Kernel/linux-stable
1
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git synced 2025-01-15 01:44:52 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity
linux-stable/arch/microblaze/Kconfig
Zhaoxiu Zeng fff7fb0b2d 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>
2016-05-20 17:58:30 -07:00

298 lines
7.3 KiB
Plaintext
Raw Blame History

config MICROBLAZE
def_bool y
select ARCH_HAS_GCOV_PROFILE_ALL
select ARCH_MIGHT_HAVE_PC_PARPORT
select ARCH_WANT_IPC_PARSE_VERSION
select ARCH_WANT_OPTIONAL_GPIOLIB
select BUILDTIME_EXTABLE_SORT
select CLKSRC_OF
select CLONE_BACKWARDS3
select COMMON_CLK
select GENERIC_ATOMIC64
select GENERIC_CLOCKEVENTS
select GENERIC_CPU_DEVICES
select GENERIC_IDLE_POLL_SETUP
select GENERIC_IRQ_PROBE
select GENERIC_IRQ_SHOW
select GENERIC_PCI_IOMAP
select GENERIC_SCHED_CLOCK
select HAVE_ARCH_KGDB
select HAVE_DEBUG_KMEMLEAK
select HAVE_DMA_API_DEBUG
select HAVE_DYNAMIC_FTRACE
select HAVE_FTRACE_MCOUNT_RECORD
select HAVE_FUNCTION_GRAPH_TRACER
select HAVE_FUNCTION_TRACER
select HAVE_MEMBLOCK
select HAVE_MEMBLOCK_NODE_MAP
select HAVE_OPROFILE
select IRQ_DOMAIN
select MODULES_USE_ELF_RELA
select OF
select OF_EARLY_FLATTREE
select TRACING_SUPPORT
select VIRT_TO_BUS
select CPU_NO_EFFICIENT_FFS
config SWAP
def_bool n
config RWSEM_GENERIC_SPINLOCK
def_bool y
config ZONE_DMA
def_bool y
config RWSEM_XCHGADD_ALGORITHM
bool
config ARCH_HAS_ILOG2_U32
def_bool n
config ARCH_HAS_ILOG2_U64
def_bool n
config GENERIC_HWEIGHT
def_bool y
config GENERIC_CALIBRATE_DELAY
def_bool y
config GENERIC_CSUM
def_bool y
config STACKTRACE_SUPPORT
def_bool y
config LOCKDEP_SUPPORT
def_bool y
source "init/Kconfig"
source "kernel/Kconfig.freezer"
source "arch/microblaze/Kconfig.platform"
menu "Processor type and features"
source "kernel/Kconfig.preempt"
source "kernel/Kconfig.hz"
config MMU
bool "MMU support"
default n
comment "Boot options"
config CMDLINE_BOOL
bool "Default bootloader kernel arguments"
config CMDLINE
string "Default kernel command string"
depends on CMDLINE_BOOL
default "console=ttyUL0,115200"
help
On some architectures there is currently no way for the boot loader
to pass arguments to the kernel. For these architectures, you should
supply some command-line options at build time by entering them
here.
config CMDLINE_FORCE
bool "Force default kernel command string"
depends on CMDLINE_BOOL
default n
help
Set this to have arguments from the default kernel command string
override those passed by the boot loader.
config SECCOMP
bool "Enable seccomp to safely compute untrusted bytecode"
depends on PROC_FS
default y
help
This kernel feature is useful for number crunching applications
that may need to compute untrusted bytecode during their
execution. By using pipes or other transports made available to
the process as file descriptors supporting the read/write
syscalls, it's possible to isolate those applications in
their own address space using seccomp. Once seccomp is
enabled via /proc/<pid>/seccomp, it cannot be disabled
and the task is only allowed to execute a few safe syscalls
defined by each seccomp mode.
If unsure, say Y. Only embedded should say N here.
endmenu
menu "Kernel features"
config NR_CPUS
int
default "1"
config ADVANCED_OPTIONS
bool "Prompt for advanced kernel configuration options"
help
This option will enable prompting for a variety of advanced kernel
configuration options. These options can cause the kernel to not
work if they are set incorrectly, but can be used to optimize certain
aspects of kernel memory management.
