added some documentation and started on compiler for custom language (not C) based on previous prototypes. pretty broken state rn.

This commit is contained in:
2026-02-01 22:16:09 +00:00
parent 52ef7872f0
commit 8f7163c459
9 changed files with 1750 additions and 17 deletions
+427
View File
@@ -0,0 +1,427 @@
# DSA Assembly Language Instruction Reference
## Overview
This document provides a comprehensive reference for the DSA (Damn Simple Architecture) assembly language, including all hardware instructions and pseudo-instructions with their syntax variations and usage examples.
## Calling Convention
| Step | Responsibility | Action | Description |
|------|----------------|--------|-------------|
| 1 | **Caller** | Push arguments | Push exactly n arguments to the stack (in order, last argument pushed first) |
| 2 | **Caller** | Call function | Execute `call namespace::function` - this automatically pushes the return address (pcx) and jumps to the function |
| 3 | **Function** | Set up stack frame | Execute `push bpr; mov spr, bpr` to establish new stack frame |
| 4 | **Function** | Access arguments | Read arguments starting at `spr+8` (first 3 args at offsets 8, 12, 16) |
| 5 | **Function** | Execute function | Perform the function's operations using the arguments |
| 6 | **Function** | Store return value | Write return value (if any) to `spr+8` |
| 7 | **Function** | Restore stack frame | Execute `mov bpr, spr; pop bpr` to restore previous stack frame |
| 8 | **Function** | Return | Execute `return` pseudo-instruction to return to caller |
| 9 | **Caller** | Clean up stack | Pop exactly n arguments from the stack to clean up |
| 10 | **Caller** | Handle unused values | Use `pop zero` to discard any unused stack values if needed |
**Notes:**
- The namespace in step 2 is the name assigned in the `include` statement
- The `call` pseudo-instruction automatically handles return address management so long as the callee does not mess with the stack
- Arguments are accessed by the callee using offsets from the base pointer (bpr)
## Registers
| Register | Type | Description |
|----------|------|---------------------------------------------------------------------------------------------------|
| `rg0-rgf` | General Purpose | General-purpose registers. |
| `acc` | Special | Accumulator for calculations and temporary storage - don't use this for variables as pseudo instructions may overwrite this implicitly! |
| `spr` | Special | Stack pointer |
| `bpr` | Special | Base pointer for stack frames |
| `ret` | Special | Return address register |
| `idr` | Privileged | Interrupt descriptor table address<br/>**on-read/write: protection fault (unless in kernel mode)** |
| `mmr` | Privileged | Hardware memory map table address<br/>**on-read/write: protection fault (unless in kernel mode)** |
| `zero` | Read-only | Always contains zero<br/>**on-read: always returns zero**<br/>**on-write: value is voided** |
| `pcx` | Read-only | Program counter<br/>**on-write: protection fault** |
| `noreg` | Placeholder | Indicates absence of register argument<br/>**on-read/write: illegal instruction fault** |
## Hardware Instructions
### Data Movement Instructions
| Mnemonic | Operands | Description |
|----------|----------|-------------|
| **MOV** | `src_reg, dest_reg` | Copy value from source to destination register |
| **MOVS** | `src_reg, dest_reg` | Copy with sign extension |
**Examples:**
```asm
mov rg0, rg1 ; Copy rg0 to rg1
movs rg0, rg1 ; Copy rg0 to rg1 with sign extension
```
### Memory Access Instructions
#### Load Instructions
| Mnemonic | Operands | Description |
|----------|----------|-------------|
| **LDB** | `base_reg, dest_reg [, offset]`<br>`label, dest_reg [, offset]` | Load byte from memory |
| **LDBS** | `base_reg, dest_reg [, offset]`<br>`label, dest_reg [, offset]` | Load byte with sign extension |
| **LDH** | `base_reg, dest_reg [, offset]`<br>`label, dest_reg [, offset]` | Load half-word (16-bit) |
| **LDHS** | `base_reg, dest_reg [, offset]`<br>`label, dest_reg [, offset]` | Load half-word with sign extension |
| **LDW** | `base_reg, dest_reg [, offset]`<br>`label, dest_reg [, offset]` | Load word (32-bit) |
**Examples:**
```asm
; Direct register addressing
ldb rg0, rg1 ; Load byte from address in rg0
ldw rg0, rg1, 8 ; Load word from (rg0 + 8)
; Label addressing
