WO2008112153A2

WO2008112153A2 - Variable instruction width software programmable data pattern generator

Info

Publication number: WO2008112153A2
Application number: PCT/US2008/003062
Authority: WO
Inventors: Andreas D. Olofsson; Christopher Jacobs; Paul Kettle
Original assignee: Analog Devices, Inc.
Priority date: 2007-03-09
Filing date: 2008-03-07
Publication date: 2008-09-18
Also published as: WO2008112207A3; US20080219112A1; US8006114B2; US8732440B2; WO2008112207A2; WO2008112153A3; US8135975B2; US20080222441A1; US20080222444A1

Abstract

A method for generating a digital signal pattern at M outputs involves retrieving an instruction from memory comprising a first set of bits identifying a first group of N outputs that includes fewer than all of the M outputs, and a second set of N bits each corresponding to a respective output included in the identified first group of N outputs. For each of the M outputs that is included in the identified first group of N outputs, the signal at the output is toggled if the one of the N bits corresponding to that output is in a first state and is kept in the same state if the one of the N bits corresponding to that output is in a second state. For each of the M outputs that is not included in the identified first group of N outputs, the signal at that output is kept in the same state.

Description

VARIABLE INSTRUCTION WIDTH SOFTWARE PROGRAMMABLE DATA

PATTERN GENERATOR

RELATED APPLICATIONS This application relates to the subject matter disclosed in each of (1) U.S. Provisional

Application Ser. No. 60/906,000, filed March 9, 2007 ("the OOO application"), (2) U.S. Patent Application Ser. No. 11/818,449, filed June 14, 2007 ("the '449 application), and (3) U.S. Patent Application Ser. No. 11/818,452, filed June 14, 2007 ("the '452 application). The entire contents of each of the OOO, '449, and '452 applications are incorporated herein by reference.

BACKGROUND

Charge coupled devices (CCDs) are used in a large variety of digital imaging applications. There are a number of different manufacturers of such devices and each manufacturer typically has numerous models. The large variety of CCDs and the continuously evolving CCD control requirements have caused challenges in designing the analog front end/CCD controller circuits that will have significant longevity in the market place. This problem is ameliorated to a large extent by the software programmable pattern generator described in the '000, '449, and '452 applications, incorporated by reference above. That software programmable pattern generator utilizes a compact and flexible assembly programmable Reduced Instruction Set Computer (RISC) that is optimized for generating high precision timing pulses and low power control functions. The architecture has a variable bit wide instruction set that includes: vector toggling instructions, jump instructions, conditional instructions, arithmetic instructions, and load/store instructions. The pattern generator can fetch and execute one instruction per clock cycle, and is parameter scalable to allow for easy optimization in different applications.

To allow every chip output to be set simultaneously at a pixel clock resolution, a large number of bits may be stored in parallel within the program memory, with each bit in a vector word corresponding to an output pin that can be selectively toggled, depending on the state of the bit. In the case of Analog Device's model number ADDI9000, this meant that every instruction was "64" bits wide. An advantage of this model was in the simple control and design logic required. We have since recognized, however, that the use of such large instructions consumes a significant amount of memory, thus imposing limits on the utility of the timing generator for certain applications. SUMMARY

According to one aspect of the present invention, a method for generating a digital signal pattern at M outputs involves retrieving a first instruction from memory comprising a first set of bits identifying a first group of N outputs that includes fewer than all of the M outputs, and a second set of N bits each corresponding to a respective output included in the first group of N outputs identified by the first set of bits included in the first instruction. For each of the M outputs that is included in the first group of N outputs identified by the first set of bits included in the first instruction, the signal at the output is toggled if the one of the N bits corresponding to that output is in a first state and is kept in the same state if the one of the N bits corresponding to that output is in a second state. For each of the M outputs that is not included in the first group of N outputs identified by the first set of bits included in the first instruction, the signal at that output is kept in the same state.

According to another aspect of the invention, an apparatus for generating a digital signal pattern at M outputs comprises a circuit configured and arranged to retrieve at least instructions of a first type from memory and to control the toggling of signals at the M outputs in response thereto, wherein each of the instructions of the first type comprises a first set of bits identifying a first group of N outputs that includes fewer than all of the M outputs, and a second set of N bits each corresponding to a respective output included in the first group of N outputs identified by the first set of bits included in the first instruction. The circuit is further configured and arranged to process each retrieved instruction of the first type such that, for each of the M outputs that is included in the first group of N outputs identified by the first set of bits included in the instruction, the signal at the output is toggled if the one of the N bits corresponding to that output is in a first state and is kept in the same state if the one of the N bits corresponding to that output is in a second state, and, for each of the M outputs that is not included in the first group of N outputs identified by the first set of bits included in the instruction, the signal at that output is kept in the same state.

