2014-11-06 15:20:19 +08:00
|
|
|
config NIOS2
|
|
|
|
def_bool y
|
|
|
|
select CLKSRC_OF
|
|
|
|
select GENERIC_ATOMIC64
|
|
|
|
select GENERIC_CLOCKEVENTS
|
|
|
|
select GENERIC_CPU_DEVICES
|
|
|
|
select GENERIC_IRQ_PROBE
|
|
|
|
select GENERIC_IRQ_SHOW
|
2017-05-08 17:14:14 +08:00
|
|
|
select GENERIC_STRNCPY_FROM_USER
|
|
|
|
select GENERIC_STRNLEN_USER
|
2014-11-06 15:20:19 +08:00
|
|
|
select HAVE_ARCH_TRACEHOOK
|
2015-02-16 19:26:43 +08:00
|
|
|
select HAVE_ARCH_KGDB
|
2014-11-06 15:20:19 +08:00
|
|
|
select IRQ_DOMAIN
|
|
|
|
select MODULES_USE_ELF_RELA
|
|
|
|
select OF
|
|
|
|
select OF_EARLY_FLATTREE
|
|
|
|
select SOC_BUS
|
|
|
|
select SPARSE_IRQ
|
|
|
|
select USB_ARCH_HAS_HCD if USB_SUPPORT
|
lib/GCD.c: use binary GCD algorithm instead of Euclidean
The binary GCD algorithm is based on the following facts:
1. If a and b are all evens, then gcd(a,b) = 2 * gcd(a/2, b/2)
2. If a is even and b is odd, then gcd(a,b) = gcd(a/2, b)
3. If a and b are all odds, then gcd(a,b) = gcd((a-b)/2, b) = gcd((a+b)/2, b)
Even on x86 machines with reasonable division hardware, the binary
algorithm runs about 25% faster (80% the execution time) than the
division-based Euclidian algorithm.
On platforms like Alpha and ARMv6 where division is a function call to
emulation code, it's even more significant.
There are two variants of the code here, depending on whether a fast
__ffs (find least significant set bit) instruction is available. This
allows the unpredictable branches in the bit-at-a-time shifting loop to
be eliminated.
If fast __ffs is not available, the "even/odd" GCD variant is used.
I use the following code to benchmark:
#include <stdio.h>
#include <stdlib.h>
#include <stdint.h>
#include <string.h>
#include <time.h>
#include <unistd.h>
#define swap(a, b) \
do { \
a ^= b; \
b ^= a; \
a ^= b; \
} while (0)
unsigned long gcd0(unsigned long a, unsigned long b)
{
unsigned long r;
if (a < b) {
swap(a, b);
}
if (b == 0)
return a;
while ((r = a % b) != 0) {
a = b;
b = r;
}
return b;
}
unsigned long gcd1(unsigned long a, unsigned long b)
{
unsigned long r = a | b;
if (!a || !b)
return r;
b >>= __builtin_ctzl(b);
for (;;) {
a >>= __builtin_ctzl(a);
if (a == b)
return a << __builtin_ctzl(r);
if (a < b)
swap(a, b);
a -= b;
}
}
unsigned long gcd2(unsigned long a, unsigned long b)
{
unsigned long r = a | b;
if (!a || !b)
return r;
r &= -r;
while (!(b & r))
b >>= 1;
for (;;) {
while (!(a & r))
a >>= 1;
if (a == b)
return a;
if (a < b)
swap(a, b);
a -= b;
a >>= 1;
if (a & r)
a += b;
a >>= 1;
}
}
unsigned long gcd3(unsigned long a, unsigned long b)
{
unsigned long r = a | b;
if (!a || !b)
return r;
b >>= __builtin_ctzl(b);
if (b == 1)
return r & -r;
for (;;) {
a >>= __builtin_ctzl(a);
if (a == 1)
return r & -r;
if (a == b)
return a << __builtin_ctzl(r);
if (a < b)
swap(a, b);
a -= b;
}
}
unsigned long gcd4(unsigned long a, unsigned long b)
{
unsigned long r = a | b;
if (!a || !b)
return r;
r &= -r;
while (!(b & r))
b >>= 1;
if (b == r)
