WO2014013298A1 - Register file module and method therefor - Google Patents

Register file module and method therefor Download PDF

Info

Publication number
WO2014013298A1
WO2014013298A1 PCT/IB2012/053721 IB2012053721W WO2014013298A1 WO 2014013298 A1 WO2014013298 A1 WO 2014013298A1 IB 2012053721 W IB2012053721 W IB 2012053721W WO 2014013298 A1 WO2014013298 A1 WO 2014013298A1
Authority
WO
WIPO (PCT)
Prior art keywords
register
file module
register file
latch devices
clock signal
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.)
Ceased
Application number
PCT/IB2012/053721
Other languages
French (fr)
Inventor
Michael Priel
Leonid Fleshel
Dan Kuzmin
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
NXP USA Inc
Original Assignee
Freescale Semiconductor Inc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Freescale Semiconductor Inc filed Critical Freescale Semiconductor Inc
Priority to US14/415,153 priority Critical patent/US9799379B2/en
Priority to PCT/IB2012/053721 priority patent/WO2014013298A1/en
Publication of WO2014013298A1 publication Critical patent/WO2014013298A1/en
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G11INFORMATION STORAGE
    • G11CSTATIC STORES
    • G11C7/00Arrangements for writing information into, or reading information out from, a digital store
    • G11C7/10Input/output [I/O] data interface arrangements, e.g. I/O data control circuits, I/O data buffers
    • G11C7/1072Input/output [I/O] data interface arrangements, e.g. I/O data control circuits, I/O data buffers for memories with random access ports synchronised on clock signal pulse trains, e.g. synchronous memories, self timed memories
    • GPHYSICS
    • G11INFORMATION STORAGE
    • G11CSTATIC STORES
    • G11C19/00Digital stores in which the information is moved stepwise, e.g. shift registers
    • GPHYSICS
    • G11INFORMATION STORAGE
    • G11CSTATIC STORES
    • G11C19/00Digital stores in which the information is moved stepwise, e.g. shift registers
    • G11C19/28Digital stores in which the information is moved stepwise, e.g. shift registers using semiconductor elements
    • GPHYSICS
    • G11INFORMATION STORAGE
    • G11CSTATIC STORES
    • G11C29/00Checking stores for correct operation ; Subsequent repair; Testing stores during standby or offline operation
    • G11C29/04Detection or location of defective memory elements, e.g. cell constructio details, timing of test signals
    • G11C29/08Functional testing, e.g. testing during refresh, power-on self testing [POST] or distributed testing
    • G11C29/12Built-in arrangements for testing, e.g. built-in self testing [BIST] or interconnection details
    • G11C29/18Address generation devices; Devices for accessing memories, e.g. details of addressing circuits
    • G11C29/30Accessing single arrays
    • G11C29/32Serial access; Scan testing
    • GPHYSICS
    • G11INFORMATION STORAGE
    • G11CSTATIC STORES
    • G11C7/00Arrangements for writing information into, or reading information out from, a digital store
    • G11C7/06Sense amplifiers; Associated circuits, e.g. timing or triggering circuits
    • G11C7/065Differential amplifiers of latching type
    • GPHYSICS
    • G11INFORMATION STORAGE
    • G11CSTATIC STORES
    • G11C7/00Arrangements for writing information into, or reading information out from, a digital store
    • G11C7/10Input/output [I/O] data interface arrangements, e.g. I/O data control circuits, I/O data buffers
    • G11C7/1015Read-write modes for single port memories, i.e. having either a random port or a serial port
    • G11C7/1039Read-write modes for single port memories, i.e. having either a random port or a serial port using pipelining techniques, i.e. using latches between functional memory parts, e.g. row/column decoders, I/O buffers, sense amplifiers
    • GPHYSICS
    • G11INFORMATION STORAGE
    • G11CSTATIC STORES
    • G11C7/00Arrangements for writing information into, or reading information out from, a digital store
    • G11C7/22Read-write [R-W] timing or clocking circuits; Read-write [R-W] control signal generators or management 
    • GPHYSICS
    • G11INFORMATION STORAGE
    • G11CSTATIC STORES
    • G11C2207/00Indexing scheme relating to arrangements for writing information into, or reading information out from, a digital store
    • G11C2207/007Register arrays