Unless you know what you are doing, say N here.
comment "Default settings for advanced configuration options are used"
depends on !ADVANCED_OPTIONS
config XILINX_UNCACHED_SHADOW
bool "Are you using uncached shadow for RAM ?"
depends on ADVANCED_OPTIONS && !MMU
default n
help
This is needed to be able to allocate uncachable memory regions.
The feature requires the design to define the RAM memory controller
window to be twice as large as the actual physical memory.
config HIGHMEM
bool "High memory support"
depends on MMU
help
The address space of Microblaze processors is only 4 Gigabytes large
and it has to accommodate user address space, kernel address
space as well as some memory mapped IO. That means that, if you
have a large amount of physical memory and/or IO, not all of the
memory can be "permanently mapped" by the kernel. The physical
memory that is not permanently mapped is called "high memory".
If unsure, say n.
config LOWMEM_SIZE_BOOL
bool "Set maximum low memory"
depends on ADVANCED_OPTIONS && MMU
help
This option allows you to set the maximum amount of memory which
will be used as "low memory", that is, memory which the kernel can
access directly, without having to set up a kernel virtual mapping.
This can be useful in optimizing the layout of kernel virtual
memory.
Say N here unless you know what you are doing.
config LOWMEM_SIZE
hex "Maximum low memory size (in bytes)" if LOWMEM_SIZE_BOOL
default "0x30000000"
config MANUAL_RESET_VECTOR
hex "Microblaze reset vector address setup"
default "0x0"
help
Set this option to have the kernel override the CPU Reset vector.
If zero, no change will be made to the MicroBlaze reset vector at
address 0x0.
If non-zero, a jump instruction to this address, will be written
to the reset vector at address 0x0.
If you are unsure, set it to default value 0x0.
config KERNEL_START_BOOL
bool "Set custom kernel base address"
depends on ADVANCED_OPTIONS
help
This option allows you to set the kernel virtual address at which
the kernel will map low memory (the kernel image will be linked at
this address). This can be useful in optimizing the virtual memory
layout of the system.
Say N here unless you know what you are doing.
config KERNEL_START
hex "Virtual address of kernel base" if KERNEL_START_BOOL
default "0xc0000000" if MMU
default KERNEL_BASE_ADDR if !MMU
config TASK_SIZE_BOOL
bool "Set custom user task size"
depends on ADVANCED_OPTIONS && MMU
help
This option allows you to set the amount of virtual address space
allocated to user tasks. This can be useful in optimizing the
virtual memory layout of the system.
Say N here unless you know what you are doing.
config TASK_SIZE
hex "Size of user task space" if TASK_SIZE_BOOL
default "0x80000000"
choice
prompt "Page size"
default MICROBLAZE_4K_PAGES
depends on ADVANCED_OPTIONS && !MMU
help
Select the kernel logical page size. Increasing the page size
will reduce software overhead at each page boundary, allow
hardware prefetch mechanisms to be more effective, and allow
larger dma transfers increasing IO efficiency and reducing
overhead. However the utilization of memory will increase.
For example, each cached file will using a multiple of the
page size to hold its contents and the difference between the
end of file and the end of page is wasted.
If unsure, choose 4K_PAGES.
config MICROBLAZE_4K_PAGES
bool "4k page size"
config MICROBLAZE_16K_PAGES
bool "16k page size"
config MICROBLAZE_64K_PAGES
bool "64k page size"
endchoice
source "mm/Kconfig"
endmenu
menu "Executable file formats"
source "fs/Kconfig.binfmt"
endmenu
menu "Bus Options"
config PCI
bool "PCI support"
config PCI_DOMAINS
def_bool PCI
config PCI_DOMAINS_GENERIC
def_bool PCI_DOMAINS
config PCI_SYSCALL
def_bool PCI
config PCI_XILINX
bool "Xilinx PCI host bridge support"
depends on PCI
source "drivers/pci/Kconfig"
endmenu
source "net/Kconfig"
source "drivers/Kconfig"
source "fs/Kconfig"
source "arch/microblaze/Kconfig.debug"
source "security/Kconfig"
source "crypto/Kconfig"
source "lib/Kconfig"
Reference in New Issue View Git Blame Copy Permalink