US20040015676A1 - Sharing of a logic operator having a work register - Google Patents
Sharing of a logic operator having a work register Download PDFInfo
- Publication number
- US20040015676A1 US20040015676A1 US10/619,105 US61910503A US2004015676A1 US 20040015676 A1 US20040015676 A1 US 20040015676A1 US 61910503 A US61910503 A US 61910503A US 2004015676 A1 US2004015676 A1 US 2004015676A1
- Authority
- US
- United States
- Prior art keywords
- operator
- function
- present
- register
- circuit
- 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
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
- G06F9/30003—Arrangements for executing specific machine instructions
- G06F9/30007—Arrangements for executing specific machine instructions to perform operations on data operands
- G06F9/3001—Arithmetic instructions
-
- 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
- G06F9/30098—Register arrangements
- G06F9/30101—Special purpose registers
Definitions
- the present invention generally relates to the processing of binary words by calculation functions.
- the present invention more specifically relates to the execution, by a state machine in wired logic of an integrated circuit, of a calculation representing a function likely to be used by several applications within this same circuit.
- An example of application of the present invention relates to the implementation, within a same circuit, of several processings all using a same operating function.
- it may be a public key signature processing, a data integrity control or a random generator for cryptography.
- a so-called “Hash” discriminating function is generally used, for example, functions known as SHA, MD5, etc.
- a first problem is linked to the existence of a work register storing the results of the different iterations. Indeed, this means in practice that the result of the functions is only obtained at the end of the multiple iterations.
- a solution would consist of having interrupts generated by other applications wait until the iteration calculation is over. This is however incompatible with a desire of real time execution required by some applications needing the operator. For example, in the context of an integrity control requiring the discrimination operator for an authentication message calculation, it cannot be awaited until the operator is freed by another application.
- the present invention aims at providing a solution to the problem of the sharing of a logic operator by several applications exploiting a same iterative discrimination function.
- the present invention also aims at providing a solution which is compatible with the desired miniaturization of integrated circuits.
- the present invention also aims at enabling sharing of the operator in wired logic without adversely affecting the need for real time processing of a priority-holding application.
- the present invention provides a circuit for calculating a discriminating function with successive iterations and with a work register on data divided into blocks, comprising:
- each register stores a current state of the operator and the rank of the corresponding iteration.
- said function is a Hash function.
- a multiplexer forming the selection element is controlled by a priority decoder associated with an integrated processor containing said calculation circuit.
- FIG. 1 very schematically shows in the form of blocks an embodiment of the circuit for calculating a discrimination function according to the present invention.
- FIG. 2 is a flowchart of a function exploited by the calculation circuit of FIG. 1 according to an embodiment of the present invention.
- a feature of the present invention is to dissociate, in a calculation circuit implementing an iterative discriminating function with a work register, the actual operator from the work register. According to the present invention, it is provided to share the operator between several work registers individually dedicated to different applications.
- FIG. 1 very schematically shows in the form of blocks an embodiment of a shared calculation circuit according to the present invention.
- Circuit 1 essentially comprises a logic operator 2 (f(PSi-1, Bi)) executing an operation using as operands a binary block B and a state PS representing the result of the operation at a previous iteration.
- the processed data (in the example of FIG. 1, block B) forms a portion of a data word for which an application requires use of the discriminating function.
- the input (PS) and the output (CS) states of operator 2 correspond to the successive contents of a single work register per application.
- work registers 3 REG 1 , . . . , REGj, . . . REGn)
- there are applications to share circuit 1 are provided.
- Each register 3 is equivalent to a conventional work register associated with a wired operator 2 .
- inputs/outputs of registers 3 are connected to the multiple inputs of a multiplexer 4 having a single input/output connected to the input (signal PS)) of operator 2 and to the output (signal CS) of operator 2 .
- Multiplexer 4 receives a selection signal (SEL) coming, for example, from a priority control (not shown) associated with the central processing unit of the processor integrating circuit 1 .
- Initial states IS 1 , . . . ISj, . . . ISn are loaded under control of the CPU into each register 3 .
- the final states FS 1 , FSj, . . . FSn of function f after the required iterations are read individually from each register, by the processor circuits having required the application of the Hash function to a given binary word.
- number m of iterations depends on the number of data blocks to be processed.
- number n of registers depends on the number of applications which require operator 2 .