Definitions

  • the field of this invention relates to a register file module and method therefor.
  • Register files are popular components within modern processor and hardware accelerator designs.
  • a register file is an array of registers typically comprising dedicated read and write ports; in contrast to ordinary memory which usually comprises shared read/write ports.
  • Register files are typically implemented as small, high speed memory components, and are often required to enable sequential read and write operations within a single clock cycle.
  • a register file is often tightly coupled to other components within the processor/accelerator design in order to enable such high speed access. Due to this need to tightly couple a register file to other components, standard memory circuits (typically random access memory (RAM)-based) are typically not appropriate. As such, it is known to implement a register file using a custom placed flip-flop implementation.
  • RAM random access memory
  • a problem with such a custom placed flip-flop implementation is that a standard flip-flop requires a relatively large silicon area and has relatively slow timing performance compared with simpler storage elements such as latches.
  • input signal changes cause immediate changes in output when enabled.
  • latches follow each other using the same clock signal, signals can propagate through all of them at once.
  • a problem with a latch-based implementation is a need to resolve hold timing of signals in order to prevent an input signal causing an immediate change in output.
  • a further problem with the use of latches is in relation to a need to implement design for test functionality within modern integrated circuit devices.
  • it is often required to enable scan design within register files, whereby registers in the design are connected in one or more scan chains.
  • a latch- based implementation is typically not appropriate for enabling such scan chains.
  • the present invention provides a register file module and a method of enabling scan chain functionality within a register array as described in the accompanying claims.
  • FIG. 1 illustrates a simplified block diagram of an example of a processing system.
  • FIG's 2 and 3 illustrate simplified block diagrams of an example of a register file module.
  • FIG. 4 illustrates a simplified flowchart of an example of a method of enabling scan chain functionality within a register array.
  • the present invention will now be described with reference to an example of a register file.
  • the example described herein and illustrated in the accompanying drawings comprises a single register array, and a single write port and a single read port.
  • the present invention may equally be applied to register file modules comprising more than one register array, more than write port and/or more than one read port.
  • the illustrated embodiments of the present invention may for the most part, be implemented using electronic components and circuits known to those skilled in the art, details will not be explained in any greater extent than that considered necessary as illustrated below, for the understanding and appreciation of the underlying concepts of the present invention and in order not to obfuscate or distract from the teachings of the present invention.
  • FIG. 1 there is illustrated a simplified block diagram of an example of a processing system 100.
  • the processing system 100 is implemented within an integrated circuit device 105 comprising at least one die within a single integrated circuit package.
  • the processing system 100 comprises one or more processing modules, such as central processing unit (CPU) 1 10.
  • the CPU 1 10 comprises one or more processing components 1 15, for example such as arithmetic and/or logic units (ALUs).
  • the CPU 1 10 further comprises one or more register files 120.
  • Other components of the processing system 100 may additionally and/or alternatively comprise register files 120, such as a crossbar component 130, accelerator hardware 140, etc.
  • FIG. 2 there is illustrated a simplified block diagram of an example of a register file module 200, such as with which one or more of the register files 120 illustrated in FIG. 1 may be implemented.
  • the register file module 200 illustrated in FIG. 2 comprises at least one register array 210.
  • the register array 210 comprises a plurality or registers 215, and in particular in the illustrated example comprises m registers, denoted Reg_1 to Reg_m.
  • Each register comprises a plurality of latch devices 220 individually arranged to provide memory bit-cells.
  • each register 215 comprises n latch device 220.
  • the register file module 200 further comprises at least one write port 230 via which data (D in ) 232 to be stored within the register file module 200 is received, and at least one read port 240 via which data (D out ) 242 stored within the register file module 200 may be read.
  • the register file module 200 comprises a write decoder 236 arranged to receive, via the write port 230, and decode a write address 234 for a register 215 within which data (D in ) 232 is to be stored within the register file module 200.
  • the write decoder 236 is further arranged to output control signals 238 at least partly in accordance with a received and decoded write address 234.
  • the register file module 200 further comprises a read decode 246 arranged to receive, via the read port 240, and decode a read address 244 for a register 215 within the register file module 200 from which data (D out ) 242 stored within the register file module 200 is to be read.
  • a read decode 246 arranged to receive, via the read port 240, and decode a read address 244 for a register 215 within the register file module 200 from which data (D out ) 242 stored within the register file module 200 is to be read.
  • the register file module 200 further comprises a clock control component 250 arranged to receive a clock signal 255, and to propagate the received clock signal 255 to the latch devices 220 within the registers 215 in accordance with the control signals 238 output by, in the illustrated example, the write decoder 236.
  • the clock control component 250 comprises a configurable clock path for each register 215, such as the clock path 252, via which the clock signal 225 may be propagated to the respective register 215.
  • such clock path 252 comprises a multiplexer 262 and a NAND gate 264.
  • the multiplexer 262 comprises a first input arranged to receive the clock signal 255 and a second input arranged to receive an output signal of the NAND gate 264.
  • the multiplexer 262 is controllable, via a control signal 266 output by the write decoder 236, to selectively output a register clock signal 265 comprising one of the signals received at its inputs.
  • the NAND gate 264 comprises a first input arranged to receive the clock signal 255 and a second input arranged to receive a further control signal 268 output by the write decoder 236. In this manner, if the control signal 268 comprises a logical state of ' ⁇ ', the NAND gate 264 will output a logical state of , irrespective of the logical state of the clock signal 255. Conversely, if the control signal 268 comprises a logical state of , the NAND gate 264 will output the opposite logical state to that of the clock signal 255. As such, if the control signal 268 comprises a logical state of , the NAND gate 264 will output an inverted clock signal.
  • the write decoder 236 is able to individually configure, via the control signals 280 output thereby, a clock path 260 for each register 215 within the register array 210 to output one of:
  • the register file module 200 is configurable to operate in a functional operating mode, whereby data (D in ) 232 to be stored within the register file module 200 is received via the write port 230 and provided to each of the registers 215 within the register array 210 (via inverse-edge latch devices 225 in the illustrated example as described in greater detail below).
  • the write decoder 236 and clock control component 250 are arranged to selectively propagate the clock signal 255 to a register 215 within the register array 210 to which the write address 234 relates during the respective write cycle, and to gate the clock signal to the other registers 215 within the register array 210.
  • the latch devices 220 within the registers 215 to which the clock signal is gated may be held within a latched state, preventing the received data (D in ) 232 to be stored within the register file module 200 from affecting data already stored within those registers 215.
  • the latches within that register may be transitioned from a latched state to a transparent state and back to a latched state during the write cycle.
  • the data (D in ) 232 to be stored within the register file module 200 will be sampled and latched by the latch devices 220 within the register 215 to which the write address 234 relates, and thus stored.
  • the register file module 200 further comprises inverse-edge latch devices 225 operably coupled between the write port 230 and the register array 210.
  • data (D in ) 232 to be stored within the register file module 200 is received via the write port 230 and provided to the registers 215 within the register array 210 via the inverse-edge latch devices 225; one inverse-edge latch device 225 for each bit of the data (D in ) 232 to be stored.
  • n such inverse-edge latch devices 225 are operably coupled in parallel between the write port 230 and the registers 215.
  • the clock control component 150 is arranged to propagate an inverted form of the clock signal 250 to the inverse-edge latch devices 225 such that the inverse-edge latch devices 225 comprise an opposing state (transparent or latched) to that of clocked latch devices 220 (i.e. latch devices 220 to which the clock signal 250 is propagated) within the register array 210 in accordance with the clock signal 250.
  • this is implemented by way of a NAND gate 270, which in the illustrated example forms a part of the clock control component 250.
  • the NAND gate 270 comprises a first input arranged to receive the clock signal 255 and a second input arranged to receive a control signal 272 output by the write decoder 236.
