On Mon, Nov 30, 2009 at 12:10 PM, Steven Bosscher stevenb@gmail.com wrote:
I'll see if I can make the intraprocedural version work again before
Christmass.
Well, it works, but then again it really does not. For example, the
original implementation doesn't even look at the alignment of var.
On Sat, Dec 19, 2009 at 2:48 PM, Steven Bosscher stevenb@gmail.com wrote:
On Mon, Nov 30, 2009 at 12:10 PM, Steven Bosscher stevenb@gmail.com
wrote:
I'll see if I can make the intraprocedural version work again before
Christmass.
Well, it works, but then again it really does not.
On Sat, Dec 19, 2009 at 11:43 PM, Daniel Berlin dber...@dberlin.org wrote:
On Sat, Dec 19, 2009 at 2:48 PM, Steven Bosscher stevenb@gmail.com
wrote:
On Mon, Nov 30, 2009 at 12:10 PM, Steven Bosscher stevenb@gmail.com
wrote:
I'll see if I can make the intraprocedural version work
Steven Bosscher stevenb@gmail.com
Sent by: gcc-ow...@gcc.gnu.org
30/11/2009 09:01
To
Daniel Berlin dber...@dberlin.org
cc
Richard Guenther richard.guent...@gmail.com, Toon Moene
t...@moene.org, gcc mailing list gcc@gcc.gnu.org
Subject
Re: Caused by unknown alignment, was: Re:
Dorit Nuzman wrote:
Steven Bosscher stevenb@gmail.com
On Mon, Nov 30, 2009 at 12:40 AM, Daniel Berlin dber...@dberlin.org
wrote:
This pass may even be on the lno branch or something.
It used to be, at least, see http://gcc.gnu.org/ml/gcc-cvs/2004-08/
msg00470.html
Happy hacking,
On Mon, Nov 30, 2009 at 11:02 AM, Toon Moene t...@moene.org wrote:
Maybe this is more/also relevant:
http://gcc.gnu.org/ml/gcc-patches/2004-11/msg01405.html
dorit
Jeepers creepers - why has this never been included in the trunk (it might
be quite a bit of work to get it going again, and I
Steven Bosscher wrote:
I'll see if I can make the intraprocedural version work again before
Christmass. It shouldn't be that much work, actually. But it's be nice
to have some test cases to demonstrate that the intraprocedural
version would do any good.
That would be very nice !
To help to
Toon Moene wrote:
I wrote:
OK, so it is an alignment issue (with -mtune=barcelona):
.L6:
movups 0(%rbp,%rax), %xmm0
movups (%rbx,%rax), %xmm1
incl%ecx
addps %xmm1, %xmm0
movaps %xmm0, (%r8,%rax)
addq$16, %rax
cmpl
Toon Moene wrote:
Tim Prince wrote:
If you want those, you must request them with -mtune=barcelona.
OK, so it is an alignment issue (with -mtune=barcelona):
.L6:
movups 0(%rbp,%rax), %xmm0
movups (%rbx,%rax), %xmm1
incl%ecx
addps %xmm1, %xmm0
Toon Moene wrote:
This is where IPA could help. I created the following main program:
real a(10), b(10), c(10)
a = 0.
b = 1.
print '(3(1x,z16))', loc(a), loc(b), loc(c)
call sum(a, b, c, 10)
print *, c(5)
end
So the alignment of a, b and c is known
On Sun, Nov 29, 2009 at 7:12 PM, Toon Moene t...@moene.org wrote:
Toon Moene wrote:
This is where IPA could help. I created the following main program:
real a(10), b(10), c(10)
a = 0.
b = 1.
print '(3(1x,z16))', loc(a), loc(b), loc(c)
call sum(a, b, c, 10)
On Sun, Nov 29, 2009 at 3:33 PM, Richard Guenther
richard.guent...@gmail.com wrote:
On Sun, Nov 29, 2009 at 9:18 PM, Daniel Berlin dber...@dberlin.org wrote:
Such a thing already existed a few years ago (IIRC Haifa had something
that Dan picked up and passed on to me). But it never brought any
On Mon, Nov 30, 2009 at 12:40 AM, Daniel Berlin dber...@dberlin.org wrote:
This pass may even be on the lno branch or something.
