VPCMPESTRM

n = 8 if imm8 & 1 else 16  # words, bytes
w = 128 // n               # bits each
m = (1 << w) - 1
k = 1 << w - 1 if imm8 & 2 else 0  # signed
# the lengths: |EAX| and |EDX|, at most n,
# the count of imm8[0] (not of imm8[3])
la = min(abs(signed(eax)), n)
lb = min(abs(signed(edx)), n)
a = xmm1.read()
b = src2.read()
agg = imm8 >> 2 & 3
# (v >> w * i & m ^ k) - k: element i of v,
# sign-extended where k is its sign bit
r = 0
for j in range(n):     # bit j: src2's
    y = (b >> w * j & m ^ k) - k  # element j
    bit = 0
    if agg == 0:       # equal any: y is
        for i in range(la):  # in xmm1
            x = (a >> w * i & m ^ k) - k
            if j < lb and x == y:
                bit = 1
    elif agg == 1:     # ranges: y is in
        for i in range(0, la - 1, 2):
            t = w * i  # a pair's range
            lo = (a >> t & m ^ k) - k
            hi = (a >> t + w & m ^ k) - k
            if j < lb and lo <= y <= hi:
                bit = 1
    elif agg == 2:     # equal each
        x = (a >> w * j & m ^ k) - k
        if j < la and j < lb:
            bit = x == y
        else:          # 1 past both ends
            bit = j >= la and j >= lb
    else:              # equal ordered: xmm1
        bit = 1        # from element j on;
        # what would fall past the end of the
        # register matches, and an empty xmm1
        # everywhere, as in Intel's manual
        # (AMD's clears these bits)
        for i in range(min(la, n - j)):
            x = (a >> w * i & m ^ k) - k
            u = j + i
            z = (b >> w * u & m ^ k) - k
            if u >= lb or x != z:
                bit = 0
    r |= bit << j
p = imm8 >> 4 & 3
if p == 1:             # negated
    r ^= (1 << n) - 1
elif p == 3:           # negated within src2
    r ^= (1 << lb) - 1
# imm8[6]: each bit made an element of ones,
# words where imm8[0] is set (whatever
# imm8[1], which Intel's table names)
if imm8 & 0x40:
    v = 0
    for j in range(n):
        if r >> j & 1:
            v |= m << w * j
    xmm0.write(v)
else:
    xmm0.write(r)      # the bits alone
cf = r != 0
zf = lb < n            # src2 is short
sf = la < n            # xmm1 is short
of = r & 1
af = pf = 0
# xmm0 is zeroed from bit 128 up

n = 8 if imm8 & 1 else 16  # words, bytes
w = 128 // n               # bits each
m = (1 << w) - 1
k = 1 << w - 1 if imm8 & 2 else 0  # signed
# the lengths: |RAX| and |RDX|, read whole
# with VEX.W1 (which AMD's manual marks as
# ignored), at most n, the count of imm8[0]
la = min(abs(signed(rax)), n)
lb = min(abs(signed(rdx)), n)
a = xmm1.read()
b = src2.read()
agg = imm8 >> 2 & 3
# (v >> w * i & m ^ k) - k: element i of v,
# sign-extended where k is its sign bit
r = 0
for j in range(n):     # bit j: src2's
    y = (b >> w * j & m ^ k) - k  # element j
    bit = 0
    if agg == 0:       # equal any: y is
        for i in range(la):  # in xmm1
            x = (a >> w * i & m ^ k) - k
            if j < lb and x == y:
                bit = 1
    elif agg == 1:     # ranges: y is in
        for i in range(0, la - 1, 2):
            t = w * i  # a pair's range
            lo = (a >> t & m ^ k) - k
            hi = (a >> t + w & m ^ k) - k
            if j < lb and lo <= y <= hi:
                bit = 1
    elif agg == 2:     # equal each
        x = (a >> w * j & m ^ k) - k
        if j < la and j < lb:
            bit = x == y
        else:          # 1 past both ends
            bit = j >= la and j >= lb
    else:              # equal ordered: xmm1
        bit = 1        # from element j on;
        # what would fall past the end of the
        # register matches, and an empty xmm1
        # everywhere, as in Intel's manual
        # (AMD's clears these bits)
        for i in range(min(la, n - j)):
            x = (a >> w * i & m ^ k) - k
            u = j + i
            z = (b >> w * u & m ^ k) - k
            if u >= lb or x != z:
                bit = 0
    r |= bit << j
p = imm8 >> 4 & 3
if p == 1:             # negated
    r ^= (1 << n) - 1
elif p == 3:           # negated within src2
    r ^= (1 << lb) - 1
# imm8[6]: each bit made an element of ones,
# words where imm8[0] is set (whatever
# imm8[1], which Intel's table names)
if imm8 & 0x40:
    v = 0
    for j in range(n):
        if r >> j & 1:
            v |= m << w * j
    xmm0.write(v)
else:
    xmm0.write(r)      # the bits alone
cf = r != 0
zf = lb < n            # src2 is short
sf = la < n            # xmm1 is short
of = r & 1
af = pf = 0
# xmm0 is zeroed from bit 128 up