According to another aspect, a method for generating a digital signal pattern at M outputs involves retrieving a first instruction from memory that consists of N bits, and retrieving a second instruction from memory that consists of fewer than N bits. Based on the first instruction, first ones of the M outputs are identified and the signals on those outputs are toggled. Based on the second instruction, second ones of the M outputs are identified and signals on those outputs are toggled. BRIEF DESCRIPTION OF THE DRAWINGS

Fig. l is a functional block diagram illustrating various components of a digital pattern generator (DPP) that may operate together to control the generation of a digital signal pattern at its outputs; Fig. 2 is a flowchart illustrating an example of an execution flow that may be used to generate a pattern of pulses on the outputs of the DPP;

Figs. 3 and 4 illustrate the format and content of several examples of toggle instructions that may be employed in some embodiments; and

Fig. 5 is a block diagram illustrating an example of hardware that may be employed by the channel control circuit of the DPP to enable the use of toggle instructions of various lengths and types.

DETAILED DESCRIPTION

This disclosure is directed to improvements to certain components and features of the system disclosed in the '449 and '452 applications (incorporated by reference above). Familiarity with the entirety of the disclosure of the '449 and '452 applications will thus be assumed. For ease of understanding, to the extent practicable this disclosure will use the same reference numerals as those used in the '449 and '452 applications to describe similar components and features. It should be appreciated, moreover, that the components and features in this disclosure that are similarly named or that are designated using the same reference numerals as the components or features described in the '449 and '452 applications may be used in the system described in the '449 and '452 applications in the same or similar manner as such similarly named or labeled components and features are used therein. That only certain key components of the system disclosed in the '449 and '452 applications are re-described herein should not be understood to mean that such components and features are incompatible in any way with the new or modified components or features disclosed herein. Rather, it is simply for conciseness that only those components and features of the system disclosed in the '449 and '452 applications that are directly impacted or modified by this disclosure are re-described herein.

Fig. 1 is similar to Fig. 3 of the '449 and '452 applications. The only pertinent difference between the two figures is the addition of toggle control lines 310 to the diagram of Fig. 1. The purpose of these additional control lines will be explained in more detail below. This figure is a functional block diagram illustrating various components of a digital pattern processor (DPP) (like the DPP 102 described in the '449 and '452 applications - incorporated by reference above) that may operate together to control the generation of a digital pattern of signals at a group of outputs. As shown, the DPP may comprise a program sequencer 106, a synchronous timer 114, a program memory 108, channel control circuitry 118, and output pads 120.

As illustrated, the program sequencer 106 may comprise an instruction decoder 302 and program sequencer logic 304 that together are responsible for fetching instructions from the memory 108, decoding the fetched instructions, and controlling the synchronous timer 114 and channel control circuitry 118 so as to appropriately generate a pattern of digital signals at the outputs 120. In the example shown, the synchronous timer 114 comprises a toggle counter 306 and a comparator 308. The comparator 308 may, for example, determine when the toggle counter 114 has reached a specified "toggle count" value. The toggle counter 306 may, for example, comprise a sixteen-bit free-running clock cycle counter. An illustrative example of an execution flow that may be employed by these components to generate a pattern of pulses by toggling the signals at the outputs 120 and/or forcing the signals at the outputs 120 to particular values is discussed below in connection with Fig. 2. Fig. 2 is identical to Fig. 8 of the '449 and '452 applications. This figure is a flowchart illustrating an example of an execution flow 800 that may be used to generate a digital signal pattern on the outputs 120. In the example shown, at steps 802 and 804, an instruction is fetched from the program memory 108 and decoded for execution. If, at a step 806, it is determined that the instruction is a toggle instruction, then the flow 800 proceeds to a step 808, where it waits until the comparator 308 has determined that the toggle counter 306 has reached a toggle count value. As discussed in more detail below, the toggle count value may be either included in the toggle instruction itself or may be read from a register of the DPP (e.g., one of the general purpose registers R0-R7 identified in Table lin the '449 and '452 applications). When the toggle count value is to be read from a register, either the same register may be referenced each time a particular type of toggle instruction is received or one or more bits may be included in the toggle instruction that identify the register that is to be referenced. As used herein, a "toggle instruction" refers to any instruction that is responsible for determining the state of one or more of the outputs 120 and is thus intended to encompass not only instructions that cause the signals at particular outputs to "toggle" (i.e., to change from one state to another) but also instructions that force the signals at particular outputs 120 to particular values (sometimes referred to herein as "force vector" instructions) and thus may or may not actually cause the output signals to toggle, depending on the initial state of each such signal. Once the toggle counter 306 has reached the specified toggle count, the flow proceeds to a step 810, where certain outputs 120 of the DPP are simultaneously toggled or forced to particular values in the manner specified by the instruction. The flow then returns to the steps 802 and 804 where the next program instruction is fetched and decoded. If, at the step 806, it is determined that the fetched instruction is not a toggle instruction, then the routine proceeds to a step 812, where the instruction is carried out to as to control the program flow in the manner specified. (Examples of the manner in which particular toggle instructions and program flow instructions may be configured and carried out in various embodiments are described in detail in the '449 and '452 applications and thus will not be repeated here). Accordingly, by employing the configuration and functionality illustrated in Figs. 1 and 2, the toggle counter 306 and a custom toggle instruction set may be used to keep the DPP in lock step execution to allow the generation of a digital signal pattern in the manner specified by the instruction set. Advantageously, in the example shown, the flow is capable of toggling or forcing the values of the signals on all output pins on any given clock cycle. In some embodiments, a single instruction may be defined for toggling or forcing the values of all of the output bits simultaneously.

