public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
To: linux-kernel@vger.kernel.org, linux-arch@vger.kernel.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	Juri Lelli <juri.lelli@gmail.com>, Ingo Molnar <mingo@kernel.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	Peter Zijlstra <a.p.zijlstra@chello.nl>
Subject: [RFC][PATCH 2/3] math128: Introduce {mult,add,cmp}_u128
Date: Tue, 24 Apr 2012 18:10:41 +0200	[thread overview]
Message-ID: <20120424162224.526249106@chello.nl> (raw)
In-Reply-To: 20120424161039.293018424@chello.nl

[-- Attachment #1: math128.patch --]
[-- Type: text/plain, Size: 7794 bytes --]

Grow rudimentary u128 support without relying on gcc/libgcc.

Cc: Ingo Molnar <mingo@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
 arch/alpha/include/asm/math128.h      |    4 ++
 arch/arm/include/asm/math128.h        |    4 ++
 arch/avr32/include/asm/math128.h      |    4 ++
 arch/blackfin/include/asm/math128.h   |    4 ++
 arch/c6x/include/asm/math128.h        |    4 ++
 arch/cris/include/asm/math128.h       |    4 ++
 arch/frv/include/asm/math128.h        |    4 ++
 arch/h8300/include/asm/math128.h      |    4 ++
 arch/hexagon/include/asm/math128.h    |    4 ++
 arch/ia64/include/asm/math128.h       |    4 ++
 arch/m32r/include/asm/math128.h       |    4 ++
 arch/m68k/include/asm/math128.h       |    4 ++
 arch/microblaze/include/asm/math128.h |    4 ++
 arch/mips/include/asm/math128.h       |    4 ++
 arch/mn10300/include/asm/math128.h    |    4 ++
 arch/openrisc/include/asm/math128.h   |    4 ++
 arch/parisc/include/asm/math128.h     |    4 ++
 arch/powerpc/include/asm/math128.h    |    4 ++
 arch/s390/include/asm/math128.h       |    4 ++
 arch/score/include/asm/math128.h      |    4 ++
 arch/sh/include/asm/math128.h         |    4 ++
 arch/sparc/include/asm/math128.h      |    4 ++
 arch/tile/include/asm/math128.h       |    4 ++
 arch/um/include/asm/math128.h         |    4 ++
 arch/unicore32/include/asm/math128.h  |    4 ++
 arch/x86/include/asm/math128.h        |    4 ++
 arch/xtensa/include/asm/math128.h     |    4 ++
 include/linux/math128.h               |   47 ++++++++++++++++++++++++++++++++++
 lib/Makefile                          |    2 -
 lib/math128.c                         |   42 ++++++++++++++++++++++++++++++
 30 files changed, 198 insertions(+), 1 deletion(-)