return r;
for (;;) {
while (!(a & r))
a >>= 1;
if (a == r)
return r;
if (a == b)
return a;
if (a < b)
swap(a, b);
a -= b;
a >>= 1;
if (a & r)
a += b;
a >>= 1;
}
}
static unsigned long (*gcd_func[])(unsigned long a, unsigned long b) = {
gcd0, gcd1, gcd2, gcd3, gcd4,
};
#define TEST_ENTRIES (sizeof(gcd_func) / sizeof(gcd_func[0]))
#if defined(__x86_64__)
#define rdtscll(val) do { \
unsigned long __a,__d; \
__asm__ __volatile__("rdtsc" : "=a" (__a), "=d" (__d)); \
(val) = ((unsigned long long)__a) | (((unsigned long long)__d)<<32); \
} while(0)
static unsigned long long benchmark_gcd_func(unsigned long (*gcd)(unsigned long, unsigned long),
unsigned long a, unsigned long b, unsigned long *res)
{
unsigned long long start, end;
unsigned long long ret;
unsigned long gcd_res;
rdtscll(start);
gcd_res = gcd(a, b);
rdtscll(end);
if (end >= start)
ret = end - start;
else
ret = ~0ULL - start + 1 + end;
*res = gcd_res;
return ret;
}
#else
static inline struct timespec read_time(void)
{
struct timespec time;
clock_gettime(CLOCK_PROCESS_CPUTIME_ID, &time);
return time;
}
static inline unsigned long long diff_time(struct timespec start, struct timespec end)
{
struct timespec temp;
if ((end.tv_nsec - start.tv_nsec) < 0) {
temp.tv_sec = end.tv_sec - start.tv_sec - 1;
temp.tv_nsec = 1000000000ULL + end.tv_nsec - start.tv_nsec;
} else {
temp.tv_sec = end.tv_sec - start.tv_sec;
temp.tv_nsec = end.tv_nsec - start.tv_nsec;
}
return temp.tv_sec * 1000000000ULL + temp.tv_nsec;
}
static unsigned long long benchmark_gcd_func(unsigned long (*gcd)(unsigned long, unsigned long),
unsigned long a, unsigned long b, unsigned long *res)
{
struct timespec start, end;
unsigned long gcd_res;
start = read_time();
gcd_res = gcd(a, b);
end = read_time();
*res = gcd_res;
return diff_time(start, end);
}
#endif
static inline unsigned long get_rand()
{
if (sizeof(long) == 8)
return (unsigned long)rand() << 32 | rand();
else
return rand();
}
int main(int argc, char **argv)
{
unsigned int seed = time(0);
int loops = 100;
int repeats = 1000;
unsigned long (*res)[TEST_ENTRIES];
unsigned long long elapsed[TEST_ENTRIES];
int i, j, k;
for (;;) {
int opt = getopt(argc, argv, "n:r:s:");
/* End condition always first */
if (opt == -1)
break;
switch (opt) {
case 'n':
loops = atoi(optarg);
break;
case 'r':
repeats = atoi(optarg);
break;
case 's':
seed = strtoul(optarg, NULL, 10);
break;
default:
/* You won't actually get here. */
break;
}
}
res = malloc(sizeof(unsigned long) * TEST_ENTRIES * loops);
memset(elapsed, 0, sizeof(elapsed));
srand(seed);
for (j = 0; j < loops; j++) {
unsigned long a = get_rand();
/* Do we have args? */
unsigned long b = argc > optind ? strtoul(argv[optind], NULL, 10) : get_rand();
unsigned long long min_elapsed[TEST_ENTRIES];
for (k = 0; k < repeats; k++) {
for (i = 0; i < TEST_ENTRIES; i++) {
unsigned long long tmp = benchmark_gcd_func(gcd_func[i], a, b, &res[j][i]);
if (k == 0 || min_elapsed[i] > tmp)
min_elapsed[i] = tmp;
}
}
for (i = 0; i < TEST_ENTRIES; i++)
