Merge pull request 'Changed mul_low algorithm to radix-4 multiplication' (#16) from Micha_i/symphony_stdlib:fast-math into main

Reviewed-on: #16

MEMORY.md

@@ -1,21 +0,0 @@
-# Memory Map
-
-To not have to allocate a ton of things at run time the Standard Library uses a static memory map for some purposes
-
-## Overview
-
-| Start | Use |
-| ---- | ---- |
-| `0x0` | Reset Vector |
-| `0x16` | Zero Page |
-| `0x100` | User Code |
-| `?` | Library Code |
-| `0x1_0000` | LUTs |
-| `?` | heap |
-| `0xXXF0_0000` | Stack |
-| `0xXXFF_0000` | quick access |
-
-## Zero Page
-Some values are needed not often enough to get their own special register, but often enough that it makes sense to keep them at a quickly accessible location.
-This is what the zero page is for. its position in memory allows us to load them into a register with a single instruction.
-

README.md

@@ -3,8 +3,7 @@
 This is a standard library for symphony.
 It is both intended as a practical toolkit to develop more complex software as well as a teaching resource.
 
-If you just want to use the standard library [[stdlib.asm]] is your main header, include it after your code.
-You also need to include [[globals.asm]] as the first line in your assembly file.
+If you just want to use the standard library [[src/stdlib.asm]] is your main header, include it after your code.
 
 If you are using it as a learning resource have a look at the [teaching folder](teaching).
 

globals.asm

@@ -1,10 +0,0 @@
-jmp 0x100
-
-@0x10
-screen:
-    frambuffer_ptr: U32 0x0
-    size: U32 0x0
-    position_xy: U32 0x0
-    mode: U32 0x0
-
-@0x100

src/imath.asm

@@ -6,20 +6,29 @@
 ; r1 - The lower 32 bits of the result
 ; Clobbers: r2, r3, r4, r5
 pub mul_low:
-	mov r3, 0 ; result
-	mov r4, 31 ; loop counter
-	
+	add r3, r2, r2 ; r3 = r2 * 2
+	mov r4, 0 ; r4 has the result
+
 	mul_low_loop:
-		asr r5, r2, 31
-		and r5, r5, r1
-		lsl r5, r5, r4
-		add r3, r3, r5
-		lsl r2, r2, 1
-		sub r4, r4, 1
-		cmp r4, 0
-		jge mul_low_loop
-	mov r1, r3
-	
+
+		and r5, r1, 1 ; a0
+		neg r5, r5 ; mask
+		and r5, r2, r5 ; a0 ? r2 : 0
+		add r4, r4, r5
+
+		and r5, r1, 2 ; a1 is now 0 or 2
+		lsr r5, r5, 1 ; normalize to 0/1
+		neg r5, r5 ; mask
+		and r5, r3, r5 ; a1 ? r2 * 2 : 0
+		add r4, r4, r5
+
+		lsl r2, r2, 2
+		lsl r3, r3, 2
+		lsr r1, r1, 2
+		cmp r1, zr
+		jne mul_low_loop
+
+	mov r1, r4
 	jmp r13
 
 ; Calculates the absolute value of the value provided in the r1 register

src/stdlib.asm

@@ -1,5 +1,6 @@
 pub include bit
 pub include imath
+pub include array
 pub include console
 
 ; Needs to be last!