renegade-project/linux-next
2
0
Fork 0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-26 06:04:14 +08:00
Code
fff7fb0b2d
linux-next/arch/m68k/Kconfig.cpu
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

500 lines
12 KiB
Plaintext
Raw Blame History

comment "Processor Type"
choice
prompt "CPU family support"
default M68KCLASSIC if MMU
default COLDFIRE if !MMU
help
The Freescale (was Motorola) M68K family of processors implements
the full 68000 processor instruction set.
The Freescale ColdFire family of processors is a modern derivative
of the 68000 processor family. They are mainly targeted at embedded
applications, and are all System-On-Chip (SOC) devices, as opposed
to stand alone CPUs. They implement a subset of the original 68000
processor instruction set.
If you anticipate running this kernel on a computer with a classic
MC68xxx processor, select M68KCLASSIC.
If you anticipate running this kernel on a computer with a ColdFire
processor, select COLDFIRE.
config M68KCLASSIC
bool "Classic M68K CPU family support"
config COLDFIRE
bool "Coldfire CPU family support"
select ARCH_HAVE_CUSTOM_GPIO_H
select CPU_HAS_NO_BITFIELDS
select CPU_HAS_NO_MULDIV64
select GENERIC_CSUM
select GPIOLIB
select HAVE_CLK
endchoice
if M68KCLASSIC
config M68000
bool "MC68000"
depends on !MMU
select CPU_HAS_NO_BITFIELDS
select CPU_HAS_NO_MULDIV64
select CPU_HAS_NO_UNALIGNED
select GENERIC_CSUM
select CPU_NO_EFFICIENT_FFS
help
The Freescale (was Motorola) 68000 CPU is the first generation of
the well known M68K family of processors. The CPU core as well as
being available as a stand alone CPU was also used in many
System-On-Chip devices (eg 68328, 68302, etc). It does not contain
a paging MMU.
config MCPU32
bool
select CPU_HAS_NO_BITFIELDS
select CPU_HAS_NO_UNALIGNED
select CPU_NO_EFFICIENT_FFS
help
The Freescale (was then Motorola) CPU32 is a CPU core that is
based on the 68020 processor. For the most part it is used in
System-On-Chip parts, and does not contain a paging MMU.
config M68020
bool "68020 support"
depends on MMU
select CPU_HAS_ADDRESS_SPACES
help
If you anticipate running this kernel on a computer with a MC68020
processor, say Y. Otherwise, say N. Note that the 68020 requires a
68851 MMU (Memory Management Unit) to run Linux/m68k, except on the
Sun 3, which provides its own version.
config M68030
bool "68030 support"
depends on MMU && !MMU_SUN3
select CPU_HAS_ADDRESS_SPACES
help
If you anticipate running this kernel on a computer with a MC68030
processor, say Y. Otherwise, say N. Note that a MC68EC030 will not
work, as it does not include an MMU (Memory Management Unit).
config M68040
bool "68040 support"
depends on MMU && !MMU_SUN3
select CPU_HAS_ADDRESS_SPACES
help
If you anticipate running this kernel on a computer with a MC68LC040
or MC68040 processor, say Y. Otherwise, say N. Note that an
MC68EC040 will not work, as it does not include an MMU (Memory
Management Unit).
config M68060
bool "68060 support"
depends on MMU && !MMU_SUN3
select CPU_HAS_ADDRESS_SPACES
help
If you anticipate running this kernel on a computer with a MC68060
processor, say Y. Otherwise, say N.
config M68328
bool "MC68328"
depends on !MMU
select M68000
help
Motorola 68328 processor support.
config M68EZ328
bool "MC68EZ328"
depends on !MMU
select M68000
help
Motorola 68EX328 processor support.
config M68VZ328
bool "MC68VZ328"
depends on !MMU
select M68000
help
Motorola 68VZ328 processor support.
endif # M68KCLASSIC
if COLDFIRE
choice
prompt "ColdFire SoC type"
default M520x
help
Select the type of ColdFire System-on-Chip (SoC) that you want
to build for.
config M5206
bool "MCF5206"
depends on !MMU
select COLDFIRE_SW_A7
select HAVE_MBAR
select CPU_NO_EFFICIENT_FFS
help
Motorola ColdFire 5206 processor support.
config M5206e
bool "MCF5206e"
depends on !MMU
select COLDFIRE_SW_A7
select HAVE_MBAR
select CPU_NO_EFFICIENT_FFS
help
Motorola ColdFire 5206e processor support.
config M520x
bool "MCF520x"
depends on !MMU
select GENERIC_CLOCKEVENTS
select HAVE_CACHE_SPLIT
help
Freescale Coldfire 5207/5208 processor support.
