[PATCH] math: Fix x86_64 build for -Os (BZ 33367)
Adhemerval Zanella Netto
adhemerval.zanella@linaro.org
Mon Sep 8 19:09:29 GMT 2025
On 08/09/25 15:59, H.J. Lu wrote:
> On Mon, Sep 8, 2025 at 9:30 AM H.J. Lu <hjl.tools@gmail.com> wrote:
>>
>> On Mon, Sep 8, 2025 at 9:04 AM Adhemerval Zanella Netto
>> <adhemerval.zanella@linaro.org> wrote:
>>>
>>>
>>>
>>> On 08/09/25 12:56, H.J. Lu wrote:
>>>> On Mon, Sep 8, 2025 at 8:27 AM Adhemerval Zanella Netto
>>>> <adhemerval.zanella@linaro.org> wrote:
>>>>>
>>>>>
>>>>>
>>>>> On 08/09/25 12:22, H.J. Lu wrote:
>>>>>> On Mon, Sep 8, 2025 at 7:26 AM H.J. Lu <hjl.tools@gmail.com> wrote:
>>>>>>>
>>>>>>> On Sat, Sep 6, 2025 at 3:22 PM Adhemerval Zanella
>>>>>>> <adhemerval.zanella@linaro.org> wrote:
>>>>>>>>
>>>>>>>> The compiler might not inline the trunc function call for
>>>>>>>> USE_TRUNC_BUILTIN, which requires adding the required objects.
>>>>>>>>
>>>>>>>> Route trunc calls for the optimized modf variants to thei
>>>>>>>> ABI-compatible version. This avoids invoking the ifunc variant
>>>>>>>> for x86_64-v1 and requires fewer objects to be added.
>>>>>>>>
>>>>>>>> Checked on x86_64, x86_64-v2, x86_64-v3, and x86_64-v4. Used -O2 and
>>>>>>>> -Os options. Performed a full make check on x86_64 with both
>>>>>>>> optimizations.
>>>>>>>> ---
>>>>>>>> sysdeps/x86_64/fpu/multiarch/Makefile | 19 ++++++++++++-------
>>>>>>>> sysdeps/x86_64/fpu/multiarch/s_modf-avx.c | 5 +++++
>>>>>>>> sysdeps/x86_64/fpu/multiarch/s_modf-sse4_1.c | 5 +++++
>>>>>>>> sysdeps/x86_64/fpu/multiarch/s_modf.c | 1 -
>>>>>>>> sysdeps/x86_64/fpu/multiarch/s_modff-avx.c | 5 +++++
>>>>>>>> sysdeps/x86_64/fpu/multiarch/s_modff-sse4_1.c | 5 +++++
>>>>>>>> sysdeps/x86_64/fpu/multiarch/s_modff.c | 1 -
>>>>>>>> 7 files changed, 32 insertions(+), 9 deletions(-)
>>>>>>>>
>>>>>>>> diff --git a/sysdeps/x86_64/fpu/multiarch/Makefile b/sysdeps/x86_64/fpu/multiarch/Makefile
>>>>>>>> index 708b14297f..baefe8dd07 100644
>>>>>>>> --- a/sysdeps/x86_64/fpu/multiarch/Makefile
>>>>>>>> +++ b/sysdeps/x86_64/fpu/multiarch/Makefile
>>>>>>>> @@ -26,6 +26,11 @@ CFLAGS-s_sinf-fma.c = -mfma -mavx2
>>>>>>>> CFLAGS-s_cosf-fma.c = -mfma -mavx2
>>>>>>>> CFLAGS-s_sincosf-fma.c = -mfma -mavx2
>>>>>>>>
>>>>>>>> +sysdep_calls += \
>>>>>>>> + s_trunc-sse4_1 \
>>>>>>>> + s_truncf-sse4_1 \
>>>>>>>> +# sysdep_calls
>>>>>>>> +
>>>>>>>> # Check if ISA level is 2 or above.
>>>>>>>> ifeq (,$(filter $(have-x86-isa-level),$(x86-isa-level-2-or-above)))
>>>>>>>> sysdep_calls += \
>>>>>>>> @@ -36,6 +41,10 @@ endif
>>>>>>>>
>>>>>>>> # Check if ISA level is 3 or above.
