2019-06-04 16:11:33 +08:00
|
|
|
/* SPDX-License-Identifier: GPL-2.0-only */
|
2011-01-15 18:23:09 +08:00
|
|
|
/*
|
|
|
|
|
* linux/arch/unicore32/include/asm/bitops.h
|
|
|
|
|
*
|
|
|
|
|
* Code specific to PKUnity SoC and UniCore ISA
|
|
|
|
|
*
|
|
|
|
|
* Copyright (C) 2001-2010 GUAN Xue-tao
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
#ifndef __UNICORE_BITOPS_H__
|
|
|
|
|
#define __UNICORE_BITOPS_H__
|
|
|
|
|
|
|
|
|
|
#define _ASM_GENERIC_BITOPS_FLS_H_
|
|
|
|
|
#define _ASM_GENERIC_BITOPS___FLS_H_
|
|
|
|
|
#define _ASM_GENERIC_BITOPS_FFS_H_
|
|
|
|
|
#define _ASM_GENERIC_BITOPS___FFS_H_
|
|
|
|
|
/*
|
|
|
|
|
* On UNICORE, those functions can be implemented around
|
|
|
|
|
* the cntlz instruction for much better code efficiency.
|
|
|
|
|
*/
|
|
|
|
|
|
2019-01-04 07:26:41 +08:00
|
|
|
static inline int fls(unsigned int x)
|
2011-01-15 18:23:09 +08:00
|
|
|
{
|
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
|
|
asm("cntlz\t%0, %1" : "=r" (ret) : "r" (x) : "cc");
|
|
|
|
|
ret = 32 - ret;
|
|
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#define __fls(x) (fls(x) - 1)
|
|
|
|
|
#define ffs(x) ({ unsigned long __t = (x); fls(__t & -__t); })
|
|
|
|
|
#define __ffs(x) (ffs(x) - 1)
|
|
|
|
|
|
|
|
|
|
#include <asm-generic/bitops.h>
|
|
|
|
|
|
2011-06-13 11:44:49 +08:00
|
|
|
/* following definitions: to avoid using codes in lib/find_*.c */
|
|
|
|
|
#define find_next_bit find_next_bit
|
|
|
|
|
#define find_next_zero_bit find_next_zero_bit
|
|
|
|
|
#define find_first_bit find_first_bit
|
|
|
|
|
#define find_first_zero_bit find_first_zero_bit
|
|
|
|
|
|
lib: optimize cpumask_next_and()
We've measured that we spend ~0.6% of sys cpu time in cpumask_next_and().
It's essentially a joined iteration in search for a non-zero bit, which is
currently implemented as a lookup join (find a nonzero bit on the lhs,
lookup the rhs to see if it's set there).
Implement a direct join (find a nonzero bit on the incrementally built
join). Also add generic bitmap benchmarks in the new `test_find_bit`
module for new function (see `find_next_and_bit` in [2] and [3] below).
For cpumask_next_and, direct benchmarking shows that it's 1.17x to 14x
faster with a geometric mean of 2.1 on 32 CPUs [1]. No impact on memory
usage. Note that on Arm, the new pure-C implementation still outperforms
the old one that uses a mix of C and asm (`find_next_bit`) [3].
[1] Approximate benchmark code:
```
unsigned long src1p[nr_cpumask_longs] = {pattern1};
unsigned long src2p[nr_cpumask_longs] = {pattern2};
for (/*a bunch of repetitions*/) {
for (int n = -1; n <= nr_cpu_ids; ++n) {
asm volatile("" : "+rm"(src1p)); // prevent any optimization
asm volatile("" : "+rm"(src2p));
unsigned long result = cpumask_next_and(n, src1p, src2p);
asm volatile("" : "+rm"(result));
}
}
```
Results:
pattern1 pattern2 time_before/time_after
0x0000ffff 0x0000ffff 1.65
0x0000ffff 0x00005555 2.24
0x0000ffff 0x00001111 2.94
0x0000ffff 0x00000000 14.0
0x00005555 0x0000ffff 1.67
0x00005555 0x00005555 1.71
0x00005555 0x00001111 1.90
0x00005555 0x00000000 6.58
0x00001111 0x0000ffff 1.46
0x00001111 0x00005555 1.49
0x00001111 0x00001111 1.45
0x00001111 0x00000000 3.10
0x00000000 0x0000ffff 1.18
0x00000000 0x00005555 1.18
0x00000000 0x00001111 1.17
0x00000000 0x00000000 1.25
-----------------------------
geo.mean 2.06
[2] test_find_next_bit, X86 (skylake)
[ 3913.477422] Start testing find_bit() with random-filled bitmap
[ 3913.477847] find_next_bit: 160868 cycles, 16484 iterations
[ 3913.477933] find_next_zero_bit: 169542 cycles, 16285 iterations
[ 3913.478036] find_last_bit: 201638 cycles, 16483 iterations
[ 3913.480214] find_first_bit: 4353244 cycles, 16484 iterations
[ 3913.480216] Start testing find_next_and_bit() with random-filled
bitmap
[ 3913.481074] find_next_and_bit: 89604 cycles, 8216 iterations
[ 3913.481075] Start testing find_bit() with sparse bitmap
[ 3913.481078] find_next_bit: 2536 cycles, 66 iterations
[ 3913.481252] find_next_zero_bit: 344404 cycles, 32703 iterations
[ 3913.481255] find_last_bit: 2006 cycles, 66 iterations
[ 3913.481265] find_first_bit: 17488 cycles, 66 iterations
[ 3913.481266] Start testing find_next_and_bit() with sparse bitmap
[ 3913.481272] find_next_and_bit: 764 cycles, 1 iterations
[3] test_find_next_bit, arm (v7 odroid XU3).
[ 267.206928] Start testing find_bit() with random-filled bitmap
[ 267.214752] find_next_bit: 4474 cycles, 16419 iterations
[ 267.221850] find_next_zero_bit: 5976 cycles, 16350 iterations
[ 267.229294] find_last_bit: 4209 cycles, 16419 iterations
[ 267.279131] find_first_bit: 1032991 cycles, 16420 iterations
[ 267.286265] Start testing find_next_and_bit() with random-filled
bitmap
[ 267.302386] find_next_and_bit: 2290 cycles, 8140 iterations
[ 267.309422] Start testing find_bit() with sparse bitmap
[ 267.316054] find_next_bit: 191 cycles, 66 iterations
[ 267.322726] find_next_zero_bit: 8758 cycles, 32703 iterations
[ 267.329803] find_last_bit: 84 cycles, 66 iterations
[ 267.336169] find_first_bit: 4118 cycles, 66 iterations
[ 267.342627] Start testing find_next_and_bit() with sparse bitmap
[ 267.356919] find_next_and_bit: 91 cycles, 1 iterations
[courbet@google.com: v6]
Link: http://lkml.kernel.org/r/20171129095715.23430-1-courbet@google.com
[geert@linux-m68k.org: m68k/bitops: always include <asm-generic/bitops/find.h>]
Link: http://lkml.kernel.org/r/1512556816-28627-1-git-send-email-geert@linux-m68k.org
Link: http://lkml.kernel.org/r/20171128131334.23491-1-courbet@google.com
Signed-off-by: Clement Courbet <courbet@google.com>
Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Yury Norov <ynorov@caviumnetworks.com>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-02-07 07:38:34 +08:00
|
|
|
#include <asm-generic/bitops/find.h>
|
|
|
|
|
|
2011-01-15 18:23:09 +08:00
|
|
|
#endif /* __UNICORE_BITOPS_H__ */
|
