# Assignment2: RISC-V Toolchain
### Contributed by<Rei-Fu-Zhang>

## install VM with Oracle VM VirtualBox
first [click here](https://www.virtualbox.org/)
because my cpu is AMD R7 5800X3D
so we need to do a prework
go to BIOS and open the CPU's VM Function
then slect ypur VM like the picture below

## Problem description:
### The problem I selected:122. Best Time to Buy and Sell Stock II from [陳邦尉](https://github.com/ram-a11y/Computer-Architecture)
### motivation:I'm a hopeless stock maniac
### the code from him

#include<stdio.h>

int maxProfit(const int *, int);

int main(){
    const int prices[] = {7,1,5,3,6,4};
    const int pricesSize = 6;
    printf("%d\n", maxProfit(prices, pricesSize));
    return 0;
}

int maxProfit(int* prices, int pricesSize) {
  int sum = 0;
  for (int i = 1; i < pricesSize; i++) {
    if (prices[i - 1] < prices[i]) {
      // check if growing then add it
      sum = sum + (prices[i] - prices[i - 1]);
    }
  }
  return sum;
}

### My version

#include<stdio.h>
#include<stdlib.h>
int main(){
int arr[]={99,32,3,56,0,2,56,99};
int size=8;
int a= maxProfit(arr,size);
printf("%d\n",a);
}
int maxProfit(int* prices, int pricesSize){
    int totalProfit = 0;
    int i=0;
    int increases = 0;
    for (i = 1; i < pricesSize; i++) {
        if (prices[i] <= prices[i - 1]) {
            totalProfit += increases;
            increases = 0;
        }
        else
            increases += prices[i] - prices[i - 1];
    }
    totalProfit += increases;
    return totalProfit;
}

## rewrite the RV32I code

.data
arr: .word 9,2,3,6,0,2,6,9
size: .word 8
.text
main:
    la s0 arr
    lw s1 size
    jal ra profit
    add s10 s10 s3
    j print
profit:
    addi s2 s2 1 #s2=i=1 i++
    add t1 s2 zero #t1=s2=i
    slli t1 t1 2 #t1*4
    add t1 t1 s0 #address arr[i]
    lw s4 0[t1]
    lw s5 -4[t1]
    bge s5 s4 process
    sub s8 s4 s5
    add s3 s3 s8
    blt s2 s1 profit
    jr ra
process:
    add s10 s10 s3
    add s3 zero zero
    blt s2 s1 profit
    jr ra
print:
    addi a0 s10 0
    li a7 1
    ecall
    li a7 10
    ecall

trying to modify my code for fit in RV32EMU

# RISC-V assembly program to print "Hello World!" to stdout.

.org 0
# Provide program starting address to linker
.global _start
/* newlib system calls */
.set SYSEXIT,  93
.set SYSWRITE, 64


.data 
arr: .word 9,2,3,6,0,2,6,9
size: .word 8
start_input_line:.string "Input:["
start_output_line:.string "Output:["
endline:.string "]\n"

.text 

main:
    la s0 arr
    lw s1 size
    jal ra profit
    add s10 s10 s3
    j print
profit:
    addi s2 s2 1 #s2=i=1 i++
    add t1 s2 zero #t1=s2=i
    slli t1 t1 2 #t1*4
    add t1 t1 s0 #address arr[i]
    lw s4 0[t1]
    lw s5 -4[t1]
    bge s5 s4 process
    sub s8 s4 s5
    add s3 s3 s8
    blt s2 s1 profit
    jr ra
process:
    add s10 s10 s3
    add s3 zero zero
    blt s2 s1 profit
    jr ra
print:
    addi a0 s10 0
    li a7 1
    ecall
    li a7 10
    ecall

### CSR cycle count:2781
## abstract about how to use a GCC toolchain
### 1.compile your c code

riscv-none-elf-gcc -march=rv32i -mabi=ilp32 -O(3~1) -o (filename you want) (your C code filename)