config M523x
bool "MCF523x"
depends on !MMU
select GENERIC_CLOCKEVENTS
select HAVE_CACHE_SPLIT
select HAVE_IPSBAR
help
Freescale Coldfire 5230/1/2/4/5 processor support
config M5249
bool "MCF5249"
depends on !MMU
select COLDFIRE_SW_A7
select HAVE_MBAR
select CPU_NO_EFFICIENT_FFS
help
Motorola ColdFire 5249 processor support.
config M525x
bool "MCF525x"
depends on !MMU
select COLDFIRE_SW_A7
select HAVE_MBAR
select CPU_NO_EFFICIENT_FFS
help
Freescale (Motorola) Coldfire 5251/5253 processor support.
config M5271
bool "MCF5271"
depends on !MMU
select M527x
select HAVE_CACHE_SPLIT
select HAVE_IPSBAR
select GENERIC_CLOCKEVENTS
help
Freescale (Motorola) ColdFire 5270/5271 processor support.
config M5272
bool "MCF5272"
depends on !MMU
select COLDFIRE_SW_A7
select HAVE_MBAR
select CPU_NO_EFFICIENT_FFS
help
Motorola ColdFire 5272 processor support.
config M5275
bool "MCF5275"
depends on !MMU
select M527x
select HAVE_CACHE_SPLIT
select HAVE_IPSBAR
select GENERIC_CLOCKEVENTS
help
Freescale (Motorola) ColdFire 5274/5275 processor support.
config M528x
bool "MCF528x"
depends on !MMU
select GENERIC_CLOCKEVENTS
select HAVE_CACHE_SPLIT
select HAVE_IPSBAR
help
Motorola ColdFire 5280/5282 processor support.
config M5307
bool "MCF5307"
depends on !MMU
select COLDFIRE_SW_A7
select HAVE_CACHE_CB
select HAVE_MBAR
select CPU_NO_EFFICIENT_FFS
help
Motorola ColdFire 5307 processor support.
config M532x
bool "MCF532x"
depends on !MMU
select M53xx
select HAVE_CACHE_CB
help
Freescale (Motorola) ColdFire 532x processor support.
config M537x
bool "MCF537x"
depends on !MMU
select M53xx
select HAVE_CACHE_CB
help
Freescale ColdFire 537x processor support.
config M5407
bool "MCF5407"
depends on !MMU
select COLDFIRE_SW_A7
select HAVE_CACHE_CB
select HAVE_MBAR
select CPU_NO_EFFICIENT_FFS
help
Motorola ColdFire 5407 processor support.
config M547x
bool "MCF547x"
select M54xx
select MMU_COLDFIRE if MMU
select HAVE_CACHE_CB
select HAVE_MBAR
select CPU_NO_EFFICIENT_FFS
help
Freescale ColdFire 5470/5471/5472/5473/5474/5475 processor support.
config M548x
bool "MCF548x"
select MMU_COLDFIRE if MMU
select M54xx
select HAVE_CACHE_CB
select HAVE_MBAR
select CPU_NO_EFFICIENT_FFS
help
Freescale ColdFire 5480/5481/5482/5483/5484/5485 processor support.
config M5441x
bool "MCF5441x"
depends on !MMU
select GENERIC_CLOCKEVENTS
select HAVE_CACHE_CB
help
Freescale Coldfire 54410/54415/54416/54417/54418 processor support.
endchoice
config M527x
bool
config M53xx
bool
config M54xx
bool
endif # COLDFIRE
comment "Processor Specific Options"
config M68KFPU_EMU
bool "Math emulation support"
depends on MMU
help
At some point in the future, this will cause floating-point math
instructions to be emulated by the kernel on machines that lack a
floating-point math coprocessor. Thrill-seekers and chronically
sleep-deprived psychotic hacker types can say Y now, everyone else
should probably wait a while.
config M68KFPU_EMU_EXTRAPREC
bool "Math emulation extra precision"
depends on M68KFPU_EMU
help
The fpu uses normally a few bit more during calculations for
correct rounding, the emulator can (often) do the same but this
extra calculation can cost quite some time, so you can disable
it here. The emulator will then "only" calculate with a 64 bit
mantissa and round slightly incorrect, what is more than enough
for normal usage.
config M68KFPU_EMU_ONLY
bool "Math emulation only kernel"
depends on M68KFPU_EMU
help
This option prevents any floating-point instructions from being
compiled into the kernel, thereby the kernel doesn't save any
floating point context anymore during task switches, so this
kernel will only be usable on machines without a floating-point
math coprocessor. This makes the kernel a bit faster as no tests
needs to be executed whether a floating-point instruction in the
kernel should be executed or not.
config ADVANCED
bool "Advanced configuration options"
depends on MMU
---help---
This gives you access to some advanced options for the CPU. The
defaults should be fine for most users, but these options may make
it possible for you to improve performance somewhat if you know what
you are doing.