  • the NAND gate 270 will output a logical state of , irrespective of the logical state of the clock signal 255. Conversely, if the control signal 272 comprises a logical state of , the NAND gate 270 will output the opposite logical state to that of the clock signal 255. As such, if the control signal 272 comprises a logical state of , the NAND gate 270 will output an inverted clock signal 275, which is provided to the inverse-edge latch devices 225.
  • the inverse-edge latch devices 225 and the latch devices 220 within the clock register 215 within which the received data (D in ) 232 is to be stored together form a flip-flop structure.
  • hold timing of received data is provided by the inverse-edge latch devices 225.
  • only a single 'column' of inverse-edge latch devices 225 is required to provide such hold timing for all the latched-based registers 215 within the register array 210.
  • the read decoder 246 is arranged to receive a read address 244 received via the read port 240, and to output a read control signal 248 arranged to selectively output, via a multiplexer 280, data stored within a register 215 to which the read address 244 relates.
  • the register file module 200 is further configurable to operate in a scan mode.
  • latch devices 220 within the register array 210 may be arranged into one or more scan chains, whereby in the or each scan chain an output of each latch device 220 therein (with the exception of a last latch device 220 in the scan chain) is operably coupled to an input of a next sequential latch device 220 in the scan chain.
  • a scan input signal received at an input of a first latch in the scan chain may be propagated from one latch to the next through the scan chain.
  • latch devices 220 within the register array 210 are laterally coupled (relative to the registers 215) into a single scan chain, illustrated generally by the arrows 290, whereby an output of a first latch device 220 of the first register Reg_1 215 is coupled to an input of the first latch device 220 of the second register Reg_2 215, etc.
  • the scan chain loops back to the next latch device 220 in the first register Reg_1 215.
  • the output of the first latch device 220 in the last register Reg_m 215 is operably coupled to the input of the second latch device 220 in the first register Reg_1 215.
  • a scan input signal (S in ) 292 is operably coupled to an input of the first latch device 220 of the first register Reg_1 215, whilst a scan output signal (S ou t) 294 is output from an output of the last (n th ) latch device 220 of the last register Reg_m 215.
  • Such a scan mode may be enabled by way of a scan enable signal (S_En) 296 provided to, in the illustrated example, the register array 210 and the write decoder 296.
  • a data input 320 of each latch device 220 within the register array 210 may be operably coupled to an output of a multiplexer 330.
  • a first input 332 of each such multiplexer 330 may be arranged to receive a respective bit of data (D in ) 232 to be stored within the register file module 200, received via the write port 230 and inverse-edge latch devices 225.
  • a second input 334 of each such multiplexer 330 may be arranged to receive a respective scan input signal.
  • the second input 334 of the respective multiplexer 330 of the first latch device 220 of the first register Reg_1 215 may be arranged to receive the initial scan input signal (S in ) 292, whilst the second input 334 of the respective multiplexer 330 of each other latch device 220 may be operably coupled to the output of the preceding latch device 220 in the scan chain 290.
  • the scan enable signal (S_En) 296 may thus be provided to the multiplexers 330 to selective configure the input of each latch device 220 between receiving a respective bit of data (D in ) 232 to be stored within the register file module 200, and receiving a respective scan input signal.
  • input signal changes cause immediate changes in output when the latch devices 220 enter a transparent state in response to a clock signal transition.
  • input signals can propagate through all of the latches at once (e.g. within a single clock cycle). As will be appreciated, this is undesirable when such a scan chain configuration is to be used to implement design for test functionality.
  • the clock control component 250 is arranged to propagate the clock signal 255 to the latch devices 220 within the register array 210, whereby alternate latch devices 220 receive an inverted form of the clock signal 255 such that a first latch within each adjacent pair of latch devices 220 within the scan chain 290 receives a non-inverted form of the clock signal 250 whilst the second latch within each adjacent pair of latch devices 220 within the scan chain 290 receives an inverted form of the clock signal 250.
  • alternate latch devices 220 receive an inverted form of the clock signal 255 such that a first latch within each adjacent pair of latch devices 220 within the scan chain 290 receives a non-inverted form of the clock signal 250 whilst the second latch within each adjacent pair of latch devices 220 within the scan chain 290 receives an inverted form of the clock signal 250.
  • the write decoder 236 may be arranged to configure, via the control signals 280 output thereby, a clock path 260 for, say, each odd numbered register 215 within the register array 210 to output a non- inverted form of the clock signal 350, by configuring the respective multiplexer 262 to output the clock signal 255 received at its first input, and a clock path 260 for each even numbered register 215 within the register array 210 to output an inverted form of the clock signal 355, by configuring the respective multiplexer 262 to output the signal received at its second input from the NAND gate 264, and to configure the control signal 268 provided to the second input of the NAND gate 264 to comprise a logical state of .
  • a clock path 260 for, say, each odd numbered register 215 within the register array 210 to output a non- inverted form of the clock signal 350
  • the respective multiplexer 262 to output the clock signal 255 received at its first input
  • FIG. 4 there is illustrated a simplified flowchart 400 of an example of a method of enabling scan chain functionality within a register array, such as may be implemented within the register file module 200 of FIG's 2 and 3.
  • the flowchart 400 illustrates a method of enabling scan chain functionality within a register array comprising a plurality of latch devices arranged to individually provide memory bit-cells when the register array is configured to operate in a first, functional operating mode.
  • the method starts at 410, and moves on to 420 where the latch devices within the register array are arranged into at least one scan chain.
  • a clock signal is propagated to the latch devices within the register array such that alternate latch devices within the at least one scan chain receive an inverted form of the clock signal.
  • the method then ends, at 440.
  • connections as discussed herein may be any type of connection suitable to transfer signals from or to the respective nodes, units or devices, for example via intermediate devices. Accordingly, unless implied or stated otherwise, the connections may for example be direct connections or indirect connections.
  • the connections may be illustrated or described in reference to being a single connection, a plurality of connections, unidirectional connections, or bidirectional connections. However, different embodiments may vary the implementation of the connections. For example, separate unidirectional connections may be used rather than bidirectional connections and vice versa.
  • plurality of connections may be replaced with a single connection that transfers multiple signals serially or in a time multiplexed manner. Likewise, single connections carrying multiple signals may be separated out into various different connections carrying subsets of these signals. Therefore, many options exist for transferring signals.
  • Each signal described herein may be designed as positive or negative logic.
  • the signal In the case of a negative logic signal, the signal is active low where the logically true state corresponds to a logic level zero.
  • the signal In the case of a positive logic signal, the signal is active high where the logically true state corresponds to a logic level one.
  • any of the signals described herein can be designed as either negative or positive logic signals. Therefore, in alternate embodiments, those signals described as positive logic signals may be implemented as negative logic signals, and those signals described as negative logic signals may be implemented as positive logic signals.
  • the terms 'assert' or 'set' and 'negate' are used herein when referring to the rendering of a signal, status bit, or similar apparatus into its logically true or logically false state, respectively. If the logically true state is a logic level one, the logically false state is a logic level zero. And if the logically true state is a logic level zero, the logically false state is a logic level one.
  • logic blocks are merely illustrative and that alternative embodiments may merge logic blocks or circuit elements or impose an alternate decomposition of functionality upon various logic blocks or circuit elements.
  • the architectures depicted herein are merely exemplary, and that in fact many other architectures can be implemented which achieve the same functionality. Any arrangement of components to achieve the same functionality is effectively 'associated' such that the desired functionality is achieved.
  • any two components herein combined to achieve a particular functionality can be seen as 'associated with' each other such that the desired functionality is achieved, irrespective of architectures or intermediary components.
  • any two components so associated can also be viewed as being 'operably connected', or 'operably coupled', to each other to achieve the desired functionality.
  • any reference signs placed between parentheses shall not be construed as limiting the claim.
  • the word 'comprising' does not exclude the presence of other elements or steps then those listed in a claim.
  • the terms 'a' or 'an', as used herein, are defined as one or more than one.

