vpaddq t2,t1,t1
vmovq t1x,d4
+ # Now do a partial reduction mod (2^130)-5, carrying h0 -> h1 -> h2 ->
+ # h3 -> h4 -> h0 -> h1 to get h0,h2,h3,h4 < 2^26 and h1 < 2^26 + a small
+ # amount. Careful: we must not assume the carry bits 'd0 >> 26',
+ # 'd1 >> 26', 'd2 >> 26', 'd3 >> 26', and '(d4 >> 26) * 5' fit in 32-bit
+ # integers. It's true in a single-block implementation, but not here.
+
# d1 += d0 >> 26
mov d0,%rax
shr $26,%rax
# h0 += (d4 >> 26) * 5
mov d4,%rax
shr $26,%rax
- lea (%eax,%eax,4),%eax
- add %eax,%ebx
+ lea (%rax,%rax,4),%rax
+ add %rax,%rbx
# h4 = d4 & 0x3ffffff
mov d4,%rax
and $0x3ffffff,%eax
mov %eax,h4
# h1 += h0 >> 26
- mov %ebx,%eax
- shr $26,%eax
+ mov %rbx,%rax
+ shr $26,%rax
add %eax,h1
# h0 = h0 & 0x3ffffff
andl $0x3ffffff,%ebx