- FIG. 2 is a simplified flowchart of the function performed by operator 2 .
- the function starts (block 10 , IS) from an initial state.
- This state is, in the example of FIG. 1, previously loaded into one of the work registers associated with the application having requested the function.
- this initial state is predetermined.
- the data words to be processed by the discriminating function are also stored in adapted memorization elements (for example, registers).
- Rank i stored in register 3 assigned to the application is used to select the appropriate data block upon resumption of the iterations for the concerned application.
- An advantage of the present invention is that it enables sharing a same operator in wired logic for several discriminating functions executed by different applications of an integrated processor.
- Another advantage of the present invention is that by avoiding storage of the intermediary calculation states in an external memory of the integrated circuit, the present invention preserves the security character generally required for applications of discriminating functions.
- Another advantage of the present invention is that its implementation is particularly simple in an integrated processor.
- the implementation of the present invention is compatible with the hardware circuits and control processes generally used in integrated processors.
- the application processed by operator 2 is transparent for said operator, in that all operates as if it was only connected to one register.
- operator 2 is shared by several applications among which at least one real time data integrity control. In this case, this application is considered as holding the highest priority.
- a second possible application may be a signature or authentication code calculation having a lower priority rank.
- the present invention is likely to have various alterations, modifications, and improvements which will readily occur to those skilled in the art.
- the practical forming of the calculation circuit according to the present invention is within the abilities of those skilled in the art based on the functional indications given hereabove.
- the commands necessary to the multiplexer and to the different register by using conventional control means are within the abilities of those skilled in the art.
- the selection of the block Bi assigned to the data word of the application may be performed in several manners. For example, the integrated circuit CPU manages the reading of the desired blocks according to the decided priorities.
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Advance Control (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Storage Device Security (AREA)
Abstract
A circuit for calculating a discriminating function with successive iterations and with a work register on data divided into blocks, comprising: a single operator in wired logic for executing the function; a plurality of work registers sharing said operator; and an element for selecting one of the work registers to be associated with the operator.
Description
- 1. Field of the Invention
- The present invention generally relates to the processing of binary words by calculation functions. The present invention more specifically relates to the execution, by a state machine in wired logic of an integrated circuit, of a calculation representing a function likely to be used by several applications within this same circuit.
- 2. Discussion of the Related Art
- An example of application of the present invention relates to the implementation, within a same circuit, of several processings all using a same operating function. For example, it may be a public key signature processing, a data integrity control or a random generator for cryptography. In all the above cases, a so-called “Hash” discriminating function is generally used, for example, functions known as SHA, MD5, etc.
- Most of these discriminating functions are based on an iterative processing of a message divided into blocks taking into account the result of the previous iteration. They thus generally use a single work register which is updated at each iteration and forms, at the function end, an output register providing the desired result (calculated signature, integrity control authentication code, or random bit train) to be exploited by the rest of the circuit.
- It would be desirable, for miniaturization, to be able to share a same logic operator for several processings exploiting a same function.
- However, this poses several problems due to the very nature of the functions to which the present invention applies.
- A first problem is linked to the existence of a work register storing the results of the different iterations. Indeed, this means in practice that the result of the functions is only obtained at the end of the multiple iterations.
- A solution would consist of having interrupts generated by other applications wait until the iteration calculation is over. This is however incompatible with a desire of real time execution required by some applications needing the operator. For example, in the context of an integrity control requiring the discrimination operator for an authentication message calculation, it cannot be awaited until the operator is freed by another application.
- It could also have been devised to memorize an intermediary state of an interruptible application to leave the work register and the operator available for another priority-holding application. However, a memorization followed by a restoring of the states of the work register associated with the operator adversely affects the system performances and weakens it as concerns security against possible piracies of the handled quantities.
- In practice, the only acceptable conventional solution when several applications (signature, integrity, random number generation) must use a Hash-type discrimination function, is to provide as many circuits (operator+register) as there are applications.
- The present invention aims at providing a solution to the problem of the sharing of a logic operator by several applications exploiting a same iterative discrimination function.
- The present invention also aims at providing a solution which is compatible with the desired miniaturization of integrated circuits.
- The present invention also aims at enabling sharing of the operator in wired logic without adversely affecting the need for real time processing of a priority-holding application.
