From mboxrd@z Thu Jan  1 00:00:00 1970
From: erik quanstrom <quanstro@coraid.com>
Date: Tue,  8 Dec 2009 15:00:46 -0500
To: 9fans@9fans.net
Message-ID: <7a13edea51b085e17fc02c0e8d0b6a62@coraid.com>
In-Reply-To: <dd6fe68a0912081135g5f051f33u25af76c81e87dc66@mail.gmail.com>
References: <f75780240912080825y51dda728q283429fa95ab462c@mail.gmail.com>
	<5d1347dfd611729cd82ac5bc0ca79c92@coraid.com>
	<dd6fe68a0912081135g5f051f33u25af76c81e87dc66@mail.gmail.com>
MIME-Version: 1.0
Content-Type: multipart/mixed;
	boundary="upas-auurhpxvnkofctevbmjbzbrhaa"
Subject: Re: [9fans] etherigbe.c using _xinc?
Topicbox-Message-UUID: acb453cc-ead5-11e9-9d60-3106f5b1d025

This is a multi-part message in MIME format.
--upas-auurhpxvnkofctevbmjbzbrhaa
Content-Disposition: inline
Content-Type: text/plain; charset="US-ASCII"
Content-Transfer-Encoding: 7bit

> do you have numbers to back up this claim?
>
> you are claiming that the locked XCHGL
> in tas (pc/l.s) called from lock (port/taslock.c)
> called from incref (port/chan.c) is "much faster"
> than the locked INCL in _xinc (pc/l.s).
> it seems to me that a locked memory bus
> is a locked memory bus.

yes, i do.  xinc on most modern intel is a real
loss.  and a moderate loss on amd.  my atom 330
is an exception.

intel core i7 2.4ghz
loop	0 nsec/call
loopxinc	20 nsec/call
looplock	11 nsec/call

intel 5000 1.6ghz
loop	0 nsec/call
loopxinc	44 nsec/call
looplock	25 nsec/call

intel atom 330 1.6ghz (exception!)
loop	2 nsec/call
loopxinc	14 nsec/call
looplock	22 nsec/call

amd k10 2.0ghz
loop	2 nsec/call
loopxinc	30 nsec/call
looplock	20 nsec/call

intel p4 xeon 3.0ghz

loop	1 nsec/call
loopxinc	76 nsec/call
looplock	42 nsec/call

- erik
--upas-auurhpxvnkofctevbmjbzbrhaa
Content-Disposition: attachment; filename=xinc.s
Content-Type: text/plain; charset="US-ASCII"
Content-Transfer-Encoding: 7bit

TEXT _xinc(SB), 1, $0				/* void _xinc(long*); */
	MOVL	l+0(FP), AX
	LOCK;	INCL 0(AX)
	RET

TEXT _xdec(SB), 1, $0				/* long _xdec(long*); */
	MOVL	l+0(FP), BX
	XORL	AX, AX
	LOCK;	DECL 0(BX)
	JLT	_xdeclt
	JGT	_xdecgt
	RET
_xdecgt:
	INCL	AX
	RET
_xdeclt:
	DECL	AX
	RET

--upas-auurhpxvnkofctevbmjbzbrhaa
Content-Disposition: attachment; filename=timing.c
Content-Type: text/plain; charset="US-ASCII"
Content-Transfer-Encoding: 7bit

#include <u.h>
#include <libc.h>

void	_xinc(uint*);
void	_xdec(uint*);

enum {
	N	= 1<<30,
};

void
loop(void)
{
	uint i;

	for(i = 0; i < N; i++)
		;
}

void
loopxinc(void)
{
	uint i, x;

	for(i = 0; i < N; i++){
		_xinc(&x);
		_xdec(&x);
	}
}

void
looplock(void)
{
	uint i;
	static Lock l;

	for(i = 0; i < N; i++){
		lock(&l);
		unlock(&l);
	}
}

void
timing(char *s, void (*f)(void))
{
	uvlong t[2];

	t[0] = nsec();
	f();
	t[1] = nsec();
	fprint(2, "%s\t%llud nsec/call\n", s, (t[1] - t[0])/(uvlong)N);
}

void
main(void)
{
	nsec();
	timing("loop", loop);
	timing("loopxinc", loopxinc);
	timing("looplock", looplock);
	exits("");
}
--upas-auurhpxvnkofctevbmjbzbrhaa--