Landscapes

  • Logic Circuits (AREA)

Description

Title: REGISTER FILE MODULE AND METHOD THEREFOR
Description Field of the invention
The field of this invention relates to a register file module and method therefor.
Background of the invention
Register files are popular components within modern processor and hardware accelerator designs. A register file is an array of registers typically comprising dedicated read and write ports; in contrast to ordinary memory which usually comprises shared read/write ports. Register files are typically implemented as small, high speed memory components, and are often required to enable sequential read and write operations within a single clock cycle. In order to achieve this, a register file is often tightly coupled to other components within the processor/accelerator design in order to enable such high speed access. Due to this need to tightly couple a register file to other components, standard memory circuits (typically random access memory (RAM)-based) are typically not appropriate. As such, it is known to implement a register file using a custom placed flip-flop implementation.
A problem with such a custom placed flip-flop implementation is that a standard flip-flop requires a relatively large silicon area and has relatively slow timing performance compared with simpler storage elements such as latches. However, in a gated latch implementation, input signal changes cause immediate changes in output when enabled. As such, when several latches follow each other using the same clock signal, signals can propagate through all of them at once. As such, a problem with a latch-based implementation is a need to resolve hold timing of signals in order to prevent an input signal causing an immediate change in output.
A further problem with the use of latches is in relation to a need to implement design for test functionality within modern integrated circuit devices. In particular, it is often required to enable scan design within register files, whereby registers in the design are connected in one or more scan chains. However, due to their inability to implement hold timing between latches, a latch- based implementation is typically not appropriate for enabling such scan chains.
Summary of the invention
The present invention provides a register file module and a method of enabling scan chain functionality within a register array as described in the accompanying claims.
Specific embodiments of the invention are set forth in the dependent claims.
These and other aspects of the invention will be apparent from and elucidated with reference to the embodiments described hereinafter. Brief description of the drawings
Further details, aspects and embodiments of the invention will be described, by way of example only, with reference to the drawings. In the drawings, like reference numbers are used to identify like or functionally similar elements. Elements in the figures are illustrated for simplicity and clarity and have not necessarily been drawn to scale.
FIG. 1 illustrates a simplified block diagram of an example of a processing system.
FIG's 2 and 3 illustrate simplified block diagrams of an example of a register file module. FIG. 4 illustrates a simplified flowchart of an example of a method of enabling scan chain functionality within a register array.
Detailed description
The present invention will now be described with reference to an example of a register file. For ease of understanding, the example described herein and illustrated in the accompanying drawings comprises a single register array, and a single write port and a single read port. However, it will be appreciated that the present invention may equally be applied to register file modules comprising more than one register array, more than write port and/or more than one read port. Furthermore, because the illustrated embodiments of the present invention may for the most part, be implemented using electronic components and circuits known to those skilled in the art, details will not be explained in any greater extent than that considered necessary as illustrated below, for the understanding and appreciation of the underlying concepts of the present invention and in order not to obfuscate or distract from the teachings of the present invention.
Referring first to FIG. 1 , there is illustrated a simplified block diagram of an example of a processing system 100. In the illustrated example, the processing system 100 is implemented within an integrated circuit device 105 comprising at least one die within a single integrated circuit package. The processing system 100 comprises one or more processing modules, such as central processing unit (CPU) 1 10. The CPU 1 10 comprises one or more processing components 1 15, for example such as arithmetic and/or logic units (ALUs). The CPU 1 10 further comprises one or more register files 120. Other components of the processing system 100 may additionally and/or alternatively comprise register files 120, such as a crossbar component 130, accelerator hardware 140, etc.
Referring now to FIG. 2, there is illustrated a simplified block diagram of an example of a register file module 200, such as with which one or more of the register files 120 illustrated in FIG. 1 may be implemented. The register file module 200 illustrated in FIG. 2 comprises at least one register array 210. The register array 210 comprises a plurality or registers 215, and in particular in the illustrated example comprises m registers, denoted Reg_1 to Reg_m. Each register comprises a plurality of latch devices 220 individually arranged to provide memory bit-cells. As is well known in the art, such a latch device 220 is arranged to receive at a first input thereof a data signal, and at a second input thereof an enable/clock signal, and is arranged to comprise a transparent state upon the enable/clock signal comprising a first logical state whereby the latch device 220 outputs a logical state corresponding to that of the data signal received at the first input thereof, and to comprise a latched state upon the enable/clock signal comprising a second logical state whereby the latch device 220 latches and maintains the logical state at its output. In the illustrated example, each register 215 comprises n latch device 220.
The register file module 200 further comprises at least one write port 230 via which data (Din) 232 to be stored within the register file module 200 is received, and at least one read port 240 via which data (Dout) 242 stored within the register file module 200 may be read. The register file module 200 comprises a write decoder 236 arranged to receive, via the write port 230, and decode a write address 234 for a register 215 within which data (Din) 232 is to be stored within the register file module 200. In the illustrated example, the write decoder 236 is further arranged to output control signals 238 at least partly in accordance with a received and decoded write address 234. The register file module 200 further comprises a read decode 246 arranged to receive, via the read port 240, and decode a read address 244 for a register 215 within the register file module 200 from which data (Dout) 242 stored within the register file module 200 is to be read.
The register file module 200 further comprises a clock control component 250 arranged to receive a clock signal 255, and to propagate the received clock signal 255 to the latch devices 220 within the registers 215 in accordance with the control signals 238 output by, in the illustrated example, the write decoder 236. In particular in the illustrated example, the clock control component 250 comprises a configurable clock path for each register 215, such as the clock path 252, via which the clock signal 225 may be propagated to the respective register 215. In the illustrated example such clock path 252 comprises a multiplexer 262 and a NAND gate 264. The multiplexer 262 comprises a first input arranged to receive the clock signal 255 and a second input arranged to receive an output signal of the NAND gate 264. The multiplexer 262 is controllable, via a control signal 266 output by the write decoder 236, to selectively output a register clock signal 265 comprising one of the signals received at its inputs. The NAND gate 264 comprises a first input arranged to receive the clock signal 255 and a second input arranged to receive a further control signal 268 output by the write decoder 236. In this manner, if the control signal 268 comprises a logical state of 'Ο', the NAND gate 264 will output a logical state of , irrespective of the logical state of the clock signal 255. Conversely, if the control signal 268 comprises a logical state of , the NAND gate 264 will output the opposite logical state to that of the clock signal 255. As such, if the control signal 268 comprises a logical state of , the NAND gate 264 will output an inverted clock signal.