- To achieve these and other objects, the present invention provides a circuit for calculating a discriminating function with successive iterations and with a work register on data divided into blocks, comprising:
- a single operator in wired logic for executing the function;
- a plurality of work registers sharing said operator; and
- an element for selecting one of the work registers to be associated with the operator.
- According to an embodiment of the present invention, each register stores a current state of the operator and the rank of the corresponding iteration.
- According to an embodiment of the present invention, said function is a Hash function.
- According to an embodiment of the present invention, a multiplexer forming the selection element is controlled by a priority decoder associated with an integrated processor containing said calculation circuit.
- The foregoing objects, features and advantages of the present invention will be discussed in detail in the following non-limiting description of specific embodiments in connection with the accompanying drawings.
- FIG. 1 very schematically shows in the form of blocks an embodiment of the circuit for calculating a discrimination function according to the present invention; and
- FIG. 2 is a flowchart of a function exploited by the calculation circuit of FIG. 1 according to an embodiment of the present invention.
- For clarity, only those steps and those elements which are necessary to the understanding of the present invention have been shown in the drawings and will be described hereafter. In particular, the exploitation made of the calculations by the discrimination function have not been detailed and are no object of the present invention, the present invention applying whatever the application requiring use of the wired operator. Further, the other components of an integrated circuit containing the calculation circuit of the present invention are conventional and have not been described.
- A feature of the present invention is to dissociate, in a calculation circuit implementing an iterative discriminating function with a work register, the actual operator from the work register. According to the present invention, it is provided to share the operator between several work registers individually dedicated to different applications.
- FIG. 1 very schematically shows in the form of blocks an embodiment of a shared calculation circuit according to the present invention.
-
Circuit 1 essentially comprises a logic operator 2 (f(PSi-1, Bi)) executing an operation using as operands a binary block B and a state PS representing the result of the operation at a previous iteration. - The processed data (in the example of FIG. 1, block B) forms a portion of a data word for which an application requires use of the discriminating function.
- The previous state PSI-1 combined by
logic state machine 2 with current block Bi is initialized at the beginning of an iteration by an initial value IS, and corresponds after the last iteration of the discriminating function to final result FS required by the application. - Up to this point, what has been described corresponds to a wired operator of a conventional discriminating function. For example, it may be a so-called Hash function.
- According to the present invention, the input (PS) and the output (CS) states of
operator 2 correspond to the successive contents of a single work register per application. However, as many work registers 3 (REG1, . . . , REGj, . . . REGn)) as there are applications to sharecircuit 1 are provided. - Each
register 3 is equivalent to a conventional work register associated with awired operator 2. However, according to the present invention, inputs/outputs ofregisters 3 are connected to the multiple inputs of a multiplexer 4 having a single input/output connected to the input (signal PS)) ofoperator 2 and to the output (signal CS) ofoperator 2. Multiplexer 4 receives a selection signal (SEL) coming, for example, from a priority control (not shown) associated with the central processing unit of theprocessor integrating circuit 1. - Initial states IS1, . . . ISj, . . . ISn are loaded under control of the CPU into each
register 3. The final states FS1, FSj, . . . FSn of function f after the required iterations are read individually from each register, by the processor circuits having required the application of the Hash function to a given binary word. - Conventionally, number m of iterations depends on the number of data blocks to be processed. According to the present invention, number n of registers depends on the number of applications which require
operator 2. - FIG. 2 is a simplified flowchart of the function performed by
operator 2. - The function starts (block10, IS) from an initial state. This state is, in the example of FIG. 1, previously loaded into one of the work registers associated with the application having requested the function. In a specific example applied to a so-called SHA function, this initial state is predetermined.
- The initial state becomes, when multiplexer4 assigns
operator 2 to the concerned register, first input value PS0 of the operator (block 11, PS0=IS). - The function of the logic operator is then executed (block12, CSi=f(PSi-1, Bi) on the first data couple, here the first data block to be processed BI and the first input state PS0. This operation is repeated for the m data blocks to be processed. Accordingly, this amounts to testing (
block 13, i=m ?) the end of the data word to be processed. If the result is negative, the iteration rank is incremented (block 14, i=i+1) and operator f is executed again with as input values PSi-1 and a new data block Bi. If the result is positive, output word CSi provided with the operator is considered as being the final state FS for the application having required the function. - According to the present invention, after each execution (block12) of the operator, current state CSi and rank i of the iteration are stored in the concerned register. This feature of the present invention enables, in case the function is interrupted to make
operator 2 available for a higher-priority application, to keep the current rank of the function to avoid restarting it from the beginning. - Of course, to implement the present invention, the data words to be processed by the discriminating function are also stored in adapted memorization elements (for example, registers). Rank i stored in
register 3 assigned to the application is used to select the appropriate data block upon resumption of the iterations for the concerned application. - Generally, for the application to a Hash function, the data words are divided into blocks Bi of 512 bits each.