As noted in the '449 and '452 applications, one application of the DPP may be as a timing generator for an image sensor. Examples of environments in which such a timing generator may operate are described in U.S. Pat. No. 6,512,546, U.S. Pat. No. 6,570,615, and U.S. Patent Application Publication No. 2006/0077275 Al , each of which is incorporated herein by reference in its entirety.

Fig. 3 shows several examples of program instruction configurations that may be used in various embodiments of the DPP disclosed herein, as well as in the '449 and '452 applications, including two examples of "short" toggle instruction formats 314 and 316 that were not disclosed in the '449 and '452 applications. In some embodiments, the program memory 108 that is employed may have a fixed width that is segmented into several sections. In the example of Fig. 3, for instance, the program memory is "64" bits wide and is segmented into four sections WO, Wl, W2, and W3. The format of the "long" toggle instruction 312 may be just like that of the toggle instructions described in the '449 and '452 applications and may be used in a similar manner. Advantageously, the short toggle instructions 314 and 316 may be used (in the manner described below) in circumstances in which it is necessary to toggle only a particular subset of the bits of the output vector. In the example of Fig. 3, for instance, the 32-bit short toggle instruction 314 may be used to toggle any or all of the bits within a particular byte (i.e., a set of eight bits) of the output vector, and the 16-bit short toggle instruction 316 may be used to toggle any or all of the bits within a particular nibble (i.e., a set of four bits) of the output vector. For the 32-bit short toggle instructions 314, a group of three byte select bits 314a may be used to identify the group of eight output bits that is to be toggled as indicated by the bits in the byte field 314b. Similarly, for the 16-bit short toggle instructions 316, a group of four nibble select bits 316a may be used to identify the group of four output bits that is to be toggled as indicated by the bits in the nibble field 316b.

Although the instructions 312, 314, 316 in the illustrated example are eight bytes, four bytes, and two bytes wide, respectively, it should be appreciated instructions of different lengths and relative sizes could additional or alternatively be employed. In some embodiments, for example, the short toggle instructions may be two and four bytes long, respectively, just as in the primary example described herein, but the long toggle instructions may be ten rather than eight bytes wide, with the two extra bytes containing additional bits of the vector field. Such a configuration would allow the generation of a digital pattern on "57" output pins, rather than on only "41" pins as in the primary example described herein.

To simply the implementation of hardware components in the system, it may be useful to align the longer instructions in memory so as to allow each instruction to be fetched in a single memory access. For example, if a memory including one thousand lines of sixty four bits is employed, each 64-bit instruction may be aligned so that it starts at the beginning of a line, rather than wrapping from one line to another. It may also be advantageous to align the 32-bit instructions in the above example so that they also do not wrap around from one memory line to another. For instructions that are aligned in such a manner, appropriate instructions may be inserted into the program code that cause the program counter to be incremented by a specific amount to account for the adjusted alignment (e.g., by skipping over one or more of the sections Wl, W2, W3 of the memory line, which may simply remain unused).