elapsed[i] += min_elapsed[i];
}
for (i = 0; i < TEST_ENTRIES; i++)
printf("gcd%d: elapsed %llu\n", i, elapsed[i]);
k = 0;
srand(seed);
for (j = 0; j < loops; j++) {
unsigned long a = get_rand();
unsigned long b = argc > optind ? strtoul(argv[optind], NULL, 10) : get_rand();
for (i = 1; i < TEST_ENTRIES; i++) {
if (res[j][i] != res[j][0])
break;
}
if (i < TEST_ENTRIES) {
if (k == 0) {
k = 1;
fprintf(stderr, "Error:\n");
}
fprintf(stderr, "gcd(%lu, %lu): ", a, b);
for (i = 0; i < TEST_ENTRIES; i++)
fprintf(stderr, "%ld%s", res[j][i], i < TEST_ENTRIES - 1 ? ", " : "\n");
}
}
if (k == 0)
fprintf(stderr, "PASS\n");
free(res);
return 0;
}
Compiled with "-O2", on "VirtualBox 4.4.0-22-generic #38-Ubuntu x86_64" got:
zhaoxiuzeng@zhaoxiuzeng-VirtualBox:~/develop$ ./gcd -r 500000 -n 10
gcd0: elapsed 10174
gcd1: elapsed 2120
gcd2: elapsed 2902
gcd3: elapsed 2039
gcd4: elapsed 2812
PASS
zhaoxiuzeng@zhaoxiuzeng-VirtualBox:~/develop$ ./gcd -r 500000 -n 10
gcd0: elapsed 9309
gcd1: elapsed 2280
gcd2: elapsed 2822
gcd3: elapsed 2217
gcd4: elapsed 2710
PASS
zhaoxiuzeng@zhaoxiuzeng-VirtualBox:~/develop$ ./gcd -r 500000 -n 10
gcd0: elapsed 9589
gcd1: elapsed 2098
gcd2: elapsed 2815
gcd3: elapsed 2030
gcd4: elapsed 2718
PASS
zhaoxiuzeng@zhaoxiuzeng-VirtualBox:~/develop$ ./gcd -r 500000 -n 10
gcd0: elapsed 9914
gcd1: elapsed 2309
gcd2: elapsed 2779
gcd3: elapsed 2228
gcd4: elapsed 2709
PASS
[akpm@linux-foundation.org: avoid #defining a CONFIG_ variable]
Signed-off-by: Zhaoxiu Zeng <zhaoxiu.zeng@gmail.com>
Signed-off-by: George Spelvin <linux@horizon.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-05-21 08:03:57 +08:00
|
|
|
select CPU_NO_EFFICIENT_FFS
|
2014-11-06 15:20:19 +08:00
|
|
|
|
|
|
|
config GENERIC_CSUM
|
|
|
|
def_bool y
|
|
|
|
|
|
|
|
config GENERIC_HWEIGHT
|
|
|
|
def_bool y
|
|
|
|
|
|
|
|
config GENERIC_CALIBRATE_DELAY
|
|
|
|
def_bool y
|
|
|
|
|
|
|
|
config NO_IOPORT_MAP
|
|
|
|
def_bool y
|
|
|
|
|
|
|
|
config HAS_DMA
|
|
|
|
def_bool y
|
|
|
|
|
|
|
|
config FPU
|
|
|
|
def_bool n
|
|
|
|
|
|
|
|
config SWAP
|
|
|
|
def_bool n
|
|
|
|
|
|
|
|
config RWSEM_GENERIC_SPINLOCK
|
|
|
|
def_bool y
|
|
|
|
|
|
|
|
config TRACE_IRQFLAGS_SUPPORT
|
|
|
|
def_bool n
|
|
|
|
|
|
|
|
source "init/Kconfig"
|
|
|
|
|
|
|
|
menu "Kernel features"
|
|
|
|
|
|
|
|
source "kernel/Kconfig.preempt"
|
|
|
|
|
|
|
|
source "kernel/Kconfig.freezer"
|
|
|
|
|
|
|
|
source "kernel/Kconfig.hz"
|
|
|
|
|
|
|
|
source "mm/Kconfig"
|
|
|
|
|
|
|
|
config FORCE_MAX_ZONEORDER
|
|
|
|
int "Maximum zone order"
|
|
|
|
range 9 20
|
|
|
|
default "11"
|
|
|
|
help
|
|
|
|
The kernel memory allocator divides physically contiguous memory
|
|
|
|
blocks into "zones", where each zone is a power of two number of
|
|
|
|
pages. This option selects the largest power of two that the kernel
|
|
|
|
keeps in the memory allocator. If you need to allocate very large
|
|
|
|
blocks of physically contiguous memory, then you may need to
|
|
|
|
increase this value.