>>>>>>>> ifneq (,$(filter $(have-x86-isa-level),$(x86-isa-level-3-or-above)))
>>>>>>>> +sysdep_calls += \
>>>>>>>> + s_trunc-avx \
>>>>>>>> + s_truncf-avx \
>>>>>>>> +# sysdep_calls
>>>>>>>> libm-sysdep_routines += \
>>>>>>>> s_ceil-avx \
>>>>>>>> s_ceilf-avx \
>>>>>>>> @@ -47,8 +56,6 @@ libm-sysdep_routines += \
>>>>>>>> s_rintf-avx \
>>>>>>>> s_roundeven-avx \
>>>>>>>> s_roundevenf-avx \
>>>>>>>> - s_trunc-avx \
>>>>>>>> - s_truncf-avx \
>>>>>>>> # libm-sysdep_routines
>>>>>>>> else
>>>>>>>> sysdep_calls += \
>>>>>>>> @@ -114,8 +121,6 @@ libm-sysdep_routines += \
>>>>>>>> s_tan-avx \
>>>>>>>> s_tan-fma \
>>>>>>>> s_tanh-fma \
>>>>>>>> - s_trunc-sse4_1 \
>>>>>>>> - s_truncf-sse4_1 \
>>>>>>>> # libm-sysdep_routines
>>>>>>>> ifeq ($(have-x86-isa-level),baseline)
>>>>>>>> libm-sysdep_routines += \
>>>>>>>> @@ -132,13 +137,13 @@ libm-sysdep_routines += \
>>>>>>>> s_trunc-c \
>>>>>>>> s_truncf-c \
>>>>>>>> # libm-sysdep_routines
>>>>>>>> -endif
>>>>>>>> +endif # ($(have-x86-isa-level),baseline)
>>>>>>>> +endif # (,$(filter $(have-x86-isa-level),$(x86-isa-level-3-or-above)))
>>>>>>>>
>>>>>>>> # $(sysdep_calls) functions are built both for libc and libm. While the
>>>>>>>> # libc objects have the prefix s_, the libm ones are prefixed with m_.
>>>>>>>> -sysdep_routines += $(sysdep_calls)
>>>>>>>> +sysdep_routines += $(sysdep_calls)
>>>>>>>> libm-sysdep_routines += $(sysdep_calls:s_%=m_%)
>>>>>>>> -endif
>>>>>>>>
>>>>>>>> CFLAGS-e_asin-fma4.c = -mfma4
>>>>>>>> CFLAGS-e_atan2-fma4.c = -mfma4
>>>>>>>> diff --git a/sysdeps/x86_64/fpu/multiarch/s_modf-avx.c b/sysdeps/x86_64/fpu/multiarch/s_modf-avx.c
>>>>>>>> index ab4f03db0e..25617c4fdc 100644
>>>>>>>> --- a/sysdeps/x86_64/fpu/multiarch/s_modf-avx.c
>>>>>>>> +++ b/sysdeps/x86_64/fpu/multiarch/s_modf-avx.c
>>>>>>>> @@ -1,3 +1,8 @@
>>>>>>>> +#include <sysdeps/x86/isa-level.h>
>>>>>>>> +#if MINIMUM_X86_ISA_LEVEL < SSE4_1_X86_ISA_LEVEL
>>>>>>>> +asm ("__trunc = __trunc_sse41");
>>>>>>>
>>>>>>> It looks odd for __modf_avx to call __trunc_sse41. But this is a
>>>>>>> separate issue.
>>>>>>> We do have s_truncf-avx.S, but it isn't used by default. I think we should
>>>>>>> make it available for s_modf.c and s_modf-avx.c first.
>>>>>>
>>>>>> Can we use inline functions?
>>>>>
>>>>> It might an option, and I think it simplified the Makefile requirement.
>>>>> I will update the patch with this.
>>>>>
>>>>> Do we have a way to force compiler always expand the builin
>>>>> regardless of the optimization level?
>>>>
>>>> #include <math.h>
>>>> #include <x86intrin.h>
>>>>
>>>> double
>>>> __trunc (double x)
>>>> {
>>>> #ifdef __AVX__
>>>> asm ("vroundsd $11, %1, %1, %0" : "=v" (x) : "v" (x));
>>>> #elif defined __SSE4_1__
>>>> asm ("roundsd $11, %1, %0" : "=x" (x) : "x" (x));
>>>> #else
>>>> x = trunc (x);
>>>> #endif
>>>> return x;
>>>> }
>>>>
>>> Yeah, that was my idea to change it. But my question was if there is an extra
>>> compiler option to avoid the libcall generation for -Os if the builtin lowering
>>> does allow to use an instruction.
>>
>> I don't know.
>>
>>> As a side note, I think it is a missed optimization that gcc is creating a
>>> libcall for x86_64-v2 and forward.
>>
>> Can you open a GCC bug and CC me?
>>
>
> I opened:
>
> https://gcc.gnu.org/bugzilla/show_bug.cgi?id=121861
>
Thanks, using inline resulted in a simpler patch. I will send a new version.
More information about the Libc-alpha
mailing list