In some embodiments, it can be advantageous to use instructions having lengths that are integer multiples of one another. In one of the examples above, for instance, the length of the 32-bit short toggle instruction is twice (or a power of two) greater than the length of the 16-bit short toggle instruction, and length of the 64-bit long toggle instruction is twice (or a power of two) greater than the length of the 32-bit short toggle instruction. The use of such "power of two" differences between instruction lengths may, for example, simply the process of fetching and decoding of instructions. For instance, in some embodiments, the mechanism used for fetching may only have to choose between incrementing the program counter by "1," "2," or "4," which in binary becomes "001," "010," and "100," respectively.

Fig. 4 is a chart showing several examples of specific toggle instructions of the above- described types that may be employed in certain embodiments. In the chart, the numbers "0" to "31 " in the row labeled "INSTRUCTION" correspond to the respective bits in the depicted instruction words. For example, the numbers "0" to "6" in the "INSTRUCTION" row of Fig. 4 correspond to the 7-bit operational codes ("opcodes") of the toggle instructions 312, 314, 316 of Fig. 3. For the long (i.e., 64-bit or longer) toggle instructions in the chart, it should be understood that, although not specifically depicted, the bits "32" to "63" (or higher) would be "vector bits" just like the bits "23" to "31 " in those examples.

The opcode in each instruction may identify not only whether the instruction is a "toggle instruction," as opposed to one of the other types of instructions described in the '449 and '452 applications, e.g., a program flow instruction, a load/store instruction, an arithmetic instruction, etc., but also the particular length and content of the toggle instruction. For example, the opcode may indicate whether the instruction is a long toggle instruction 312

(which may be either an instruction to toggle certain bits or instruction to force certain bits to particular values), a 32-bit short toggle instruction 314, or a 16-bit short toggle instruction.

In the examples of Fig. 4, the assertion of bits "1" and "2" of the opcode indicates that the instruction is a toggle instruction. The assertion of bit "0" in addition to bits "1" and "2" indicates that the toggle instruction is a "force vector" instruction. The assertion of bit "3" in addition to bits "1" and "2" indicates that the toggle instruction is "short" (i.e., either "32" bits or "16" bits) rather than "long" (i.e., "64" bits or more). The assertion of both of bits "4" and "5" in addition to bits " 1 , "2," and "3" indicates that the short toggle instruction is " 16" bits long rather than "32" bits long. (Because the "clear" and "relative" options are never simultaneously asserted for a short toggle instruction 314, the assertion of both such bits may be used for this purpose).

As shown, the long toggle instructions 312 and the 32-bit short toggle instructions 314 may also each include an "immediate count" field. This field may, for example, be used to identify the "toggle count" value that the toggle counter 306 must reach for an output event (e.g., a toggling of specified output bits or forcing of output bits to particular values) to occur. Alternatively, some or all of the same bits may be used to identify a particular register (e.g., one of the general purpose registers R0-R7 identified in Table 1 of the '449 and '452 applications) that contains the toggle count value that is to be used for such a purpose. In the examples shown in Fig. 4, the assertion of bit "6" in an instruction opcode indicates that the toggle count value is to be determined from the bits in the "immediate count" field (i.e., the bits labeled "I"), rather looking to bits "7" to "9" (i.e.., the bits labeled as "RM") to identify the register containing the toggle count value. In the illustrative example shown, the 16-bit toggle instruction does not include either an "immediate count" field or a set of bits 5 identifying a register. Instead, the DPP knows to look by default to a specific register (e.g., the general purpose register RO identified in Table 1 of the '449 and '452 applications) for the toggle count value that is to be used when such an instruction is received.

Fig. 5 shows an example of channel control circuitry 118 that may be employed in the DPP to facilitate the implementation of short toggle instructions in addition to long toggle0 instructions. Although the details of only channel select circuit 118₀ associated with the output pads 12Oo will now be described, it should be appreciated that the other channel select circuits 1181 to 118N associated with the other output pads 12O₁ to 120_N, respectively, may include the same or similar circuitry. As shown, in the illustrated example, the channel select circuit 118o includes three multiplexers 324, 326, 328, four AND gates 330, 332, 334, 336, 5 three inverters 338, 340, 342, an XOR gate 344, and a flip-flop 346.