- An advantage of the present invention is that it enables sharing a same operator in wired logic for several discriminating functions executed by different applications of an integrated processor.
- Another advantage of the present invention is that by avoiding storage of the intermediary calculation states in an external memory of the integrated circuit, the present invention preserves the security character generally required for applications of discriminating functions.
- Another advantage of the present invention is that its implementation is particularly simple in an integrated processor. In particular, the implementation of the present invention is compatible with the hardware circuits and control processes generally used in integrated processors. Further, the application processed by
operator 2 is transparent for said operator, in that all operates as if it was only connected to one register. - According to a preferred example of application of the present invention,
operator 2 is shared by several applications among which at least one real time data integrity control. In this case, this application is considered as holding the highest priority. - A second possible application may be a signature or authentication code calculation having a lower priority rank.
- To hold the third priority rank, it may be provided to use
operator 2 in the generation of a pseudo-random number which then holds the lowest priority rank. - Of course, the present invention is likely to have various alterations, modifications, and improvements which will readily occur to those skilled in the art. In particular, the practical forming of the calculation circuit according to the present invention is within the abilities of those skilled in the art based on the functional indications given hereabove. Further, the commands necessary to the multiplexer and to the different register by using conventional control means are within the abilities of those skilled in the art. Moreover, although this has not been detailed, the selection of the block Bi assigned to the data word of the application may be performed in several manners. For example, the integrated circuit CPU manages the reading of the desired blocks according to the decided priorities.
- Such alterations, modifications, and improvements are intended to be part of this disclosure, and are intended to be within the spirit and the scope of the present invention. Accordingly, the foregoing description is by way of example only and is not intended to be limiting. The present invention is limited only as defined in the following claims and the equivalents thereto.
Claims (3)
1. A circuit for calculating a discriminating function with successive iterations and with a work register on data divided into blocks, comprising:
a single operator (2) in wired logic for executing the function;
a plurality of work registers (3) sharing said operator, each register storing a current state of the operator and the rank of the corresponding iteration; and
an element (4) for selecting one of the work registers to be associated with the operator.
2. The circuit of claim 1 , wherein said function is a Hash function.
3. The calculation circuit of claim 1 , wherein a multiplexer (4) forming the selection element is controlled by a priority decoder associated with an integrated processor containing said calculation circuit.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US11/585,658 US7783691B2 (en) | 2002-07-17 | 2006-10-24 | Sharing of a logic operator having a work register |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
FR02/09072 | 2002-07-17 | ||
FR0209072 | 2002-07-17 |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US11/585,658 Continuation US7783691B2 (en) | 2002-07-17 | 2006-10-24 | Sharing of a logic operator having a work register |
Publications (1)
Publication Number | Publication Date |
---|---|
US20040015676A1 true US20040015676A1 (en) | 2004-01-22 |
Family
ID=29763902
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US10/619,105 Abandoned US20040015676A1 (en) | 2002-07-17 | 2003-07-14 | Sharing of a logic operator having a work register |
US11/585,658 Active 2025-11-27 US7783691B2 (en) | 2002-07-17 | 2006-10-24 | Sharing of a logic operator having a work register |
Family Applications After (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US11/585,658 Active 2025-11-27 US7783691B2 (en) | 2002-07-17 | 2006-10-24 | Sharing of a logic operator having a work register |
Country Status (2)
Country | Link |
---|---|
US (2) | US20040015676A1 (en) |