### look at the elf header
riscv-none-elf-readelf -h (your filename)

### check size
riscv-none-elf-size (your filename)

## -Os
### read elf
### check size
### exe

### Disassembly code

000101cc <maxProfit>:
   101cc:	00000793          	li	a5,0
   101d0:	00100613          	li	a2,1
   101d4:	00000693          	li	a3,0
   101d8:	00b64663          	blt	a2,a1,101e4 <maxProfit+0x18>
   101dc:	00f68533          	add	a0,a3,a5
   101e0:	00008067          	ret
   101e4:	00452703          	lw	a4,4(a0)
   101e8:	00052803          	lw	a6,0(a0)
   101ec:	00e84c63          	blt	a6,a4,10204 <maxProfit+0x38>
   101f0:	00f686b3          	add	a3,a3,a5
   101f4:	00000793          	li	a5,0
   101f8:	00160613          	addi	a2,a2,1
   101fc:	00450513          	addi	a0,a0,4
   10200:	fd9ff06f          	j	101d8 <maxProfit+0xc>
   10204:	41070733          	sub	a4,a4,a6
   10208:	00e787b3          	add	a5,a5,a4
   1020c:	fedff06f          	j	101f8 <maxProfit+0x2c>

## -Ofast
### code
### exe and check size
### check elf
### exe

### Disassembly code

000101ac <maxProfit>:
   101ac:	00100793          	li	a5,1
   101b0:	0cb7d263          	bge	a5,a1,10274 <maxProfit+0xc8>
   101b4:	00300793          	li	a5,3
   101b8:	0cb7d263          	bge	a5,a1,1027c <maxProfit+0xd0>
   101bc:	ffc58713          	addi	a4,a1,-4
   101c0:	00052783          	lw	a5,0(a0)
   101c4:	ffe77713          	andi	a4,a4,-2
   101c8:	00450693          	addi	a3,a0,4
   101cc:	00370713          	addi	a4,a4,3
   101d0:	00000813          	li	a6,0
   101d4:	00100313          	li	t1,1
   101d8:	00000893          	li	a7,0
   101dc:	0006a603          	lw	a2,0(a3)
   101e0:	00000e13          	li	t3,0
   101e4:	40f60eb3          	sub	t4,a2,a5
   101e8:	06c7d863          	bge	a5,a2,10258 <maxProfit+0xac>
   101ec:	0046a783          	lw	a5,4(a3)
   101f0:	010e8e33          	add	t3,t4,a6
   101f4:	00000813          	li	a6,0
   101f8:	40c78eb3          	sub	t4,a5,a2
   101fc:	06f65863          	bge	a2,a5,1026c <maxProfit+0xc0>
   10200:	01ce8833          	add	a6,t4,t3
   10204:	00230313          	addi	t1,t1,2 # 101a2 <frame_dummy+0x16>
   10208:	00868693          	addi	a3,a3,8
   1020c:	fce318e3          	bne	t1,a4,101dc <maxProfit+0x30>
   10210:	00271793          	slli	a5,a4,0x2
   10214:	00f507b3          	add	a5,a0,a5
   10218:	0180006f          	j	10230 <maxProfit+0x84>
   1021c:	00170713          	addi	a4,a4,1
   10220:	010888b3          	add	a7,a7,a6
   10224:	00478793          	addi	a5,a5,4
   10228:	00000813          	li	a6,0
   1022c:	02b75263          	bge	a4,a1,10250 <maxProfit+0xa4>
   10230:	0007a603          	lw	a2,0(a5)
   10234:	ffc7a683          	lw	a3,-4(a5)
   10238:	40d60533          	sub	a0,a2,a3
   1023c:	fec6d0e3          	bge	a3,a2,1021c <maxProfit+0x70>
   10240:	00170713          	addi	a4,a4,1
   10244:	00a80833          	add	a6,a6,a0
   10248:	00478793          	addi	a5,a5,4
   1024c:	feb742e3          	blt	a4,a1,10230 <maxProfit+0x84>
   10250:	01088533          	add	a0,a7,a6
   10254:	00008067          	ret
   10258:	0046a783          	lw	a5,4(a3)
   1025c:	010888b3          	add	a7,a7,a6
   10260:	00000813          	li	a6,0
   10264:	40c78eb3          	sub	t4,a5,a2
   10268:	f8f64ce3          	blt	a2,a5,10200 <maxProfit+0x54>
   1026c:	01c888b3          	add	a7,a7,t3
   10270:	f95ff06f          	j	10204 <maxProfit+0x58>
   10274:	00000513          	li	a0,0
   10278:	00008067          	ret
   1027c:	00000813          	li	a6,0
   10280:	00100713          	li	a4,1
   10284:	00000893          	li	a7,0
   10288:	f89ff06f          	j	10210 <maxProfit+0x64>

