From: HAO CHEN GUI <guihaoc@linux.ibm.com>
To: gcc-patches <gcc-patches@gcc.gnu.org>
Cc: Bill Schmidt <wschmidt@linux.ibm.com>,
Segher Boessenkool <segher@kernel.crashing.org>
Subject: PING^3 [PATCH, rs6000] Disable gimple fold for float or double vec_minmax when fast-math is not set
Date: Mon, 11 Oct 2021 13:26:54 +0800 [thread overview]
Message-ID: <2af3edbc-49b2-cce9-89ea-b5d4a6c1a752@linux.ibm.com> (raw)
In-Reply-To: <3dfeebb7-f854-c709-5a92-4903755e3e9d@linux.ibm.com>
Hi,
Gentle ping this:
https://gcc.gnu.org/pipermail/gcc-patches/2021-August/578162.html
Thanks
On 22/9/2021 下午 2:52, HAO CHEN GUI wrote:
> Hi,
>
> Gentle ping this:
>
> https://gcc.gnu.org/pipermail/gcc-patches/2021-August/578162.html
>
> Thanks
>
>
> On 6/9/2021 下午 2:01, HAO CHEN GUI wrote:
>> Hi,
>>
>> Gentle ping this:
>>
>> https://gcc.gnu.org/pipermail/gcc-patches/2021-August/578162.html
>>
>> Thanks
>>
>> On 26/8/2021 上午 9:19, HAO CHEN GUI wrote:
>>> Hi Bill,
>>>
>>> Thanks for your comments.
>>>
>>> Hi Segher,
>>>
>>> Here is the ChangeLog and patch diff. Thanks.
>>>
>>> 2021-08-25 Haochen Gui <guihaoc@linux.ibm.com>
>>>
>>> gcc/
>>> * config/rs6000/rs6000-call.c (rs6000_gimple_fold_builtin):
>>> Modify the VSX_BUILTIN_XVMINDP, ALTIVEC_BUILTIN_VMINFP,
>>> VSX_BUILTIN_XVMAXDP, ALTIVEC_BUILTIN_VMAXFP expansions.
>>>
>>> gcc/testsuite/
>>> * gcc.target/powerpc/vec-minmax-1.c: New test.
>>> * gcc.target/powerpc/vec-minmax-2.c: Likewise.
>>>
>>> diff --git a/gcc/config/rs6000/rs6000-call.c b/gcc/config/rs6000/rs6000-call.c
>>> index b4e13af4dc6..90527734ceb 100644
>>> --- a/gcc/config/rs6000/rs6000-call.c
>>> +++ b/gcc/config/rs6000/rs6000-call.c
>>> @@ -12159,6 +12159,11 @@ rs6000_gimple_fold_builtin (gimple_stmt_iterator *gsi)
>>> return true;
>>> /* flavors of vec_min. */
>>> case VSX_BUILTIN_XVMINDP:
>>> + case ALTIVEC_BUILTIN_VMINFP:
>>> + if (!flag_finite_math_only || flag_signed_zeros)
>>> + return false;
>>> + /* Fall through to MIN_EXPR. */
>>> + gcc_fallthrough ();
>>> case P8V_BUILTIN_VMINSD:
>>> case P8V_BUILTIN_VMINUD:
>>> case ALTIVEC_BUILTIN_VMINSB:
>>> @@ -12167,7 +12172,6 @@ rs6000_gimple_fold_builtin (gimple_stmt_iterator *gsi)
>>> case ALTIVEC_BUILTIN_VMINUB:
>>> case ALTIVEC_BUILTIN_VMINUH:
>>> case ALTIVEC_BUILTIN_VMINUW:
>>> - case ALTIVEC_BUILTIN_VMINFP:
>>> arg0 = gimple_call_arg (stmt, 0);
>>> arg1 = gimple_call_arg (stmt, 1);
>>> lhs = gimple_call_lhs (stmt);
>>> @@ -12177,6 +12181,11 @@ rs6000_gimple_fold_builtin (gimple_stmt_iterator *gsi)
>>> return true;
>>> /* flavors of vec_max. */
>>> case VSX_BUILTIN_XVMAXDP:
