# Lab2: RISC-V Toolchain
###### tags: `Course` `RISC-V` `Computer Architecture 2022`

## Rewrite [Decode XORed Array](https://leetcode.com/problems/decode-xored-array/)
* **Problem :** I chose the **Decode XORed Array** from [黃冠宇](https://hackmd.io/@ZLQisilvQvOh2DclLmk1bg/SyjKI7sZi)
* **Motivation :** Because I think this problem is tricky."

#include<stdio.h>
int* decode(int* encoded, int encodedSize, int first, int* returnSize){
    int* result = (int*)malloc(sizeof(int)*(encodedSize+1));
    result[0]=first;
    for(int i=0;i<encodedSize;i++){
        result[i+1]=result[i] ^ encoded[i];
    }
    *returnSize = encodedSize+1;
    return result;
}

* **Modefied :**
Because his C code doesn't include tha data for testing. so I modify his C code as below

#include <stdlib.h>
#include <stdio.h>
int* decode(int* encoded, int encodedSize, int first){
    int* result = (int*)malloc(sizeof(int)*(encodedSize+1));
    result[0]=first;
    for(int i=0;i<encodedSize;i++){
        result[i+1]=result[i] ^ encoded[i];
    }
    return result;
}
int main(){
    int nums1[4] = {6,2,7,3};
    int* result1 = decode(nums1, 4, 4);
    printf("THe result is : ");
    for(int j=0; j<5; j++){
        printf("%d ", result1[j]);
    }
}


## Using RISC-V gcc
* 環境變數
> cd $HOME
> source riscv-none-elf-gcc/setenv
* 編譯
> riscv-none-elf-gcc -march=rv32i -mabi=ilp32 -O3 -o HW2 HW2.c
* 反組譯並存成txt
> riscv-none-elf-objdump -d ./HW2 > asb.txt
* 看elf標頭
> riscv-none-elf-readelf -h ./HW2
* 看size
> riscv-none-elf-size ./HW2
* 執行code
> build/rv32emu HW2

## Compare Assembly Code
### Original Code (From [黃冠宇](https://hackmd.io/@ZLQisilvQvOh2DclLmk1bg/SyjKI7sZi))
### -O1 Optimized Assembly Code
* Assembly code