In the illustrated example, the channel control circuitry 118 includes a separate circuit 118o, 118i, 118N for each nibble (i.e., group of four bits) that is provided at a respective group of four output pads 12O₀, 12O₁, 12O_N of the DPP. As shown, each of the channel control circuits 118₀, 118χ, 118_N may be provided with toggle control signals 310 from the decoder0 302, as well as a "toggle match" signal from the comparator 308 of the synchronous timer 114. Vector data from a particular part of the instruction being executed is also supplied to each channel control circuit 118₀, 118], 118N as indicated by blocks 318, 320, and 322. For ^M example, with reference to Figs. 3 and 4, each block 322 may be provided with bits "11" to "14" of every executed instruction (which, for 16-bit short toggle instructions 316, 5 corresponds to the "nibble" field 316b in Fig. 3), each block 320 may be provided with either bits "24" to "27" or bits "28" to "31" of every executed instruction that includes such bits (which, for 32-bit short toggle instructions 314, corresponds to one half of the "byte" field 314b in Fig. 3), and each block 318 may be provided with a different group of four bits from the "vector field" of every executed long instruction that includes such bits. 0 A sufficient number of channel select circuits 118₀, 118₁ , 118_N may be employed to provide four different bits from the long instruction vector field (e.g., bits "23" to "63" in the example of Fig. 4) to the respective blocks 318 of such circuits. For example, the bits provided to the block 318 of the circuit 118₀ may correspond to bits "23" to "26" of a received instruction, the bits provided to the same block of the circuit 118i may correspond to the bits "27" to "30" of the received instruction, and so on. Because each channel control circuit 118₀, 118i, 118N may be permanently associated with and responsible for driving a respective group of four output pads 12O₀, 120i, 12O_N, the same group of bits from each instruction word may be provided to the same blocks 318, 320, 322 of a particular channel control circuit 118₀, 118j, 118N every time a new instruction is decoded.

In the example shown, when the short toggle line 310b is low (indicating that the decoded instruction is not a short toggle instruction 314, 316), the multiplexer 326 is controlled (via the inverter 340) to provide the contents of the block 318 to one of the inputs of the AND gate 334. (If the opcodes shown in Fig. 4 are employed, then the decoder 306 may simply provide bit "3" of the opcode as the control signal on the short toggle line 310b). If a toggle match signal is received from the synchronous timer 114 when the circuit is in such a state (and the toggle/force line 310c is high), then the signals at the outputs 12O₀ will be caused to toggle in the manner specified by the bits in the block 318. It should be appreciated that all of the other channel control circuits 1 IS₁ to 118_N may similarly selectively cause the signals on their corresponding output pads 12Oi to 12O_N toggle at the same time when a toggle match signal is received from the synchronous timer 114, thus causing all of the outputs of the DPP to toggle at the same time as indicated in the vector field of the received instruction.

In the illustrated example, the short toggle width select line 310a from the decoder 302 controls the multiplexer 324 to select either the four bits from the block 320 or the four bits from block 322 as an input to the multiplexer 326. As noted above, the four bits from the block 322 may be selected when a 16-bit toggle instruction is being processed, and the four bits from the block 320 may be selected when a 32-bit toggle instruction is being processed. (If the opcodes shown in Fig. 4 are employed, then the decoder 306 may generate an appropriate control signal on the select line 310a, for example, simply by performing a logical AND operation on bits "4" and "5" of the opcode of the received instruction.)

The "nibble select line" for each channel select circuit (e.g., nibble select lineo 31Od for channel select circuit 118₀) may be asserted when the decoder 302 determines (e.g., by examining the bits in the nibble select field 316a or the byte select field 314a) that the particular output nibble for which the channel control circuit is responsible has been selected for toggling. With reference to Figs. 3 and 4, for example, the nibble select line₀ 310d may be asserted if either (1) the nibble select bits 316a (i.e., bits "7" to "10" in Fig. 4) in a 16-bit short toggle instruction 316 identify the particular output nibble for which the channel control circuit 118o is responsible, or (2) the byte select bits 314a (i.e., bits "20" to "23" in Fig. 4) in a 32-bit short toggle instruction 314 identify an output byte containing the particular output nibble for which the channel control circuit 118₀ is responsible. Thus, for 16-bit short toggle instructions 316 (which can select one or more bits within only a single nibble for toggling), the nibble select line of only a single channel control circuit 118₀, 118i, 118_N will be asserted. For 32-bit short toggle instructions 314 (which can select one or more bits within only a single byte for toggling), the nibble select lines of only the two channel control circuits 118₀, 118i, 118_N responsible for driving the bits of the selected output byte will be asserted.

As shown in Fig. 5, the short toggle select line 310b and nibble selecto line 31Od from the decoder 302 may together control the multiplexer 326 (via AND gates 330, 332 and inverters 338, 340) to select one of: (1) the four bits from the block 318, (2) the selected four bits from the multiplexer 324, and (3) a set of four zeros. If the decoded instruction is a toggle instruction 312, 314, 316, then the selected one of these three inputs will determine how the four output bits for which the channel select circuit 118₀ is responsible are to be toggled (unless the signal on the toggle/force line 310c indicates that the toggle instruction is a force vector instruction) upon receipt of a toggle match signal from the synchronous timer 114.