ldb buffer, rg2 ; Load byte from label 'buffer'
ldw stack, bpr ; Load stack address into base pointer
```
**Label Expansions:**
```asm
; ldb buffer, rg2 expands to:
lli buffer, rg2 ; Load lower 16 bits of buffer address
lui buffer, rg2 ; Load upper 16 bits of buffer address
ldb rg2, rg2 ; Load byte from address in rg2
; ldw stack, bpr expands to:
lli stack, bpr ; Load lower 16 bits of stack address
lui stack, bpr ; Load upper 16 bits of stack address
ldw bpr, bpr ; Load word from address in bpr
```
#### Store Instructions
| Mnemonic | Operands | Description |
|----------|----------|-------------|
| **STB** | `src_reg, base_reg [, offset]`<br>`src_reg, label [, offset]` | Store byte to memory |
| **STH** | `src_reg, base_reg [, offset]`<br>`src_reg, label [, offset]` | Store half-word to memory |
| **STW** | `src_reg, base_reg [, offset]`<br>`src_reg, label [, offset]` | Store word to memory |
**Examples:**
```asm
; Direct register addressing
stb rg0, rg1 ; Store byte from rg0 to address in rg1
stw rg0, rg1, 12 ; Store word to (rg1 + 12)
; Label addressing
stb acc, buffer ; Store byte from accumulator to 'buffer'
stw rg1, current ; Store word to 'current' variable
```
**Label Expansions:**
```asm
; stb acc, buffer expands to:
lli buffer, rgf ; Load lower 16 bits of buffer address
lui buffer, rgf ; Load upper 16 bits of buffer address
stb acc, rgf ; Store byte from acc to address in rgf
; stw rg1, current expands to:
lli current, rgf ; Load lower 16 bits of current address
lui current, rgf ; Load upper 16 bits of current address
stw rg1, rgf ; Store word from rg1 to address in rgf
```
### Immediate Load Instructions
| Mnemonic | Operands | Description |
|----------|----------|------------------------------------------------------------------------|
| **LLI** | `imm, dest_reg` | Load 16-bit immediate into lower 16 bits<br/>**Clears upper 16 bits!** |
| **LUI** | `imm, dest_reg` | Load 16-bit immediate into upper 16 bits |
**Usage**
ensure that you always run **Lli** before **Lui** as **Lli** clears the upper 16 bits.
**Examples:**
```asm
lli 0x1234, rg0 ; Load 0x1234 into lower 16 bits of rg0
lui 0xABCD, rg0 ; Load 0xABCD into upper 16 bits of rg0
```
### Jump Instructions
| Mnemonic | Operands | Description |
|----------|----------|-------------|
| **JMP** | `addr [, offset_reg]`<br>`imm, offset_reg` | Unconditional jump |
| **JEQ** | `addr [, offset_reg]` | Jump if equal flag set |
| **JNE** | `addr [, offset_reg]` | Jump if not equal flag set |
| **JGT** | `addr [, offset_reg]` | Jump if greater than flag set |
| **JGE** | `addr [, offset_reg]` | Jump if greater or equal flags set |
| **JLT** | `addr [, offset_reg]` | Jump if less than flag set |
| **JLE** | `addr [, offset_reg]` | Jump if less or equal flags set |
**Examples:**
```asm
jmp start ; Jump to label 'start'
jmp 4, ret ; Jump to address (4 + ret register)
jeq end ; Jump to 'end' if equal flag set
jgt loop ; Jump to 'loop' if greater than flag set
```
### Arithmetic Instructions
| Mnemonic | Operands | Description |
|----------|----------|-------------|
| **ADD** | `src1_reg, src2_reg, dest_reg` | Addition |
| **SUB** | `src1_reg, src2_reg, dest_reg` | Subtraction |
| **IADD** | `src_reg, imm [, dest_reg]` | Immediate addition |
| **ISUB** | `src_reg, imm [, dest_reg]` | Immediate subtraction |
| **INC** | `reg` | Increment register by 1 |
| **DEC** | `reg` | Decrement register by 1 |
**Examples:**
```asm
add rg0, rg1, rg2 ; rg2 = rg0 + rg1
sub rg0, rg1, rg2 ; rg2 = rg0 - rg1
iadd rg0, 10 ; rg0 = rg0 + 10
// or using alternate syntax
addi rg0, 1 ; rg0 = rg0 + 1
inc rg0 ; rg0 = rg0 + 1
```
### Bitwise Operations
| Mnemonic | Operands | Description |
|----------|----------|-------------|
| **AND** | `src1_reg, src2_reg, dest_reg` | Bitwise AND |
| **OR** | `src1_reg, src2_reg, dest_reg` | Bitwise OR |
| **XOR** | `src1_reg, src2_reg, dest_reg` | Bitwise XOR |
| **NOT** | `src_reg, dest_reg` | Bitwise NOT |
| **NAND** | `src1_reg, src2_reg, dest_reg` | Bitwise NAND |
| **NOR** | `src1_reg, src2_reg, dest_reg` | Bitwise NOR |
| **XNOR** | `src1_reg, src2_reg, dest_reg` | Bitwise XNOR |
**Examples:**
```asm
and rg0, rg1, rg2 ; rg2 = rg0 & rg1
not rg0, rg1 ; rg1 = ~rg0
```
### Shift Operations
| Mnemonic | Operands | Description |
|----------|----------|-------------|
| **SHL** | `reg, shift_amount` | Shift left |
