[Bug target/38201] New: -mfma/-mavx and -msse5/-msse4a don't work together

[Bug target/38201] New: -mfma/-mavx and -msse5/-msse4a don't work together

[hjl dot tools at gmail dot com]

Both Intel FMA and AMD SSE5 support FMA. For -mfma, which enables
Intel FMA and is a dummy at the moment, or -msse5, we will
generate FMA instructions for

double f;

void
foo (double x, double y, double z)
{
  f = x * y + z;
}

What FMA should "-mfma -msse5" generate? Also currently, with
"-O2 -mavx -msse5", we generate

foo:
        fmaddsd %xmm2, %xmm1, %xmm0, %xmm0
        vmovsd  %xmm0, f(%rip)
        ret

which won't run on any machines. For "-mfma -msse5" and
"-mavx -msse5",

1. Should these combinations be allowed? If allowed,
2. Should the last option turn off the first one?


-- 
           Summary: -mfma/-mavx and -msse5/-msse4a don't work together
           Product: gcc
           Version: 4.4.0
            Status: UNCONFIRMED
          Severity: major
          Priority: P3
         Component: target
        AssignedTo: unassigned at gcc dot gnu dot org
        ReportedBy: hjl dot tools at gmail dot com


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=38201

[Bug target/38201] -mfma/-mavx and -msse5/-msse4a don't work together

[dwarak dot rajagopal at amd dot com]

------- Comment #1 from dwarak dot rajagopal at amd dot com  2008-11-20 16:48 -------
1) -msse5 includes -mfma switch (because fma is a part of sse5 instructions).
So having "-msse5 -mfma" is same as having just "msse5", though you can just
have -fma (without -msse5).

2) "-mavx -msse5" => Yes. This would not make sense since no machine can run
this.

- Dwarak


(In reply to comment #0)
> Both Intel FMA and AMD SSE5 support FMA. For -mfma, which enables
> Intel FMA and is a dummy at the moment, or -msse5, we will
> generate FMA instructions for
> 
> double f;
> 
> void
> foo (double x, double y, double z)
> {
>   f = x * y + z;
> }
> 
> What FMA should "-mfma -msse5" generate? Also currently, with
> "-O2 -mavx -msse5", we generate
> 
> foo:
>         fmaddsd %xmm2, %xmm1, %xmm0, %xmm0
>         vmovsd  %xmm0, f(%rip)
>         ret
> 
> which won't run on any machines. For "-mfma -msse5" and
> "-mavx -msse5",
> 
> 1. Should these combinations be allowed? If allowed,
> 2. Should the last option turn off the first one?
> 

(In reply to comment #0)
> Both Intel FMA and AMD SSE5 support FMA. For -mfma, which enables
> Intel FMA and is a dummy at the moment, or -msse5, we will
> generate FMA instructions for
> 
> double f;
> 
> void
> foo (double x, double y, double z)
> {
>   f = x * y + z;
> }
> 
> What FMA should "-mfma -msse5" generate? Also currently, with
> "-O2 -mavx -msse5", we generate
> 
> foo:
>         fmaddsd %xmm2, %xmm1, %xmm0, %xmm0
>         vmovsd  %xmm0, f(%rip)
>         ret
> 
> which won't run on any machines. For "-mfma -msse5" and
> "-mavx -msse5",
> 
> 1. Should these combinations be allowed? If allowed,
> 2. Should the last option turn off the first one?
> 


-- 

dwarak dot rajagopal at amd dot com changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
                 CC|                            |dwarak dot rajagopal at amd
                   |                            |dot com


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=38201

[Bug target/38201] -mfma/-mavx and -msse5/-msse4a don't work together

[hjl dot tools at gmail dot com]

------- Comment #2 from hjl dot tools at gmail dot com  2008-11-20 16:57 -------
(In reply to comment #1)
> 1) -msse5 includes -mfma switch (because fma is a part of sse5 instructions).
> So having "-msse5 -mfma" is same as having just "msse5", though you can just
> have -fma (without -msse5).