Accordingly, in the illustrated example the write decoder 236 is able to individually configure, via the control signals 280 output thereby, a clock path 260 for each register 215 within the register array 210 to output one of:
a non-inverted form of the clock signal 255, by configuring the respective multiplexer
262 to output the clock signal 255 received at its first input; an inverted form of the clock signal 255, by configuring the respective multiplexer 262 to output the signal received at its second input from the NAND gate 264, and to configure the control signal 268 provided to the second input of the NAND gate 264 to comprise a logical state of ; and
- a constant (gated) logical state of , by configuring the respective multiplexer 262 to output the signal received at its second input from the NAND gate 264, and to configure the control signal 268 provided to the second input of the NAND gate 264 to comprise a logical state of 'Ο'. The register file module 200 is configurable to operate in a functional operating mode, whereby data (Din) 232 to be stored within the register file module 200 is received via the write port 230 and provided to each of the registers 215 within the register array 210 (via inverse-edge latch devices 225 in the illustrated example as described in greater detail below). In the functional operating mode, the write decoder 236 and clock control component 250 are arranged to selectively propagate the clock signal 255 to a register 215 within the register array 210 to which the write address 234 relates during the respective write cycle, and to gate the clock signal to the other registers 215 within the register array 210. In this manner, the latch devices 220 within the registers 215 to which the clock signal is gated may be held within a latched state, preventing the received data (Din) 232 to be stored within the register file module 200 from affecting data already stored within those registers 215. Conversely, by propagating the clock signal 255 to the latches within the register 215 to which the write address 234 relates, the latches within that register may be transitioned from a latched state to a transparent state and back to a latched state during the write cycle. In this manner, the data (Din) 232 to be stored within the register file module 200 will be sampled and latched by the latch devices 220 within the register 215 to which the write address 234 relates, and thus stored.
In the illustrated example, the register file module 200 further comprises inverse-edge latch devices 225 operably coupled between the write port 230 and the register array 210. As mentioned above, data (Din) 232 to be stored within the register file module 200 is received via the write port 230 and provided to the registers 215 within the register array 210 via the inverse-edge latch devices 225; one inverse-edge latch device 225 for each bit of the data (Din) 232 to be stored. Thus, in the illustrated example, n such inverse-edge latch devices 225 are operably coupled in parallel between the write port 230 and the registers 215. The clock control component 150 is arranged to propagate an inverted form of the clock signal 250 to the inverse-edge latch devices 225 such that the inverse-edge latch devices 225 comprise an opposing state (transparent or latched) to that of clocked latch devices 220 (i.e. latch devices 220 to which the clock signal 250 is propagated) within the register array 210 in accordance with the clock signal 250. In the illustrated example, this is implemented by way of a NAND gate 270, which in the illustrated example forms a part of the clock control component 250. The NAND gate 270 comprises a first input arranged to receive the clock signal 255 and a second input arranged to receive a control signal 272 output by the write decoder 236. In this manner, if the control signal 272 comprises a logical state of 'Ο', the NAND gate 270 will output a logical state of , irrespective of the logical state of the clock signal 255. Conversely, if the control signal 272 comprises a logical state of , the NAND gate 270 will output the opposite logical state to that of the clock signal 255. As such, if the control signal 272 comprises a logical state of , the NAND gate 270 will output an inverted clock signal 275, which is provided to the inverse-edge latch devices 225.
Advantageously, by providing the data (Din) 232 to be stored within the register file module 200 to each of the registers 215 within the register array 210 via the inverse-edge latch devices 225, the inverse-edge latch devices 225 and the latch devices 220 within the clock register 215 within which the received data (Din) 232 is to be stored together form a flip-flop structure. In this manner, hold timing of received data is provided by the inverse-edge latch devices 225. Furthermore, by providing the inverse-edge latch devices 225 between the write port 230 and the register array 210, only a single 'column' of inverse-edge latch devices 225 is required to provide such hold timing for all the latched-based registers 215 within the register array 210.
For completeness, in the functional operating mode, the read decoder 246 is arranged to receive a read address 244 received via the read port 240, and to output a read control signal 248 arranged to selectively output, via a multiplexer 280, data stored within a register 215 to which the read address 244 relates.
The register file module 200 is further configurable to operate in a scan mode. In the scan mode, latch devices 220 within the register array 210 may be arranged into one or more scan chains, whereby in the or each scan chain an output of each latch device 220 therein (with the exception of a last latch device 220 in the scan chain) is operably coupled to an input of a next sequential latch device 220 in the scan chain. In this manner, a scan input signal received at an input of a first latch in the scan chain may be propagated from one latch to the next through the scan chain.
In the illustrated example, when the register file module 200 is configured to operate in the scan mode, latch devices 220 within the register array 210 are laterally coupled (relative to the registers 215) into a single scan chain, illustrated generally by the arrows 290, whereby an output of a first latch device 220 of the first register Reg_1 215 is coupled to an input of the first latch device 220 of the second register Reg_2 215, etc. At the end of a lateral row of latch devices 220, the scan chain loops back to the next latch device 220 in the first register Reg_1 215. For example, the output of the first latch device 220 in the last register Reg_m 215 is operably coupled to the input of the second latch device 220 in the first register Reg_1 215. A scan input signal (Sin) 292 is operably coupled to an input of the first latch device 220 of the first register Reg_1 215, whilst a scan output signal (Sout) 294 is output from an output of the last (nth) latch device 220 of the last register Reg_m 215.
Such a scan mode may be enabled by way of a scan enable signal (S_En) 296 provided to, in the illustrated example, the register array 210 and the write decoder 296. For example, and as illustrated in FIG. 3, a data input 320 of each latch device 220 within the register array 210 may be operably coupled to an output of a multiplexer 330. A first input 332 of each such multiplexer 330 may be arranged to receive a respective bit of data (Din) 232 to be stored within the register file module 200, received via the write port 230 and inverse-edge latch devices 225. A second input 334 of each such multiplexer 330 may be arranged to receive a respective scan input signal. For example, the second input 334 of the respective multiplexer 330 of the first latch device 220 of the first register Reg_1 215 may be arranged to receive the initial scan input signal (Sin) 292, whilst the second input 334 of the respective multiplexer 330 of each other latch device 220 may be operably coupled to the output of the preceding latch device 220 in the scan chain 290. The scan enable signal (S_En) 296 may thus be provided to the multiplexers 330 to selective configure the input of each latch device 220 between receiving a respective bit of data (Din) 232 to be stored within the register file module 200, and receiving a respective scan input signal.
