深入理解计算机系统 CSAPP 实验lab：Architecture Lab

apple_50569014

742人浏览 · 2024-08-17 10:20:49

apple_50569014 · 2024-08-17 10:20:49 发布

前期准备参考: 深入理解计算机系统 CSAPP 第四章 Y86-64模拟器安装与使用-CSDN博客

writeup上写了要求,这里就不赘述了.

Part A:

sum.ys:

# Execution begins at address 0 
	.pos 0
	irmovq stack, %rsp  	# Set up stack pointer
	call main		# Execute main program
	halt			# Terminate program 

# Sample linked list
	.align 8
ele1:
	.quad 0x00a
	.quad ele2
ele2:
	.quad 0x0b0
	.quad ele3
ele3:
	.quad 0xc00
	.quad 0


main:	irmovq ele1,%rdi
	call sum	     # sum(ele1)
	ret

# long sum(long *start)
# start in %rdi
sum:	xorq %rax,%rax	     # sum = 0
	andq %rdi,%rdi	     # Set CC
	jmp     test         # Goto test
loop:	mrmovq (%rdi),%r10   # Get *start
	irmovq $8,%r8
	addq %r10,%rax       # Add to sum
	addq %r8,%rdi  	     # start++
	mrmovq (%rdi),%rdi   # *start
	andq %rdi,%rdi	     # Set CC
test:	jne    loop          # Stop when 0
	ret                  # Return

# Stack starts here and grows to lower addresses
	.pos 0x200
stack:

addq %r8,%rdi 是下一个元素的地址,不是值.

rsum.ys:

# Execution begins at address 0 
	.pos 0
	irmovq stack, %rsp  	# Set up stack pointer
	call main		# Execute main program
	halt			# Terminate program 

# Sample linked list
	.align 8
ele1:
	.quad 0x00a
	.quad ele2
ele2:
	.quad 0x0b0
	.quad ele3
ele3:
	.quad 0xc00
	.quad 0


main:	irmovq ele1,%rdi
	xorq %rax,%rax	     # sum = 0
	call rsum	     # rsum(rsum)
	ret

# long rsum(long *start)
# start in %rdi
rsum:	andq %rdi,%rdi	     # Set CC
	je return            # Stop when 0
	mrmovq (%rdi),%rbx   # Get *start
	mrmovq 8(%rdi),%rdi   # *start
	pushq %rbx
	call rsum
	popq %rbx
	addq %rbx,%rax       # Add to sum
return:	ret                  # Return

# Stack starts here and grows to lower addresses
	.pos 0x200
stack:

copy.ys:

# Execution begins at address 0 
	.pos 0
	irmovq stack, %rsp  	# Set up stack pointer
	call main		# Execute main program
	halt			# Terminate program 

.align 8
# Source block
src:
.quad 0x00a
.quad 0x0b0
.quad 0xc00
# Destination block
dest:
.quad 0x111
.quad 0x222
.quad 0x333


main:	irmovq src,%rdi
	irmovq dest,%rsi
	irmovq $3,%rdx
	call copy	     # copy(src,dest,0)
	ret

# long copy(long *src,long *dest,long len)
# src in %rdi ,dest in %rsi,len in %rdx
copy:	xorq %rax,%rax	     # result = 0
loop:	andq %rdx,%rdx
	mrmovq (%rdi),%rcx
	rmmovq %rcx,(%rsi)
	irmovq $1,%r10
	irmovq $8,%r8
	xorq %rcx,%rax
	addq %r8,%rdi
	addq %r8,%rsi
	subq %r10,%rdx
	jg loop    # >0
return:	ret                  # Return

# Stack starts here and grows to lower addresses
	.pos 0x200
stack:

Part B:

因为前面的家庭作业和练习题已经做过这个,这里不在赘述了.

参考,图4-18,在不同的阶段需要用哪写寄存器,修改哪些逻辑,添加上 ,IIADDQ 即可.

