Re: [tip:perf/core] bitops: Provide compile timeHWEIGHT{8,16,32,64}

From: Peter Zijlstra
Date: Sat Jan 30 2010 - 11:28:37 EST


On Fri, 2010-01-29 at 14:50 -0800, H. Peter Anvin wrote:

> I would personally say that the Right Way[TM] to do this is to call
> these __constant_hweightX() -- so the name reflects the function -- and
> then have
>
> #define hweight(x) (__builtin_constant_p(x) ? __constant_hweight(x) :
> __arch_hweight(x))

I actually considered that, but since I didn't have a full cross compile
set around I wasn't sure.

The trouble is that asm/bitops.h used to be sufficient for hweightN(),
but with such a scheme we'd need linux/bitops.h.

Anyway, something like the below, I'll try and run it through the cross
compilers I have on monday or something.


---
arch/alpha/include/asm/bitops.h | 14 +++++++-------
arch/sparc/include/asm/bitops_64.h | 8 ++++----
include/asm-generic/bitops/hweight.h | 8 ++++----
include/linux/bitops.h | 33 +++++++++++++++++++--------------
lib/hweight.c | 19 ++++++++++---------
5 files changed, 44 insertions(+), 38 deletions(-)

Index: linux-2.6/arch/alpha/include/asm/bitops.h
===================================================================
--- linux-2.6.orig/arch/alpha/include/asm/bitops.h
+++ linux-2.6/arch/alpha/include/asm/bitops.h
@@ -405,24 +405,24 @@ static inline int fls(int x)

#if defined(CONFIG_ALPHA_EV6) && defined(CONFIG_ALPHA_EV67)
/* Whee. EV67 can calculate it directly. */
-static inline unsigned long hweight64(unsigned long w)
+static inline unsigned long __arch_hweight64(unsigned long w)
{
return __kernel_ctpop(w);
}

-static inline unsigned int hweight32(unsigned int w)
+static inline unsigned int __arch_hweight32(unsigned int w)
{
- return hweight64(w);
+ return __arch_hweight64(w);
}

-static inline unsigned int hweight16(unsigned int w)
+static inline unsigned int __arch_hweight16(unsigned int w)
{
- return hweight64(w & 0xffff);
+ return __arch_hweight64(w & 0xffff);
}

-static inline unsigned int hweight8(unsigned int w)
+static inline unsigned int __arch_hweight8(unsigned int w)
{
- return hweight64(w & 0xff);
+ return __arch_hweight64(w & 0xff);
}
#else
#include <asm-generic/bitops/hweight.h>
Index: linux-2.6/arch/sparc/include/asm/bitops_64.h
===================================================================
--- linux-2.6.orig/arch/sparc/include/asm/bitops_64.h
+++ linux-2.6/arch/sparc/include/asm/bitops_64.h
@@ -44,7 +44,7 @@ extern void change_bit(unsigned long nr,

#ifdef ULTRA_HAS_POPULATION_COUNT

-static inline unsigned int hweight64(unsigned long w)
+static inline unsigned int __arch_hweight64(unsigned long w)
{
unsigned int res;

@@ -52,7 +52,7 @@ static inline unsigned int hweight64(uns
return res;
}

-static inline unsigned int hweight32(unsigned int w)
+static inline unsigned int __arch_hweight32(unsigned int w)
{
unsigned int res;

@@ -60,7 +60,7 @@ static inline unsigned int hweight32(uns
return res;
}

-static inline unsigned int hweight16(unsigned int w)
+static inline unsigned int __arch_hweight16(unsigned int w)
{
unsigned int res;

@@ -68,7 +68,7 @@ static inline unsigned int hweight16(uns
return res;
}

-static inline unsigned int hweight8(unsigned int w)
+static inline unsigned int __arch_hweight8(unsigned int w)
{
unsigned int res;

Index: linux-2.6/include/asm-generic/bitops/hweight.h
===================================================================
--- linux-2.6.orig/include/asm-generic/bitops/hweight.h
+++ linux-2.6/include/asm-generic/bitops/hweight.h
@@ -3,9 +3,9 @@

#include <asm/types.h>

-extern unsigned int hweight32(unsigned int w);
-extern unsigned int hweight16(unsigned int w);
-extern unsigned int hweight8(unsigned int w);
-extern unsigned long hweight64(__u64 w);
+extern unsigned int __arch_hweight32(unsigned int w);
+extern unsigned int __arch_hweight16(unsigned int w);
+extern unsigned int __arch_hweight8(unsigned int w);
+extern unsigned long __arch_hweight64(__u64 w);

#endif /* _ASM_GENERIC_BITOPS_HWEIGHT_H_ */
Index: linux-2.6/include/linux/bitops.h
===================================================================
--- linux-2.6.orig/include/linux/bitops.h
+++ linux-2.6/include/linux/bitops.h
@@ -40,16 +40,7 @@ static __inline__ int get_count_order(un
return order;
}

-static inline unsigned long hweight_long(unsigned long w)
-{
- return sizeof(w) == 4 ? hweight32(w) : hweight64(w);
-}
-
-/*
- * Clearly slow versions of the hweightN() functions, their benefit is
- * of course compile time evaluation of constant arguments.
- */
-#define HWEIGHT8(w) \
+#define __const_hweight8(w) \
( BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + \
(!!((w) & (1ULL << 0))) + \
(!!((w) & (1ULL << 1))) + \
@@ -60,15 +51,29 @@ static inline unsigned long hweight_long
(!!((w) & (1ULL << 6))) + \
(!!((w) & (1ULL << 7))) )

-#define HWEIGHT16(w) (HWEIGHT8(w) + HWEIGHT8((w) >> 8))
-#define HWEIGHT32(w) (HWEIGHT16(w) + HWEIGHT16((w) >> 16))
-#define HWEIGHT64(w) (HWEIGHT32(w) + HWEIGHT32((w) >> 32))
+#define __const_hweight16(w) (__const_hweight8(w) + __const_hweight8((w) >> 8))
+#define __const_hweight32(w) (__const_hweight16(w) + __const_hweight16((w) >> 16))
+#define __const_hweight64(w) (__const_hweight32(w) + __const_hweight32((w) >> 32))
+
+#define hweight8(w) \
+ (__builtin_constant_p(w) ? __const_hweight8(w) : __arch_hweight8(w))
+#define hweight16(w) \
+ (__builtin_constant_p(w) ? __const_hweight16(w) : __arch_hweight16(w))
+#define hweight32(w) \
+ (__builtin_constant_p(w) ? __const_hweight32(w) : __arch_hweight32(w))
+#define hweight64(w) \
+ (__builtin_constant_p(w) ? __const_hweight64(w) : __arch_hweight64(w))

/*
* Type invariant version that simply casts things to the
* largest type.
*/
-#define HWEIGHT(w) HWEIGHT64((u64)(w))
+#define HWEIGHT(w) __const_hweight64((u64)(w))
+
+static inline unsigned long hweight_long(unsigned long w)
+{
+ return sizeof(w) == 4 ? hweight32(w) : hweight64(w);
+}

/**
* rol32 - rotate a 32-bit value left
Index: linux-2.6/lib/hweight.c
===================================================================
--- linux-2.6.orig/lib/hweight.c
+++ linux-2.6/lib/hweight.c
@@ -9,7 +9,7 @@
* The Hamming Weight of a number is the total number of bits set in it.
*/

-unsigned int hweight32(unsigned int w)
+unsigned int __arhc_hweight32(unsigned int w)
{
#ifdef ARCH_HAS_FAST_MULTIPLIER
w -= (w >> 1) & 0x55555555;
@@ -24,29 +24,30 @@ unsigned int hweight32(unsigned int w)
return (res + (res >> 16)) & 0x000000FF;
#endif
}
-EXPORT_SYMBOL(hweight32);
+EXPORT_SYMBOL(__arch_hweight32);

-unsigned int hweight16(unsigned int w)
+unsigned int __arch_hweight16(unsigned int w)
{
unsigned int res = w - ((w >> 1) & 0x5555);
res = (res & 0x3333) + ((res >> 2) & 0x3333);
res = (res + (res >> 4)) & 0x0F0F;
return (res + (res >> 8)) & 0x00FF;
}
-EXPORT_SYMBOL(hweight16);
+EXPORT_SYMBOL(__arch_hweight16);

-unsigned int hweight8(unsigned int w)
+unsigned int __arch_hweight8(unsigned int w)
{
unsigned int res = w - ((w >> 1) & 0x55);
res = (res & 0x33) + ((res >> 2) & 0x33);
return (res + (res >> 4)) & 0x0F;
}
-EXPORT_SYMBOL(hweight8);
+EXPORT_SYMBOL(__arch_hweight8);

-unsigned long hweight64(__u64 w)
+unsigned long __arch_hweight64(__u64 w)
{
#if BITS_PER_LONG == 32
- return hweight32((unsigned int)(w >> 32)) + hweight32((unsigned int)w);
+ return __arch_hweight32((unsigned int)(w >> 32)) +
+ __arch_hweight32((unsigned int)w);
#elif BITS_PER_LONG == 64
#ifdef ARCH_HAS_FAST_MULTIPLIER
w -= (w >> 1) & 0x5555555555555555ul;
@@ -63,4 +64,4 @@ unsigned long hweight64(__u64 w)
#endif
#endif
}
-EXPORT_SYMBOL(hweight64);
+EXPORT_SYMBOL(__arch_hweight64);


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/