Nicolas Pitre <[email protected]> writes:
> +static inline uint64_t __arch_xprod_64(uint64_t m, uint64_t n, bool bias)
> +{
> + unsigned long long res;
> + unsigned int tmp = 0;
> +
> + if (!bias) {
> + asm ( "umull %Q0, %R0, %Q1, %Q2\n\t"
> + "mov %Q0, #0"
> + : "=&r" (res)
> + : "r" (m), "r" (n)
> + : "cc");
> + } else if (!(m & ((1ULL << 63) | (1ULL << 31)))) {
> + res = m;
> + asm ( "umlal %Q0, %R0, %Q1, %Q2\n\t"
> + "mov %Q0, #0"
> + : "+&r" (res)
> + : "r" (m), "r" (n)
> + : "cc");
> + } else {
> + asm ( "umull %Q0, %R0, %Q2, %Q3\n\t"
> + "cmn %Q0, %Q2\n\t"
> + "adcs %R0, %R0, %R2\n\t"
> + "adc %Q0, %1, #0"
> + : "=&r" (res), "+&r" (tmp)
> + : "r" (m), "r" (n)
Why is tmp using a +r constraint here? The register is not written, so
using an input-only operand could/should result in better code. That is
also what the old code did.
> + : "cc");
> + }
> +
> + if (!(m & ((1ULL << 63) | (1ULL << 31)))) {
> + asm ( "umlal %R0, %Q0, %R1, %Q2\n\t"
> + "umlal %R0, %Q0, %Q1, %R2\n\t"
> + "mov %R0, #0\n\t"
> + "umlal %Q0, %R0, %R1, %R2"
> + : "+&r" (res)
> + : "r" (m), "r" (n)
> + : "cc");
> + } else {
> + asm ( "umlal %R0, %Q0, %R2, %Q3\n\t"
> + "umlal %R0, %1, %Q2, %R3\n\t"
> + "mov %R0, #0\n\t"
> + "adds %Q0, %1, %Q0\n\t"
> + "adc %R0, %R0, #0\n\t"
> + "umlal %Q0, %R0, %R2, %R3"
> + : "+&r" (res), "+&r" (tmp)
> + : "r" (m), "r" (n)
> + : "cc");
> + }
> +
> + return res;
> +}
--
Måns Rullgård
[email protected]
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