#/* $begin seq-all-hcl */
####################################################################
#  HCL Description of Control for Single Cycle Y86-64 Processor SEQ   #
#  Copyright (C) Randal E. Bryant, David R. O'Hallaron, 2010       #
####################################################################

## Your task is to implement the iaddq instruction
## The file contains a declaration of the icodes
## for iaddq (IIADDQ)
## Your job is to add the rest of the logic to make it work

####################################################################
#    C Include's.  Don't alter these                               #
####################################################################

quote '#include <stdio.h>'
quote '#include "isa.h"'
quote '#include "sim.h"'
quote 'int sim_main(int argc, char *argv[]);'
quote 'word_t gen_pc(){return 0;}'
quote 'int main(int argc, char *argv[])'
quote '  {plusmode=0;return sim_main(argc,argv);}'

####################################################################
#    Declarations.  Do not change/remove/delete any of these       #
####################################################################

##### Symbolic representation of Y86-64 Instruction Codes #############
wordsig INOP 	'I_NOP'
wordsig IHALT	'I_HALT'
wordsig IRRMOVQ	'I_RRMOVQ'
wordsig IIRMOVQ	'I_IRMOVQ'
wordsig IRMMOVQ	'I_RMMOVQ'
wordsig IMRMOVQ	'I_MRMOVQ'
wordsig IOPQ	'I_ALU'
wordsig IJXX	'I_JMP'
wordsig ICALL	'I_CALL'
wordsig IRET	'I_RET'
wordsig IPUSHQ	'I_PUSHQ'
wordsig IPOPQ	'I_POPQ'
# Instruction code for iaddq instruction
wordsig IIADDQ	'I_IADDQ'

##### Symbolic represenations of Y86-64 function codes                  #####
wordsig FNONE    'F_NONE'        # Default function code

##### Symbolic representation of Y86-64 Registers referenced explicitly #####
wordsig RRSP     'REG_RSP'    	# Stack Pointer
wordsig RNONE    'REG_NONE'   	# Special value indicating "no register"

##### ALU Functions referenced explicitly                            #####
wordsig ALUADD	'A_ADD'		# ALU should add its arguments

##### Possible instruction status values                             #####
wordsig SAOK	'STAT_AOK'	# Normal execution
wordsig SADR	'STAT_ADR'	# Invalid memory address
wordsig SINS	'STAT_INS'	# Invalid instruction
wordsig SHLT	'STAT_HLT'	# Halt instruction encountered

##### Signals that can be referenced by control logic ####################

##### Fetch stage inputs		#####
wordsig pc 'pc'				# Program counter
##### Fetch stage computations		#####
wordsig imem_icode 'imem_icode'		# icode field from instruction memory
wordsig imem_ifun  'imem_ifun' 		# ifun field from instruction memory
wordsig icode	  'icode'		# Instruction control code
wordsig ifun	  'ifun'		# Instruction function
wordsig rA	  'ra'			# rA field from instruction
wordsig rB	  'rb'			# rB field from instruction
wordsig valC	  'valc'		# Constant from instruction
wordsig valP	  'valp'		# Address of following instruction
boolsig imem_error 'imem_error'		# Error signal from instruction memory
boolsig instr_valid 'instr_valid'	# Is fetched instruction valid?

##### Decode stage computations		#####
wordsig valA	'vala'			# Value from register A port
wordsig valB	'valb'			# Value from register B port

##### Execute stage computations	#####
wordsig valE	'vale'			# Value computed by ALU
boolsig Cnd	'cond'			# Branch test

##### Memory stage computations		#####
wordsig valM	'valm'			# Value read from memory
boolsig dmem_error 'dmem_error'		# Error signal from data memory


####################################################################
#    Control Signal Definitions.                                   #
####################################################################

################ Fetch Stage     ###################################

# Determine instruction code
word icode = [
	imem_error: INOP;
	1: imem_icode;		# Default: get from instruction memory
];

# Determine instruction function
word ifun = [
	imem_error: FNONE;
	1: imem_ifun;		# Default: get from instruction memory
];

bool instr_valid = icode in 
	{ INOP, IHALT, IRRMOVQ, IIRMOVQ, IRMMOVQ, IMRMOVQ,
	       IOPQ, IJXX, ICALL, IRET, IPUSHQ, IPOPQ, IIADDQ };#changed