|
|
|
|
|
|
|
|
This config option is actually maximum order plus one. For example,
|
|
|
|
a value of 11 means that the largest free memory block is 2^10 pages.
|
|
|
|
|
|
|
|
endmenu
|
|
|
|
|
|
|
|
source "arch/nios2/platform/Kconfig.platform"
|
|
|
|
|
|
|
|
menu "Processor type and features"
|
|
|
|
|
|
|
|
config MMU
|
|
|
|
def_bool y
|
|
|
|
|
2014-11-24 16:13:39 +08:00
|
|
|
config NR_CPUS
|
|
|
|
int
|
|
|
|
default "1"
|
|
|
|
|
2014-11-06 15:20:19 +08:00
|
|
|
config NIOS2_ALIGNMENT_TRAP
|
|
|
|
bool "Catch alignment trap"
|
|
|
|
default y
|
|
|
|
help
|
|
|
|
Nios II CPUs cannot fetch/store data which is not bus aligned,
|
|
|
|
i.e., a 2 or 4 byte fetch must start at an address divisible by
|
|
|
|
2 or 4. Any non-aligned load/store instructions will be trapped and
|
|
|
|
emulated in software if you say Y here, which has a performance
|
|
|
|
impact.
|
|
|
|
|
|
|
|
comment "Boot options"
|
|
|
|
|
|
|
|
config CMDLINE_BOOL
|
|
|
|
bool "Default bootloader kernel arguments"
|
|
|
|
default y
|
|
|
|
|
|
|
|
config CMDLINE
|
|
|
|
string "Default kernel command string"
|
|
|
|
default ""
|
|
|
|
depends on CMDLINE_BOOL
|
|
|
|
help
|
|
|
|
On some platforms, there is currently no way for the boot loader to
|
|
|
|
pass arguments to the kernel. For these platforms, you can supply
|
|
|
|
some command-line options at build time by entering them here. In
|
|
|
|
other cases you can specify kernel args so that you don't have
|
|
|
|
to set them up in board prom initialization routines.
|
|
|
|
|
|
|
|
config CMDLINE_FORCE
|
|
|
|
bool "Force default kernel command string"
|
|
|
|
depends on CMDLINE_BOOL
|
|
|
|
help
|
|
|
|
Set this to have arguments from the default kernel command string
|
|
|
|
override those passed by the boot loader.
|
|
|
|
|
|
|
|
config NIOS2_CMDLINE_IGNORE_DTB
|
|
|
|
bool "Ignore kernel command string from DTB"
|
2014-11-24 16:40:04 +08:00
|
|
|
depends on CMDLINE_BOOL
|
2014-11-06 15:20:19 +08:00
|
|
|
depends on !CMDLINE_FORCE
|
|
|
|
default y
|
|
|
|
help
|
|
|
|
Set this to ignore the bootargs property from the devicetree's
|
|
|
|
chosen node and fall back to CMDLINE if nothing is passed.
|
|
|
|
|
|
|
|
config NIOS2_PASS_CMDLINE
|
|
|
|
bool "Passed kernel command line from u-boot"
|
|
|
|
default n
|
|
|
|
help
|
|
|
|
Use bootargs env variable from u-boot for kernel command line.
|
|
|
|
will override "Default kernel command string".
|
|
|
|
Say N if you are unsure.
|
|
|
|
|
2015-02-10 23:26:34 +08:00
|
|
|
config NIOS2_BOOT_LINK_OFFSET
|
|
|
|
hex "Link address offset for booting"
|
|
|
|
default "0x00500000"
|
|
|
|
help
|
|
|
|
This option allows you to set the link address offset of the zImage.
|
|
|
|
This can be useful if you are on a board which has a small amount of
|
|
|
|
memory.
|
|
|
|
|
2014-11-06 15:20:19 +08:00
|
|
|
endmenu
|
|
|
|
|
|
|
|
menu "Advanced setup"
|
|
|
|
|
|
|
|
config ADVANCED_OPTIONS
|
|
|
|
bool "Prompt for advanced kernel configuration options"
|
|
|
|
help
|
|
|
|
|
|
|
|
comment "Default settings for advanced configuration options are used"
|
|
|
|
depends on !ADVANCED_OPTIONS
|
|
|
|
|
|
|
|
config NIOS2_KERNEL_MMU_REGION_BASE_BOOL
|
|
|
|
bool "Set custom kernel MMU region base address"
|
|
|
|
depends on ADVANCED_OPTIONS
|
|
|
|
help
|
|
|
|
This option allows you to set the virtual address of the kernel MMU region.
|
|
|
|
|
|
|
|
Say N here unless you know what you are doing.
|
|
|
|
|
|
|
|
config NIOS2_KERNEL_MMU_REGION_BASE
|
|
|
|
hex "Virtual base address of the kernel MMU region " if NIOS2_KERNEL_MMU_REGION_BASE_BOOL
|
|
|
|
default "0x80000000"
|
|
|
|
help
|
|
|
|
This option allows you to set the virtual base address of the kernel MMU region.
|
|
|
|
|
|
|
|
config NIOS2_KERNEL_REGION_BASE_BOOL
|
|
|
|
bool "Set custom kernel region base address"
|
|
|
|
depends on ADVANCED_OPTIONS
|
|
|
|
help
|
|
|
|
This option allows you to set the virtual address of the kernel region.
|
|
|
|
|
|
|
|
Say N here unless you know what you are doing.
|
|
|
|
|
|
|
|
config NIOS2_KERNEL_REGION_BASE
|
|
|
|
hex "Virtual base address of the kernel region " if NIOS2_KERNEL_REGION_BASE_BOOL
|
|
|
|
default "0xc0000000"
|
|
|
|
|
|
|
|
config NIOS2_IO_REGION_BASE_BOOL
|
|
|
|
bool "Set custom I/O region base address"
|
|
|
|
depends on ADVANCED_OPTIONS
|
|
|
|
help
|
|
|
|
This option allows you to set the virtual address of the I/O region.
|
|
|
|
|
|
|
|
Say N here unless you know what you are doing.
|
|
|
|
|
|
|
|
config NIOS2_IO_REGION_BASE
|
|
|
|
hex "Virtual base address of the I/O region" if NIOS2_IO_REGION_BASE_BOOL
|
|
|
|
default "0xe0000000"
|
|
|
|
|
|
|
|
endmenu
|
|
|
|
|
|
|
|
menu "Executable file formats"
|
|
|
|
|
|
|
|
source "fs/Kconfig.binfmt"
|
|
|
|
|
|
|
|
endmenu
|
|
|
|
|
|
|
|
source "net/Kconfig"
|
|
|
|
|
|
|
|
source "drivers/Kconfig"
|
|
|
|
|
|
|
|
source "fs/Kconfig"
|
|
|
|
|
|
|
|
source "arch/nios2/Kconfig.debug"
|
|
|
|
|
|
|
|
source "security/Kconfig"
|
|
|
|
|
|
|
|
source "crypto/Kconfig"
|
|
|
|
|
|
|
|
source "lib/Kconfig"
|