>>> + case ALTIVEC_BUILTIN_VMAXFP:
>>> + if (!flag_finite_math_only || flag_signed_zeros)
>>> + return false;
>>> + /* Fall through to MAX_EXPR. */
>>> + gcc_fallthrough ();
>>> case P8V_BUILTIN_VMAXSD:
>>> case P8V_BUILTIN_VMAXUD:
>>> case ALTIVEC_BUILTIN_VMAXSB:
>>> @@ -12185,7 +12194,6 @@ rs6000_gimple_fold_builtin (gimple_stmt_iterator *gsi)
>>> case ALTIVEC_BUILTIN_VMAXUB:
>>> case ALTIVEC_BUILTIN_VMAXUH:
>>> case ALTIVEC_BUILTIN_VMAXUW:
>>> - case ALTIVEC_BUILTIN_VMAXFP:
>>> arg0 = gimple_call_arg (stmt, 0);
>>> arg1 = gimple_call_arg (stmt, 1);
>>> lhs = gimple_call_lhs (stmt);
>>> diff --git a/gcc/testsuite/gcc.target/powerpc/vec-minmax-1.c b/gcc/testsuite/gcc.target/powerpc/vec-minmax-1.c
>>> new file mode 100644
>>> index 00000000000..547798fd65c
>>> --- /dev/null
>>> +++ b/gcc/testsuite/gcc.target/powerpc/vec-minmax-1.c
>>> @@ -0,0 +1,53 @@
>>> +/* { dg-do compile { target { powerpc*-*-* } } } */
>>> +/* { dg-require-effective-target powerpc_p9vector_ok } */
>>> +/* { dg-options "-O2 -mdejagnu-cpu=power9" } */
>>> +/* { dg-final { scan-assembler-times {\mxvmaxdp\M} 1 } } */
>>> +/* { dg-final { scan-assembler-times {\mxvmaxsp\M} 1 } } */
>>> +/* { dg-final { scan-assembler-times {\mxvmindp\M} 1 } } */
>>> +/* { dg-final { scan-assembler-times {\mxvminsp\M} 1 } } */
>>> +
>>> +/* This test verifies that float or double vec_min/max are bound to
>>> + xv[min|max][d|s]p instructions when fast-math is not set. */
>>> +
>>> +
>>> +#include <altivec.h>
>>> +
>>> +#ifdef _BIG_ENDIAN
>>> + const int PREF_D = 0;
>>> +#else
>>> + const int PREF_D = 1;
>>> +#endif
>>> +
>>> +double vmaxd (double a, double b)
>>> +{
>>> + vector double va = vec_promote (a, PREF_D);
>>> + vector double vb = vec_promote (b, PREF_D);
>>> + return vec_extract (vec_max (va, vb), PREF_D);
>>> +}
>>> +
>>> +double vmind (double a, double b)
>>> +{
>>> + vector double va = vec_promote (a, PREF_D);
>>> + vector double vb = vec_promote (b, PREF_D);
>>> + return vec_extract (vec_min (va, vb), PREF_D);
>>> +}
>>> +
>>> +#ifdef _BIG_ENDIAN
>>> + const int PREF_F = 0;
>>> +#else
>>> + const int PREF_F = 3;
>>> +#endif
>>> +
>>> +float vmaxf (float a, float b)
>>> +{
>>> + vector float va = vec_promote (a, PREF_F);
>>> + vector float vb = vec_promote (b, PREF_F);
>>> + return vec_extract (vec_max (va, vb), PREF_F);
>>> +}
>>> +
>>> +float vminf (float a, float b)
>>> +{
>>> + vector float va = vec_promote (a, PREF_F);
>>> + vector float vb = vec_promote (b, PREF_F);
>>> + return vec_extract (vec_min (va, vb), PREF_F);
>>> +}