# Does fetched instruction require a regid byte?
bool need_regids =
	icode in { IRRMOVQ, IOPQ, IPUSHQ, IPOPQ, 
		     IIRMOVQ, IRMMOVQ, IMRMOVQ , IIADDQ};#changed

# Does fetched instruction require a constant word?
bool need_valC =
	icode in { IIRMOVQ, IRMMOVQ, IMRMOVQ, IJXX, ICALL, IIADDQ };#changed

################ Decode Stage    ###################################

## What register should be used as the A source?
word srcA = [
	icode in { IRRMOVQ, IRMMOVQ, IOPQ, IPUSHQ  } : rA;
	icode in { IPOPQ, IRET } : RRSP;
	1 : RNONE; # Don't need register
];

## What register should be used as the B source?
word srcB = [
	icode in { IOPQ, IRMMOVQ, IMRMOVQ , IIADDQ } : rB;#changed
	icode in { IPUSHQ, IPOPQ, ICALL, IRET } : RRSP;
	1 : RNONE;  # Don't need register
];

## What register should be used as the E destination?
word dstE = [
	icode in { IRRMOVQ } && Cnd : rB;
	icode in { IIRMOVQ, IOPQ, IIADDQ} : rB;#changed
	icode in { IPUSHQ, IPOPQ, ICALL, IRET } : RRSP;
	1 : RNONE;  # Don't write any register
];

## What register should be used as the M destination?
word dstM = [
	icode in { IMRMOVQ, IPOPQ } : rA;
	1 : RNONE;  # Don't write any register
];

################ Execute Stage   ###################################

## Select input A to ALU
word aluA = [
	icode in { IRRMOVQ, IOPQ } : valA;
	icode in { IIRMOVQ, IRMMOVQ, IMRMOVQ, IIADDQ } : valC;#changed
	icode in { ICALL, IPUSHQ } : -8;
	icode in { IRET, IPOPQ } : 8;
	# Other instructions don't need ALU
];

## Select input B to ALU
word aluB = [
	icode in { IRMMOVQ, IMRMOVQ, IOPQ, ICALL, 
		      IPUSHQ, IRET, IPOPQ, IIADDQ } : valB;#changed
	icode in { IRRMOVQ, IIRMOVQ } : 0;
	# Other instructions don't need ALU
];

## Set the ALU function
word alufun = [
	icode == IOPQ : ifun;
	1 : ALUADD;
];

## Should the condition codes be updated?
bool set_cc = icode in { IOPQ, IIADDQ };#changed

################ Memory Stage    ###################################

## Set read control signal
bool mem_read = icode in { IMRMOVQ, IPOPQ, IRET };

## Set write control signal
bool mem_write = icode in { IRMMOVQ, IPUSHQ, ICALL };

## Select memory address
word mem_addr = [
	icode in { IRMMOVQ, IPUSHQ, ICALL, IMRMOVQ } : valE;
	icode in { IPOPQ, IRET } : valA;
	# Other instructions don't need address
];

## Select memory input data
word mem_data = [
	# Value from register
	icode in { IRMMOVQ, IPUSHQ } : valA;
	# Return PC
	icode == ICALL : valP;
	# Default: Don't write anything
];

## Determine instruction status
word Stat = [
	imem_error || dmem_error : SADR;
	!instr_valid: SINS;
	icode == IHALT : SHLT;
	1 : SAOK;
];

################ Program Counter Update ############################

## What address should instruction be fetched at

word new_pc = [
	# Call.  Use instruction constant
	icode == ICALL : valC;
	# Taken branch.  Use instruction constant
	icode == IJXX && Cnd : valC;
	# Completion of RET instruction.  Use value from stack
	icode == IRET : valM;
	# Default: Use incremented PC
	1 : valP;
];
#/* $end seq-all-hcl */

sim文件夹中右键启动终端,重新生成版本为full的ssim版本:

make clean;make VERSION=full

sim/seq文件夹中右键启动终端,运行单个程序测试:

./ssim -t ../y86-code/asumi.yo

单步调试命令:

 ./ssim -g ../y86-code/asumi.yo

sim/ptest文件夹中右键启动终端,运行所有测试:全部通过.

make SIM=../seq/ssim TFLAGS=-i

Part C:

修改好.ys文件后生成.yo文件:

 make drivers

测试.yo文件正确性:

./correctness.pl

测试.yo文件性能:

./benchmark.pl

ncopy.ys文件:

#/* $begin ncopy-ys */
##################################################################
# ncopy.ys - Copy a src block of len words to dst.
# Return the number of positive words (>0) contained in src.
#
# Include your name and ID here.
#
# Describe how and why you modified the baseline code.
#
##################################################################
# Do not modify this portion
# Function prologue.
# %rdi = src, %rsi = dst, %rdx = len
ncopy:

##################################################################
# You can modify this portion
	# Loop header
	xorq %rax,%rax		# count = 0;
	rrmovq %rdx,%rcx	# limit = 1
	irmovq $7,%r9		
 	xorq %rbp,%rbp		# rbp i = 0;
	andq %rdx,%rdx		# len <= 0?
	jle Done		# if so, goto Done:
	subq %r9,%rcx		# limit=len-4=1
	jle Loop1x1		# limit > 0?

Loop8x8:mrmovq (%rdi), %r8
	mrmovq 8(%rdi), %r9
	mrmovq 16(%rdi), %r10	
	mrmovq 24(%rdi), %r11
	mrmovq 32(%rdi), %r12	
	mrmovq 40(%rdi), %r13	
	mrmovq 48(%rdi), %r14	
	mrmovq 56(%rdi), %rbx

	rmmovq %r8, (%rsi)
	rmmovq %r9, 8(%rsi)
	rmmovq %r10, 16(%rsi)
	rmmovq %r11, 24(%rsi)
	rmmovq %r12, 32(%rsi)
	rmmovq %r13, 40(%rsi)
	rmmovq %r14, 48(%rsi)
	rmmovq %rbx, 56(%rsi)

judge0: andq   %r8,%r8
	jle judge1
	iaddq $1,%rax

judge1: andq   %r9,%r9
	jle judge2
	iaddq $1,%rax

judge2: andq   %r10,%r10
	jle judge3
	iaddq $1,%rax

judge3: andq   %r11,%r11
	jle judge4
	iaddq $1,%rax

judge4: andq   %r12,%r12
	jle judge5
	iaddq $1,%rax

judge5: andq   %r13,%r13
	jle judge6
	iaddq $1,%rax

judge6: andq   %r14,%r14
	jle judge7
	iaddq $1,%rax

judge7: andq   %rbx,%rbx
	jle add8
	iaddq $1,%rax

add8:	iaddq $64,%rdi   
	iaddq $64,%rsi    
	iaddq $8,%rbp           # i+8

	rrmovq %rbp,%r13        # i
	subq %rcx,%r13 		# i:limit =2
	jl Loop8x8

	rrmovq %rbp,%r8         # i
	subq %rdx,%r8		# i:len >=0?
	je Done

Loop1x1:mrmovq (%rdi), %r10	# read val from src...
	rmmovq %r10, (%rsi)	# ...and store it to dst
	andq %r10, %r10		# val <= 0?
	jle nopes
	iaddq $1,%rax		# count+

nopes:	iaddq $1, %rbp		# i+1
	iaddq $8, %rdi		# src++
	iaddq $8, %rsi		# dst++
	rrmovq %rbp,%r8		# i
	subq %rdx,%r8		# i-len < 0?
	jl Loop1x1		# if so, goto Loop:


##################################################################
# Do not modify the following section of code
# Function epilogue.
Done:
	ret
##################################################################
# Keep the following label at the end of your function
End:
#/* $end ncopy-ys */

这是8*8循环展开的形式.

目前只拿到20.9分,剩下的可以通过修改pipe-full.hcl文件来获得.