--- /dev/null
+++ b/arch/alpha/include/asm/math128.h
@@ -0,0 +1,4 @@
+#ifndef _ASM_MATH128_H
+#define _ASM_MATH128_H
+
+#endif /* _ASM_MATH128_H */
--- /dev/null
+++ b/arch/arm/include/asm/math128.h
@@ -0,0 +1,4 @@
+#ifndef _ASM_MATH128_H
+#define _ASM_MATH128_H
+
+#endif /* _ASM_MATH128_H */
--- /dev/null
+++ b/arch/avr32/include/asm/math128.h
@@ -0,0 +1,4 @@
+#ifndef _ASM_MATH128_H
+#define _ASM_MATH128_H
+
+#endif /* _ASM_MATH128_H */
--- /dev/null
+++ b/arch/blackfin/include/asm/math128.h
@@ -0,0 +1,4 @@
+#ifndef _ASM_MATH128_H
+#define _ASM_MATH128_H
+
+#endif /* _ASM_MATH128_H */
--- /dev/null
+++ b/arch/c6x/include/asm/math128.h
@@ -0,0 +1,4 @@
+#ifndef _ASM_MATH128_H
+#define _ASM_MATH128_H
+
+#endif /* _ASM_MATH128_H */
--- /dev/null
+++ b/arch/cris/include/asm/math128.h
@@ -0,0 +1,4 @@
+#ifndef _ASM_MATH128_H
+#define _ASM_MATH128_H
+
+#endif /* _ASM_MATH128_H */
--- /dev/null
+++ b/arch/frv/include/asm/math128.h
@@ -0,0 +1,4 @@
+#ifndef _ASM_MATH128_H
+#define _ASM_MATH128_H
+
+#endif /* _ASM_MATH128_H */
--- /dev/null
+++ b/arch/h8300/include/asm/math128.h
@@ -0,0 +1,4 @@
+#ifndef _ASM_MATH128_H
+#define _ASM_MATH128_H
+
+#endif /* _ASM_MATH128_H */
--- /dev/null
+++ b/arch/hexagon/include/asm/math128.h
@@ -0,0 +1,4 @@
+#ifndef _ASM_MATH128_H
+#define _ASM_MATH128_H
+
+#endif /* _ASM_MATH128_H */
--- /dev/null
+++ b/arch/ia64/include/asm/math128.h
@@ -0,0 +1,4 @@
+#ifndef _ASM_MATH128_H
+#define _ASM_MATH128_H
+
+#endif /* _ASM_MATH128_H */
--- /dev/null
+++ b/arch/m32r/include/asm/math128.h
@@ -0,0 +1,4 @@
+#ifndef _ASM_MATH128_H
+#define _ASM_MATH128_H
+
+#endif /* _ASM_MATH128_H */
--- /dev/null
+++ b/arch/m68k/include/asm/math128.h
@@ -0,0 +1,4 @@
+#ifndef _ASM_MATH128_H
+#define _ASM_MATH128_H
+
+#endif /* _ASM_MATH128_H */
--- /dev/null
+++ b/arch/microblaze/include/asm/math128.h
@@ -0,0 +1,4 @@
+#ifndef _ASM_MATH128_H
+#define _ASM_MATH128_H
+
+#endif /* _ASM_MATH128_H */
--- /dev/null
+++ b/arch/mips/include/asm/math128.h
@@ -0,0 +1,4 @@
+#ifndef _ASM_MATH128_H
+#define _ASM_MATH128_H
+
+#endif /* _ASM_MATH128_H */
--- /dev/null
+++ b/arch/mn10300/include/asm/math128.h
@@ -0,0 +1,4 @@
+#ifndef _ASM_MATH128_H
+#define _ASM_MATH128_H
+
+#endif /* _ASM_MATH128_H */
--- /dev/null
+++ b/arch/openrisc/include/asm/math128.h
@@ -0,0 +1,4 @@
+#ifndef _ASM_MATH128_H
+#define _ASM_MATH128_H
+
+#endif /* _ASM_MATH128_H */
--- /dev/null
+++ b/arch/parisc/include/asm/math128.h
@@ -0,0 +1,4 @@
+#ifndef _ASM_MATH128_H
+#define _ASM_MATH128_H
+
+#endif /* _ASM_MATH128_H */
--- /dev/null
+++ b/arch/powerpc/include/asm/math128.h
@@ -0,0 +1,4 @@
+#ifndef _ASM_MATH128_H
+#define _ASM_MATH128_H
+
+#endif /* _ASM_MATH128_H */
--- /dev/null
+++ b/arch/s390/include/asm/math128.h
@@ -0,0 +1,4 @@
+#ifndef _ASM_MATH128_H
+#define _ASM_MATH128_H
+
+#endif /* _ASM_MATH128_H */
--- /dev/null
+++ b/arch/score/include/asm/math128.h
@@ -0,0 +1,4 @@
+#ifndef _ASM_MATH128_H
+#define _ASM_MATH128_H
+
+#endif /* _ASM_MATH128_H */
--- /dev/null
+++ b/arch/sh/include/asm/math128.h
@@ -0,0 +1,4 @@
+#ifndef _ASM_MATH128_H
+#define _ASM_MATH128_H
+
+#endif /* _ASM_MATH128_H */
--- /dev/null
+++ b/arch/sparc/include/asm/math128.h
@@ -0,0 +1,4 @@
+#ifndef _ASM_MATH128_H
+#define _ASM_MATH128_H
+
+#endif /* _ASM_MATH128_H */
--- /dev/null
+++ b/arch/tile/include/asm/math128.h
@@ -0,0 +1,4 @@
+#ifndef _ASM_MATH128_H
+#define _ASM_MATH128_H
+
+#endif /* _ASM_MATH128_H */
--- /dev/null
+++ b/arch/um/include/asm/math128.h
@@ -0,0 +1,4 @@
+#ifndef _ASM_MATH128_H
+#define _ASM_MATH128_H
+
+#endif /* _ASM_MATH128_H */
--- /dev/null
+++ b/arch/unicore32/include/asm/math128.h
@@ -0,0 +1,4 @@
+#ifndef _ASM_MATH128_H
+#define _ASM_MATH128_H
+
+#endif /* _ASM_MATH128_H */
--- /dev/null
+++ b/arch/x86/include/asm/math128.h
@@ -0,0 +1,4 @@
+#ifndef _ASM_MATH128_H
+#define _ASM_MATH128_H
+
+#endif /* _ASM_MATH128_H */
--- /dev/null
+++ b/arch/xtensa/include/asm/math128.h
@@ -0,0 +1,4 @@
+#ifndef _ASM_MATH128_H
+#define _ASM_MATH128_H
+
+#endif /* _ASM_MATH128_H */
--- /dev/null
+++ b/include/linux/math128.h
@@ -0,0 +1,47 @@
+#ifndef _LINUX_MATH128_H
+#define _LINUX_MATH128_H
+
+#include <linux/types.h>
+
+typedef struct {
+	u64 hi, lo;
+} u128;
+
+#include <asm/math128.h>
+
+#ifndef add_u128
+static inline u128 add_u128(u128 a, u128 b)
+{
+	u128 res;
+
+	res.hi = a.hi + b.hi;
+	res.lo = a.lo + b.lo;
+
+	if (res.lo < a.lo || res.lo < b.lo)
+		res.hi++;
+
+	return res;
+}
+#endif /* add_u128 */
+
+#ifndef mult_u128
+extern int u128 mult_u128(u64 a, u64 b);
+#endif
+
+#ifndef cmp_u128
+static inline int cmp_u128(u128 a, u128 b)
+{
+	if (a.hi > b.hi)
+		return 1;
+	if (a.hi < b.hi)
+		return -1;
+	if (a.lo > b.lo)
+		return 1;
+	if (a.lo < b.lo)
+		return -1;
+
+	return 0;
+}
+#endif /* cmp_u128 */
+
+#endif /* _LINUX_MATH128_H */
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -12,7 +12,7 @@ lib-y := ctype.o string.o vsprintf.o cmd
 	 idr.o int_sqrt.o extable.o prio_tree.o \
 	 sha1.o md5.o irq_regs.o reciprocal_div.o argv_split.o \
 	 proportions.o prio_heap.o ratelimit.o show_mem.o \
-	 is_single_threaded.o plist.o decompress.o
+	 is_single_threaded.o plist.o decompress.o math128.o
 