>>> diff --git a/gcc/testsuite/gcc.target/powerpc/vec-minmax-2.c b/gcc/testsuite/gcc.target/powerpc/vec-minmax-2.c
>>> new file mode 100644
>>> index 00000000000..4c6f4365830
>>> --- /dev/null
>>> +++ b/gcc/testsuite/gcc.target/powerpc/vec-minmax-2.c
>>> @@ -0,0 +1,51 @@
>>> +/* { dg-do compile { target { powerpc*-*-* } } } */
>>> +/* { dg-require-effective-target powerpc_p9vector_ok } */
>>> +/* { dg-options "-O2 -mdejagnu-cpu=power9 -ffast-math" } */
>>> +/* { dg-final { scan-assembler-times {\mxsmaxcdp\M} 2 } } */
>>> +/* { dg-final { scan-assembler-times {\mxsmincdp\M} 2 } } */
>>> +
>>> +/* This test verifies that float or double vec_min/max can be converted
>>> + to scalar comparison when fast-math is set. */
>>> +
>>> +
>>> +#include <altivec.h>
>>> +
>>> +#ifdef _BIG_ENDIAN
>>> + const int PREF_D = 0;
>>> +#else
>>> + const int PREF_D = 1;
>>> +#endif
>>> +
>>> +double vmaxd (double a, double b)
>>> +{
>>> + vector double va = vec_promote (a, PREF_D);
>>> + vector double vb = vec_promote (b, PREF_D);
>>> + return vec_extract (vec_max (va, vb), PREF_D);
>>> +}
>>> +
>>> +double vmind (double a, double b)
>>> +{
>>> + vector double va = vec_promote (a, PREF_D);
>>> + vector double vb = vec_promote (b, PREF_D);
>>> + return vec_extract (vec_min (va, vb), PREF_D);
>>> +}
>>> +
>>> +#ifdef _BIG_ENDIAN
>>> + const int PREF_F = 0;
>>> +#else
>>> + const int PREF_F = 3;
>>> +#endif
>>> +
>>> +float vmaxf (float a, float b)
>>> +{
>>> + vector float va = vec_promote (a, PREF_F);
>>> + vector float vb = vec_promote (b, PREF_F);
>>> + return vec_extract (vec_max (va, vb), PREF_F);
>>> +}
>>> +
>>> +float vminf (float a, float b)
>>> +{
>>> + vector float va = vec_promote (a, PREF_F);
>>> + vector float vb = vec_promote (b, PREF_F);
>>> + return vec_extract (vec_min (va, vb), PREF_F);
>>> +}
>>>
>>> On 25/8/2021 下午 8:34, Bill Schmidt wrote:
>>>> Hi Haochen,
>>>>
>>>> Thanks for the updates! This looks good to me; please await Segher's response.
>>>>
>>>> Bill
>>>>
>>>> On 8/25/21 2:06 AM, HAO CHEN GUI wrote:
>>>>> Hi,
>>>>>
>>>>> I refined the patch according to Bill's advice. I pasted the
>>>>> ChangeLog and diff file here. If it doesn't work, please let me know.
>>>>> Thanks.
>>>>>
>>>>> 2021-08-25 Haochen Gui <guihaoc@linux.ibm.com>
>>>>>
>>>>> gcc/
>>>>> * config/rs6000/rs6000-call.c (rs6000_gimple_fold_builtin):
>>>>> Modify the VSX_BUILTIN_XVMINDP, ALTIVEC_BUILTIN_VMINFP,
>>>>> VSX_BUILTIN_XVMAXDP, ALTIVEC_BUILTIN_VMAXFP expansions.
>>>>>
>>>>> gcc/testsuite/
>>>>> * gcc.target/powerpc/vec-minmax-1.c: New test.
>>>>> * gcc.target/powerpc/vec-minmax-2.c: Likewise.
>>>>>
>>>>> diff --git a/gcc/config/rs6000/rs6000-call.c
>>>>> b/gcc/config/rs6000/rs6000-call.c
>>>>> index b4e13af4dc6..90527734ceb 100644
>>>>> --- a/gcc/config/rs6000/rs6000-call.c
>>>>> +++ b/gcc/config/rs6000/rs6000-call.c
>>>>> @@ -12159,6 +12159,11 @@ rs6000_gimple_fold_builtin
>>>>> (gimple_stmt_iterator *gsi)
>>>>> return true;
>>>>> /* flavors of vec_min. */
>>>>> case VSX_BUILTIN_XVMINDP:
>>>>> + case ALTIVEC_BUILTIN_VMINFP:
>>>>> + if (!flag_finite_math_only || flag_signed_zeros)
>>>>> + return false;
>>>>> + /* Fall through to MIN_EXPR. */
>>>>> + gcc_fallthrough ();
>>>>> case P8V_BUILTIN_VMINSD:
>>>>> case P8V_BUILTIN_VMINUD:
>>>>> case ALTIVEC_BUILTIN_VMINSB:
>>>>> @@ -12167,7 +12172,6 @@ rs6000_gimple_fold_builtin (gimple_stmt_iterator
>>>>> *gsi)
>>>>> case ALTIVEC_BUILTIN_VMINUB:
>>>>> case ALTIVEC_BUILTIN_VMINUH:
>>>>> case ALTIVEC_BUILTIN_VMINUW:
>>>>> - case ALTIVEC_BUILTIN_VMINFP:
>>>>> arg0 = gimple_call_arg (stmt, 0);
>>>>> arg1 = gimple_call_arg (stmt, 1);
>>>>> lhs = gimple_call_lhs (stmt);
>>>>> @@ -12177,6 +12181,11 @@ rs6000_gimple_fold_builtin
>>>>> (gimple_stmt_iterator *gsi)
>>>>> return true;
>>>>> /* flavors of vec_max. */
>>>>> case VSX_BUILTIN_XVMAXDP:
>>>>> + case ALTIVEC_BUILTIN_VMAXFP:
>>>>> + if (!flag_finite_math_only || flag_signed_zeros)
>>>>> + return false;
>>>>> + /* Fall through to MAX_EXPR. */
>>>>> + gcc_fallthrough ();
>>>>> case P8V_BUILTIN_VMAXSD:
>>>>> case P8V_BUILTIN_VMAXUD:
>>>>> case ALTIVEC_BUILTIN_VMAXSB:
>>>>> @@ -12185,7 +12194,6 @@ rs6000_gimple_fold_builtin (gimple_stmt_iterator
>>>>> *gsi)
>>>>> case ALTIVEC_BUILTIN_VMAXUB:
>>>>> case ALTIVEC_BUILTIN_VMAXUH:
>>>>> case ALTIVEC_BUILTIN_VMAXUW:
>>>>> - case ALTIVEC_BUILTIN_VMAXFP:
>>>>> arg0 = gimple_call_arg (stmt, 0);
>>>>> arg1 = gimple_call_arg (stmt, 1);
>>>>> lhs = gimple_call_lhs (stmt);
>>>>> diff --git a/gcc/testsuite/gcc.target/powerpc/vec-minmax-1.c
>>>>> b/gcc/testsuite/gcc.target/powerpc/vec-minmax-1.c
>>>>> new file mode 100644
>>>>> index 00000000000..da92f059aea
>>>>> --- /dev/null
>>>>> +++ b/gcc/testsuite/gcc.target/powerpc/vec-minmax-1.c
>>>>> @@ -0,0 +1,53 @@
>>>>> +/* { dg-do compile { target { powerpc64le-*-* } } } */
>>>>> +/* { dg-require-effective-target powerpc_p9vector_ok } */
>>>>> +/* { dg-options "-O2 -mdejagnu-cpu=power9" } */
>>>>> +/* { dg-final { scan-assembler-times {\mxvmaxdp\M} 1 } } */
>>>>> +/* { dg-final { scan-assembler-times {\mxvmaxsp\M} 1 } } */
>>>>> +/* { dg-final { scan-assembler-times {\mxvmindp\M} 1 } } */
>>>>> +/* { dg-final { scan-assembler-times {\mxvminsp\M} 1 } } */
>>>>> +
>>>>> +/* This test verifies that float or double vec_min/max are bound to
>>>>> + xv[min|max][d|s]p instructions when fast-math is not set. */
>>>>> +
>>>>> +
>>>>> +#include <altivec.h>
>>>>> +
>>>>> +#ifdef _BIG_ENDIAN
>>>>> + const int PREF_D = 0;
>>>>> +#else
>>>>> + const int PREF_D = 1;
>>>>> +#endif
>>>>> +
>>>>> +double vmaxd (double a, double b)
>>>>> +{
>>>>> + vector double va = vec_promote (a, PREF_D);
>>>>> + vector double vb = vec_promote (b, PREF_D);
>>>>> + return vec_extract (vec_max (va, vb), PREF_D);
>>>>> +}
>>>>> +
>>>>> +double vmind (double a, double b)
>>>>> +{
>>>>> + vector double va = vec_promote (a, PREF_D);
>>>>> + vector double vb = vec_promote (b, PREF_D);
>>>>> + return vec_extract (vec_min (va, vb), PREF_D);
>>>>> +}
>>>>> +
>>>>> +#ifdef _BIG_ENDIAN
>>>>> + const int PREF_F = 0;
>>>>> +#else
>>>>> + const int PREF_F = 3;
>>>>> +#endif
>>>>> +
>>>>> +float vmaxf (float a, float b)
>>>>> +{
>>>>> + vector float va = vec_promote (a, PREF_F);
>>>>> + vector float vb = vec_promote (b, PREF_F);
>>>>> + return vec_extract (vec_max (va, vb), PREF_F);
>>>>> +}
>>>>> +
>>>>> +float vminf (float a, float b)
>>>>> +{
>>>>> + vector float va = vec_promote (a, PREF_F);
>>>>> + vector float vb = vec_promote (b, PREF_F);
>>>>> + return vec_extract (vec_min (va, vb), PREF_F);
>>>>> +}
>>>>> diff --git a/gcc/testsuite/gcc.target/powerpc/vec-minmax-2.c
>>>>> b/gcc/testsuite/gcc.target/powerpc/vec-minmax-2.c
>>>>> new file mode 100644
>>>>> index 00000000000..d318b933181
>>>>> --- /dev/null
>>>>> +++ b/gcc/testsuite/gcc.target/powerpc/vec-minmax-2.c
>>>>> @@ -0,0 +1,51 @@
>>>>> +/* { dg-do compile { target { powerpc64le-*-* } } } */
>>>>> +/* { dg-require-effective-target powerpc_p9vector_ok } */
>>>>> +/* { dg-options "-O2 -mdejagnu-cpu=power9 -ffast-math" } */
>>>>> +/* { dg-final { scan-assembler-times {\mxsmaxcdp\M} 2 } } */
>>>>> +/* { dg-final { scan-assembler-times {\mxsmincdp\M} 2 } } */
>>>>> +
>>>>> +/* This test verifies that float or double vec_min/max can be converted
>>>>> + to scalar comparison when fast-math is set. */
>>>>> +
>>>>> +
>>>>> +#include <altivec.h>
>>>>> +
>>>>> +#ifdef _BIG_ENDIAN
>>>>> + const int PREF_D = 0;
>>>>> +#else
>>>>> + const int PREF_D = 1;
>>>>> +#endif
>>>>> +
>>>>> +double vmaxd (double a, double b)
>>>>> +{
>>>>> + vector double va = vec_promote (a, PREF_D);
>>>>> + vector double vb = vec_promote (b, PREF_D);
>>>>> + return vec_extract (vec_max (va, vb), PREF_D);
>>>>> +}
>>>>> +
>>>>> +double vmind (double a, double b)
>>>>> +{