In such a gated latch implementation, input signal changes cause immediate changes in output when the latch devices 220 enter a transparent state in response to a clock signal transition. As such, when several latches follow each other, such as in a scan chain configuration, using the same clock signal, input signals can propagate through all of the latches at once (e.g. within a single clock cycle). As will be appreciated, this is undesirable when such a scan chain configuration is to be used to implement design for test functionality.
In the example illustrated in FIG. 2, when the register file module 200 is configured to operate in the scan mode, the clock control component 250 is arranged to propagate the clock signal 255 to the latch devices 220 within the register array 210, whereby alternate latch devices 220 receive an inverted form of the clock signal 255 such that a first latch within each adjacent pair of latch devices 220 within the scan chain 290 receives a non-inverted form of the clock signal 250 whilst the second latch within each adjacent pair of latch devices 220 within the scan chain 290 receives an inverted form of the clock signal 250. For example, and as illustrated in FIG. 3, the write decoder 236 may be arranged to configure, via the control signals 280 output thereby, a clock path 260 for, say, each odd numbered register 215 within the register array 210 to output a non- inverted form of the clock signal 350, by configuring the respective multiplexer 262 to output the clock signal 255 received at its first input, and a clock path 260 for each even numbered register 215 within the register array 210 to output an inverted form of the clock signal 355, by configuring the respective multiplexer 262 to output the signal received at its second input from the NAND gate 264, and to configure the control signal 268 provided to the second input of the NAND gate 264 to comprise a logical state of . In this manner, and as illustrated in FIG. 3, adjacent latch devices 220 within the scan chain will receive clock signals clock signals output phase by half a clock cycle, effectively creating a flip-flop structure, as illustrated at 360 in FIG. 3, between each pair of adjacent latch devices 220. Referring now to FIG. 4, there is illustrated a simplified flowchart 400 of an example of a method of enabling scan chain functionality within a register array, such as may be implemented within the register file module 200 of FIG's 2 and 3. Specifically, the flowchart 400 illustrates a method of enabling scan chain functionality within a register array comprising a plurality of latch devices arranged to individually provide memory bit-cells when the register array is configured to operate in a first, functional operating mode. The method starts at 410, and moves on to 420 where the latch devices within the register array are arranged into at least one scan chain. Next, at 430, a clock signal is propagated to the latch devices within the register array such that alternate latch devices within the at least one scan chain receive an inverted form of the clock signal. The method then ends, at 440.
In the foregoing specification, the invention has been described with reference to specific examples of embodiments of the invention. It will, however, be evident that various modifications and changes may be made therein without departing from the broader spirit and scope of the invention as set forth in the appended claims.
The connections as discussed herein may be any type of connection suitable to transfer signals from or to the respective nodes, units or devices, for example via intermediate devices. Accordingly, unless implied or stated otherwise, the connections may for example be direct connections or indirect connections. The connections may be illustrated or described in reference to being a single connection, a plurality of connections, unidirectional connections, or bidirectional connections. However, different embodiments may vary the implementation of the connections. For example, separate unidirectional connections may be used rather than bidirectional connections and vice versa. Also, plurality of connections may be replaced with a single connection that transfers multiple signals serially or in a time multiplexed manner. Likewise, single connections carrying multiple signals may be separated out into various different connections carrying subsets of these signals. Therefore, many options exist for transferring signals.
Although specific conductivity types or polarity of potentials have been described in the examples, it will be appreciated that conductivity types and polarities of potentials may be reversed.
Each signal described herein may be designed as positive or negative logic. In the case of a negative logic signal, the signal is active low where the logically true state corresponds to a logic level zero. In the case of a positive logic signal, the signal is active high where the logically true state corresponds to a logic level one. Note that any of the signals described herein can be designed as either negative or positive logic signals. Therefore, in alternate embodiments, those signals described as positive logic signals may be implemented as negative logic signals, and those signals described as negative logic signals may be implemented as positive logic signals.
Furthermore, the terms 'assert' or 'set' and 'negate' (or 'de-assert' or 'clear') are used herein when referring to the rendering of a signal, status bit, or similar apparatus into its logically true or logically false state, respectively. If the logically true state is a logic level one, the logically false state is a logic level zero. And if the logically true state is a logic level zero, the logically false state is a logic level one.
Those skilled in the art will recognize that the boundaries between logic blocks are merely illustrative and that alternative embodiments may merge logic blocks or circuit elements or impose an alternate decomposition of functionality upon various logic blocks or circuit elements. Thus, it is to be understood that the architectures depicted herein are merely exemplary, and that in fact many other architectures can be implemented which achieve the same functionality. Any arrangement of components to achieve the same functionality is effectively 'associated' such that the desired functionality is achieved. Hence, any two components herein combined to achieve a particular functionality can be seen as 'associated with' each other such that the desired functionality is achieved, irrespective of architectures or intermediary components. Likewise, any two components so associated can also be viewed as being 'operably connected', or 'operably coupled', to each other to achieve the desired functionality.
Furthermore, those skilled in the art will recognize that boundaries between the above described operations merely illustrative. The multiple operations may be combined into a single operation, a single operation may be distributed in additional operations and operations may be executed at least partially overlapping in time. Moreover, alternative embodiments may include multiple instances of a particular operation, and the order of operations may be altered in various other embodiments.
Other modifications, variations and alternatives are also possible. The specifications and drawings are, accordingly, to be regarded in an illustrative rather than in a restrictive sense.
In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word 'comprising' does not exclude the presence of other elements or steps then those listed in a claim. Furthermore, the terms 'a' or 'an', as used herein, are defined as one or more than one. Also, the use of introductory phrases such as 'at least one' and 'one or more' in the claims should not be construed to imply that the introduction of another claim element by the indefinite articles 'a' or 'an' limits any particular claim containing such introduced claim element to inventions containing only one such element, even when the same claim includes the introductory phrases 'one or more' or 'at least one' and indefinite articles such as 'a' or 'an'. The same holds true for the use of definite articles. Unless stated otherwise, terms such as 'first' and 'second' are used to arbitrarily distinguish between the elements such terms describe. Thus, these terms are not necessarily intended to indicate temporal or other prioritization of such elements. The mere fact that certain measures are recited in mutually different claims does not indicate that a combination of these measures cannot be used to advantage.

