Re: target/5381: __builtin_ia32_pmulhuw seems unknown to compiler

Re: target/5381: __builtin_ia32_pmulhuw seems unknown to compiler

[rodrigc]

Synopsis: __builtin_ia32_pmulhuw seems unknown to compiler

State-Changed-From-To: open->closed
State-Changed-By: rodrigc
State-Changed-When: Mon Jan 14 18:43:16 2002
State-Changed-Why:
    See:
    http://gcc.gnu.org/ml/gcc-prs/2002-01/msg00543.html

http://gcc.gnu.org/cgi-bin/gnatsweb.pl?cmd=view%20audit-trail&database=gcc&pr=5381

Re: target/5381: __builtin_ia32_pmulhuw seems unknown to compiler

[Richard Henderson]

The following reply was made to PR target/5381; it has been noted by GNATS.

From: Richard Henderson <rth@redhat.com>
To: David.Kastrup@t-online.de
Cc: gcc-gnats@gcc.gnu.org
Subject: Re: target/5381: __builtin_ia32_pmulhuw seems unknown to compiler
Date: Mon, 14 Jan 2002 18:29:54 -0800

 On Mon, Jan 14, 2002 at 08:44:34PM -0000, David.Kastrup@t-online.de wrote:
 > Strangely, while using -mmmx, __builtin_ia32_pmulhuw is unknown to
 > the compiler, while, for example, __builtin_ia32_pmulhw seems known.
 
 Not a bug -- pmulhuw is an SSE instruction, not part of
 the base MMX instruction set.
 
 > Anyhow, as you can see from the generated code, the compiler fails to
 > emit an emmx instruction at the end of the routine, leading to possible
 > floating point errors after return.
 
 Again, not a bug.  The user is responsible for handling emmx.
 
 If the compiler were deciding to emit MMX code on its own, 
 then yes I would agree that it must clean up after itself.
 But this is not the case here.
 
 
 r~

target/5381: __builtin_ia32_pmulhuw seems unknown to compiler

[David.Kastrup]

>Number:         5381
>Category:       target
>Synopsis:       __builtin_ia32_pmulhuw seems unknown to compiler
>Confidential:   no
>Severity:       serious
>Priority:       medium
>Responsible:    unassigned
>State:          open
>Class:          sw-bug
>Submitter-Id:   net
>Arrival-Date:   Mon Jan 14 12:46:02 PST 2002
>Closed-Date:
>Last-Modified:
>Originator:     Myself
>Release:        gcc version 3.1 20020106 (Red Hat Linux Rawhide 3.1-0.17)
>Organization:
>Environment:
Reading specs from /usr/lib/gcc-lib/i386-redhat-linux/3.1/specs
Configured with: ../configure --prefix=/usr --mandir=/usr/share/man --infodir=/usr/share/info --enable-shared --enable-threads=posix --disable-checking --host=i386-redhat-linux --with-system-zlib
Thread model: posix
>Description:
Strangely, while using -mmmx, __builtin_ia32_pmulhuw is unknown to the compiler, while, for example, __builtin_ia32_pmulhw seems known.  Anyhow, as you can see from the generated code, the compiler fails to emit an emmx instruction at the end of the routine, leading to possible floating point errors after return.
>How-To-Repeat:

>Fix:

>Release-Note:
>Audit-Trail:
>Unformatted:
----gnatsweb-attachment----
Content-Type: application/octet-stream; name="test.c"
Content-Transfer-Encoding: base64
Content-Disposition: attachment; filename="test.c"