#/* $begin pipe-all-hcl */
####################################################################
#    HCL Description of Control for Pipelined Y86-64 Processor     #
#    Copyright (C) Randal E. Bryant, David R. O'Hallaron, 2014     #
####################################################################

## Your task is to implement the iaddq instruction
## The file contains a declaration of the icodes
## for iaddq (IIADDQ)
## Your job is to add the rest of the logic to make it work

####################################################################
#    C Include's.  Don't alter these                               #
####################################################################

quote '#include <stdio.h>'
quote '#include "isa.h"'
quote '#include "pipeline.h"'
quote '#include "stages.h"'
quote '#include "sim.h"'
quote 'int sim_main(int argc, char *argv[]);'
quote 'int main(int argc, char *argv[]){return sim_main(argc,argv);}'

####################################################################
#    Declarations.  Do not change/remove/delete any of these       #
####################################################################

##### Symbolic representation of Y86-64 Instruction Codes #############
wordsig INOP 	'I_NOP'
wordsig IHALT	'I_HALT'
wordsig IRRMOVQ	'I_RRMOVQ'
wordsig IIRMOVQ	'I_IRMOVQ'
wordsig IRMMOVQ	'I_RMMOVQ'
wordsig IMRMOVQ	'I_MRMOVQ'
wordsig IOPQ	'I_ALU'
wordsig IJXX	'I_JMP'
wordsig ICALL	'I_CALL'
wordsig IRET	'I_RET'
wordsig IPUSHQ	'I_PUSHQ'
wordsig IPOPQ	'I_POPQ'
# Instruction code for iaddq instruction
wordsig IIADDQ	'I_IADDQ'

##### Symbolic represenations of Y86-64 function codes            #####
wordsig FNONE    'F_NONE'        # Default function code

##### Symbolic representation of Y86-64 Registers referenced      #####
wordsig RRSP     'REG_RSP'    	     # Stack Pointer
wordsig RNONE    'REG_NONE'   	     # Special value indicating "no register"

##### ALU Functions referenced explicitly ##########################
wordsig ALUADD	'A_ADD'		     # ALU should add its arguments

##### Possible instruction status values                       #####
wordsig SBUB	'STAT_BUB'	# Bubble in stage
wordsig SAOK	'STAT_AOK'	# Normal execution
wordsig SADR	'STAT_ADR'	# Invalid memory address
wordsig SINS	'STAT_INS'	# Invalid instruction
wordsig SHLT	'STAT_HLT'	# Halt instruction encountered

##### Signals that can be referenced by control logic ##############

##### Pipeline Register F ##########################################

wordsig F_predPC 'pc_curr->pc'	     # Predicted value of PC

##### Intermediate Values in Fetch Stage ###########################

wordsig imem_icode  'imem_icode'      # icode field from instruction memory
wordsig imem_ifun   'imem_ifun'       # ifun  field from instruction memory
wordsig f_icode	'if_id_next->icode'  # (Possibly modified) instruction code
wordsig f_ifun	'if_id_next->ifun'   # Fetched instruction function
wordsig f_valC	'if_id_next->valc'   # Constant data of fetched instruction
wordsig f_valP	'if_id_next->valp'   # Address of following instruction
boolsig imem_error 'imem_error'	     # Error signal from instruction memory
boolsig instr_valid 'instr_valid'    # Is fetched instruction valid?

##### Pipeline Register D ##########################################
wordsig D_icode 'if_id_curr->icode'   # Instruction code
wordsig D_rA 'if_id_curr->ra'	     # rA field from instruction
wordsig D_rB 'if_id_curr->rb'	     # rB field from instruction
wordsig D_valP 'if_id_curr->valp'     # Incremented PC

##### Intermediate Values in Decode Stage  #########################

wordsig d_srcA	 'id_ex_next->srca'  # srcA from decoded instruction
wordsig d_srcB	 'id_ex_next->srcb'  # srcB from decoded instruction
wordsig d_rvalA 'd_regvala'	     # valA read from register file
wordsig d_rvalB 'd_regvalb'	     # valB read from register file