Claims

Claims
1 . A register file module comprising:
at least one register array comprising a plurality of latch devices arranged to individually provide memory bit-cells when the register file module is configured to operate in a first, functional operating mode; and
at least one clock control component arranged to receive a clock signal and to propagate the clock signal to the plurality of latch devices within the at least one register array;
the register file module being configurable to operate in a second, scan mode in which the plurality of latch devices within the at least one register array are arranged into at least one scan chain;
wherein the at least one clock control component is arranged to propagate the clock signal to the plurality of latch devices within the at least one register array such that alternate latch devices within the at least one scan chain receive an inverted form of the clock signal.
2. The register file module of Claim 1 , wherein the at least one register array comprises a plurality of registers, each register comprising a plurality of latch devices arranged to individually provide memory bit-cells when the register file module is configured to operate in the first, functional operating mode.
3. The register file module of Claim 2, wherein the plurality of latch devices within the register array are laterally coupled, relative to the registers, into at least one scan chain.
4. The register file module of Claim 3, wherein the clock control component is arranged to propagate the clock signal to the plurality of latch devices within the respective registers such that alternate registers of the plurality of latch devices receive an inverted form of the clock signal.
5. The register file module of any preceding Claim, wherein the register file module further comprises at least one inverse-edge latch device operably coupled between at least one write port of the register file module and the at least one register array; the at least one inverse-edge latch device arranged to comprise an opposing state to that of clocked latch devices within the at least one register array when the register file module is configured to operate in the first, functional operating mode.
6. The register file module of Claim 5, wherein the register file module comprises n inverse-edge latch devices operably coupled in parallel between the at least one write port of the register file module and the at least one register array, where n equals the number of latch devices within each register of the at least one register array.
7. The register file module of Claim 5 or Claim 6, wherein the at least one clock control component is arranged to propagate an inverted form of the clock signal to the at least one inverse- edge latch device.
8. The register file module of any preceding Claim implemented within an integrated circuit device comprising at least one die within a single integrated circuit package.
9. A processing system comprising at least one register file module according to any of the preceding claims.
10. A method of enabling scan chain functionality within a register array comprising a plurality of latch devices arranged to individually provide memory bit-cells when the register array is configured to operate in a first, functional operating mode; the method comprising:
arranging the plurality of latch devices within the register array into at least one scan chain; and propagating a clock signal to the latch devices within the register array such that alternate latch devices within the at least one scan chain receive an inverted form of the clock signal.
PCT/IB2012/053721 2012-07-20 2012-07-20 Register file module and method therefor Ceased WO2014013298A1 (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
US14/415,153 US9799379B2 (en) 2012-07-20 2012-07-20 Hold time aware register file module and method therefor
PCT/IB2012/053721 WO2014013298A1 (en) 2012-07-20 2012-07-20 Register file module and method therefor

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/IB2012/053721 WO2014013298A1 (en) 2012-07-20 2012-07-20 Register file module and method therefor

Publications (1)

Publication Number Publication Date
WO2014013298A1 true WO2014013298A1 (en) 2014-01-23