When the toggle/force line 310 is low, the inverter 342 supplies a high signal to one of the inputs of the AND gate 336. Thus, when a toggle match signal is received from the synchronous timer 114, the AND gate 336 causes the multiplexer 328 to select the long vector nibble block 318, rather than the output of the XOR gate 344, as the input to the flip- flop 346, and thus causes the values of the long vector nibble block 318 to be forced upon the output pads 12O₀ rather than allowing the four bits from the multiplexer 326 to determine how the outputs should be toggled. (If the opcodes of Fig. 4 are employed, then the decoder 306 may simply provide bits "3" and "0" of the opcode as the control signals on the short toggle line 31 Ob and the toggle/force line 31 Oc, respectively).

In the example circuit shown, receipt of a toggle match signal will cause the AND gate 334 to provide the four bits from the multiplexer 326 to one of the inputs of the XOR gate 344. The XOR gate 344, in turn, causes the four bits held by the "Q" output of the flip- flop 346 to be toggled as specified by those four bits (provided the toggle/force line 310c is high). If the nibble selecto line 31Od is low when the short toggle select line 310b is high (indicating that the instruction is either a 16-bit short toggle instruction 316 or a 32-bit short toggle instruction 314) and the toggle/force select line 310c is also high, then the multiplexer 326 provides four zeros to the input of the AND gate 334, thus causing the outputs of that particular nibble to maintain their current state, and not be toggled, when the toggle match signal is received. If, however, the nibble selecto line 31Od is high (indicating that the decoder has determined that the particular output nibble for which the channel control circuit 118₀ is responsible has been selected for toggling) when the short toggle select line 31 Ob and toggle/force select line 310c are both high, then the multiplexer 326 provides the four output bits of multiplexer 324 to the input of the AND gate 344, thus resulting in the output bits of that particular output nibble being toggled as indicated by those bits when the toggle match signal is received.

In some embodiments, a pattern generation program may be written using only "long" toggle instructions (several examples of such programs were disclosed in the '449 and '452 applications, incorporated by reference above) and the determination of which long toggle instructions can be converted into either 16-bit or 32-bit short toggle instructions can be left to the timing generator assembler (TGASM). For example, any toggle instructions that require the toggling of one or more bits from only a single byte may be compressed into a 32- bit toggle instruction. Similarly, any toggle instructions that require the toggling of one or more bits from only a single nibble may be compressed into 16-bit toggle instructions. The TGASM may also automatically align the remaining longer instructions in memory and insert appropriate "align" instructions in the code so as to ensure that each such instruction can be fetched in a single memory access.

Having described several embodiments of the invention in detail, various modifications and improvements will readily occur to those skilled in the art. Such modifications and improvements are intended to be within the spirit and scope of the invention. Accordingly, the foregoing description is by way of example only, and is not intended as limiting. The invention is limited only as defined by the following claims and the equivalents thereto.

Claims

1. A method for generating a digital signal pattern at M outputs, comprising steps of: (a) retrieving a first instruction from memory comprising a first set of bits identifying a first group of N outputs that includes fewer than all of the M outputs, and a second set of N bits each corresponding to a respective output included in the first group of N outputs identified by the first set of bits included in the first instruction;

(b) upon the occurrence of a first event, for each of the M outputs that is included in the first group of N outputs identified by the first set of bits included in the first instruction, toggling the signal at the output if the one of the N bits corresponding to that output is in a first state and keeping the signal at the output in the same state if the one of the N bits corresponding to that output is in a second state; and

(c) for each of the M outputs that is not included in the first group of N outputs identified by the first set of bits included in the first instruction, keeping the signal at that output in the same state upon the occurrence of the first event.

2. The method of claim 1, wherein the first instruction consists of a first number of bits, and the method further comprises steps of: (d) retrieving a second instruction from memory that includes more than the first number of bits;

(e) based on the second instruction, identifying particular ones of the M outputs for which the signals thereon are to be toggled upon the occurrence of a second event; and

(f) upon the occurrence of the second event, toggling the signals on the particular ones of the M outputs that were identified by the second instruction.

3. The method of claim 2, wherein the second instruction includes twice as many bits as the first instruction.

4. The method of claim 2 or 3, further comprising steps of:

(g) retrieving a third instruction from memory comprising a first set of bits identifying a group of X outputs that includes fewer than all of the M outputs, and a second set of X bits each corresponding to a respective output included in the group of X outputs identified by the first set of bits included in the third instruction, wherein X is not equal to N; (h) upon the occurrence of a third event, for each of the M outputs that is included in the group of X outputs identified by the first set of bits included in the third instruction, toggling the signal at the output if the one of the X bits corresponding to that output is in the first state and keeping the signal at the output in the same state if the one of the X bits corresponding to that output is in the second state; and

(i) for each of the M outputs that is not included in the group of X outputs identified by the first set of bits included in the third instruction, keeping the signal at that output in the same state upon the occurrence of the third event.

5. The method of claim 4, wherein the number of bits included in the second instruction is an integer multiple of the number of bits included in the first instruction, and the number of bits included in the third instruction is an integer multiple of the number of bits include in the first instruction.

6. The method of claim 5, wherein the third instruction includes twice as many bits as the first instruction, and the second instruction includes twice as many bits as the third instruction.

7. The method of any of claims 1 -6, further comprising steps of: (d) retrieving a second instruction from memory comprising a first set of bits identifying a second group of N outputs that includes fewer than all of the M outputs and is different than the first group of N outputs, and a second set of N bits each corresponding to a respective output included in the second group of N outputs identified by the first set of bits included in the second instruction; (e) upon the occurrence of a second event, for each of the M outputs that is included in the second group of N outputs identified by the first set of bits included in the second instruction, toggling the signal at the output if the one of the N bits corresponding to that output is in the first state and keeping the signal at the output in the same state if the one of the N bits corresponding to that output is in the second state; and (f) for each of the M outputs that is not included in the second group of N outputs identified by the first set of bits included in the second instruction, keeping the signal at that output in the same state upon the occurrence of the second event.

8. The method of any of claims 1-6, further comprising steps of:

(d) retrieving a second instruction from memory comprising a first set of bits identifying a group of X outputs that includes fewer than all of the M outputs, and a second set of X bits each corresponding to a respective output included in the group of X outputs identified by the first set of bits included in the second instruction, wherein X is not equal to N;

(e) upon the occurrence of a second event, for each of the M outputs that is included in the group of X outputs identified by the first set of bits included in the second instruction, toggling the signal at the output if the one of the X bits corresponding to that output is in the first state and keeping the signal at the output in the same state if the one of the X bits corresponding to that output is in the second state; and

(f) for each of the M outputs that is not included in the group of X outputs identified by the first set of bits included in the second instruction, keeping the signal at that output in the same state upon the occurrence of the second event.

9. The method of claim 8 or 9, wherein the second instruction includes twice as many bits as the first instruction.

10. The method of any of claims 1 -9, further comprising a step of: indicating that the first event has occurred upon determining that a particular number of clock cycles have elapsed following retrieval of the first instruction.

11. The method of claim 10, further comprising a step of: identifying the particular number of clock cycles that are to elapse following receipt of the first instruction before indicating that the first event has occurred based upon a third set of bits included in the first instruction.

12. The method of claim 10, further comprising a step of: identifying the particular number of clock cycles that are to elapse following receipt of the first instruction before indicating that the first event has occurred based the content of a register.

13. The method of claim 12, further comprising a step of: identifying the register based upon at least one bit included in the first instruction.

14. An apparatus for generating a digital signal pattern at M outputs, comprising: a circuit configured and arranged to retrieve at least instructions of a first type from memory and to control the toggling of signals at the M outputs in response thereto, wherein each of the instructions of the first type comprises a first set of bits identifying a first group of N outputs that includes fewer than all of the M outputs, and a second set of N bits each corresponding to a respective output included in the first group of N outputs identified by the first set of bits included in the first instruction, the circuit being further configured and arranged to process each retrieved instruction of the first type such that, for each of the M outputs that is included in the first group of N outputs identified by the first set of bits included in the instruction, the signal at the output is toggled if the one of the N bits corresponding to that output is in a first state and is kept in the same state if the one of the N bits corresponding to that output is in a second state, and, for each of the M outputs that is not included in the first group of N outputs identified by the first set of bits included in the instruction, the signal at that output is kept in the same state.

15. The apparatus of claim 14, wherein the circuit is further configured and arranged to retrieve instructions of a second type, which comprise more bits than the instructions of the first type, from memory and to control the toggling of signals at the M outputs in response thereto, the circuit being configured to process each instruction of the second type to identify, based on the instruction, particular ones of the M outputs for which the signals thereon are to be toggled, and to toggle the signals on the particular ones of the M outputs that were identified by the second instruction.

16. The apparatus of claim 14 or 15, wherein the circuit is configured and arranged to retrieve and process instructions of the second type that include twice as many bits as instructions of the first type.

17. The apparatus of any of claims 14-17, wherein the circuit is further configured to retrieve instructions of a third type from memory and to control the toggling of signals at the M outputs in response thereto, each instruction of the third type comprising a first set of bits identifying a group of X outputs that includes fewer than all of the M outputs, and a ' second set of X bits each corresponding to a respective output included in the identified group of X outputs, wherein X is not equal to N, the circuit being further configured and arranged to process each retrieved instruction of the third type such that, for each of the M outputs that is included in the group of X outputs identified by the first set of bits included in the instruction, the signal at the output is toggled if the one of the X bits corresponding to that output is in the first state and is kept in the same state if the one of the X bits corresponding to that output is in the second state, and, for each of the M outputs that is not included in the group of X outputs identified by the first set of bits included in the instruction, the signal at that output is kept in the same state.

18. The apparatus of claim 17, wherein the circuit is configured and arranged to retrieve and process instructions of the second type that include a number of bits that is an integer multiple of the number of bits included in instructions of the first type, and to retrieve and process instructions of the third type that include a number of bits that is an integer multiple of the number of bits included in instructions of the first type.

19. The apparatus of claim 17 or 18, wherein the circuit is configured and arranged to retrieve and process instructions of the third type that include twice as many bits as instructions of the first type, and to retrieve and process instructions of the second type that include twice as many bits as instructions of the third type.

20. The apparatus of any of claims 14-19, wherein the circuit is further configured to retrieve instructions of a second type from memory and to control the toggling of signals at the M outputs in response thereto, each instruction of the second type comprising a first set of bits identifying a group of X outputs that includes fewer than all of the M outputs, and a second set of X bits each corresponding to a respective output included in the identified group of X outputs, wherein X is not equal to N, the circuit being further configured and arranged to process each retrieved instruction of the second type such that, for each of the M outputs that is included in the group of X outputs identified by the first set of bits included in the instruction, the signal at the output is toggled if the one of the X bits corresponding to that output is in the first state and is kept in the same state if the one of the X bits corresponding to that output is in the second state, and, for each of the M outputs that is not included in the group of X outputs identified by the first set of bits included in the instruction, the signal at that output is kept in the same state.

21. The apparatus of any of claims 14-20, wherein the circuit further comprises a timer configured to generate a toggle event signal a particular number of clock cycles following receipt of an instruction of the first type and is configured to control the toggling of the signals at the M outputs upon generation of the toggle event signal. ,

22. The apparatus of claim 21 , wherein the circuit is configured to determine the particular number of clock cycles the timer is to wait before generating a toggle event signal after receiving an instruction of the first type based upon the content of each instruction of the first type.

23. The apparatus of claim 21, wherein the circuit is configured to determine the particular number of clock cycles the timer is to wait before generating a toggle event signal after receiving an instruction of the first type based upon the contents of a register.

24. The apparatus of any of claims 14-23 , wherein the circuit comprises a decoder configured to interpret the instructions of the first type and provide control signals to a channel select circuit based thereupon, the channel select circuit being configured to control toggling of signals at each of the M outputs in response to the received control signals.

25. The apparatus of any of claims 14-24, further comprising a memory having at least the first instructions stored therein.

26. A method for generating a digital signal pattern at M outputs, comprising steps of: (a) retrieving a first instruction from memory that consists of N bits;

(b) based on the first instruction, identifying first ones of the M outputs for which the signals thereon are to be toggled upon the occurrence of a first event;

(c) upon the occurrence of the first event, toggling the signals on the first ones of the M outputs that were identified by the first instruction; (d) retrieving a second instruction from memory that includes more than N bits;

(e) based on the second instruction, identifying second ones of the M outputs for which the signals thereon are to be toggled upon the occurrence of a second event; and

(f) upon the occurrence of the second event, toggling the signals on the second ones of the M outputs that were identified by the second instruction.

27. The method of claim 26, further comprising steps of:

(g) indicating that the first event has occurred upon determining that a first number of clock cycles have elapsed following retrieval of the first instruction; and (h) indicating that the second event has occurred upon determining that a second number of clock cycles have elapsed following retrieval of the second instruction.

28. The method of claim 27, further comprising a step of: determining the first number of clock cycles that are to elapse following receipt of the first instruction before indicating that the first event has occurred based upon the content of a register.

29. The method of claim 28, further comprising a step of: identifying the register based upon at least one bit included in the first instruction.

30. The method of any of claims 26-29, wherein the second instruction includes twice as many bits as the first instruction.