It used to be, at least, see http://gcc.gnu.org/ml/gcc-cvs/2004-08/msg00470.html
Happy hacking, Toon :-)
Ciao!
Steven
L.S.,
Due to the discussion on register allocation, I went back to a hobby of
mine: Studying the assembly output of the compiler.
For this Fortran subroutine (note: unless otherwise told to the Fortran
front end, reals are 32 bit floating point numbers):
subroutine sum(a, b, c, n)
On Sat, Nov 28, 2009 at 3:21 AM, Toon Moene t...@moene.org wrote:
L.S.,
Due to the discussion on register allocation, I went back to a hobby of
mine: Studying the assembly output of the compiler.
For this Fortran subroutine (note: unless otherwise told to the Fortran
front end, reals are 32
H.J. Lu wrote:
On Sat, Nov 28, 2009 at 3:21 AM, Toon Moene t...@moene.org wrote:
L.S.,
Due to the discussion on register allocation, I went back to a hobby of
mine: Studying the assembly output of the compiler.
For this Fortran subroutine (note: unless otherwise told to the Fortran
front end,
Toon Moene wrote:
H.J. Lu wrote:
On Sat, Nov 28, 2009 at 3:21 AM, Toon Moene t...@moene.org wrote:
L.S.,
Due to the discussion on register allocation, I went back to a hobby of
mine: Studying the assembly output of the compiler.
For this Fortran subroutine (note: unless otherwise told to the
On Sat, Nov 28, 2009 at 4:26 PM, Tim Prince n...@aol.com wrote:
Toon Moene wrote:
H.J. Lu wrote:
On Sat, Nov 28, 2009 at 3:21 AM, Toon Moene t...@moene.org wrote:
L.S.,
Due to the discussion on register allocation, I went back to a hobby of
mine: Studying the assembly output of the
Richard Guenther wrote:
On Sat, Nov 28, 2009 at 4:26 PM, Tim Prince n...@aol.com wrote:
Toon Moene wrote:
H.J. Lu wrote:
On Sat, Nov 28, 2009 at 3:21 AM, Toon Moene t...@moene.org wrote:
L.S.,
Due to the discussion on register allocation, I went back to a hobby of
mine: Studying the
On Sat, Nov 28, 2009 at 5:31 PM, Tim Prince n...@aol.com wrote:
Richard Guenther wrote:
On Sat, Nov 28, 2009 at 4:26 PM, Tim Prince n...@aol.com wrote:
Toon Moene wrote:
H.J. Lu wrote:
On Sat, Nov 28, 2009 at 3:21 AM, Toon Moene t...@moene.org wrote:
L.S.,
Due to the discussion on
Tim Prince wrote:
If you want those, you must request them with -mtune=barcelona.
OK, so it is an alignment issue (with -mtune=barcelona):
.L6:
movups 0(%rbp,%rax), %xmm0
movups (%rbx,%rax), %xmm1
incl%ecx
addps %xmm1, %xmm0
movaps %xmm0,
Toon Moene wrote:
Tim Prince wrote:
If you want those, you must request them with -mtune=barcelona.
OK, so it is an alignment issue (with -mtune=barcelona):
.L6:
movups 0(%rbp,%rax), %xmm0
movups (%rbx,%rax), %xmm1
incl%ecx
addps %xmm1, %xmm0
Toon Moene wrote:
Toon Moene wrote:
Tim Prince wrote:
If you want those, you must request them with -mtune=barcelona.
OK, so it is an alignment issue (with -mtune=barcelona):
.L6:
movups 0(%rbp,%rax), %xmm0
movups (%rbx,%rax), %xmm1
incl%ecx
addps
23 matches
Mail list logo