode of offset addressing with the offset being added.
If the determination at step 20 was that bit [8] = 0, then processing proceeds to step 28 where the manipulation mode control field [10:8] of halfword HW2 is decoded to determine which of the previously mentioned address manipulation modes is to be used. Then at step 30 the data access specified by the opcode HW1 [7:4] is performed I using the smaller 8-bit offset value and the specified manipulation. I Figure 5 schematically illustrates a general purpose computer 200 which may implement program instructions in accordance with the above described techniques.
The general purpose computer 200 includes a central processing unit 202, a random access memory 204, a read only memory 206, a network interface card 208, a hard disk drive 210, a display driver 212 and monitor 214 and a user input/output circuit 216 with a keyboard 218 and mouse 220 all connected via a common bus 222. In operation the central processing unit 202 will execute computer program instructions that may be stored in one or more of the random access memory 204, the read only memory 206 and the hard disk drive 210 or dynamically downloaded via the network interface card 208. The results of the processing performed may be displayed to a user via the display driver 212 and the monitor 214. User inputs for controlling the operation of the general purpose computer 200 may be received via the user input output circuit 216 from the keyboard 218 or the mouse 220. It will be appreciated that the computer program could be written in a variety of different computer languages. I The computer program may be stored and distributed on a recording medium or dynamically downloaded to the general purpose computer 200. When operating under control of an appropriate computer program, the general purpose computer 200 can perform the above described techniques and can be considered to form an apparatus for performing the above described technique. The architecture of the general purpose computer 200 could vary considerably and Figure 5 is only one example.
Claims (30)
1. Apparatus for processing data, said apparatus comprising: a register bank having one or more registers operable to hold respective data values; a data access circuit operable to perform data access operations transferring one or more data values between said apparatus and addressed memory locations within a memory circuit; and an instruction decoder responsive to data access program instructions to control said data access circuit to perform respective data access operations, each of said data access program instructions including an address offset field that specifies an offset value and including a base register field that specifies a base address register within said register bank and specifying a manipulation to be performed upon said offset value and a base address value held in said base address register to form a memory address value to be accessed within said memory circuit upon execution of said data access program instruction; wherein said data access program instructions have: (i) a first form including an address offset field having a first address offset
field length; and
(ii) a second form including an address offset field having a second address offset field length, said first address offset field length being greater than said second address offset field length and said first form being capable of specifying a lesser number of possible manipulations to be performed upon said base address value and said offset value than said second form.
2. Apparatus as claimed in claim 1, wherein said manipulation forms a modified address value by one out of: adding said offset value to said base address value; and subtracting said offset value from said base address value.
3. Apparatus as claimed in any one of claims 1 and 2, wherein said manipulation also allows at least one of the following options for a data access operation: using said base address value as said memory address value; using said modified address value as said memory address value; using said base address value and writing back said modified address value to said base address register as said memory address value; and using said modified address value and writing back said modified address value to said base address register as said memory address value.
4. Apparatus as claimed in any of claims 1, 2 and 3, wherein said apparatus can operate in a plurality of modes at least one of which is privileged and at least one of which is unprivileged, data accesses being marked either privileged or unprivileged to allow code to be given different levels of access to said memory circuit.
5. Apparatus as claimed in claim 4, wherein at least one form of said manipulation allows a memory access to be forced to be unprivileged regardless of the current mode.
6. Apparatus as claimed in any one of the preceding claims, wherein data access program instructions of said first form operate with a fixed manipulation in which a sum of said base address value and said offset value is used as said memory address value and said base address value is unchanged after execution.
7. Apparatus as claimed in any one of the preceding claims, wherein said data access program instructions of said second form includes a manipulation mode control field specifying which one of a plurality of different manipulations is to be used.
8. Apparatus as claimed in any one of the preceding claims wherem the sets of manipulations provided by said first form and said second form are disjoint.
9. Apparatus as claimed in any one of the preceding claims, wherein said data values are transferred between respective registers of said register bank and said addressed memory locations.
