Re: [PATCH 2/5] bitops: compile time optimization forhweight_long(CONSTANT)
From: Borislav Petkov
Date: Fri Feb 05 2010 - 07:11:32 EST
On Thu, Feb 04, 2010 at 05:04:17PM +0100, Peter Zijlstra wrote:
> No, just don't touch hweight_long(), simply provide
> __arch_hweight{8,16,32,64} and all will be well.
Ok, another day, another version :)
It is, of course, completely untested but it builds and the asm looks
ok. I think I've addressed all concerns so far.
--
arch/x86/include/asm/hweight.h | 14 ++++++++
arch/x86/lib/Makefile | 2 +-
arch/x86/lib/hweight.c | 57 ++++++++++++++++++++++++++++++++++
include/asm-generic/bitops/hweight.h | 45 ++++++++++++++++++++++++--
lib/hweight.c | 16 +++++-----
5 files changed, 121 insertions(+), 13 deletions(-)
create mode 100644 arch/x86/include/asm/hweight.h
create mode 100644 arch/x86/lib/hweight.c
diff --git a/arch/x86/include/asm/hweight.h b/arch/x86/include/asm/hweight.h
new file mode 100644
index 0000000..762125f
--- /dev/null
+++ b/arch/x86/include/asm/hweight.h
@@ -0,0 +1,14 @@
+#ifndef _ASM_X86_HWEIGHT_H
+#define _ASM_X86_HWEIGHT_H
+
+#define __arch_hweight8 __arch_hweight8
+#define __arch_hweight16 __arch_hweight16
+#define __arch_hweight32 __arch_hweight32
+#define __arch_hweight64 __arch_hweight64
+
+extern unsigned int __arch_hweight8(unsigned int);
+extern unsigned int __arch_hweight16(unsigned int);
+extern unsigned int __arch_hweight32(unsigned int);
+extern unsigned long __arch_hweight64(__u64);
+
+#endif /*_ASM_X86_HWEIGHT_H */
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index cffd754..e811bbd 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -22,7 +22,7 @@ lib-y += usercopy_$(BITS).o getuser.o putuser.o
lib-y += memcpy_$(BITS).o
lib-$(CONFIG_KPROBES) += insn.o inat.o
-obj-y += msr.o msr-reg.o msr-reg-export.o
+obj-y += msr.o msr-reg.o msr-reg-export.o hweight.o
ifeq ($(CONFIG_X86_32),y)
obj-y += atomic64_32.o
diff --git a/arch/x86/lib/hweight.c b/arch/x86/lib/hweight.c
new file mode 100644
index 0000000..3cf51c8
--- /dev/null
+++ b/arch/x86/lib/hweight.c
@@ -0,0 +1,57 @@
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/bitops.h>
+
+#define POPCNT32 ".byte 0xf3\n\t.byte 0x0f\n\t.byte 0xb8\n\t.byte 0xff"
+#define POPCNT64 ".byte 0xf3\n\t.byte 0x48\n\t.byte 0x0f\n\t.byte 0xb8\n\t.byte 0xff"
+
+#define __arch_hweight_alt(size) \
+ ALTERNATIVE("call _hweight"#size, POPCNT##size, X86_FEATURE_POPCNT)
+
+unsigned int __arch_hweight16(unsigned int w)
+{
+ unsigned int res = 0;
+
+ asm volatile("xor %%dh, %%dh\n\t"
+ __arch_hweight_alt(32)
+ : "=di" (res)
+ : "di" (w)
+ : "ecx", "memory");
+
+ return res;
+}
+EXPORT_SYMBOL(__arch_hweight16);
+
+unsigned int __arch_hweight8(unsigned int w)
+{
+ return __arch_hweight16(w & 0xff);
+}
+EXPORT_SYMBOL(__arch_hweight8);
+
+unsigned int __arch_hweight32(unsigned int w)
+{
+ unsigned int res = 0;
+
+ asm volatile(__arch_hweight_alt(32)
+ : "=di" (res)
+ : "di" (w)
+ : "ecx", "memory");
+
+ return res;
+
+}
+EXPORT_SYMBOL(__arch_hweight32);
+
+unsigned long __arch_hweight64(__u64 w)
+{
+ unsigned int res = 0;
+
+ asm volatile(__arch_hweight_alt(64)
+ : "=di" (res)
+ : "di" (w)
+ : "rsi", "rcx", "r8", "r9", "r10", "r11",
+ "memory");
+
+ return res;
+}
+EXPORT_SYMBOL(__arch_hweight64);
diff --git a/include/asm-generic/bitops/hweight.h b/include/asm-generic/bitops/hweight.h
index fbbc383..340ad4e 100644
--- a/include/asm-generic/bitops/hweight.h
+++ b/include/asm-generic/bitops/hweight.h
@@ -2,10 +2,47 @@
#define _ASM_GENERIC_BITOPS_HWEIGHT_H_
#include <asm/types.h>
+#include <asm/hweight.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 _hweight32(unsigned int w);
+extern unsigned int _hweight16(unsigned int w);
+extern unsigned int _hweight8(unsigned int w);
+extern unsigned long _hweight64(__u64 w);
+
+static inline unsigned int hweight8(unsigned int w)
+{
+#ifdef __arch_hweight8
+ return __arch_hweight8(w);
+#else
+ return _hweight8(w);
+#endif
+}
+
+static inline unsigned int hweight16(unsigned int w)
+{
+#ifdef __arch_hweight16
+ return __arch_hweight16(w);
+#else
+ return _hweight16(w);
+#endif
+}
+
+static inline unsigned int hweight32(unsigned int w)
+{
+#ifdef __arch_hweight32
+ return __arch_hweight32(w);
+#else
+ return _hweight32(w);
+#endif
+}
+
+static inline unsigned long hweight64(__u64 w)
+{
+#ifdef __arch_hweight64
+ return __arch_hweight64(w);
+#else
+ return _hweight64(w);
+#endif
+}
#endif /* _ASM_GENERIC_BITOPS_HWEIGHT_H_ */
diff --git a/lib/hweight.c b/lib/hweight.c
index 389424e..f7b81a1 100644
--- a/lib/hweight.c
+++ b/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 _hweight32(unsigned int w)
{
unsigned int res = w - ((w >> 1) & 0x55555555);
res = (res & 0x33333333) + ((res >> 2) & 0x33333333);
@@ -17,26 +17,26 @@ unsigned int hweight32(unsigned int w)
res = res + (res >> 8);
return (res + (res >> 16)) & 0x000000FF;
}
-EXPORT_SYMBOL(hweight32);
+EXPORT_SYMBOL(_hweight32);
-unsigned int hweight16(unsigned int w)
+unsigned int _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(_hweight16);
-unsigned int hweight8(unsigned int w)
+unsigned int _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(_hweight8);
-unsigned long hweight64(__u64 w)
+unsigned long _hweight64(__u64 w)
{
#if BITS_PER_LONG == 32
return hweight32((unsigned int)(w >> 32)) + hweight32((unsigned int)w);
@@ -56,4 +56,4 @@ unsigned long hweight64(__u64 w)
#endif
#endif
}
-EXPORT_SYMBOL(hweight64);
+EXPORT_SYMBOL(_hweight64);
--
1.6.4.2
--
Regards/Gruss,
Boris.
-
Advanced Micro Devices, Inc.
Operating Systems Research Center
--
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/