>>>>> + vector double va = vec_promote (a, PREF_D);
>>>>> + vector double vb = vec_promote (b, PREF_D);
>>>>> + return vec_extract (vec_min (va, vb), PREF_D);
>>>>> +}
>>>>> +
>>>>> +#ifdef _BIG_ENDIAN
>>>>> + const int PREF_F = 0;
>>>>> +#else
>>>>> + const int PREF_F = 3;
>>>>> +#endif
>>>>> +
>>>>> +float vmaxf (float a, float b)
>>>>> +{
>>>>> + vector float va = vec_promote (a, PREF_F);
>>>>> + vector float vb = vec_promote (b, PREF_F);
>>>>> + return vec_extract (vec_max (va, vb), PREF_F);
>>>>> +}
>>>>> +
>>>>> +float vminf (float a, float b)
>>>>> +{
>>>>> + vector float va = vec_promote (a, PREF_F);
>>>>> + vector float vb = vec_promote (b, PREF_F);
>>>>> + return vec_extract (vec_min (va, vb), PREF_F);
>>>>> +}
>>>>>
>>>>> On 25/8/2021 上午 6:40, Segher Boessenkool wrote:
>>>>>> Hi!
>>>>>>
>>>>>> On Tue, Aug 24, 2021 at 03:04:26PM -0500, Bill Schmidt wrote:
>>>>>>> On 8/24/21 3:52 AM, HAO CHEN GUI wrote:
>>>>>>> Thanks for this patch! In the future, if you can put your ChangeLog and
>>>>>>> patch inline in your post, it makes it easier to review. (Otherwise we
>>>>>>> have to manually copy it into our response and manipulate it to look
>>>>>>> quoted, etc.)
>>>>>> It is encoded even, making it impossible to easily apply the patch, etc.
>>>>>>
>>>>>>>> diff --git a/gcc/config/rs6000/rs6000-call.c
>>>>>>>> b/gcc/config/rs6000/rs6000-call.c index b4e13af4dc6..90527734ceb
>>>>>>>> 100644 --- a/gcc/config/rs6000/rs6000-call.c +++
>>>>>>>> b/gcc/config/rs6000/rs6000-call.c @@ -12159,6 +12159,11 @@
>>>>>>>> rs6000_gimple_fold_builtin (gimple_stmt_iterator *gsi) return true; /*
>>>>>>>> flavors of vec_min. */ case VSX_BUILTIN_XVMINDP: + case
>>>>>> format=flawed :-(
>>>>>>
>>>>>>
>>>>>> Segher
next prev parent reply other threads:[~2021-10-11 5:27 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-08-24 8:52 HAO CHEN GUI
2021-08-24 20:04 ` Bill Schmidt
2021-08-24 22:40 ` Segher Boessenkool
2021-08-25 7:06 ` HAO CHEN GUI
2021-08-25 7:50 ` Kewen.Lin
2021-08-25 8:17 ` HAO CHEN GUI
2021-08-25 8:44 ` HAO CHEN GUI
2021-08-25 12:34 ` Bill Schmidt
2021-08-26 1:19 ` HAO CHEN GUI
2021-09-06 6:01 ` HAO CHEN GUI
2021-09-22 6:52 ` PING^2 " HAO CHEN GUI
2021-10-11 5:26 ` HAO CHEN GUI [this message]
2021-10-11 15:55 ` Segher Boessenkool
2021-10-11 16:07 ` Segher Boessenkool
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=2af3edbc-49b2-cce9-89ea-b5d4a6c1a752@linux.ibm.com \
--to=guihaoc@linux.ibm.com \
--cc=gcc-patches@gcc.gnu.org \
--cc=segher@kernel.crashing.org \
--cc=wschmidt@linux.ibm.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).