Family

ID=49948355

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/IB2012/053721 Ceased WO2014013298A1 (en) 2012-07-20 2012-07-20 Register file module and method therefor

Country Status (2)

Country Link
US (1) US9799379B2 (en)
WO (1) WO2014013298A1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9666301B2 (en) 2014-09-16 2017-05-30 Qualcomm Incorporated Scannable memories with robust clocking methodology to prevent inadvertent reads or writes

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9811628B1 (en) 2016-10-14 2017-11-07 Baysand Inc. Metal configurable register file
US10970074B2 (en) 2018-05-30 2021-04-06 Texas Instruments Incorporated Broadside random access memory for low cycle memory access and additional functions
CN111382091A (en) * 2018-12-30 2020-07-07 德克萨斯仪器股份有限公司 Broadside random access memory for low cycle memory access and additional functions
US11443823B2 (en) 2020-10-29 2022-09-13 SambaNova Systems, Inc. Method and circuit for scan dump of latch array
CN114528019B (en) * 2020-11-23 2025-09-12 深圳比特微电子科技有限公司 Multi-bit registers, chips, and computing devices
US11449404B1 (en) 2021-07-09 2022-09-20 SambaNova Systems, Inc. Built-in self-test for processor unit with combined memory and logic
US11604223B1 (en) * 2021-12-16 2023-03-14 Nxp Usa, Inc. Clock control system for scan chains
US12295577B2 (en) * 2022-03-25 2025-05-13 Cilag Gmbh International Tissue cushion adjuncts for surgical stapler end effector
IT202200007967A1 (en) * 2022-04-22 2023-10-22 St Microelectronics Srl RANDOM ACCESS MEMORY AND CORRESPONDING METHOD OF MANAGING A RANDOM ACCESS MEMORY

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7657807B1 (en) * 2005-06-27 2010-02-02 Sun Microsystems, Inc. Integrated circuit with embedded test functionality
US20100332929A1 (en) * 2009-06-30 2010-12-30 Texas Instruments Incorporated Scan testable register file
US20110095801A1 (en) * 2008-04-14 2011-04-28 Teklatech A/S Method for controlling the dynamic power signature of a circuit
US20120072793A1 (en) * 2010-09-21 2012-03-22 Qualcomm Incorporated Registers with Full Scan Capability

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS63276138A (en) 1987-04-30 1988-11-14 インターナシヨナル・ビジネス・マシーンズ・コーポレーシヨン Register file
US4916670A (en) * 1988-02-02 1990-04-10 Fujitsu Limited Semiconductor memory device having function of generating write signal internally
JP2004102799A (en) 2002-09-11 2004-04-02 Nec Electronics Corp Register file and method for designing register file
WO2005026966A1 (en) 2003-09-08 2005-03-24 Fujitsu Limited Register file and its storage element
JP2009222644A (en) * 2008-03-18 2009-10-01 Toshiba Corp Semiconductor integrated circuit, and design automating system
US8356202B2 (en) * 2008-03-28 2013-01-15 Intel Corporation System and method for reducing power consumption in a device using register files
US20110241744A1 (en) 2008-08-28 2011-10-06 Aspen Acquisition Corporation Latch-based implementation of a register file for a multi-threaded processor

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7657807B1 (en) * 2005-06-27 2010-02-02 Sun Microsystems, Inc. Integrated circuit with embedded test functionality
US20110095801A1 (en) * 2008-04-14 2011-04-28 Teklatech A/S Method for controlling the dynamic power signature of a circuit
US20100332929A1 (en) * 2009-06-30 2010-12-30 Texas Instruments Incorporated Scan testable register file
US20120072793A1 (en) * 2010-09-21 2012-03-22 Qualcomm Incorporated Registers with Full Scan Capability

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9666301B2 (en) 2014-09-16 2017-05-30 Qualcomm Incorporated Scannable memories with robust clocking methodology to prevent inadvertent reads or writes

Also Published As

Publication number Publication date
US9799379B2 (en) 2017-10-24
US20150206559A1 (en) 2015-07-23

Similar Documents

Publication Publication Date Title
US9799379B2 (en) Hold time aware register file module and method therefor
US10720205B2 (en) Systems and methods involving multi-bank, dual-pipe memory circuitry
US10303632B2 (en) Accessing status information
US9658971B2 (en) Universal SPI (serial peripheral interface)
US9964596B2 (en) Integrated circuit with low power scan system
CN1667746B (en) Apparatus for producing wirte-in gating clock signal
US4852061A (en) High density, high performance register file having improved clocking means
CN107544616B (en) Method and apparatus for phase aligned 2X frequency clock generation
US9665377B2 (en) Processing apparatus and method of synchronizing a first processing unit and a second processing unit
CN103528691B (en) The row strobe generation circuit of infrared focal plane array sensing circuit
US9531351B1 (en) Configurable latch circuit
TWI790088B (en) Processors and Computing Systems
KR101643302B1 (en) Parallel configuration of a reconfigurable instruction cell array
CN1787376B (en) Techniques for implementing hardwired decoders with differential input circuits
EP4052373B1 (en) Programmable device configuration memory system
CN105843356B (en) Shared logic for multiple registers with asynchronous initialization
KR20200090874A (en) Data bus with multiple input pipelines
US9698784B1 (en) Level-sensitive two-phase single-wire latch controllers without contention
US20150088950A1 (en) Storing an entropy signal from a self-timed logic bit stream generator in an entropy storage ring
CN117686879A (en) Scan test circuit, digital chip, electronic device and power consumption reduction method
US20090259892A1 (en) Method and Apparatus for Producing a Metastable Flip Flop
US7839168B2 (en) Circuit with parallel functional circuits with multi-phase control inputs
EP0288774B1 (en) High density, high performance register file circuit
KR100728554B1 (en) Data processing device of semiconductor memory
US10289585B1 (en) Cross-point programming of pipelined interconnect circuitry

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 12881215

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 14415153

Country of ref document: US

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 12881215

Country of ref document: EP

Kind code of ref document: A1