00010208 <main>:
   10208:	fe010113          	addi	sp,sp,-32
   1020c:	00112e23          	sw	ra,28(sp)
   10210:	00812c23          	sw	s0,24(sp)
   10214:	00912a23          	sw	s1,20(sp)
   10218:	01212823          	sw	s2,16(sp)
   1021c:	000217b7          	lui	a5,0x21
   10220:	73878793          	addi	a5,a5,1848 # 21738 <__clzsi2+0xa4>
   10224:	0007a603          	lw	a2,0(a5)
   10228:	0047a683          	lw	a3,4(a5)
   1022c:	0087a703          	lw	a4,8(a5)
   10230:	00c7a783          	lw	a5,12(a5)
   10234:	00c12023          	sw	a2,0(sp)
   10238:	00d12223          	sw	a3,4(sp)
   1023c:	00e12423          	sw	a4,8(sp)
   10240:	00f12623          	sw	a5,12(sp)
   10244:	00400613          	li	a2,4
   10248:	00400593          	li	a1,4
   1024c:	00010513          	mv	a0,sp
   10250:	f35ff0ef          	jal	ra,10184 <decode>
   10254:	00050493          	mv	s1,a0
   10258:	00021537          	lui	a0,0x21
   1025c:	72050513          	addi	a0,a0,1824 # 21720 <__clzsi2+0x8c>
   10260:	209000ef          	jal	ra,10c68 <printf>
   10264:	00048413          	mv	s0,s1
   10268:	01448493          	addi	s1,s1,20
   1026c:	00021937          	lui	s2,0x21
   10270:	00042583          	lw	a1,0(s0)
   10274:	73490513          	addi	a0,s2,1844 # 21734 <__clzsi2+0xa0>
   10278:	1f1000ef          	jal	ra,10c68 <printf>
   1027c:	00440413          	addi	s0,s0,4
   10280:	fe9418e3          	bne	s0,s1,10270 <main+0x68>
   10284:	00000513          	li	a0,0
   10288:	01c12083          	lw	ra,28(sp)
   1028c:	01812403          	lw	s0,24(sp)
   10290:	01412483          	lw	s1,20(sp)
   10294:	01012903          	lw	s2,16(sp)
   10298:	02010113          	addi	sp,sp,32
   1029c:	00008067          	ret
00010184 <decode>:
   10184:	fe010113          	addi	sp,sp,-32
   10188:	00112e23          	sw	ra,28(sp)
   1018c:	00812c23          	sw	s0,24(sp)
   10190:	00912a23          	sw	s1,20(sp)
   10194:	01212823          	sw	s2,16(sp)
   10198:	01312623          	sw	s3,12(sp)
   1019c:	00050413          	mv	s0,a0
   101a0:	00058913          	mv	s2,a1
   101a4:	00060993          	mv	s3,a2
   101a8:	00158493          	addi	s1,a1,1
   101ac:	00249493          	slli	s1,s1,0x2
   101b0:	00048513          	mv	a0,s1
   101b4:	1f0000ef          	jal	ra,103a4 <malloc>
   101b8:	01352023          	sw	s3,0(a0)
   101bc:	03205863          	blez	s2,101ec <decode+0x68>
   101c0:	00050793          	mv	a5,a0
   101c4:	00040693          	mv	a3,s0
   101c8:	ffc48593          	addi	a1,s1,-4
   101cc:	00a585b3          	add	a1,a1,a0
   101d0:	0007a703          	lw	a4,0(a5)
   101d4:	0006a603          	lw	a2,0(a3)
   101d8:	00c74733          	xor	a4,a4,a2
   101dc:	00e7a223          	sw	a4,4(a5)
   101e0:	00478793          	addi	a5,a5,4
   101e4:	00468693          	addi	a3,a3,4
   101e8:	feb794e3          	bne	a5,a1,101d0 <decode+0x4c>
   101ec:	01c12083          	lw	ra,28(sp)
   101f0:	01812403          	lw	s0,24(sp)
   101f4:	01412483          	lw	s1,20(sp)
   101f8:	01012903          	lw	s2,16(sp)
   101fc:	00c12983          	lw	s3,12(sp)
   10200:	02010113          	addi	sp,sp,32
   10204:	00008067          	ret

* Observation
* LOC(line of code) : `73`
* Allocate `32` bytes on stack
* Number of registers used : `$ra`, `$s0~$s3`, `$a0~$a5`
* Number of `lw` and `sw` used : `16` and `15`

* Execution & CSR count

  yuchengwang@yuchengwang-virtual-machine:~/Desktop/rv32emu$ build/rv32emu --stats HW2.1
  The result is : 4 2 0 7 4 inferior exit code 0
  CSR cycle count: 4532