## -O1
### compile your c code -O1
### watch elf head
### check size
### executing

### Disassembly code

00010184 <maxProfit>:
   10184:	00100793          	li	a5,1
   10188:	04b7d263          	bge	a5,a1,101cc <maxProfit+0x48>
   1018c:	00450793          	addi	a5,a0,4
   10190:	00259593          	slli	a1,a1,0x2
   10194:	00b505b3          	add	a1,a0,a1
   10198:	00000613          	li	a2,0
   1019c:	00000513          	li	a0,0
   101a0:	0140006f          	j	101b4 <maxProfit+0x30>
   101a4:	40d70733          	sub	a4,a4,a3
   101a8:	00e60633          	add	a2,a2,a4
   101ac:	00478793          	addi	a5,a5,4
   101b0:	02b78263          	beq	a5,a1,101d4 <maxProfit+0x50>
   101b4:	0007a703          	lw	a4,0(a5)
   101b8:	ffc7a683          	lw	a3,-4(a5)
   101bc:	fee6c4e3          	blt	a3,a4,101a4 <maxProfit+0x20>
   101c0:	00c50533          	add	a0,a0,a2
   101c4:	00000613          	li	a2,0
   101c8:	fe5ff06f          	j	101ac <maxProfit+0x28>
   101cc:	00000613          	li	a2,0
   101d0:	00000513          	li	a0,0
   101d4:	00c50533          	add	a0,a0,a2
   101d8:	00008067          	ret

## -O2
### compile your c code -O2

### watch elf

### check size
### exe

### Disassembly code

00010200 <maxProfit>:
   10200:	00100793          	li	a5,1
   10204:	04b7da63          	bge	a5,a1,10258 <maxProfit+0x58>
   10208:	00259593          	slli	a1,a1,0x2
   1020c:	00052703          	lw	a4,0(a0)
   10210:	00450793          	addi	a5,a0,4
   10214:	00b505b3          	add	a1,a0,a1
   10218:	00000613          	li	a2,0
   1021c:	00000513          	li	a0,0
   10220:	0140006f          	j	10234 <maxProfit+0x34>
   10224:	00478793          	addi	a5,a5,4
   10228:	00c50533          	add	a0,a0,a2
   1022c:	00000613          	li	a2,0
   10230:	02b78063          	beq	a5,a1,10250 <maxProfit+0x50>
   10234:	00070693          	mv	a3,a4
   10238:	0007a703          	lw	a4,0(a5)
   1023c:	40d70833          	sub	a6,a4,a3
   10240:	fee6d2e3          	bge	a3,a4,10224 <maxProfit+0x24>
   10244:	00478793          	addi	a5,a5,4
   10248:	01060633          	add	a2,a2,a6
   1024c:	feb794e3          	bne	a5,a1,10234 <maxProfit+0x34>
   10250:	00c50533          	add	a0,a0,a2
   10254:	00008067          	ret
   10258:	00000513          	li	a0,0
   1025c:	00008067          	ret

