Re: Pushed: [PATCH v3 0/5] LoongArch: SIMD fixes and optimizations

[chenglulu <chenglulu@loongson.cn>]

在 2023/11/29 下午3:12, Xi Ruoyao 写道:
> On Mon, 2023-11-20 at 08:47 +0800, Xi Ruoyao wrote:
>> The [1/5] patch is the PR112578 fix at
>> https://gcc.gnu.org/pipermail/gcc-patches/2023-November/637097.html.
>> It has been changed to remove the nearbyint pattern (because nearbyint
>> should not raise FE_INEXACT even if -ffp-int-builtin-inexact).
>> As other patches depending on the simd.md file introduced by this, sending
>> it as the first of this series.
>>
>> As many LASX instructions are only differentiated from the corresponding
>> LSX instruction with operand length, create simd.md file to contain the
>> RTX templates sharable by LSX and LASX.  This makes the code cleaner and
>> easier to maintain.
>>
>> The [2/5] and [3/5] patches make vector product highpart and rotate
>> shift operations for GNU vectors and auto vectorization.
>>
>> The [4/5] patch is a simple code cleanup, with no function change.
>>
>> The [5/5] patch uses LSX for FP scalar rounding operations if LSX is
>> available and -ffp-int-builtin-exact.  We do this because the base FP
>> ISA does not have such instructions.  Using LSX is overkill, but still
>> much faster than calling libc functions.
>>
>> Bootstrapped and regtested on loongarch64-linux-gnu.  Ok for trunk?
> Pushed r14-5950 .. r14-5954 with minor change: a FSF copyright
> disclaimer is added into simd.md in the 1st patch, and an used
> match_scratch is removed from <simd_frint_pattern><mode>2 in the 5th
> patch.
>
Thank you very much!:-)
>> Xi Ruoyao (5):
>>    LoongArch: Fix usage of LSX and LASX frint/ftint instructions
>>      [PR112578]
>>    LoongArch: Use standard pattern name and RTX code for LSX/LASX muh
>>      instructions
>>    LoongArch: Use standard pattern name and RTX code for LSX/LASX rotate
>>      shift
>>    LoongArch: Remove lrint_allow_inexact
>>    LoongArch: Use LSX for scalar FP rounding with explicit rounding mode
>>
>>   gcc/config/loongarch/lasx.md                  | 283 -----------------
>>   gcc/config/loongarch/loongarch-builtins.cc    |  52 ++--
>>   gcc/config/loongarch/loongarch.md             |  12 +-
>>   gcc/config/loongarch/lsx.md                   | 293 ------------------
>>   gcc/config/loongarch/simd.md                  | 268 ++++++++++++++++
>>   .../loongarch/vect-frint-no-inexact.c         |  48 +++
>>   .../loongarch/vect-frint-scalar-no-inexact.c  |  23 ++
>>   .../gcc.target/loongarch/vect-frint-scalar.c  |  43 +++
>>   .../gcc.target/loongarch/vect-frint.c         |  85 +++++
>>   .../loongarch/vect-ftint-no-inexact.c         |  44 +++
>>   .../gcc.target/loongarch/vect-ftint.c         |  83 +++++
>>   gcc/testsuite/gcc.target/loongarch/vect-muh.c |  36 +++
>>   .../gcc.target/loongarch/vect-rotr.c          |  36 +++
>>   13 files changed, 701 insertions(+), 605 deletions(-)
>>   create mode 100644 gcc/config/loongarch/simd.md
>>   create mode 100644 gcc/testsuite/gcc.target/loongarch/vect-frint-no-inexact.c
>>   create mode 100644 gcc/testsuite/gcc.target/loongarch/vect-frint-scalar-no-inexact.c
>>   create mode 100644 gcc/testsuite/gcc.target/loongarch/vect-frint-scalar.c
>>   create mode 100644 gcc/testsuite/gcc.target/loongarch/vect-frint.c
>>   create mode 100644 gcc/testsuite/gcc.target/loongarch/vect-ftint-no-inexact.c
>>   create mode 100644 gcc/testsuite/gcc.target/loongarch/vect-ftint.c
>>   create mode 100644 gcc/testsuite/gcc.target/loongarch/vect-muh.c
>>   create mode 100644 gcc/testsuite/gcc.target/loongarch/vect-rotr.c