Please look closely. I added -mfma to i386.opt:

---
mfma
Target Report Mask(ISA_FMA) Var(ix86_isa_flags) VarExists
Support MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, AVX and FMA built-in
functions and code generation
---

It has nothing to with SSE5. SSE5 never implies TARGET_FMA.


-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=38201

[Bug target/38201] -mfma/-mavx and -msse5/-msse4a don't work together

[hjl dot tools at gmail dot com]

------- Comment #3 from hjl dot tools at gmail dot com  2008-11-20 18:52 -------
Since -mfma implies -mavx, we got

[hjl@gnu-26 gcc]$ cat f.c
double f;

void
foo (double x, double y, double z)
{
  f = x * y + z;
}
[hjl@gnu-26 gcc]$ ./xgcc -B./ -O2 -mfma -msse5 f.c -S
-fno-asynchronous-unwind-tables
[hjl@gnu-26 gcc]$ cat f.s
        .file   "f.c"
        .text
        .p2align 4,,15
.globl foo
        .type   foo, @function
foo:
        fmaddsd %xmm2, %xmm1, %xmm0, %xmm0
        vmovsd  %xmm0, f(%rip)
        ret
        .size   foo, .-foo
        .comm   f,8,8
        .ident  "GCC: (GNU) 4.4.0 20081120 (experimental) [trunk revision
142045]"
        .section        .note.GNU-stack,"",@progbits
[hjl@gnu-26 gcc]$ 


-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=38201

[Bug target/38201] -mfma/-mavx and -msse5/-msse4a don't work together

[dwarak dot rajagopal at amd dot com]

------- Comment #4 from dwarak dot rajagopal at amd dot com  2008-11-20 19:35 -------
Yes, you are right. "-mfma -msse5" does not make sense. I mistook -mfma for
-mfused-madd and hence the confusion.

Hence these combinations (1 and 2) does not make sense. 

Thanks,
Dwarak


-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=38201

[Bug target/38201] -mfma/-mavx and -msse5/-msse4a don't work together

[hjl dot tools at gmail dot com]

------- Comment #5 from hjl dot tools at gmail dot com  2008-11-20 19:46 -------
(In reply to comment #4)
> Yes, you are right. "-mfma -msse5" does not make sense. I mistook -mfma for
> -mfused-madd and hence the confusion.
> 
> Hence these combinations (1 and 2) does not make sense. 
> 

Should we disallow such combinations?


-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=38201

[Bug target/38201] -mfma/-mavx and -msse5/-msse4a don't work together

[dwarak dot rajagopal at amd dot com]

------- Comment #6 from dwarak dot rajagopal at amd dot com  2008-11-20 19:49 -------

> Should we disallow such combinations?
> 
Yes.
- Dwarak


-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=38201

[Bug target/38201] -mfma/-mavx and -msse5/-msse4a don't work together

[hjl dot tools at gmail dot com]

------- Comment #7 from hjl dot tools at gmail dot com  2008-11-20 21:29 -------
We have the same issue with -m3dnow, -m3dnowa and -msse4a.


-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=38201

[Bug target/38201] -mfma/-mavx and -msse5/-msse4a don't work together

[Joey dot ye at intel dot com]

------- Comment #8 from Joey dot ye at intel dot com  2008-11-21 12:00 -------
In short, set A={-favx, -ffma}, set B={-f3dnow, -f3dnowa, -fsse4a, -fsse5}. Any
option combination from both sets should be prohibited.

Please add more options into these set in case I missed any.


-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=38201

[Bug target/38201] -mfma/-mavx and -msse5/-msse4a don't work together

[hjl dot tools at gmail dot com]

------- Comment #9 from hjl dot tools at gmail dot com  2008-11-21 13:35 -------
(In reply to comment #8)
> In short, set A={-favx, -ffma}, set B={-f3dnow, -f3dnowa, -fsse4a, -fsse5}. Any

It is -mXXX, not -fXXX.

> option combination from both sets should be prohibited.
> 

That is correct.