### -O2 Optimized Assembly Code
* Assembly code

000100c4 <main>:
   100c4:	000217b7          	lui	a5,0x21
   100c8:	73078793          	addi	a5,a5,1840 # 21730 <__clzsi2+0xa4>
   100cc:	0007a803          	lw	a6,0(a5)
   100d0:	0047a683          	lw	a3,4(a5)
   100d4:	0087a703          	lw	a4,8(a5)
   100d8:	00c7a783          	lw	a5,12(a5)
   100dc:	fe010113          	addi	sp,sp,-32
   100e0:	00400613          	li	a2,4
   100e4:	00400593          	li	a1,4
   100e8:	00010513          	mv	a0,sp
   100ec:	00112e23          	sw	ra,28(sp)
   100f0:	00812c23          	sw	s0,24(sp)
   100f4:	00912a23          	sw	s1,20(sp)
   100f8:	01212823          	sw	s2,16(sp)
   100fc:	01012023          	sw	a6,0(sp)
   10100:	00d12223          	sw	a3,4(sp)
   10104:	00e12423          	sw	a4,8(sp)
   10108:	00f12623          	sw	a5,12(sp)
   1010c:	10c000ef          	jal	ra,10218 <decode>
   10110:	00050413          	mv	s0,a0
   10114:	00021537          	lui	a0,0x21
   10118:	71850513          	addi	a0,a0,1816 # 21718 <__clzsi2+0x8c>
   1011c:	345000ef          	jal	ra,10c60 <printf>
   10120:	01440913          	addi	s2,s0,20
   10124:	000214b7          	lui	s1,0x21
   10128:	00042583          	lw	a1,0(s0)
   1012c:	72c48513          	addi	a0,s1,1836 # 2172c <__clzsi2+0xa0>
   10130:	00440413          	addi	s0,s0,4
   10134:	32d000ef          	jal	ra,10c60 <printf>
   10138:	ff2418e3          	bne	s0,s2,10128 <main+0x64>
   1013c:	01c12083          	lw	ra,28(sp)
   10140:	01812403          	lw	s0,24(sp)
   10144:	01412483          	lw	s1,20(sp)
   10148:	01012903          	lw	s2,16(sp)
   1014c:	00000513          	li	a0,0
   10150:	02010113          	addi	sp,sp,32
   10154:	00008067          	ret
00010218 <decode>:
   10218:	fe010113          	addi	sp,sp,-32
   1021c:	01212823          	sw	s2,16(sp)
   10220:	00158913          	addi	s2,a1,1
   10224:	00291913          	slli	s2,s2,0x2
   10228:	00812c23          	sw	s0,24(sp)
   1022c:	00050413          	mv	s0,a0
   10230:	00090513          	mv	a0,s2
   10234:	00912a23          	sw	s1,20(sp)
   10238:	01312623          	sw	s3,12(sp)
   1023c:	00060493          	mv	s1,a2
   10240:	00112e23          	sw	ra,28(sp)
   10244:	00058993          	mv	s3,a1
   10248:	154000ef          	jal	ra,1039c <malloc>
   1024c:	00952023          	sw	s1,0(a0)
   10250:	03305663          	blez	s3,1027c <decode+0x64>
   10254:	ffc90613          	addi	a2,s2,-4
   10258:	00040793          	mv	a5,s0
   1025c:	00450713          	addi	a4,a0,4
   10260:	00c40633          	add	a2,s0,a2
   10264:	0007a683          	lw	a3,0(a5)
   10268:	00470713          	addi	a4,a4,4
   1026c:	00478793          	addi	a5,a5,4
   10270:	00d4c4b3          	xor	s1,s1,a3
   10274:	fe972e23          	sw	s1,-4(a4)
   10278:	fec796e3          	bne	a5,a2,10264 <decode+0x4c>
   1027c:	01c12083          	lw	ra,28(sp)
   10280:	01812403          	lw	s0,24(sp)
   10284:	01412483          	lw	s1,20(sp)
   10288:	01012903          	lw	s2,16(sp)
   1028c:	00c12983          	lw	s3,12(sp)
   10290:	02010113          	addi	sp,sp,32
   10294:	00008067          	ret

* Observation
* LOC(line of code) : `71`
* Allocate `32` bytes on stack
* Number of registers used : `$ra`, `$s0~$s3`, `$a0~$a6`
* Number of `lw` and `sw` used : `15` and `15`

* Execution & CSR count

  yuchengwang@yuchengwang-virtual-machine:~/Desktop/rv32emu$ build/rv32emu --stats HW2.2
  The result is : 4 2 0 7 4 inferior exit code 0
  CSR cycle count: 4527