##### Pipeline Register E ##########################################
wordsig E_icode 'id_ex_curr->icode'   # Instruction code
wordsig E_ifun  'id_ex_curr->ifun'    # Instruction function
wordsig E_valC  'id_ex_curr->valc'    # Constant data
wordsig E_srcA  'id_ex_curr->srca'    # Source A register ID
wordsig E_valA  'id_ex_curr->vala'    # Source A value
wordsig E_srcB  'id_ex_curr->srcb'    # Source B register ID
wordsig E_valB  'id_ex_curr->valb'    # Source B value
wordsig E_dstE 'id_ex_curr->deste'    # Destination E register ID
wordsig E_dstM 'id_ex_curr->destm'    # Destination M register ID

##### Intermediate Values in Execute Stage #########################
wordsig e_valE 'ex_mem_next->vale'	# valE generated by ALU
boolsig e_Cnd 'ex_mem_next->takebranch' # Does condition hold?
wordsig e_dstE 'ex_mem_next->deste'      # dstE (possibly modified to be RNONE)

##### Pipeline Register M                  #########################
wordsig M_stat 'ex_mem_curr->status'     # Instruction status
wordsig M_icode 'ex_mem_curr->icode'	# Instruction code
wordsig M_ifun  'ex_mem_curr->ifun'	# Instruction function
wordsig M_valA  'ex_mem_curr->vala'      # Source A value
wordsig M_dstE 'ex_mem_curr->deste'	# Destination E register ID
wordsig M_valE  'ex_mem_curr->vale'      # ALU E value
wordsig M_dstM 'ex_mem_curr->destm'	# Destination M register ID
boolsig M_Cnd 'ex_mem_curr->takebranch'	# Condition flag
boolsig dmem_error 'dmem_error'	        # Error signal from instruction memory

##### Intermediate Values in Memory Stage ##########################
wordsig m_valM 'mem_wb_next->valm'	# valM generated by memory
wordsig m_stat 'mem_wb_next->status'	# stat (possibly modified to be SADR)

##### Pipeline Register W ##########################################
wordsig W_stat 'mem_wb_curr->status'     # Instruction status
wordsig W_icode 'mem_wb_curr->icode'	# Instruction code
wordsig W_dstE 'mem_wb_curr->deste'	# Destination E register ID
wordsig W_valE  'mem_wb_curr->vale'      # ALU E value
wordsig W_dstM 'mem_wb_curr->destm'	# Destination M register ID
wordsig W_valM  'mem_wb_curr->valm'	# Memory M value

####################################################################
#    Control Signal Definitions.                                   #
####################################################################

################ Fetch Stage     ###################################

## What address should instruction be fetched at
word f_pc = [
	# Mispredicted branch.  Fetch at incremented PC
	M_icode == IJXX && !M_Cnd : M_valA;
	# Completion of RET instruction
	W_icode == IRET : W_valM;
	# Default: Use predicted value of PC
	1 : F_predPC;
];

## Determine icode of fetched instruction
word f_icode = [
	imem_error : INOP;
	1: imem_icode;
];

# Determine ifun
word f_ifun = [
	imem_error : FNONE;
	1: imem_ifun;
];

# Is instruction valid?
bool instr_valid = f_icode in 
	{ INOP, IHALT, IRRMOVQ, IIRMOVQ, IRMMOVQ, IMRMOVQ,
	  IOPQ, IJXX, ICALL, IRET, IPUSHQ, IPOPQ, IIADDQ };

# Determine status code for fetched instruction
word f_stat = [
	imem_error: SADR;
	!instr_valid : SINS;
	f_icode == IHALT : SHLT;
	1 : SAOK;
];

# Does fetched instruction require a regid byte?
bool need_regids =
	f_icode in { IRRMOVQ, IOPQ, IPUSHQ, IPOPQ, 
		     IIRMOVQ, IRMMOVQ, IMRMOVQ , IIADDQ};

# Does fetched instruction require a constant word?
bool need_valC =
	f_icode in { IIRMOVQ, IRMMOVQ, IMRMOVQ, IJXX, ICALL, IIADDQ  };