 lib-$(CONFIG_MMU) += ioremap.o
 lib-$(CONFIG_SMP) += cpumask.o
--- /dev/null
+++ b/lib/math128.c
@@ -0,0 +1,42 @@
+#include <linux/math128.h>
+
+#ifndef mult_u128
+/*
+ * a * b = (ah * 2^32 + al) * (bh * 2^32 + bl) =
+ *   ah*bh * 2^64 + (ah*bl + bh*al) * 2^32 + al*bl
+ */
+u128 mult_u128(u64 a, u64 b)
+{
+	u128 res;
+	u64 ah, al;
+	u64 bh, bl;
+	u128 t1, t2, t3, t4;
+
+	ah = a >> 32;
+	al = a & ((1ULL << 32) - 1);
+
+	bh = b >> 32;
+	bl = b & ((1ULL << 32) - 1);
+
+	t1.lo = 0;
+	t1.hi = ah * bh;
+
+	t2.lo = ah * bl;
+	t2.hi = t2.lo >> 32;
+	t2.lo <<= 32;
+
+	t3.lo = al * bh;
+	t3.hi = t3.lo >> 32;
+	t3.lo <<= 32;
+
+	t4.lo = al * bl;
+	t4.hi = 0;
+
+	res = add_u128(t1, t2);
+	res = add_u128(res, t3);
+	res = add_u128(res, t4);
+
+	return res;
+}
+#endif /* mult_u128 */
+



  parent reply	other threads:[~2012-04-24 16:25 UTC|newest]

Thread overview: 34+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-04-24 16:10 [RFC][PATCH 0/3] gcc work-around and math128 Peter Zijlstra
2012-04-24 16:10 ` [RFC][PATCH 1/3] kernel,sched,time: Clean up gcc work-arounds Peter Zijlstra
2012-04-24 19:39   ` Linus Torvalds
2012-04-25  0:14   ` Stephen Rothwell
2012-04-24 16:10 ` Peter Zijlstra [this message]
2012-04-24 19:37   ` [RFC][PATCH 2/3] math128: Introduce {mult,add,cmp}_u128 Linus Torvalds
2012-04-24 19:43     ` Peter Zijlstra
2012-04-24 20:12     ` Måns Rullgård
2012-04-24 21:54     ` Peter Zijlstra
2012-04-25  0:09       ` H. Peter Anvin
2012-04-25  1:46       ` Linus Torvalds
2012-04-25  8:35         ` Peter Zijlstra
2012-04-25 10:13         ` Peter Zijlstra
2012-04-25  0:23   ` Stephen Rothwell
2012-04-25  8:11     ` Peter Zijlstra
2012-04-25 11:23       ` Geert Uytterhoeven
2012-04-25 11:58         ` Peter Zijlstra
2012-04-25 14:35           ` Geert Uytterhoeven
2012-04-25 15:09             ` Peter Zijlstra
2012-04-24 16:10 ` [RFC][PATCH 3/3] math128, x86_64: Implement {mult,add}_u128 in 64bit asm Peter Zijlstra
2012-04-24 16:34   ` H. Peter Anvin
2012-04-24 16:36     ` Peter Zijlstra
2012-04-24 17:17       ` H. Peter Anvin
2012-04-24 17:19         ` Peter Zijlstra
2012-04-24 17:20           ` H. Peter Anvin
2012-04-24 22:00             ` Peter Zijlstra
2012-04-24 22:03               ` H. Peter Anvin
2012-04-24 17:22 ` [RFC][PATCH 0/3] gcc work-around and math128 H. Peter Anvin
2012-04-24 17:27   ` H. Peter Anvin
2012-04-24 21:15 ` Andy Lutomirski
2012-04-24 21:18   ` Linus Torvalds
2012-04-24 21:32   ` Peter Zijlstra
2012-04-24 21:35     ` Andy Lutomirski
2012-04-24 21:51       ` Peter Zijlstra

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20120424162224.526249106@chello.nl \
    --to=a.p.zijlstra@chello.nl \
    --cc=akpm@linux-foundation.org \
    --cc=juri.lelli@gmail.com \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=tglx@linutronix.de \
    --cc=torvalds@linux-foundation.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox