This is the mail archive of the gcc-patches@gcc.gnu.org mailing list for the GCC project.

Index Nav:	[Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav:	[Date Prev] [Date Next]	[Thread Prev] [Thread Next]
Other format:	[Raw text]

Re: [PATCH] rs6000: Add a builtin to read the time base register on PowerPC

From: Segher Boessenkool <segher at kernel dot crashing dot org>
To: Hans-Peter Nilsson <hp at bitrange dot com>
Cc: Tulio Magno Quites Machado Filho <tuliom at linux dot vnet dot ibm dot com>, gcc-patches at gcc dot gnu dot org, dje dot gcc at gmail dot com, meissner at gcc dot gnu dot org
Date: Wed, 29 Aug 2012 21:02:14 +0200
Subject: Re: [PATCH] rs6000: Add a builtin to read the time base register on PowerPC
References: <1346248585-10972-1-git-send-email-tuliom@linux.vnet.ibm.com> <9E0E3467-1111-4514-90D8-5CC994DD6ADA@kernel.crashing.org> <alpine.BSF.2.00.1208291347460.78697@dair.pair.com>

On some systems the timebase runs at a rather low frequency, say 20MHz. This test will spuriously fail there. Waste a million CPU cycles before reading TB the second time?
Waste said million cycles portably by calling sched_yield()?
(Available only on POSIX systems. :)

I was thinking more along the lines of

	int j;
	for (j = 0; j < 1000000; j++)
		asm("" : : "r"(j));

which is more portable (and a lot more predictable).

Segher

References:
- [PATCH] rs6000: Add a builtin to read the time base register on PowerPC
  - From: Tulio Magno Quites Machado Filho
- Re: [PATCH] rs6000: Add a builtin to read the time base register on PowerPC
  - From: Segher Boessenkool
- Re: [PATCH] rs6000: Add a builtin to read the time base register on PowerPC
  - From: Hans-Peter Nilsson

Index Nav:	[Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav:	[Date Prev] [Date Next]	[Thread Prev] [Thread Next]