### -O3 Optimized Assembly Code
* Assembly code

000100c4 <main>:
   100c4:	000217b7          	lui	a5,0x21
   100c8:	73078793          	addi	a5,a5,1840 # 21730 <__clzsi2+0xa4>
   100cc:	0007a803          	lw	a6,0(a5)
   100d0:	0047a683          	lw	a3,4(a5)
   100d4:	0087a703          	lw	a4,8(a5)
   100d8:	00c7a783          	lw	a5,12(a5)
   100dc:	fe010113          	addi	sp,sp,-32
   100e0:	00400613          	li	a2,4
   100e4:	00400593          	li	a1,4
   100e8:	00010513          	mv	a0,sp
   100ec:	00112e23          	sw	ra,28(sp)
   100f0:	00812c23          	sw	s0,24(sp)
   100f4:	00912a23          	sw	s1,20(sp)
   100f8:	01212823          	sw	s2,16(sp)
   100fc:	01012023          	sw	a6,0(sp)
   10100:	00d12223          	sw	a3,4(sp)
   10104:	00e12423          	sw	a4,8(sp)
   10108:	00f12623          	sw	a5,12(sp)
   1010c:	10c000ef          	jal	ra,10218 <decode>
   10110:	00050413          	mv	s0,a0
   10114:	00021537          	lui	a0,0x21
   10118:	71850513          	addi	a0,a0,1816 # 21718 <__clzsi2+0x8c>
   1011c:	345000ef          	jal	ra,10c60 <printf>
   10120:	01440913          	addi	s2,s0,20
   10124:	000214b7          	lui	s1,0x21
   10128:	00042583          	lw	a1,0(s0)
   1012c:	72c48513          	addi	a0,s1,1836 # 2172c <__clzsi2+0xa0>
   10130:	00440413          	addi	s0,s0,4
   10134:	32d000ef          	jal	ra,10c60 <printf>
   10138:	ff2418e3          	bne	s0,s2,10128 <main+0x64>
   1013c:	01c12083          	lw	ra,28(sp)
   10140:	01812403          	lw	s0,24(sp)
   10144:	01412483          	lw	s1,20(sp)
   10148:	01012903          	lw	s2,16(sp)
   1014c:	00000513          	li	a0,0
   10150:	02010113          	addi	sp,sp,32
   10154:	00008067          	ret
00010218 <decode>:
   10218:	fe010113          	addi	sp,sp,-32
   1021c:	01212823          	sw	s2,16(sp)
   10220:	00158913          	addi	s2,a1,1
   10224:	00291913          	slli	s2,s2,0x2
   10228:	00812c23          	sw	s0,24(sp)
   1022c:	00050413          	mv	s0,a0
   10230:	00090513          	mv	a0,s2
   10234:	00912a23          	sw	s1,20(sp)
   10238:	01312623          	sw	s3,12(sp)
   1023c:	00060493          	mv	s1,a2
   10240:	00112e23          	sw	ra,28(sp)
   10244:	00058993          	mv	s3,a1
   10248:	154000ef          	jal	ra,1039c <malloc>
   1024c:	00952023          	sw	s1,0(a0)
   10250:	03305663          	blez	s3,1027c <decode+0x64>
   10254:	ffc90613          	addi	a2,s2,-4
   10258:	00040793          	mv	a5,s0
   1025c:	00450713          	addi	a4,a0,4
   10260:	00c40633          	add	a2,s0,a2
   10264:	0007a683          	lw	a3,0(a5)
   10268:	00470713          	addi	a4,a4,4
   1026c:	00478793          	addi	a5,a5,4
   10270:	00d4c4b3          	xor	s1,s1,a3
   10274:	fe972e23          	sw	s1,-4(a4)
   10278:	fef616e3          	bne	a2,a5,10264 <decode+0x4c>
   1027c:	01c12083          	lw	ra,28(sp)
   10280:	01812403          	lw	s0,24(sp)
   10284:	01412483          	lw	s1,20(sp)
   10288:	01012903          	lw	s2,16(sp)
   1028c:	00c12983          	lw	s3,12(sp)
   10290:	02010113          	addi	sp,sp,32
   10294:	00008067          	ret

* Observation
* LOC(line of code) : `71`
* Allocate `32` bytes on stack
* Number of registers used : `$ra`, `$s0~$s3`, `$a0~$a6`
* Number of `lw` and `sw` used : `15` and `15`

* Execution & CSR count

  yuchengwang@yuchengwang-virtual-machine:~/Desktop/rv32emu$ build/rv32emu --stats HW2.3
  THe result is : 4 2 0 7 4 inferior exit code 0
  CSR cycle count: 4527