EP (1) | EP1383041A1 (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060195828A1 (en) * | 2005-02-28 | 2006-08-31 | Kabushiki Kaisha Toshiba | Instruction generator, method for generating instructions and computer program product that executes an application for an instruction generator |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10409827B2 (en) | 2014-10-31 | 2019-09-10 | 21, Inc. | Digital currency mining circuitry having shared processing logic |
US9942046B2 (en) * | 2015-05-06 | 2018-04-10 | 21, Inc. | Digital currency mining circuitry with adaptable difficulty compare capabilities |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5608801A (en) * | 1995-11-16 | 1997-03-04 | Bell Communications Research, Inc. | Efficient cryptographic hash functions and methods for amplifying the security of hash functions and pseudo-random functions |
US20040032347A1 (en) * | 2002-04-26 | 2004-02-19 | Masato Yamazaki | Soft-output decoder with computation decision unit |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5475822A (en) | 1993-11-15 | 1995-12-12 | Motorola, Inc. | Data processing system for resuming instruction execution after an interrupt and method therefor |
US5666300A (en) * | 1994-12-22 | 1997-09-09 | Motorola, Inc. | Power reduction in a data processing system using pipeline registers and method therefor |
US6434584B1 (en) | 1998-06-04 | 2002-08-13 | Texas Instruments Incorporated | Flexible accumulator register file for use in high performance microprocessors |
EP0967544B1 (en) * | 1998-06-25 | 2006-04-19 | Texas Instruments Incorporated | Digital signal processor for data having a large bit-length |
JP2001306298A (en) * | 2000-04-27 | 2001-11-02 | Mitsubishi Electric Corp | Information processor |
-
2003
- 2003-07-14 US US10/619,105 patent/US20040015676A1/en not_active Abandoned
- 2003-07-17 EP EP03300064A patent/EP1383041A1/en not_active Withdrawn
-
2006
- 2006-10-24 US US11/585,658 patent/US7783691B2/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5608801A (en) * | 1995-11-16 | 1997-03-04 | Bell Communications Research, Inc. | Efficient cryptographic hash functions and methods for amplifying the security of hash functions and pseudo-random functions |
US20040032347A1 (en) * | 2002-04-26 | 2004-02-19 | Masato Yamazaki | Soft-output decoder with computation decision unit |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060195828A1 (en) * | 2005-02-28 | 2006-08-31 | Kabushiki Kaisha Toshiba | Instruction generator, method for generating instructions and computer program product that executes an application for an instruction generator |
Also Published As
Publication number | Publication date |
---|---|
EP1383041A1 (en) | 2004-01-21 |
US20070220074A1 (en) | 2007-09-20 |
US7783691B2 (en) | 2010-08-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US4870562A (en) | Microcomputer capable of accessing internal memory at a desired variable access time | |
EP3252605A1 (en) | Vehicle-mounted control device, program writing device, program generating device and program | |
EP0127440A2 (en) | Integrated circuit device incorporating a data processing unit and a ROM storing applications program therein | |
US4199810A (en) | Radiation hardened register file | |
US5684728A (en) | Data processing system having a saturation arithmetic operation function | |
US4368532A (en) | Memory checking method | |
US7783691B2 (en) | Sharing of a logic operator having a work register | |
US20130247058A1 (en) | System for scheduling the execution of tasks based on logical time vectors | |
US4101967A (en) | Single bit logic microprocessor | |
KR100188374B1 (en) | Central processing unit and an arithmetic operation processing unit | |
EP0843253B1 (en) | A method for reducing the number of bits needed for the representation of constant values in a data processing device | |
US7076641B2 (en) | Programmable controller | |
JPS58178464A (en) | Parallel arithmetic processing unit | |
US5542080A (en) | Method for controlling execution of data driven type information processor | |
US8078657B2 (en) | Multi-source dual-port linked list purger | |
JP3837293B2 (en) | SIMD type microprocessor having constant selection function | |
US20230110499A1 (en) | Address solving for instruction sequence generation | |
JP2005032020A (en) | Storage device | |
KR0184786B1 (en) | Interrupt processor | |
JPH09223009A (en) | Device and method for processing data | |
JPH10187790A (en) | Logic circuit simulator | |
JP2616542B2 (en) | Pseudo failure generation system | |
JP3166193B2 (en) | Semiconductor integrated circuit | |
JP2000029508A (en) | Programmable controller | |
JPH0250258A (en) | Vector processing device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: STMICROELECTRONICS, S.A., FRANCE Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:LIARDET, PIERRE-YVAN;ORLANDO, WILLIAM;REEL/FRAME:014284/0525 Effective date: 20030619 |
|
STCB | Information on status: application discontinuation |
Free format text: ABANDONED -- FAILURE TO PAY ISSUE FEE |