# Predict next value of PC
word f_predPC = [
	f_icode in { IJXX, ICALL } : f_valC;
	1 : f_valP;
];

################ Decode Stage ######################################


## What register should be used as the A source?
word d_srcA = [
	D_icode in { IRRMOVQ, IRMMOVQ, IOPQ, IPUSHQ  } : D_rA;
	D_icode in { IPOPQ, IRET } : RRSP;
	1 : RNONE; # Don't need register
];

## What register should be used as the B source?
word d_srcB = [
	D_icode in { IOPQ, IRMMOVQ, IMRMOVQ , IIADDQ  } : D_rB;
	D_icode in { IPUSHQ, IPOPQ, ICALL, IRET } : RRSP;
	1 : RNONE;  # Don't need register
];

## What register should be used as the E destination?
word d_dstE = [
	D_icode in { IRRMOVQ, IIRMOVQ, IOPQ , IIADDQ} : D_rB;
	D_icode in { IPUSHQ, IPOPQ, ICALL, IRET } : RRSP;
	1 : RNONE;  # Don't write any register
];

## What register should be used as the M destination?
word d_dstM = [
	D_icode in { IMRMOVQ, IPOPQ } : D_rA;
	1 : RNONE;  # Don't write any register
];

## What should be the A value?
## Forward into decode stage for valA
word d_valA = [
	D_icode in { ICALL, IJXX } : D_valP; # Use incremented PC
	d_srcA == e_dstE : e_valE;    # Forward valE from execute
	d_srcA == M_dstM : m_valM;    # Forward valM from memory
	d_srcA == M_dstE : M_valE;    # Forward valE from memory
	d_srcA == W_dstM : W_valM;    # Forward valM from write back
	d_srcA == W_dstE : W_valE;    # Forward valE from write back
	1 : d_rvalA;  # Use value read from register file
];

word d_valB = [
	d_srcB == e_dstE : e_valE;    # Forward valE from execute
	d_srcB == M_dstM : m_valM;    # Forward valM from memory
	d_srcB == M_dstE : M_valE;    # Forward valE from memory
	d_srcB == W_dstM : W_valM;    # Forward valM from write back
	d_srcB == W_dstE : W_valE;    # Forward valE from write back
	1 : d_rvalB;  # Use value read from register file
];

################ Execute Stage #####################################

## Select input A to ALU
word aluA = [
	E_icode in { IRRMOVQ, IOPQ } : E_valA;
	E_icode in { IIRMOVQ, IRMMOVQ, IMRMOVQ, IIADDQ } : E_valC;
	E_icode in { ICALL, IPUSHQ } : -8;
	E_icode in { IRET, IPOPQ } : 8;
	# Other instructions don't need ALU
];

## Select input B to ALU
word aluB = [
	E_icode in { IRMMOVQ, IMRMOVQ, IOPQ, ICALL, 
		     IPUSHQ, IRET, IPOPQ , IIADDQ} : E_valB;
	E_icode in { IRRMOVQ, IIRMOVQ } : 0;
	# Other instructions don't need ALU
];

## Set the ALU function
word alufun = [
	E_icode == IOPQ : E_ifun;
	1 : ALUADD;
];

## Should the condition codes be updated?
bool set_cc = E_icode in { IOPQ, IIADDQ }&&
	# State changes only during normal operation
	!m_stat in { SADR, SINS, SHLT } && !W_stat in { SADR, SINS, SHLT };

## Generate valA in execute stage
word e_valA = E_valA;    # Pass valA through stage

## Set dstE to RNONE in event of not-taken conditional move
word e_dstE = [
	E_icode == IRRMOVQ && !e_Cnd : RNONE;
	1 : E_dstE;
];

################ Memory Stage ######################################

## Select memory address
word mem_addr = [
	M_icode in { IRMMOVQ, IPUSHQ, ICALL, IMRMOVQ } : M_valE;
	M_icode in { IPOPQ, IRET } : M_valA;
	# Other instructions don't need address
];

