Assembly 对大整数进行签名和扩展的最有效的代码是什么？
我正在用x86-64汇编语言编写一个代码库，为Assembly 对大整数进行签名和扩展的最有效的代码是什么？,assembly,x86-64,avx,bigint,sign-extension,Assembly,X86 64,Avx,Bigint,Sign Extension,我正在用x86-64汇编语言编写一个代码库，为s0128，s0256，s0512，s1024，s2048，和s4096有符号整数类型和f0128，f0256，提供所有常规的按位、移位、逻辑、比较、算术和数学函数，f0512，f1024，f2048，以及f4096浮点类型 现在，我正在编写一些类型转换例程，遇到了一些应该很简单但需要的指令比我预期的多得多的东西。我觉得我一定错过了一些让这更容易的东西（一些说明），但到目前为止没有运气 s0256结果的低位128位仅仅是s0128输入参数的副本，而s
s0128s0256s0512s1024s2048s4096f0128f0256f0512f1024f2048f4096s0256s0128s0256s0128s0256s0128.text
.align 64
big_m63:
.quad -63, -63 # two shift counts for vpshaq instruction
big_s0256_eq_s0128: # (s0256* arg0, const s0128* arg1); # s0256 = s0256(s0128)
orq %rdi, %rdi # is arg0 a valid address ???
jz error_argument_invalid # nope
orq %rsi, %rsi # is arg1 a valid address ???
jz error_argument_invalid # nope
vmovapd (%rsi), %xmm0 # ymm0 = arg1.ls64 : arg1.ms64 : 0 : 0
vmovhlps %xmm0, %xmm0, %xmm1 # ymm1 = arg1.ms64 : arg1.ms64 : 0 : 0
vpshaq big_m63, %xmm1, %xmm1 # ymm1 = arg1.sign : arg1.sign : 0 : 0
vperm2f128 $32, %ymm1, %ymm0, %ymm0 # ymm1 = arg1.ls64 : arg1.ms64 : sign : sign
vmovapd %ymm0, (%rdi) # arg0 = arg1 (sign-extended to 256-bits)
xorq %rax, %rax # rax = 0 == no error
ret # return from function
.text
.align 64
big_m63:
.quad -63, -63 # two shift counts for vpshaq instruction
big_s0256_eq_s0128: # (s0256* arg0, const s0128* arg1); # s0256 = s0256(s0128)
orq %rdi, %rdi # is arg0 a valid address ???
jz error_argument_invalid # nope
orq %rsi, %rsi # is arg1 a valid address ???
jz error_argument_invalid # nope
vmovapd (%rsi), %xmm0 # ymm0 = arg1.ls64 : arg1.ms64 : 0 : 0
vmovhlps %xmm0, %xmm0, %xmm1 # ymm1 = arg1.ms64 : arg1.ms64 : 0 : 0
vpshaq big_m63, %xmm1, %xmm1 # ymm1 = arg1.sign : arg1.sign : 0 : 0
vperm2f128 $32, %ymm1, %ymm0, %ymm0 # ymm1 = arg1.ls64 : arg1.ms64 : sign : sign
vmovapd %ymm0, (%rdi) # arg0 = arg1 (sign-extended to 256-bits)
xorq %rax, %rax # rax = 0 == no error
ret # return from function
vpshaqvpshaqvpxorvmovapd.text
.align 64
big_s0256_eq_s0128: # (s0256* arg0, const s0128* arg1); # s0256 = s0256(s0128)
orq %rdi, %rdi # is arg0 a valid address ???
jz error_argument_invalid # nope
orq %rsi, %rsi # is arg1 a valid address ???
jz error_argument_invalid # nope
vmovapd (%rsi), %xmm0 # ymm0 = arg1.ls64 : arg1.ms64 : 0 : 0
vpxor %xmm2, %xmm2, %xmm2 # ymm2 = 0 : 0 : 0 : 0
vmovhlps %xmm0, %xmm0, %xmm1 # ymm1 = arg1.ms64 : arg1.ms64 : 0 : 0
vpcmpgtq %xmm1, %xmm2, %xmm1 # ymm1 = arg1.sign : arg1.sign : 0 : 0
vperm2f128 $32, %ymm1, %ymm0, %ymm0 # ymm1 = arg1.ls64 : arg1.ms64 : sign : sign
vmovapd %ymm0, (%rdi) # arg0 = arg1 (sign-extended to 256-bits)
xorq %rax, %rax # rax = 0 == no error
ret # return from function
我不确定，但不需要从内存中读取这两个64位移位计数也可能会稍微加快代码的速度。很好。你把事情复杂化了。登录
raxymm0vbroadcastq经过进一步考虑，我有以下建议：
vmovhlps %xmm0, %xmm0, %xmm1 // could use a permute instead to stay in integer domain.
vpxor %xmm2, %xmm2, %xmm2
vpcmpgtq %xmm1, %xmm2, %xmm2 // generate sign-extension without shift
FWIW，如果目标是AVX2，我可能会这样写：
vmovdqa (%rsi), %xmm0 // { x0, x1, 0, 0 }
vpermq $0x5f, %ymm0, %ymm1 // { 0, 0, x1, x1 }
vpxor %ymm2, %ymm2, %ymm2 // { 0, 0, 0, 0 }
vpcmpgtq %ymm1, %ymm2, %ymm2 // { 0, 0, s, s } s = sign extension
vpor %ymm2, %ymm0, %ymm0 // { x0, x1, s, s }
vmovdqa %ymm0, (%rdi)
不幸的是，我不认为
vpermqAVX2FX8150FX8350s0128s0256s0512s1024s2048s4096f0128f0256f0512f1024f2048f4096SIMDymmmovhlps