iv/linux
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

__div64_const32(): improve the generic C version

Browse Source 
Let's rework that code to avoid large immediate values and convert some
64-bit variables to 32-bit ones when possible. This allows gcc to
produce smaller and better code. This even produces optimal code on
RISC-V.

Signed-off-by: Nicolas Pitre <nico@fluxnic.net>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
This commit is contained in:
Nicolas Pitre 2019-08-20 23:05:42 -04:00 committed by Arnd Bergmann
parent 3940ba8eea
commit 602828c1aa
1 changed files with 10 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
include/asm-generic/div64.h
View File

@ -178,7 +178,8 @@ static inline uint64_t __arch_xprod_64(const uint64_t m, uint64_t n, bool bias)
uint32_t m_hi = m >> 32; uint32_t m_hi = m >> 32;
uint32_t n_lo = n; uint32_t n_lo = n;
uint32_t n_hi = n >> 32; uint32_t n_hi = n >> 32;
uint64_t res, tmp; uint64_t res;
uint32_t res_lo, res_hi, tmp;
if (!bias) { if (!bias) {
res = ((uint64_t)m_lo * n_lo) >> 32; res = ((uint64_t)m_lo * n_lo) >> 32;
@ -187,8 +188,9 @@ static inline uint64_t __arch_xprod_64(const uint64_t m, uint64_t n, bool bias)
res = (m + (uint64_t)m_lo * n_lo) >> 32; res = (m + (uint64_t)m_lo * n_lo) >> 32;
} else { } else {
res = m + (uint64_t)m_lo * n_lo; res = m + (uint64_t)m_lo * n_lo;
tmp = (res < m) ? (1ULL << 32) : 0; res_lo = res >> 32;
res = (res >> 32) + tmp; res_hi = (res_lo < m_hi);
res = res_lo | ((uint64_t)res_hi << 32);
} }
if (!(m & ((1ULL << 63) | (1ULL << 31)))) { if (!(m & ((1ULL << 63) | (1ULL << 31)))) {
@ -197,10 +199,12 @@ static inline uint64_t __arch_xprod_64(const uint64_t m, uint64_t n, bool bias)
res += (uint64_t)m_hi * n_lo; res += (uint64_t)m_hi * n_lo;
res >>= 32; res >>= 32;
} else { } else {
tmp = res += (uint64_t)m_lo * n_hi; res += (uint64_t)m_lo * n_hi;
tmp = res >> 32;
res += (uint64_t)m_hi * n_lo; res += (uint64_t)m_hi * n_lo;
tmp = (res < tmp) ? (1ULL << 32) : 0; res_lo = res >> 32;
res = (res >> 32) + tmp; res_hi = (res_lo < tmp);
res = res_lo | ((uint64_t)res_hi << 32);
} }
res += (uint64_t)m_hi * n_hi; res += (uint64_t)m_hi * n_hi;