10. A method of processing data, said method comprising the steps of: holding data values within respective ones of one or more registers of a register bank, said register bank forming part of a data processing apparatus; performing data access operations with a data access circuit to transfer one or more data values between said data processing apparatus and addressed memory locations within a memory circuit; and in response to data access program instructions, controlling said data access circuit with an instruction decoder to perform respective data access operations, each of said data access program instructions including an address offset field that specifies l O an offset value and including a base register field that specifies a base address register within said register bank and specifying a manipulation to be performed upon said offset value and a base address value held in said base address register to form a memory address value to be accessed within said memory circuit upon execution of said data access program instruction; wherein said data access program instructions have: (i) a first form including an address offset field having a first address offset
field length; and
(ii) a second form including an address offset field having a second address offset field length, said first address offset field length being greater than said second address offset field length and said first form being capable of specifying a lesser number of possible manipulations to be performed upon said base address value and said offset value than said second form.
11. A method as claimed in claim 10, wherein said manipulation forms a modified address value by one out of: adding said offset value to said base address value; and subtracting said offset value from said base address value.
12. A method as claimed in any one of claims l 0 and l l, wherein said manipulation also allows at least one of the following options for a data access operation: using said base address value as said memory address value; using said modified address value as said memory address value; using said base address value and writing back said modified address value to said base address register as said memory address value; and using said modified address value and writing back said modified address value to said base address register as said memory address value.
13. A method as claimed in any one of claims 10, 1 1 and 12, wherein said method is operable in a plurality of modes at least one of which is privileged and at least one of which is unprivileged, data accesses being marked either privileged or unprivileged to allow code to be given different levels of access to said memory circuit.
14. A method as claimed in claim 13, wherein at least one form of said manipulation allows a memory access to be forced to be unprivileged regardless of the current mode.
15. A method as claimed in any one of claims 10 to 14, wherein data access program instructions of said first form operate with a fixed manipulation in which a sum of said base address value and said offset value is used as said memory address value and said base address value is unchanged after execution.
16. A method as claimed in any one of claims 10 to 15, wherein said data access program instructions of said second form includes a manipulation mode control field specifying which one of a plurality of different manipulations is to be used.
17. A method as claimed in any one of claims 10 to 16, wherein the sets of manipulations provided by said first form and said second form are disjoint.
18. A method as claimed in any one of claims 10 to 17, wherein said data values are transferred between respective registers of said register bank and said addressed memory locations.
19. A computer program product having a computer program operable to control a data processing apparatus, said computer program holding one or more data values for manipulation within respective ones of one or more registers of a register bank, and comprising: data access code operable to perform data access operations with a data access circuit to transfer one or more data values between said data processing apparatus and addressed memory locations within a memory circuit; wherein I said data access code includes a plurality of data access program instructions, each of said data access program instructions including an address offset field that specifies an offset value and including a base register field that specifies a base address register within said register bank and specifying a manipulation to be performed upon said offset value and a base address value held in said base address register to form a memory address value to be accessed within said memory circuit upon execution of said data access program instruction; wherein said data access program instructions include at least one data access program instruction of each of: (i) a first form including an address offset field having a first address offset
field length; and
(ii) a second form including an address offset field having a second address offset field length, said first address offset field length being greater than said second address offset field length and said first form being capable of specifying a lesser number of possible manipulations to be performed upon said base address value and said offset value than said second form.
20. A computer program product as claimed in claim 19, wherein said manipulation forms a modified address value by one out of: adding said offset value to said base address value; and subtracting said offset value from said base address value.
21. A computer program product as claimed in any one of claims 19 and 20, wherein said manipulation also allows at least one of the following options for a data access operation: using said base address value as said memory address value; using said modified address value as said memory address value; using said base address value and writing back said modified address value to said base address register as said memory address value; and using said modified address value and writing back said modified address value to said base address register as said memory address value.
22. A computer program product as claimed in any one of claims 19, 20 and 21, wherein said method is operable in a plurality of modes at least one of which is privileged and at least one of which is unprivileged, data accesses being marked either privileged or unprivileged to allow code to be given different levels of access to said memory circuit.
23. A computer program product as claimed in claim 22, wherein at least one form of said manipulation allows a memory access to be forced to be unprivileged regardless of the current mode.
24. A computer program product as claimed in any one of claims 19 to 23, wherein data access program instructions of said first form operate with a fixed manipulation in which a sum of said base address value and said offset value is used as said memory address value and said base address value is unchanged after execution.
25. A computer program product as claimed in any one of claims 19 to 24, wherein said data access program instructions of said second form includes a manipulation mode control field specifying which one of a plurality of different manipulations is to be used.
26. A computer program product as claimed in any one of claims 19 to 25, wherein the sets of manipulations provided by said first form and said second form are disjoint.
27. A computer program product as claimed in any one of claims 19 to 26, wherein said data values are transferred between respective registers of said register bank and said addressed memory locations.
28. Apparatus for processing data substantially as hereinbefore described with reference to the accompanying drawings.
29. A method of processing data substantially as hereinbefore described with reference to the accompanying drawings.
30. A computer program product substantially as hereinbefore described with reference to the accompanying drawings.
Priority Applications (13)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
GB0313765A GB2402763B (en) | 2003-06-13 | 2003-06-13 | Data access program instruction encoding |
AU2003290356A AU2003290356A1 (en) | 2003-06-13 | 2003-12-30 | Data access program instruction encoding |
PCT/GB2003/005684 WO2004111834A2 (en) | 2003-06-13 | 2003-12-30 | Data access program instruction encoding |
RU2006101156/09A RU2006101156A (en) | 2003-06-13 | 2003-12-30 | CODING DATA ACCESS PROGRAM TEAMS |
EP03782717A EP1634164A2 (en) | 2003-06-13 | 2003-12-30 | Data access program instruction encoding |
CNB2003801104169A CN100409178C (en) | 2003-06-13 | 2003-12-30 | Data access program instruction encoding |
KR1020057023642A KR100972160B1 (en) | 2003-06-13 | 2003-12-30 | Data access program instruction encoding |
JP2005500707A JP3990423B2 (en) | 2003-06-13 | 2003-12-30 | Coding data access program instructions |
US10/765,181 US7231507B2 (en) | 2003-06-13 | 2004-01-28 | Data access program instruction encoding |
TW093102677A TWI325542B (en) | 2003-06-13 | 2004-02-05 | Data access program instruction encoding |
MYPI20040390A MY135360A (en) | 2003-06-13 | 2004-02-10 | Data access program instruction encoding |
IL172236A IL172236A0 (en) | 2003-06-13 | 2005-11-28 | Data access program instruction encoding |
US11/703,091 US7447871B2 (en) | 2003-06-13 | 2007-02-07 | Data access program instruction encoding |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
GB0313765A GB2402763B (en) | 2003-06-13 | 2003-06-13 | Data access program instruction encoding |
Publications (3)
Publication Number | Publication Date |
---|---|
GB0313765D0 GB0313765D0 (en) | 2003-07-23 |
GB2402763A true GB2402763A (en) | 2004-12-15 |
GB2402763B GB2402763B (en) | 2006-03-01 |
Family
ID=27636507
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
GB0313765A Expired - Lifetime GB2402763B (en) | 2003-06-13 | 2003-06-13 | Data access program instruction encoding |
Country Status (12)
Country | Link |
---|---|
US (2) | US7231507B2 (en) |
EP (1) | EP1634164A2 (en) |
JP (1) | JP3990423B2 (en) |
KR (1) | KR100972160B1 (en) |
CN (1) | CN100409178C (en) |
AU (1) | AU2003290356A1 (en) |
GB (1) | GB2402763B (en) |
IL (1) | IL172236A0 (en) |
MY (1) | MY135360A (en) |
RU (1) | RU2006101156A (en) |
TW (1) | TWI325542B (en) |
WO (1) | WO2004111834A2 (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2017068317A1 (en) * | 2015-10-20 | 2017-04-27 | Arm Limited | Memory access instructions |
Families Citing this family (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8909676B1 (en) * | 2006-10-06 | 2014-12-09 | Uei Cayman Inc. | Star cluster codeset database for universal remote control devices |