## -O3
### compile your c code -O3
### watch elf

### check size
### exe

### Disassembly code

000101ac <maxProfit>:
   101ac:	00100793          	li	a5,1
   101b0:	0cb7d263          	bge	a5,a1,10274 <maxProfit+0xc8>
   101b4:	00300793          	li	a5,3
   101b8:	0cb7d263          	bge	a5,a1,1027c <maxProfit+0xd0>
   101bc:	ffc58713          	addi	a4,a1,-4
   101c0:	00052783          	lw	a5,0(a0)
   101c4:	ffe77713          	andi	a4,a4,-2
   101c8:	00450693          	addi	a3,a0,4
   101cc:	00370713          	addi	a4,a4,3
   101d0:	00000813          	li	a6,0
   101d4:	00100313          	li	t1,1
   101d8:	00000893          	li	a7,0
   101dc:	0006a603          	lw	a2,0(a3)
   101e0:	00000e13          	li	t3,0
   101e4:	40f60eb3          	sub	t4,a2,a5
   101e8:	06c7d863          	bge	a5,a2,10258 <maxProfit+0xac>
   101ec:	0046a783          	lw	a5,4(a3)
   101f0:	010e8e33          	add	t3,t4,a6
   101f4:	00000813          	li	a6,0
   101f8:	40c78eb3          	sub	t4,a5,a2
   101fc:	06f65863          	bge	a2,a5,1026c <maxProfit+0xc0>
   10200:	01ce8833          	add	a6,t4,t3
   10204:	00230313          	addi	t1,t1,2 # 101a2 <frame_dummy+0x16>
   10208:	00868693          	addi	a3,a3,8
   1020c:	fce318e3          	bne	t1,a4,101dc <maxProfit+0x30>
   10210:	00271793          	slli	a5,a4,0x2
   10214:	00f507b3          	add	a5,a0,a5
   10218:	0180006f          	j	10230 <maxProfit+0x84>
   1021c:	00170713          	addi	a4,a4,1
   10220:	010888b3          	add	a7,a7,a6
   10224:	00478793          	addi	a5,a5,4
   10228:	00000813          	li	a6,0
   1022c:	02b75263          	bge	a4,a1,10250 <maxProfit+0xa4>
   10230:	0007a603          	lw	a2,0(a5)
   10234:	ffc7a683          	lw	a3,-4(a5)
   10238:	40d60533          	sub	a0,a2,a3
   1023c:	fec6d0e3          	bge	a3,a2,1021c <maxProfit+0x70>
   10240:	00170713          	addi	a4,a4,1
   10244:	00a80833          	add	a6,a6,a0
   10248:	00478793          	addi	a5,a5,4
   1024c:	feb742e3          	blt	a4,a1,10230 <maxProfit+0x84>
   10250:	01088533          	add	a0,a7,a6
   10254:	00008067          	ret
   10258:	0046a783          	lw	a5,4(a3)
   1025c:	010888b3          	add	a7,a7,a6
   10260:	00000813          	li	a6,0
   10264:	40c78eb3          	sub	t4,a5,a2
   10268:	f8f64ce3          	blt	a2,a5,10200 <maxProfit+0x54>
   1026c:	01c888b3          	add	a7,a7,t3
   10270:	f95ff06f          	j	10204 <maxProfit+0x58>
   10274:	00000513          	li	a0,0
   10278:	00008067          	ret
   1027c:	00000813          	li	a6,0
   10280:	00100713          	li	a4,1
   10284:	00000893          	li	a7,0
   10288:	f89ff06f          	j	10210 <maxProfit+0x64>

## observation
| | line of code | Allocate bytes on stack | Registers used |||CSR|
| -------- | -------- | -------- | -------- | -------- | -------- | -------- |
| O0 |22 | 96 |```ra``` ```sp``` ```a0 ~ a7``` ```s0``` ```t1``` | | |2832|
| O1 | 22 | 96 |```ra``` ```sp``` ```a0 ~ a7``` ```s0``` ```t1``` | | |2822 |
| O2 | 24 | 80 |```ra``` ```sp``` ```a0 ~ a7``` ```s0``` | | |2826 |
| O3 | 96 | 16 |```ra``` ```sp``` ```a0 ~ a7``` | | |2760 |
| Ofast | 96 | 16 |```ra``` ```sp``` ```a0 ~ a7``` | | |2760 |
| Os | 17 | 42 |```ra``` ```sp``` ```a0 ~ a7``` ``s0`` | | |2861 |

### anaylize
* **O1** : O0 and O1 Almost the same.
* **O1** to **O2** : Fewer lines of Code, stack usage amount, lw/sw count, CSR. The register ```t1```not used since O2.
* **O2** to **O3** : More Fewer lines of Code, stack usage amount, lw/sw count, CSR. The register ```s0``` is not used in O3. Futhermore, O3's main funtion address is in front of the singlenumber fuction.
* **Ofast** :As same as O3, not any differance.
* **Os**: Lines of Code, stack usage amount, lw/sw count, register usage amount.
is between O2 and O3, but CSR is between O0 and O1.

* Comparison (">" means better)
* CSR: O3 = Ofast > O2 > O1 = Os
* LOC total: O2 > O1 > Os > O3 > Ofast