### -Os Optimized Assembly Code

000100c4 <main>:
   100c4:	fe010113          	addi	sp,sp,-32
   100c8:	000215b7          	lui	a1,0x21
   100cc:	01000613          	li	a2,16
   100d0:	71058593          	addi	a1,a1,1808 # 21710 <__clzsi2+0xa0>
   100d4:	00010513          	mv	a0,sp
   100d8:	00112e23          	sw	ra,28(sp)
   100dc:	00812c23          	sw	s0,24(sp)
   100e0:	00912a23          	sw	s1,20(sp)
   100e4:	01212823          	sw	s2,16(sp)
   100e8:	231000ef          	jal	ra,10b18 <memcpy>
   100ec:	00400613          	li	a2,4
   100f0:	00400593          	li	a1,4
   100f4:	00010513          	mv	a0,sp
   100f8:	10c000ef          	jal	ra,10204 <decode>
   100fc:	00050413          	mv	s0,a0
   10100:	00021537          	lui	a0,0x21
   10104:	6f850513          	addi	a0,a0,1784 # 216f8 <__clzsi2+0x88>
   10108:	4e1000ef          	jal	ra,10de8 <printf>
   1010c:	01440493          	addi	s1,s0,20
   10110:	00021937          	lui	s2,0x21
   10114:	00042583          	lw	a1,0(s0)
   10118:	70c90513          	addi	a0,s2,1804 # 2170c <__clzsi2+0x9c>
   1011c:	00440413          	addi	s0,s0,4
   10120:	4c9000ef          	jal	ra,10de8 <printf>
   10124:	fe9418e3          	bne	s0,s1,10114 <main+0x50>
   10128:	01c12083          	lw	ra,28(sp)
   1012c:	01812403          	lw	s0,24(sp)
   10130:	01412483          	lw	s1,20(sp)
   10134:	01012903          	lw	s2,16(sp)
   10138:	00000513          	li	a0,0
   1013c:	02010113          	addi	sp,sp,32
   10140:	00008067          	ret
00010204 <decode>:
   10204:	ff010113          	addi	sp,sp,-16
   10208:	00912223          	sw	s1,4(sp)
   1020c:	00050493          	mv	s1,a0
   10210:	00158513          	addi	a0,a1,1
   10214:	00251513          	slli	a0,a0,0x2
   10218:	00812423          	sw	s0,8(sp)
   1021c:	01212023          	sw	s2,0(sp)
   10220:	00112623          	sw	ra,12(sp)
   10224:	00060913          	mv	s2,a2
   10228:	00058413          	mv	s0,a1
   1022c:	154000ef          	jal	ra,10380 <malloc>
   10230:	01252023          	sw	s2,0(a0)
   10234:	00050713          	mv	a4,a0
   10238:	00000793          	li	a5,0
   1023c:	00470713          	addi	a4,a4,4
   10240:	0087ce63          	blt	a5,s0,1025c <decode+0x58>
   10244:	00c12083          	lw	ra,12(sp)
   10248:	00812403          	lw	s0,8(sp)
   1024c:	00412483          	lw	s1,4(sp)
   10250:	00012903          	lw	s2,0(sp)
   10254:	01010113          	addi	sp,sp,16
   10258:	00008067          	ret
   1025c:	00279693          	slli	a3,a5,0x2
   10260:	00d486b3          	add	a3,s1,a3
   10264:	0006a683          	lw	a3,0(a3)
   10268:	ffc72603          	lw	a2,-4(a4)
   1026c:	00178793          	addi	a5,a5,1
   10270:	00c6c6b3          	xor	a3,a3,a2
   10274:	00d72023          	sw	a3,0(a4)
   10278:	fc5ff06f          	j	1023c <decode+0x38>

* Observation
* LOC(line of code) : `64`
* Allocate `32` bytes on stack :
* Number of registers used : `$ra`, `$s0~$s2`, `$a0~$a5`
* Number of `lw` and `sw` used : `11` and `10`

* Execution & CSR count

  yuchengwang@yuchengwang-virtual-machine:~/Desktop/rv32emu$ build/rv32emu --stats HW2
  The result is : 4 2 0 7 4 inferior exit code 0
  CSR cycle count: 4562