The accumulator should be an earlyclobber because it is written before
all input operands are read. Otherwise, the asm code computes a wrong
result if the accumulator shares a register with one of the other input
operands (which happens if we pass in the same expression for the
accumulator and the operand).
Closes https://github.com/official-stockfish/Stockfish/pull/4339
No functional change
asm(
"vpdpbusd %[b0], %[a0], %[acc]\n\t"
"vpdpbusd %[b1], %[a1], %[acc]\n\t"
- : [acc]"+v"(acc)
+ : [acc]"+&v"(acc)
: [a0]"v"(a0), [b0]"vm"(b0), [a1]"v"(a1), [b1]"vm"(b1)
);
# else
asm(
VNNI_PREFIX "vpdpbusd %[b0], %[a0], %[acc]\n\t"
VNNI_PREFIX "vpdpbusd %[b1], %[a1], %[acc]\n\t"
- : [acc]"+v"(acc)
+ : [acc]"+&v"(acc)
: [a0]"v"(a0), [b0]"vm"(b0), [a1]"v"(a1), [b1]"vm"(b1)
);
# else