## Set read control signal
bool mem_read = M_icode in { IMRMOVQ, IPOPQ, IRET };

## Set write control signal
bool mem_write = M_icode in { IRMMOVQ, IPUSHQ, ICALL };

#/* $begin pipe-m_stat-hcl */
## Update the status
word m_stat = [
	dmem_error : SADR;
	1 : M_stat;
];
#/* $end pipe-m_stat-hcl */

## Set E port register ID
word w_dstE = W_dstE;

## Set E port value
word w_valE = W_valE;

## Set M port register ID
word w_dstM = W_dstM;

## Set M port value
word w_valM = W_valM;

## Update processor status
word Stat = [
	W_stat == SBUB : SAOK;
	1 : W_stat;
];

################ Pipeline Register Control #########################

# Should I stall or inject a bubble into Pipeline Register F?
# At most one of these can be true.
bool F_bubble = 0;
bool F_stall =
	# Conditions for a load/use hazard
	E_icode in { IMRMOVQ, IPOPQ } &&
	 E_dstM in { d_srcA, d_srcB } ||
	# Stalling at fetch while ret passes through pipeline
	IRET in { D_icode, E_icode, M_icode };

# Should I stall or inject a bubble into Pipeline Register D?
# At most one of these can be true.
bool D_stall = 
	# Conditions for a load/use hazard
	E_icode in { IMRMOVQ, IPOPQ } &&
	 E_dstM in { d_srcA, d_srcB };

bool D_bubble =
	# Mispredicted branch
	(E_icode == IJXX && !e_Cnd) ||
	# Stalling at fetch while ret passes through pipeline
	# but not condition for a load/use hazard
	!(E_icode in { IMRMOVQ, IPOPQ } && E_dstM in { d_srcA, d_srcB }) &&
	  IRET in { D_icode, E_icode, M_icode };

# Should I stall or inject a bubble into Pipeline Register E?
# At most one of these can be true.
bool E_stall = 0;
bool E_bubble =
	# Mispredicted branch
	(E_icode == IJXX && !e_Cnd) ||
	# Conditions for a load/use hazard
	E_icode in { IMRMOVQ, IPOPQ } &&
	 E_dstM in { d_srcA, d_srcB};

# Should I stall or inject a bubble into Pipeline Register M?
# At most one of these can be true.
bool M_stall = 0;
# Start injecting bubbles as soon as exception passes through memory stage
bool M_bubble = m_stat in { SADR, SINS, SHLT } || W_stat in { SADR, SINS, SHLT };

# Should I stall or inject a bubble into Pipeline Register W?
bool W_stall = W_stat in { SADR, SINS, SHLT };
bool W_bubble = 0;
#/* $end pipe-all-hcl */

这是家庭作业4.55的内容.

pipe-full.hcl本来的是默认预测选择条件分支.

而我们写的ncopy.ys的条件是判断寄存器是空则跳过不加+1,所以运行时全部预测都错了.

另外,还和预测错误后,信号的转发相关.

DAMO开发者矩阵

DAMO开发者矩阵，由阿里巴巴达摩院和中国互联网协会联合发起，致力于探讨最前沿的技术趋势与应用成果，搭建高质量的交流与分享平台，推动技术创新与产业应用链接，围绕“人工智能与新型计算”构建开放共享的开发者生态。

更多推荐

EmbodiedSkills：用于协调、训练和部署 VLA 智能体的统一框架

DAMO开发者矩阵

当下热门的SEO优化服务机构，究竟哪家更靠谱？

DAMO开发者矩阵

深度解读：AI长程任务如何重塑工作执行范式

大模型技术发展的早期，大众对AI的认知大多停留在聊天问答层面。用户输入问题，模型返回一段文本，一次交互就此结束。随着模型理解能力迭代，多轮对话成为常态，AI可以承接上下文，围绕同一个主题完成多轮沟通，但行动依旧需要人类一步步下达指令。工具调用能力出现之后，AI不再局限于文本生成，能够调动外部能力完成检索、计算、文件处理等动作。而Work Agent的出现，把工具调用进一步升级，形成自主推进的任务链