-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=38201

[Bug target/38201] -mfma/-mavx and -msse5/-msse4a don't work together

[rguenth at gcc dot gnu dot org]

------- Comment #10 from rguenth at gcc dot gnu dot org  2008-11-22 15:03 -------
We should have -mfma to enable a fused multiply-add instruction that is
available
when enabling either -msse5 or -mavx.  -mfma should not itself enable any
of the instruction set enabling features.

HJ, why did you need -mfma and could not have used -mfused-madd for this?
IMHO -mfma is confusing and should be removed.


-- 

rguenth at gcc dot gnu dot org changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
                 CC|                            |rguenth at gcc dot gnu dot
                   |                            |org


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=38201

[Bug target/38201] -mfma/-mavx and -msse5/-msse4a don't work together

[hjl dot tools at gmail dot com]

------- Comment #11 from hjl dot tools at gmail dot com  2008-11-22 15:09 -------
(In reply to comment #10)
> We should have -mfma to enable a fused multiply-add instruction that is
> available
> when enabling either -msse5 or -mavx.  -mfma should not itself enable any
> of the instruction set enabling features.
> 
> HJ, why did you need -mfma and could not have used -mfused-madd for this?
> IMHO -mfma is confusing and should be removed.
> 

Intel FMA is a separate instruction set with its own feature bit in CPUID.
Using -mfused-madd -mavx to enable an instruction set doesn't look
appropriate to me.


-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=38201

[Bug target/38201] -mfma/-mavx and -msse5/-msse4a don't work together

[hjl dot tools at gmail dot com]

------- Comment #12 from hjl dot tools at gmail dot com  2008-11-22 15:15 -------
Richard asked:

Why should it (-mavx -msse5) be disallowed if a user asks for it?  Do we
disallow -msse4a -mssse4?

Reply:

-msse4a -mssse4 can generate code which runs if you check the feature
bit in CPUID before calling an appropriate function. But -mavx -msse5
will generate codes which won't run on any machines.


-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=38201

[Bug target/38201] -mfma/-mavx and -msse5/-msse4a don't work together

[rguenth at gcc dot gnu dot org]

------- Comment #13 from rguenth at gcc dot gnu dot org  2008-11-22 15:31 -------
I see.


-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=38201

[Bug target/38201] -mfma/-mavx and -msse5/-msse4a don't work together

[pinskia at gcc dot gnu dot org]

------- Comment #14 from pinskia at gcc dot gnu dot org  2008-11-23 18:28 -------
>But -mavx -msse5 will generate codes which won't run on any machines.

It could run on a simulator that has both (or a new processor which has not
come out yet).  Or are there conflicts with the opcodes themselves?  So I don't
see why this is a really a bug.


-- 

pinskia at gcc dot gnu dot org changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
           Severity|major                       |normal
             Status|UNCONFIRMED                 |WAITING


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=38201

[Bug target/38201] -mfma/-mavx and -msse5/-msse4a don't work together

[hjl dot tools at gmail dot com]

------- Comment #15 from hjl dot tools at gmail dot com  2008-12-03 16:50 -------
Simulator is fine. AVX executable can only run on simulator. If
there is a simulator which can run SSE5 and AVX, we will add
a new switch for it.


-- 

hjl dot tools at gmail dot com changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
   Last reconfirmed|0000-00-00 00:00:00         |2008-12-03 16:50:15
               date|                            |


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=38201

[Bug target/38201] -mfma/-mavx and -msse5/-msse4a don't work together

[hjl dot tools at gmail dot com]

------- Comment #16 from hjl dot tools at gmail dot com  2008-12-09 21:58 -------
A patch is posted at

http://gcc.gnu.org/ml/gcc-patches/2008-12/msg00585.html


-- 

hjl dot tools at gmail dot com changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
                URL|                            |http://gcc.gnu.org/ml/gcc-
                   |                            |patches/2008-
                   |                            |12/msg00585.html
             Status|WAITING                     |NEW
     Ever Confirmed|0                           |1
   Last reconfirmed|2008-12-03 16:50:15         |2008-12-09 21:58:04
               date|                            |


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=38201