Note that the answer to this question won't directly affect the
kernel: saying N will just cause the configurator to skip all
the questions about these options.
Most users should say N to this question.
config RMW_INSNS
bool "Use read-modify-write instructions"
depends on ADVANCED
---help---
This allows to use certain instructions that work with indivisible
read-modify-write bus cycles. While this is faster than the
workaround of disabling interrupts, it can conflict with DMA
( = direct memory access) on many Amiga systems, and it is also said
to destabilize other machines. It is very likely that this will
cause serious problems on any Amiga or Atari Medusa if set. The only
configuration where it should work are 68030-based Ataris, where it
apparently improves performance. But you've been warned! Unless you
really know what you are doing, say N. Try Y only if you're quite
adventurous.
config SINGLE_MEMORY_CHUNK
bool "Use one physical chunk of memory only" if ADVANCED && !SUN3
depends on MMU
default y if SUN3
select NEED_MULTIPLE_NODES
help
Ignore all but the first contiguous chunk of physical memory for VM
purposes. This will save a few bytes kernel size and may speed up
some operations. Say N if not sure.
config ARCH_DISCONTIGMEM_ENABLE
def_bool MMU && !SINGLE_MEMORY_CHUNK
config 060_WRITETHROUGH
bool "Use write-through caching for 68060 supervisor accesses"
depends on ADVANCED && M68060
---help---
The 68060 generally uses copyback caching of recently accessed data.
Copyback caching means that memory writes will be held in an on-chip
cache and only written back to memory some time later. Saying Y
here will force supervisor (kernel) accesses to use writethrough
caching. Writethrough caching means that data is written to memory
straight away, so that cache and memory data always agree.
Writethrough caching is less efficient, but is needed for some
drivers on 68060 based systems where the 68060 bus snooping signal
is hardwired on. The 53c710 SCSI driver is known to suffer from
this problem.
config M68K_L2_CACHE
bool
depends on MAC
default y
config NODES_SHIFT
int
default "3"
depends on !SINGLE_MEMORY_CHUNK
config CPU_HAS_NO_BITFIELDS
bool
config CPU_HAS_NO_MULDIV64
bool
config CPU_HAS_NO_UNALIGNED
bool
config CPU_HAS_ADDRESS_SPACES
bool
config FPU
bool
config COLDFIRE_SW_A7
bool
config HAVE_CACHE_SPLIT
bool
config HAVE_CACHE_CB
bool
config HAVE_MBAR
bool
config HAVE_IPSBAR
bool
config CLOCK_FREQ
int "Set the core clock frequency"
default "25000000" if M5206
default "54000000" if M5206e
default "166666666" if M520x
default "140000000" if M5249
default "150000000" if M527x || M523x
default "90000000" if M5307
default "50000000" if M5407
default "266000000" if M54xx
default "66666666"
depends on COLDFIRE
help
Define the CPU clock frequency in use. This is the core clock
frequency, it may or may not be the same as the external clock
crystal fitted to your board. Some processors have an internal
PLL and can have their frequency programmed at run time, others
use internal dividers. In general the kernel won't setup a PLL
if it is fitted (there are some exceptions). This value will be
specific to the exact CPU that you are using.
config OLDMASK
bool "Old mask 5307 (1H55J) silicon"
depends on M5307
help
Build support for the older revision ColdFire 5307 silicon.
Specifically this is the 1H55J mask revision.
if HAVE_CACHE_SPLIT
choice
prompt "Split Cache Configuration"
default CACHE_I
config CACHE_I
bool "Instruction"
help
Use all of the ColdFire CPU cache memory as an instruction cache.
config CACHE_D
bool "Data"
help
Use all of the ColdFire CPU cache memory as a data cache.
config CACHE_BOTH
bool "Both"
help
Split the ColdFire CPU cache, and use half as an instruction cache
and half as a data cache.
endchoice
endif
if HAVE_CACHE_CB
choice
prompt "Data cache mode"
default CACHE_WRITETHRU
config CACHE_WRITETHRU
bool "Write-through"
help
The ColdFire CPU cache is set into Write-through mode.
config CACHE_COPYBACK
bool "Copy-back"
help
The ColdFire CPU cache is set into Copy-back mode.
endchoice
endif
View Git Blame Copy Permalink