| **SHR** | `reg, shift_amount` | Shift right |
**Examples:**
```asm
shl rg0, 2 ; Shift rg0 left by 2 bits
shr rg0, 3 ; Shift rg0 right by 3 bits
```
### Comparison and Control
| Mnemonic | Operands | Description |
|----------|----------|-------------|
| **CMP** | `reg1, reg2` | Compare registers and set flags |
**Examples:**
```asm
cmp rg0, zero ; Compare rg0 with zero register
cmp rg1, rg2 ; Compare rg1 with rg2
```
### System Instructions
| Mnemonic | Operands | Description |
|----------|----------|-------------|
| **HLT** | - | Halt processor execution |
| **NOP** | - | No operation |
| **INT** | `interrupt_code` | Trigger interrupt |
| **IRT** | - | Return from interrupt |
**Examples:**
```asm
hlt ; Stop processor execution
int 0x21 ; Trigger interrupt 0x21
```
## Pseudo-Instructions
### Data Definition
| Mnemonic | Syntax | Description |
|----------|--------|-------------|
| **DB** | `name: value1 [, value2, ...]` | Define bytes |
| **DH** | `name: value1 [, value2, ...]` | Define half-words |
| **DW** | `name: value1 [, value2, ...]` | Define words |
**Examples:**
```asm
db message: "Hello World", 0
dh numbers: 1000, 2000, 3000
dw stack: 0x10000
```
### Memory Reservation
| Mnemonic | Syntax | Description |
|----------|--------|-------------|
| **RESB** | `name: size` | Reserve bytes |
| **RESH** | `name: size` | Reserve half-words |
| **RESW** | `name: size` | Reserve words |
**Examples:**
```asm
resb buffer: 256 ; Reserve 256 bytes
resh array: 100 ; Reserve space for 100 half-words
resw heap: 1024 ; Reserve space for 1024 words
```
### Stack Operations
| Mnemonic | Operands | Description |
|----------|----------|-------------|
| **PUSH** | `reg` | Push register value onto stack |
| **POP** | `reg` | Pop stack value into register |
**Examples:**
```asm
push rg0 ; Push rg0 value onto stack
pop ret ; Pop return address
```
### Memory Access Shortcuts
| Mnemonic | Operands | Description |
|----------|----------|-------------|
| **LWI** | `name, reg` | Load address into register |
**Examples:**
```asm
lwi string, rg1 ; Load address of 'string' into rg1
```
### Function Control
| Mnemonic | Operands | Description |
|----------|----------|-------------|
| **CALL** | `namespace::function` | Call a function with automatic return address management |
| **RETURN** | - | Return from a function to the caller |
**Examples:**
```asm
call print::print ; Call the print function from the print namespace
return ; Return from the current function
```
### Module System
| Mnemonic | Syntax | Description |
|----------|--------|-------------|
| **INCLUDE** | `module_name "path"` | Include module |
**Examples:**
```asm
include print "print.dsa"
include fib "fib.dsa"
```
## Library Examples
### Multiplication Library (multiply.dsa)
```asm
// multiply.dsa
// usage:
//
// include multiply "<relative path>"
//
// usage for multiply:
// push (arg1)
// push (arg0)
// call multiply::multiply
// pop (arg0)
// pop (arg1)
multiply:
push bpr
mov spr, bpr
ldw bpr, rg0, 8 // load op 1
ldw bpr, rg1, 12 // load op 2
lli 0, acc // initialize accumulator
start:
add acc, rg0, acc
dec rg1
cmp rg1, zero
jgt start
end:
stw acc, bpr, 8 // store result for caller
mov bpr, spr
pop bpr
return
```
### Print Library (print.dsa)
```asm
// print.dsa
// usage:
//
// include print "<relative path>"
//
// usage for print:
// push (register containing address of string)
// call print::print
// pop zero
//
// usage for reset:
// call print::reset
dw display: 0x20000
dw current: 0x20000
// prints the given text to the screen.
print:
push bpr
mov spr, bpr
ldw bpr, rg0, 8 // get string address argument
ldw current, rg1 // get current display position
print_loop:
ldb rg0, acc
stb acc, rg1
iadd rg0, 1
iadd rg1, 1
cmp acc, zero
jne print_loop
jmp end
// return
end:
stw rg1, current
mov bpr, spr
pop bpr
return
// resets the cursor position on the screen
reset:
push bpr
mov spr, bpr
ldw display, rg1
stw rg1, current
mov bpr, spr
pop bpr
return
```
### Example Program (main.dsa)
```asm
include print "./print.dsa"
dw stack: 0x10000
db string: "'To confuse your enemy, you must first confuse yourself' - Probably Sun Tzu."
init:
// set up a stack.
ldw stack, bpr
mov bpr, spr
start:
lwi string, rg1
// push string address argument
push rg1
// call print function
call print::print
// clean up stack
pop rg1
hlt
```