WO2008077805A1 (en) * | 2006-12-22 | 2008-07-03 | Telefonaktiebolaget L M Ericsson (Publ) | Data-processing unit |
EP1936493A1 (en) * | 2006-12-22 | 2008-06-25 | Telefonaktiebolaget LM Ericsson (publ) | Data-processing unit |
US20090177687A1 (en) * | 2008-01-09 | 2009-07-09 | Rune Ljungbjorn | Method for providing flexible inheritance of program environment |
JP2010039503A (en) * | 2008-07-31 | 2010-02-18 | Panasonic Corp | Serial memory device and signal processing system |
US8677100B2 (en) * | 2009-07-17 | 2014-03-18 | Macronix International Co., Ltd. | Serial memory interface for extended address space |
US10163187B2 (en) * | 2009-10-30 | 2018-12-25 | Intel Corproation | Graphics rendering using a hierarchical acceleration structure |
US20130339656A1 (en) * | 2012-06-15 | 2013-12-19 | International Business Machines Corporation | Compare and Replace DAT Table Entry |
US9089239B2 (en) | 2013-02-28 | 2015-07-28 | Planetary Design | Infuser with solid region to selectively stop infusion and vessel for said infuser |
US20160378480A1 (en) * | 2015-06-27 | 2016-12-29 | Pavel G. Matveyev | Systems, Methods, and Apparatuses for Improving Performance of Status Dependent Computations |
KR20190052315A (en) * | 2017-11-08 | 2019-05-16 | 에스케이하이닉스 주식회사 | Memory device and memory system including the same |
CN111158756B (en) * | 2019-12-31 | 2021-06-29 | 百度在线网络技术(北京)有限公司 | Method and apparatus for processing information |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO1994016391A1 (en) * | 1992-12-31 | 1994-07-21 | Intel Corporation | Bus to bus interface with address translation |
EP0730226A2 (en) * | 1995-03-03 | 1996-09-04 | Hal Computer Systems, Inc. | Hardware support for fast software emulation of unimplemented instructions |
US20020013691A1 (en) * | 2000-03-15 | 2002-01-31 | Peter Warnes | Method and apparatus for processor code optimization using code compression |
Family Cites Families (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1187255A (en) * | 1995-06-07 | 1998-07-08 | 高级微型器件公司 | Microprocessor using instruction field to specify expanded functionality |
JP2889845B2 (en) * | 1995-09-22 | 1999-05-10 | 松下電器産業株式会社 | Information processing device |
US5926642A (en) * | 1995-10-06 | 1999-07-20 | Advanced Micro Devices, Inc. | RISC86 instruction set |
US5987583A (en) * | 1997-10-07 | 1999-11-16 | Microchip Technology Inc. | Processor architecture scheme and instruction set for maximizing available opcodes and address selection modes |
US6282633B1 (en) * | 1998-11-13 | 2001-08-28 | Tensilica, Inc. | High data density RISC processor |
US6560694B1 (en) * | 2000-01-14 | 2003-05-06 | Advanced Micro Devices, Inc. | Double prefix overrides to provide 16-bit operand size in a 32/64 operating mode |
JP3556556B2 (en) * | 2000-02-08 | 2004-08-18 | 株式会社東芝 | Instruction code conversion device and information processing system |
US6651160B1 (en) * | 2000-09-01 | 2003-11-18 | Mips Technologies, Inc. | Register set extension for compressed instruction set |
US7093108B2 (en) * | 2001-02-01 | 2006-08-15 | Arm Limited | Apparatus and method for efficiently incorporating instruction set information with instruction addresses |
AU2003210749A1 (en) * | 2002-01-31 | 2003-09-02 | Arc International | Configurable data processor with multi-length instruction set architecture |
US7191318B2 (en) * | 2002-12-12 | 2007-03-13 | Alacritech, Inc. | Native copy instruction for file-access processor with copy-rule-based validation |
-
2003
- 2003-06-13 GB GB0313765A patent/GB2402763B/en not_active Expired - Lifetime
- 2003-12-30 EP EP03782717A patent/EP1634164A2/en not_active Ceased
- 2003-12-30 CN CNB2003801104169A patent/CN100409178C/en not_active Expired - Lifetime
- 2003-12-30 AU AU2003290356A patent/AU2003290356A1/en not_active Abandoned
- 2003-12-30 RU RU2006101156/09A patent/RU2006101156A/en not_active Application Discontinuation
