Re: SMS in gcc4.0

2005-06-02 Thread Mostafa Hagog
[EMAIL PROTECTED] wrote on 02/06/2005 04:29:17: > Steven Bosscher <[EMAIL PROTECTED]>: > > > On Wednesday 01 June 2005 16:43, Canqun Yang wrote: > > > Hi, all > > > > > > I've taken a look on modulo-sched.c recently, and found > > > that both new_cycles and orig_cycles are imprecise. The > > >

Re: SMS in gcc4.0

2005-06-02 Thread Steven Bosscher
On Jun 02, 2005 03:09 PM, Mostafa Hagog <[EMAIL PROTECTED]> wrote: > As to the subtraction for IA-64; I expect that the gen_sub2_insn handles > the subtraction correctly and generate the required RTL to do the > subtraction according to the machine description. But that expectation is incorrect.

Re: SMS in gcc4.0

2005-06-02 Thread Mostafa Hagog
Steven Bosscher <[EMAIL PROTECTED]> wrote on 01/06/2005 17:35:20: > On Wednesday 01 June 2005 16:43, Canqun Yang wrote: > > > 3) The counted loop register 'ar.lc' of IA-64 can not be > > updated directly. Another temporary register is needed > > to evaluate the value of the actural loop coun

Re: SMS in gcc4.0

2005-06-01 Thread Canqun Yang
Canqun Yang <[EMAIL PROTECTED]>: > Steven Bosscher <[EMAIL PROTECTED]>: > > > On Wednesday 01 June 2005 16:43, Canqun Yang wrote: > > > Hi, all > > > > > > I've taken a look on modulo-sched.c recently, and > found > > > that both new_cycles and orig_cycles are > imprecise. The > > > reason is that

Re: SMS in gcc4.0

2005-06-01 Thread Canqun Yang
Steven Bosscher <[EMAIL PROTECTED]>: > On Wednesday 01 June 2005 16:43, Canqun Yang wrote: > > Hi, all > > > > I've taken a look on modulo-sched.c recently, and found > > that both new_cycles and orig_cycles are imprecise. The > > reason is that kernel_number_of_cycles does not take the > > dat

Re: SMS in gcc4.0

2005-06-01 Thread Steven Bosscher
On Wednesday 01 June 2005 16:43, Canqun Yang wrote: > Hi, all > > I've taken a look on modulo-sched.c recently, and found > that both new_cycles and orig_cycles are imprecise. The > reason is that kernel_number_of_cycles does not take the > data dependences of insns into account as the DFA > schedu

Re: SMS in gcc4.0

2005-06-01 Thread Canqun Yang
Hi, all I've taken a look on modulo-sched.c recently, and found that both new_cycles and orig_cycles are imprecise. The reason is that kernel_number_of_cycles does not take the data dependences of insns into account as the DFA scheduler does in haifa-sched.c. On IA-64, three improvements are ne

Re: SMS in gcc4.0

2005-05-09 Thread Mostafa Hagog
Steven Bosscher <[EMAIL PROTECTED]> wrote on 22/04/2005 09:39:09: > > Thanks! > For the record, this refers to a patch I sent to Mostafa and Canqun to > do what Mostafa suggested last month to make SMS work for ia64, see > http://gcc.gnu.org/ml/gcc-patches/2005-03/msg02848.html. I have teste

Re: SMS in gcc4.0

2005-04-21 Thread Steven Bosscher
On Friday 22 April 2005 04:43, Canqun Yang wrote: > Steven Bosscher <[EMAIL PROTECTED]>: > > On Thursday 21 April 2005 17:37, Mostafa Hagog wrote: > > > The other thing is to analyze this problem more > > deeply but I don't have > > > > IA64. > > > > ...and I don't care enough about it. Canqun? >

Re: SMS in gcc4.0

2005-04-21 Thread Canqun Yang
Steven Bosscher <[EMAIL PROTECTED]>: > On Thursday 21 April 2005 17:37, Mostafa Hagog wrote: > > The other thing is to analyze this problem more deeply but I don't have > > IA64. > ...and I don't care enough about it. Canqun? > > Gr. > Steven > > Ok, I'll try this. Canqun Yang Creative Compil

RE: SMS in gcc4.0

2005-03-31 Thread Mostafa Hagog
Steven Bosscher <[EMAIL PROTECTED]> wrote on 31/03/2005 16:55:52: > On Mar 31, 2005 03:56 PM, Canqun Yang <[EMAIL PROTECTED]> wrote: > > > This patch will fix doloop_register_get defined in > > modulo-sched.c, and let the program of PI caculation > > on IA-64 be successfully modulo scheduled.

RE: SMS in gcc4.0

2005-03-31 Thread Steven Bosscher
On Mar 31, 2005 03:56 PM, Canqun Yang <[EMAIL PROTECTED]> wrote: > This patch will fix doloop_register_get defined in > modulo-sched.c, and let the program of PI caculation > on IA-64 be successfully modulo scheduled. On 1GHz > Itanium-2, it costs just 3.128 seconds to execute when > compiled

RE: SMS in gcc4.0

2005-03-31 Thread Steven Bosscher
On Mar 31, 2005 03:56 PM, Canqun Yang <[EMAIL PROTECTED]> wrote: > This patch will fix doloop_register_get defined in > modulo-sched.c, and let the program of PI caculation > on IA-64 be successfully modulo scheduled. On 1GHz > Itanium-2, it costs just 3.128 seconds to execute when > compiled

RE: SMS in gcc4.0

2005-03-31 Thread Canqun Yang
Hi, all This patch will fix doloop_register_get defined in modulo-sched.c, and let the program of PI caculation on IA-64 be successfully modulo scheduled. On 1GHz Itanium-2, it costs just 3.128 seconds to execute when compiled with "-fmodulo-shced -O3" turned on, while 5.454 seconds whithout

RE: SMS in gcc4.0

2005-03-31 Thread Mostafa Hagog
Hi Mark, First of all I would like this discussion to be on the GCC mailing list; so I am CCing the GCC mailing list (I hope this is OK with all the others). "Davis, Mark" <[EMAIL PROTECTED]> wrote on 31/03/2005 00:23:02: > Mostafa & Gerald, > ... > It was mentioned that you folks had recentl