-
Notifications
You must be signed in to change notification settings - Fork 940
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Getting error on make -j4 gpt-2 #45
Comments
I was able to overcome this issue by undefine-ing the AVX2 macro in ggml.c, specifically above the definition for the vec_dot functions, for example something like:
|
CCLDArjun
pushed a commit
to CCLDArjun/ggml
that referenced
this issue
Dec 18, 2023
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Consolidate compiler generated dependencies of target ggml
[ 33%] Built target ggml_utils
[ 50%] Building C object src/CMakeFiles/ggml.dir/ggml.c.o
In file included from /usr/lib/gcc/x86_64-redhat-linux/8/include/immintrin.h:99,
from /home/kumapra/MACHINE/ggml/src/ggml.c:153:
/home/kumapra/MACHINE/ggml/src/ggml.c: In function ‘ggml_vec_dot_f16’:
/usr/lib/gcc/x86_64-redhat-linux/8/include/f16cintrin.h:52:1: error: inlining failed in call to always_inline ‘_mm256_cvtph_ps’: target specific option mismatch
_mm256_cvtph_ps (__m128i __A)
^~~~~~~~~~~~~~~
/home/kumapra/MACHINE/ggml/src/ggml.c:543:33: note: called from here
#define GGML_F32Cx8_LOAD(x) _mm256_cvtph_ps(_mm_loadu_si128((__m128i )(x)))
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
/home/kumapra/MACHINE/ggml/src/ggml.c:553:37: note: in expansion of macro ‘GGML_F32Cx8_LOAD’
#define GGML_F16_VEC_LOAD(p, i) GGML_F32Cx8_LOAD(p)
^~~~~~~~~~~~~~~~
/home/kumapra/MACHINE/ggml/src/ggml.c:906:21: note: in expansion of macro ‘GGML_F16_VEC_LOAD’
ay[j] = GGML_F16_VEC_LOAD(y + i + jGGML_F16_EPR, j);
^~~~~~~~~~~~~~~~~
In file included from /usr/lib/gcc/x86_64-redhat-linux/8/include/immintrin.h:99,
from /home/kumapra/MACHINE/ggml/src/ggml.c:153:
/usr/lib/gcc/x86_64-redhat-linux/8/include/f16cintrin.h:52:1: error: inlining failed in call to always_inline ‘_mm256_cvtph_ps’: target specific option mismatch
_mm256_cvtph_ps (__m128i __A)
^~~~~~~~~~~~~~~
/home/kumapra/MACHINE/ggml/src/ggml.c:543:33: note: called from here
#define GGML_F32Cx8_LOAD(x) _mm256_cvtph_ps(_mm_loadu_si128((__m128i )(x)))
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
/home/kumapra/MACHINE/ggml/src/ggml.c:553:37: note: in expansion of macro ‘GGML_F32Cx8_LOAD’
#define GGML_F16_VEC_LOAD(p, i) GGML_F32Cx8_LOAD(p)
^~~~~~~~~~~~~~~~
/home/kumapra/MACHINE/ggml/src/ggml.c:905:21: note: in expansion of macro ‘GGML_F16_VEC_LOAD’
ax[j] = GGML_F16_VEC_LOAD(x + i + jGGML_F16_EPR, j);
^~~~~~~~~~~~~~~~~
In file included from /usr/lib/gcc/x86_64-redhat-linux/8/include/immintrin.h:99,
from /home/kumapra/MACHINE/ggml/src/ggml.c:153:
/usr/lib/gcc/x86_64-redhat-linux/8/include/f16cintrin.h:52:1: error: inlining failed in call to always_inline ‘_mm256_cvtph_ps’: target specific option mismatch
_mm256_cvtph_ps (__m128i __A)
^~~~~~~~~~~~~~~
/home/kumapra/MACHINE/ggml/src/ggml.c:543:33: note: called from here
#define GGML_F32Cx8_LOAD(x) _mm256_cvtph_ps(_mm_loadu_si128((__m128i )(x)))
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
/home/kumapra/MACHINE/ggml/src/ggml.c:553:37: note: in expansion of macro ‘GGML_F32Cx8_LOAD’
#define GGML_F16_VEC_LOAD(p, i) GGML_F32Cx8_LOAD(p)
^~~~~~~~~~~~~~~~
/home/kumapra/MACHINE/ggml/src/ggml.c:905:21: note: in expansion of macro ‘GGML_F16_VEC_LOAD’
ax[j] = GGML_F16_VEC_LOAD(x + i + jGGML_F16_EPR, j);
^~~~~~~~~~~~~~~~~
In file included from /usr/lib/gcc/x86_64-redhat-linux/8/include/immintrin.h:99,
from /home/kumapra/MACHINE/ggml/src/ggml.c:153:
/usr/lib/gcc/x86_64-redhat-linux/8/include/f16cintrin.h:52:1: error: inlining failed in call to always_inline ‘_mm256_cvtph_ps’: target specific option mismatch
_mm256_cvtph_ps (__m128i __A)
^~~~~~~~~~~~~~~
/home/kumapra/MACHINE/ggml/src/ggml.c:543:33: note: called from here
#define GGML_F32Cx8_LOAD(x) _mm256_cvtph_ps(_mm_loadu_si128((__m128i )(x)))
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
/home/kumapra/MACHINE/ggml/src/ggml.c:553:37: note: in expansion of macro ‘GGML_F32Cx8_LOAD’
#define GGML_F16_VEC_LOAD(p, i) GGML_F32Cx8_LOAD(p)
^~~~~~~~~~~~~~~~
/home/kumapra/MACHINE/ggml/src/ggml.c:906:21: note: in expansion of macro ‘GGML_F16_VEC_LOAD’
ay[j] = GGML_F16_VEC_LOAD(y + i + jGGML_F16_EPR, j);
^~~~~~~~~~~~~~~~~
In file included from /usr/lib/gcc/x86_64-redhat-linux/8/include/immintrin.h:99,
from /home/kumapra/MACHINE/ggml/src/ggml.c:153:
/usr/lib/gcc/x86_64-redhat-linux/8/include/f16cintrin.h:52:1: error: inlining failed in call to always_inline ‘_mm256_cvtph_ps’: target specific option mismatch
_mm256_cvtph_ps (__m128i __A)
^~~~~~~~~~~~~~~
/home/kumapra/MACHINE/ggml/src/ggml.c:543:33: note: called from here
#define GGML_F32Cx8_LOAD(x) _mm256_cvtph_ps(_mm_loadu_si128((__m128i )(x)))
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
/home/kumapra/MACHINE/ggml/src/ggml.c:553:37: note: in expansion of macro ‘GGML_F32Cx8_LOAD’
#define GGML_F16_VEC_LOAD(p, i) GGML_F32Cx8_LOAD(p)
^~~~~~~~~~~~~~~~
/home/kumapra/MACHINE/ggml/src/ggml.c:905:21: note: in expansion of macro ‘GGML_F16_VEC_LOAD’
ax[j] = GGML_F16_VEC_LOAD(x + i + jGGML_F16_EPR, j);
^~~~~~~~~~~~~~~~~
In file included from /usr/lib/gcc/x86_64-redhat-linux/8/include/immintrin.h:99,
from /home/kumapra/MACHINE/ggml/src/ggml.c:153:
/usr/lib/gcc/x86_64-redhat-linux/8/include/f16cintrin.h:52:1: error: inlining failed in call to always_inline ‘_mm256_cvtph_ps’: target specific option mismatch
_mm256_cvtph_ps (__m128i __A)
^~~~~~~~~~~~~~~
/home/kumapra/MACHINE/ggml/src/ggml.c:543:33: note: called from here
#define GGML_F32Cx8_LOAD(x) _mm256_cvtph_ps(_mm_loadu_si128((__m128i )(x)))
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
/home/kumapra/MACHINE/ggml/src/ggml.c:553:37: note: in expansion of macro ‘GGML_F32Cx8_LOAD’
#define GGML_F16_VEC_LOAD(p, i) GGML_F32Cx8_LOAD(p)
^~~~~~~~~~~~~~~~
/home/kumapra/MACHINE/ggml/src/ggml.c:906:21: note: in expansion of macro ‘GGML_F16_VEC_LOAD’
ay[j] = GGML_F16_VEC_LOAD(y + i + jGGML_F16_EPR, j);
^~~~~~~~~~~~~~~~~
make[3]: *** [src/CMakeFiles/ggml.dir/build.make:76: src/CMakeFiles/ggml.dir/ggml.c.o] Error 1
make[2]: *** [CMakeFiles/Makefile2:205: src/CMakeFiles/ggml.dir/all] Error 2
make[1]: *** [CMakeFiles/Makefile2:499: examples/gpt-2/CMakeFiles/gpt-2.dir/rule] Error 2
make: *** [Makefile:322: gpt-2] Error 2
The text was updated successfully, but these errors were encountered: