Custom Processor Design Using VHDL

Custom Processor design using VHDL
Centre for Development of Advanced Computing, INDIA Page 1

CUSTOM PROCESSOR DESIGN USING VHDL

Aneesh Raveendran
Centre for development of Advanced Computing, INDIA
[email protected]



CHAPTER 1
INTRODUCTION

A microcontroller is a computer-on-a-chip, or, a single-chip computer. Micro suggests
that the device is small, and controller tells you that the device might be used to control
objects, processes, or events. Another term to describe a microcontroller is embedded
controller, because the microcontroller and its support circuits are often built into, or
embedded in, the devices they control. We can find microcontrollers in all kinds of things
these days. Any device that measures, stores, controls, calculates, or displays information is a
candidate for putting a microcontroller inside. The largest single use for microcontrollers is in
automobiles. Just about every car manufactured today includes at least one microcontroller
for engine control, and often more to control additional systems in the car. In desktop
computers, can find microcontrollers inside keyboards, modems, printers, and other
peripherals. In test equipment, microcontrollers make it easy to add features such as the
ability to store measurements, to create and store user routines, and to display messages and
waveforms. Consumer products that use microcontrollers include cameras, video recorders,
compact-disk players, and ovens are just a few examples.

A microcontroller is similar to the microprocessor inside a personal computer.
Examples of microprocessors include Intels 8086, Motorolas 68000, and Zilogs Z80. Both
microcontrollers and microprocessors contain a central processing unit, or CPU. The CPU
executes instructions that perform the basic logic, math, and data-moving functions of a
computer. To make a complete computer, a microprocessor requires memory for storing data
and programs, and input/output (I/O) interfaces for connecting external devices like
keyboards and displays. In contrast, a microcontroller is a single-chip computer because it
contains memory and I/O interfaces in addition to the CPU. Because the amount of memory
and interfaces that can fit on a single chip is limited, microcontrollers tend to be used in
smaller systems that require little more than the microcontroller and a few support
components. Examples of popular Microcontrollers are Intel 8051,PIC,Motorolas
68HC11and Zilogs Z8.
Increasing performance and gate capacity of recent FPGA devices permits complex
logic systems to be implemented on a single programmable device. Such a growing
complexity demands design approaches, which can cope with designs containing hundreds of


thousands of logic gates, memories, high-speed interfaces, and other high-performance
components.

One category of such design approaches are design methodologies based on languages
derived from traditional programming languages such as C, Pascal, Java or others. These
allow designers to use the familiar language syntax to develop hardware systems at high
level. In this report, the design of a RISC controller is presented. Hardware description
language is used for the proposed work and the work is targeted towards FPGA.



CHAPTER 2
RISC ARCHITETURE
2.1 RISC Architecture
In the early 1980s, a number of computer designers were questioning the need for
complex instruction sets used in the computer of the time. In studies of popular computer
systems, almost 80% of the instructions are rarely being used. So they recommended that
computers should have fewer instructions and with simple constructs. This type of computer
is classified as reduced instruction set computer or RISC.
The first characteristic of RISC is the uniform series of single cycle, fetch-and-
execute operations for each instruction implemented on the computer system being
developed. A single-cycle fetch can be achieved by keeping all the instructions a standard
size. The standard instruction size should be equal to the number of data lines in the system
bus, connecting the memory where the program is stored to the CPU. At any fetch cycle, a
complete single instruction will be transferred to the CPU. For instance, if the basic word size
is 16 bits, and the data port of the data bus has 16 lines, the standard instruction length should
be 16-bits.
Achieving uniform execution of all instructions is much more difficult than achieving
a uniform fetch. Some instructions may involve simple logical operations on a CPU register
(such as clearing a register) and can be executed in a single CPU clock cycle without any
problem. Other instructions may involve memory access (load from or store to memory, fetch
data) or multi-cycle operations (multiply, divide, floating point), and may be impossible to be
executed in a single cycle. Ideally, we would like to see a streamlined and uniform handling
of all instructions, where the fetch and the execute stages take up the same time for any
instruction, desirably, a single cycle. This is basically one of the first and most important
principles inherent in the RISC design approach. All instructions go from the memory to the
CPU, where they get executed, in a constant stream. Each instruction is executed at the same
pace and no instruction is made to wait. The CPU is kept busy all the time.
Thus, some of the necessary conditions to achieve such a streamlined operation are:

Standard, fixed size of the instruction, equal to the computer word length and to the
width of the data bus.
Standard execution time of all instructions, desirably within a single CPU cycle.



While it might not practical to hope that all instructions will execute in a single cycle, one
can hope that at least 75% should. Which instructions should be selected to be on the reduced
instruction list? The obvious answer is: the ones used most often. It has been established in a
number of earlier studies that a relatively small percentage of instructions (10 20%) take up
about 80% 90% of execution time in an extended selection of benchmark programs [3].
Among the most often executed instructions were data moves, arithmetic and logic
operations. As mentioned earlier, one of the reasons preventing an instruction from being
able to execute in a single cycle is the possible need to access memory to fetch operands
and/or store results. The conclusion is therefore obvious, we should minimize as much as
possible the number instructions that access memory during the execution stage. This
consideration brought forward the following RISC principles:
Memory access, during the execution stage, is done by load/store instructions only.
All operations, except load/store, are register-to-register, within the CPU.
Most of the CISC systems are micro programmed; because of the flexibility that
microprogramming offers the designer. Different instructions usually have micro routines of
different lengths. This means that each instruction will take a number of different cycles to
execute. This contradicts the principle of a uniform, streamlined handling of all instructions.
An exception to this rule can be made when each instruction has a one-to one correspondence
with a single micro instruction. That is, each micro routine consists of a single control word,
and still let the designer benefit from the advantages of micro programming. However,
contemporary CAD tools allow the designer of hardwired control units almost as easy as
micro programmed ones. This enables the single cycle rule to be enforced, while reducing
transistor count.
In order to facilitate the implementation of most instruction as register-to register
operations, a sufficient amount of CPU general purpose registers has to be provided. A
sufficiently large register set will permit temporary storage of intermediate results, needed as
operands in subsequent operations, in the CPU register file. This, in turn, will reduce the
number of memory accesses by reducing the number of load/store operations in the program,
speeding up its run time. A minimal number of 16 general purpose CPU registers has been
adopted, by most of the industrial RISC system designers.



The characteristics of RISC architecture are summarized as follow:
Single-cycle instruction execution
Fixed-length, easily decoded instruction format
Relatively few instructions
Relatively few addressing modes
Memory access limited to load and store instructions
Hardwired rather than micro programmed control unit
Relatively large number of general purpose register file
2.2 Benefits of RISC Architecture
1. RISC architecture makes the implementation of a processor on a single chip feasible. It is
more difficult to realize a complex architecture on a chip than a less complicated architecture.
So only a RISC processor can be implemented on an FPGA chip with a limited number of
logic cells.
2. RISC architecture helps in implementing more efficient pipelining. The length of the
pipeline is dependent on the length of the longest step. RISC instructions are all of the same
length and can be fetched in a single operation. Ideally, each of the stages in a RISC
processor pipeline takes 1 clock cycle so that the processor finishes an instruction during each
clock cycle and averages one cycle per instruction. All RISCs use pipelined execution where
pipelining involves finding a balance between the four parts of a RISC instruction execution:
instruction fetch, register read, arithmetic/ logic operation and register write.
3. The difficulty in system design is less for RISC processors. The design time and the time
required for testing and debugging is thus reduced leading to an edge in the industry. This
also assists in implementing the project within the time frame. Documentation and
maintenance is also easier for RISC architecture.
4. RISC architecture saves chip area by getting rid of the more complicated hardware
necessary in CISC processors. The space on a chip spared by implementing only hardware
for a reduced instruction set can be used to promote pipelining and a larger cache, thus
improving the performance of the system.


5. A RISC processor is capable of executing commonly used algorithms at a high speed with
a simple architecture. Better use of chip area, use of newer technologies facilitated by
reduced design time, simpler control structures and the presence of fewer gates in the critical
path in the machine could give RISC processors an edge in algorithm execution speed
2.3 Common RISC Traits
The operations and addressing modes are reduced. Operations between registers complete in
one cycle, permitting a simpler, hardwired control for RISC, instead of microcode. Only one
or a very few simple addressing modes are provided. More complicated addressing modes
can be synthesized from the simple ones.
2. Operations are register-to-register, with only load and store operations accessing memory.
Operands are not discarded after being fetched, as in the memory-to- memory architecture.
This allows compilers to reuse operands stored in registers. As a result cycle time is
shortened.
3. Instruction formats are simple and are usually of uniform length. This restriction allows
RISCs to remove instruction decoding time from the critical execution path. So register
access can take place simultaneously with op-code decoding. This removes the instruction
decoding stage from the pipelined execution, making it more effective by shortening the
pipeline. Single-sized instructions also simplify virtual memory, since they cannot be broken
into parts that might wind up on different pages. Since the instructions are simple their
execution time is very low and so the processor cycle time was reduced. Due to the uniform
length and execution time of RISC instructions this architectural approach is highly
supportive of pipelined and superscalar processors.
4. RISC architecture usually supports only one or two data types in a bid to simplify the
instruction set and associated hardware. These two data types are the integer and floating
point data types.
5. RISC branches avoid pipeline penalties. A branch instruction in a pipelined computer will
normally delay the pipeline until the instruction at the branch address is fetched The RISC
solution, commonly used is to redefine jumps so that they do not take effect until after the
following instruction; this is called the delayed branch. The delayed branch allows RISCs to
always fetch the next instruction during the execution of the current instruction.


CHAPTER 3
CONTROLLER SPECIFICATIONS

The specifications are:-
8-bit RISC microcontroller
13-bit program counter
16-bit instruction register
Uses Harvard architecture
Program memory 8k x16
o Address Bus - 13 bit
o Data Bus - 16 bit
Data memory 256 x 8
o Address Bus - 8 bit
o Data Bus - 8 bit
Data memory 256 x 8
Memory access is only through LOAD and STORE instructions
16 instructions of fixed length op-code
Sixteen 8-bit general purpose registers
Four 8-bit special purpose registers
Four ports for Input/Output Communication
All ports are bidirectional
Supports 2 flags:- Carry and Zero
The top level entity of the controller is shown in fig 63.

Fig63:-Top Level Entity:-Microcontroller


CHAPTER 4
INSTRUCTION SET ARCHITECTURE

The Instruction Set Architecture (ISA) is the part of the processor that is visible to the
programmer or compiler writer. The ISA serves as the boundary between software and
hardware. The operation of the CPU is determined by the instruction it executes, referred to
as machine instructions or computer instructions. The collection of different instructions that
the CPU can execute is referred to as the CPUs instruction set.
4.1 Register Files
The proposed microcontroller consists of both 16 general purpose registers and 4 special
purpose registers. All the register can hold an 8 bit data. The structure of register file is
shown below.

R0
R1
R2
R3
R8
R9
R10
R11
R4
R5
R6
R7
R12
R13
R14
R15
PORTA
PORTB
PORTC
PORTD
Table12: General Purpose Register
Table13: Special Purpose Register


4.2 Instruction Formats
RISC instructions have a fix length and are easily decoded. For this microcontroller, all
instructions have a fixed-length of 16-bits. The instruction format is simple in order to be
decoded easily. The instructions are of fixed length opcode. The proposed controller supports
four different types of instruction formats are as follows.
A. Immediate type (I-type)
In immediate type instruction format, an 8-bit data is used as an immediate value.

B. Register type (R-type)
In register type instruction format, both the source and destination be register. The format is
shown below.

C. Jump type (J-type)
In jump type instruction format, it contains only the opcode and address. The address is
specified as part of instruction. The jump type instruction format is shown below.

OP Rd
4
Immediate_value
OP Rd
4
Rs
4

OP Address_12


4.2 Instruction Set
The proposed microcontroller is designed to execute 16 instructions of fixed length op-code.
The instructions set for our design is shown below.
OP-CODE INSTRUCTION EXAMPLE
0000 NOP NOP
0001 MOV MOV Rd, Rs
0010 MVI MVI Rd, Immediate_value
0011 LD LD address_12
0100 ST ST sddress_12
0101 ADD ADD Rd, Rs
0110 SUB SUB Rd, Rs
0111 XOR XOR Rd, Rs
1000 CMP CMP Rd, Rs
1001 JMP JMP address_12
1010 JNZ JNZ address_12
1011 JEQ JEQ address-12
1100 IN IN port_num
1101 OUT OUT port_num
1110 BS BS bit_pos
1111 BC BC bit_pos
Table14: Instruction set
Our controller design is carry out to perform above instructions. In this MOV, ADD, SUB,
XOR, CMP instructions are register type. MVI is of immediate type; in this an 8-bit
immediate value is used as a source. LD, ST, JMP, JNZ, JEQ, IN, OUT, BS, BC is of jump
type; in this only opcode and address is present.



CHAPTER 5
INTERNAL ARCHITECTURE

Fig64: Internal Architecture of custom controller
The figure 64 repents the internal architecture of our proposed custom controller. Mainly it is
having 4 units
1. FETCH UNIT
2. DECODE UNIT
3. EXECUTE UNIT
4. CONTROL UNIT
The Fetch unit fetches the instructions from the program memory. After the execution of
fetch operation, it generates s completion signal to control unit. The control unit enables the
decode module, and decode the instruction according to the decoding algorithm. After the
completion of decode module, it provides a decode completion signal. Then control unit
enables the execution unit and after the completion of execution, the fetch module will be
enabled.


CHAPTER 6
STAGE CONTROL UNIT

The proposed microcontroller follows a non-pipelined architecture. So the stage control unit
controls the flow for executing an instruction. This control unit monitors the completion
signal of each unit and once the completion signal is available, then it enables the other unit
for subsequent operation. The top level entity is shown in figure65.

Fig65: Top Level Entity:-Stage Control Unit
The flow of executing an instruction in our microcontroller is FETCH, DECODE then
Execute. The stage control unit controls this flow by checking the completion signal from
each unit and enables the next unit to continue the execution. The stage control unit accepts
the completion signal as inputs and enable signal as output. It has a reset signal to reset the
entire unit.
The flow chart for the stage control unit is shown in figure 66. It has 5 states, RESET,
FETCH_aft_rst, Fetch, Decode, and Execute. In RESET state all the units are in reset state.In
this state no unit is in enabled. After the removal of reset it comes to the FETCH_aft_rst. In
this state it enables the fetch unit and waits for the completion signal from fetch unit. If
fetch_comp signal is HIGH then it goes to DECODE state and enables the decode unit and
wait in the same state for the completion signal. If the Dco_comp signal is HIGH then it
moves to the Execute state and enables the execute state and waits for the completion signal
from execute unit. If Exe_comp signal is HIGH then it goes to the FETCH unit enables the
fetch units and continous with decode ste and so on.

Reset
Fetch_En
Dco_En
Exe_En Exe_comp
Dco_comp
Fetch_comp

STAGE
CONTROL


Fig66: Flow Chart-Stage Control Unit

Centre for Development of Advanced Computing, INDIA

The fetch unit fetches the instructions from program memory.
Program counter (PC), which holds the address of next instruction to be executed
Instruction Register (IR) which holds the current instruction to be executed
entity of a fetch unit is shown in fig
Fig
The fetch unit have an enable signal (FETCH_EN) for enabling the fetch unit. After the
completion of fetch operation it produces a completion signal (FETCH_COMP).
diagram for the fetch unit is shown in fig
Fig
Custom Processor design
ent of Advanced Computing, INDIA
CHAPTER 7
FETCH UNIT
fetch unit fetches the instructions from program memory. The fetch unit consist of a
Program counter (PC), which holds the address of next instruction to be executed
Instruction Register (IR) which holds the current instruction to be executed
entity of a fetch unit is shown in figure 67
Fig67: Top level Entity-Fetch Unit
completion of fetch operation it produces a completion signal (FETCH_COMP).
diagram for the fetch unit is shown in figure 68
Fig68: State Diagram-Fetch Unit
design using VHDL
Page 15
The fetch unit consist of a
Program counter (PC), which holds the address of next instruction to be executed and an
Instruction Register (IR) which holds the current instruction to be executed. The top level

completion of fetch operation it produces a completion signal (FETCH_COMP). The state



When a reset is applied, the Program counter and instruction register are set to be zero. After
the removal of reset it comes to the work state and checks for the fetch enable signal, if it is
enabled it places the program counter value on to the address bus of program memory and
provides a read signal to the program memory. Within the one clock cycle duration the
program memory will performs the read operation.
In update state the value on to the data bus of the program memory is copied to the
instruction register and program counter is incremented by one. After this operation a fetch
completion signal is given to the stage control unit and state changed to work state.



CHAPTER 8
DECODE UNIT

The decode unit in the processor performs the decoding of the instruction register obtained
from the fetch unit. The top level entity of the fetch module is shown in figure 69.

Fig69: Top Level Entity:-decode Unit
The input to the decode module is Inst_reg, a 16 bit register from the fetch unit. It has output
of destination register (4-bit), source register (4-bit), immediate bus (8-bit), Branch address
(12-bit), and a bit position (3 bit). The source and destination register is used to identify the
source and destination registers used. The immediate bus is used to hold an 8-bit immediate
value for immediate data transfers. The branch address bus is a 12-bit bus used to hold the
addresses for jump operations. The Bit_pos bus is a 8-bit used for holding the bit position for
the bit set and clear operations. The figure 70 shows the state diagram used for the decode
operations.

Fig70: State machine:-Decode unit


The state machine of the decode unit contains 4 states; RESET, IDLE, DECODE,
DECODE_COMP. The RESET state is for reset operations. The IDLE state is the default
state in decode unit. It checks for the enable signal of the decode unit. If it is enabled then it
moves to the DECODE state otherwise it stays in IDLE state. In DECODE state it performs
the decode operation and moves to the DECODE_COMP state and produces a decode
completion signal. The operations done at DECODE state is shown in figure 71.

Fig71: Working of DECODE state
In decode state first it checks for the first 4 bit to identify the opcode, based on that it
performs the appropriate information extraction. The above figure shows the some of the
information extraction done during the decode operation.



CHAPTER 9
EXECUTION UNIT

The execution unit performs the execution of the instructions that is already decoded. The
execution unit is divided into several subunits to perform operations. The structure of an
execution unit is shown in figure72.

Fig72: Structure:-Execution Unit
The Execution unit performs the proposed instruction set (16 instructions). The 16
instructions are grouped into 7 sub units which are described below.
A) MOVE unit
The MOVE unit is designed to perform MVI and MOV instructions. The MVI is move
immediate. It performs the immediate movement of an 8-bit data to destination register. The
example is shown below
MVI R0, 00010010
The above instruction performs the movement of immediate value 00010010 to the
destination register r0. The MOV instruction performs the movement of data between source
and destination registers. The example is shown below
MOV R1, R2
The above instruction performs the movement of the content of R2 into R1.
MOVE
ARITHMETIC
JUMP
NOP
LOAD
STORE
IN and
OUT
SET and
CLEAR
PORT1
PORT2
PORT3
PORT4
LOGIC


The flow chart for the MOVE unit is shown in figure 73.

Fig73: Flow Chart-- MOVE unit
The default state is RESET state. After the reset release it moves to the MOV_STATE, and
checks for the enable signal. If it is enabled then it checks the instructions to be executed. If
the instruction is MVI then it performs the immediate data movement or if the instruction is
MOV then it performs data movement between the source and destination registers. After the
execution of the instruction it moves to the completion state and provides an execution
completion signal.
B) ARITHMETIC unit
The ARITHMETIC unit is designed to perform ADD and SUB instructions. The ADD
instruction performs the addition of content in registers. The example is shown below.
ADD R0, R1
The above instruction performs the addition of contents in register R0 and R1. After the
addition the result of operation is stored in destination register (R0). If any carry occur during
the addition operation a carry flag is set. The content of register R1 is not altered.



The SUB instruction performs the subtraction of contents in register. The example is shown
below.
SUB R0, R1
The above instruction performs the subtraction of contents in register R0 and R1. After the
subtraction the result of operation is stored in destination register (R0). If any borrow occur
during the subtraction operation a carry flag is set. The content of register R1 is not altered.
The flowchart is used is shown in figure 74.

Fig74: Flow Chart-- ARITMETIC unit
The default state is RESET state. After the reset release it moves to the ARITH_STATE, and
checks for the enable signal. If it is enabled then it checks the instructions to be executed. If
the instruction is ADD then it performs the addition or if the instruction is SUB then it
performs the subtraction between the source and destination registers. After the execution of
the instruction it moves to the completion state and provides an execution completion signal.



C) LOGIC unit
The ARITHMETIC unit is designed to perform XOR and CMP instructions. The XOR
instruction is used performs the Exclusive-OR operation between the source and destination
registers. The example is shown below.
XOR R2, R3
The above instruction performs the Exclusive-OR operation between registers R2 and
R3.After the execution of operation the result is stored on to the register R2. The content of
register R3 is not altered. If the result of operation is zero then a zero flag is set.
The CMP instruction is used to perform comparison between source and destination registers.
The example is shown below.
CMP R2, R3
The above instruction performs the comparison operation between registers R2 and R3. After
the execution of operation the result is stored on to the register R2. If the contents of registers
are same the zero flag is set or otherwise it is reset. The content of registers is not altered after
the execution.

D) LOAD_STORE unit
The LOAD_STORE unit is designed to perform LD and ST instructions. The base register
used for load and store operation is R0.The LD instruction is used to perform the LOAD
operation. As a part of instruction an 8-bit data memory address is specified. The example is
shown below.
LD 00100000
The above instruction loads the content of memory location 00100000 (0x20H) in the base
register R0.
The ST instruction is used to perform the STORE operation. The memory address is specified
as a part of the instruction. The example is shown below.
ST 00100000
The above instruction stores the contents of base register on to the memory location
00100000 (0x20H).


E) JUMP unit
The JUMP unit is designed to perform JMP, JNZ, and JEQ instructions. It performs the jump
in program memory. The jump address is specified as a part of instruction. The JMP is an
unconditional jump instruction and JNZ and JEQ are conditional jump instruction. The
maximum supported jump in program memory is 2
12
. This unit works on the content of status
of flag registers. The example is shown below
JMP 0x020
JNZ 0x1FF
JEQ 0X2FF
In the above instruction JMP 0x020 it jumps to the program memory location 0x020.For this
instruction only the program counter (PC) value is substituted with jump address, and normal
instruction fetch continuous. In the instruction JNZ0x1FF it jumps to the program memory
location 0x1FF only the zero flag is in reset condition (active LOW). If the zero flag set then
this instruction is not been executed. The instruction JEQ 0x2FF it jumps to the program
memory location 0x2FF, only the zero flag is set. If the zero flag is low then this instruction
is not been executed.

F) IN_OUT unit
The IN and OUT instructions used for transferring data to and from the Input/output ports.
The IN instruction stores the data from port to the base register R0. The OUT instruction
stores the data on to the I/O port from base register R0. The address of the port is shown in
table 15.
PORT NAME PORT ADDRESS
PORT1 00000001
PORT2 00000010
PORT3 00000011
PORT4 00000100
Table15: Port Address



The example is shown below
IN 00000001
OUT 00000001
The above IN instructions stores the status of the port 00000001 to the base register R0. The
OUT instructions load the base register on to the port 00000001. All the ports are directly
mapped to the first four locations in the data memory.

G) SET_CLEAR unit
The SET_CLEAR unit is used to perform bit setting and resetting of the specified register.
This operation is done by specifying the bit position as a part of the instruction. The example
is shown below.
BS R0, 00000001
The above instruction sets (high) the first position in the R0 register.
BC RO, 00000000
The above instruction resets (zero) the zero
th
bit position in R0 register.

H) NOP unit
The NOP unit is used to perform the no operation. This operation used to wait the operation
of the controller to 3 clock cycle. It doesnt alter the content of any register. The example is
shown below.
NOP
The above instruction is used to perform the no operation.


CHAPTER 10
SIMULATION RESULT

MOV R1, 00000100

design using VHDL
Page 25


MOV R2, R1
design using VHDL
Page 26


CHAPTER 11
SYNTHESIS REPORT

The proposed microcontroller is designed by using VHDL and synthesised by using
ALTERA QUARTUS II for ALTERA STRATIX II EP2S60F672C3N FPGA. The
synthesised report is shown in figure 75.

Fig 75: Synthesis Report-Custom Controller
The Register Transfer level representation of the custom controller is shown in figure 76.

Fig76: RTL view:-Custom Controller



If you have any quries please feel free to contact
aneesh [email protected]

Custom Processor Design Using VHDL

Uploaded by

Copyright:

Available Formats

Custom Processor Design Using VHDL

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Custom Processor Design Using VHDL

Uploaded by

Copyright:

Available Formats

Custom Processor design using VHDL

Centre for Development of Advanced Computing, INDIA Page 1

You might also like