- 2003-12-30 KR KR1020057023642A patent/KR100972160B1/en active IP Right Grant
- 2003-12-30 WO PCT/GB2003/005684 patent/WO2004111834A2/en active Application Filing
- 2003-12-30 JP JP2005500707A patent/JP3990423B2/en not_active Expired - Lifetime
-
2004
- 2004-01-28 US US10/765,181 patent/US7231507B2/en active Active
- 2004-02-05 TW TW093102677A patent/TWI325542B/en not_active IP Right Cessation
- 2004-02-10 MY MYPI20040390A patent/MY135360A/en unknown
-
2005
- 2005-11-28 IL IL172236A patent/IL172236A0/en active IP Right Grant
-
2007
- 2007-02-07 US US11/703,091 patent/US7447871B2/en not_active Expired - Lifetime
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO1994016391A1 (en) * | 1992-12-31 | 1994-07-21 | Intel Corporation | Bus to bus interface with address translation |
EP0730226A2 (en) * | 1995-03-03 | 1996-09-04 | Hal Computer Systems, Inc. | Hardware support for fast software emulation of unimplemented instructions |
US20020013691A1 (en) * | 2000-03-15 | 2002-01-31 | Peter Warnes | Method and apparatus for processor code optimization using code compression |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2017068317A1 (en) * | 2015-10-20 | 2017-04-27 | Arm Limited | Memory access instructions |
US11669467B2 (en) | 2015-10-20 | 2023-06-06 | Arm Limited | Memory access instructions |
Also Published As
Publication number | Publication date |
---|---|
CN1826582A (en) | 2006-08-30 |
US7231507B2 (en) | 2007-06-12 |
TW200428225A (en) | 2004-12-16 |
KR20060028403A (en) | 2006-03-29 |
GB2402763B (en) | 2006-03-01 |
EP1634164A2 (en) | 2006-03-15 |
AU2003290356A1 (en) | 2005-01-04 |
KR100972160B1 (en) | 2010-07-26 |
US20040255095A1 (en) | 2004-12-16 |
WO2004111834A2 (en) | 2004-12-23 |
JP3990423B2 (en) | 2007-10-10 |
IL172236A0 (en) | 2006-04-10 |
CN100409178C (en) | 2008-08-06 |
RU2006101156A (en) | 2006-06-10 |
JP2006527420A (en) | 2006-11-30 |
US20070136558A1 (en) | 2007-06-14 |
US7447871B2 (en) | 2008-11-04 |
MY135360A (en) | 2008-03-31 |
GB0313765D0 (en) | 2003-07-23 |
TWI325542B (en) | 2010-06-01 |
WO2004111834A3 (en) | 2005-12-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7447871B2 (en) | Data access program instruction encoding | |
US7558942B1 (en) | Memory mapped register file and method for accessing the same | |
US6021265A (en) | Interoperability with multiple instruction sets | |
US7051190B2 (en) | Intra-instruction fusion | |
US6351806B1 (en) | Risc processor using register codes for expanded instruction set | |
JP5027669B2 (en) | Microprocessor, integrated circuit, system and method | |
US20110225397A1 (en) | Mapping between registers used by multiple instruction sets | |
US7546442B1 (en) | Fixed length memory to memory arithmetic and architecture for direct memory access using fixed length instructions | |
EP1680735B1 (en) | Apparatus and method that accomodate multiple instruction sets and multiple decode modes | |
US6578139B1 (en) | Processor architecture scheme which uses virtual address registers to implement different addressing modes and method therefor | |
EP0982655A2 (en) | Data processing unit and method for executing instructions of variable lengths | |
US5987583A (en) | Processor architecture scheme and instruction set for maximizing available opcodes and address selection modes | |
US20110047355A1 (en) | Offset Based Register Address Indexing | |
US20070245120A1 (en) | Multiple microcontroller system, instruction, and instruction execution method for the same | |
US6321319B2 (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 | |
US20100115239A1 (en) | Variable instruction width digital signal processor | |
CA1250666A (en) | Central processing unit for a digital computer | |
US20050188183A1 (en) | Digital signal processor having data address generator with speculative register file |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PE20 | Patent expired after termination of 20 years |
Expiry date: 20230612 |