Unable to compile - error: inlining failed in call to ‘always_inline’ ‘_mm256_cvtph_ps’

[jahnke]

Hi, I downloaded the files with git and run make just as in the instruction. Unfortunately, the compilation is not working. Can someone help me figure out what's going wrong here?

I'm adding the full error in the following.

In file included from /usr/lib/gcc/x86_64-linux-gnu/10/include/immintrin.h:113, from ggml.c:155: ggml.c: In function ‘ggml_vec_dot_f16’: /usr/lib/gcc/x86_64-linux-gnu/10/include/f16cintrin.h:52:1: error: inlining failed in call to ‘always_inline’ ‘_mm256_cvtph_ps’: target specific option mismatch 52 | _mm256_cvtph_ps (__m128i __A) | ^~~~~~~~~~~~~~~ ggml.c:911:33: note: called from here 911 | #define GGML_F32Cx8_LOAD(x) _mm256_cvtph_ps(_mm_loadu_si128((__m128i *)(x))) | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ggml.c:921:37: note: in expansion of macro ‘GGML_F32Cx8_LOAD’ 921 | #define GGML_F16_VEC_LOAD(p, i) GGML_F32Cx8_LOAD(p) | ^~~~~~~~~~~~~~~~ ggml.c:1274:21: note: in expansion of macro ‘GGML_F16_VEC_LOAD’ 1274 | ay[j] = GGML_F16_VEC_LOAD(y + i + j*GGML_F16_EPR, j); | ^~~~~~~~~~~~~~~~~ In file included from /usr/lib/gcc/x86_64-linux-gnu/10/include/immintrin.h:113, from ggml.c:155: /usr/lib/gcc/x86_64-linux-gnu/10/include/f16cintrin.h:52:1: error: inlining failed in call to ‘always_inline’ ‘_mm256_cvtph_ps’: target specific option mismatch 52 | _mm256_cvtph_ps (__m128i __A) | ^~~~~~~~~~~~~~~ ggml.c:911:33: note: called from here 911 | #define GGML_F32Cx8_LOAD(x) _mm256_cvtph_ps(_mm_loadu_si128((__m128i *)(x))) | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ggml.c:921:37: note: in expansion of macro ‘GGML_F32Cx8_LOAD’ 921 | #define GGML_F16_VEC_LOAD(p, i) GGML_F32Cx8_LOAD(p) | ^~~~~~~~~~~~~~~~ ggml.c:1273:21: note: in expansion of macro ‘GGML_F16_VEC_LOAD’ 1273 | ax[j] = GGML_F16_VEC_LOAD(x + i + j*GGML_F16_EPR, j); | ^~~~~~~~~~~~~~~~~ In file included from /usr/lib/gcc/x86_64-linux-gnu/10/include/immintrin.h:113, from ggml.c:155: /usr/lib/gcc/x86_64-linux-gnu/10/include/f16cintrin.h:52:1: error: inlining failed in call to ‘always_inline’ ‘_mm256_cvtph_ps’: target specific option mismatch 52 | _mm256_cvtph_ps (__m128i __A) | ^~~~~~~~~~~~~~~ ggml.c:911:33: note: called from here 911 | #define GGML_F32Cx8_LOAD(x) _mm256_cvtph_ps(_mm_loadu_si128((__m128i *)(x))) | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ggml.c:921:37: note: in expansion of macro ‘GGML_F32Cx8_LOAD’ 921 | #define GGML_F16_VEC_LOAD(p, i) GGML_F32Cx8_LOAD(p) | ^~~~~~~~~~~~~~~~ ggml.c:1273:21: note: in expansion of macro ‘GGML_F16_VEC_LOAD’ 1273 | ax[j] = GGML_F16_VEC_LOAD(x + i + j*GGML_F16_EPR, j); | ^~~~~~~~~~~~~~~~~ In file included from /usr/lib/gcc/x86_64-linux-gnu/10/include/immintrin.h:113, from ggml.c:155: /usr/lib/gcc/x86_64-linux-gnu/10/include/f16cintrin.h:52:1: error: inlining failed in call to ‘always_inline’ ‘_mm256_cvtph_ps’: target specific option mismatch 52 | _mm256_cvtph_ps (__m128i __A) | ^~~~~~~~~~~~~~~ ggml.c:911:33: note: called from here 911 | #define GGML_F32Cx8_LOAD(x) _mm256_cvtph_ps(_mm_loadu_si128((__m128i *)(x))) | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ggml.c:921:37: note: in expansion of macro ‘GGML_F32Cx8_LOAD’ 921 | #define GGML_F16_VEC_LOAD(p, i) GGML_F32Cx8_LOAD(p) | ^~~~~~~~~~~~~~~~ ggml.c:1274:21: note: in expansion of macro ‘GGML_F16_VEC_LOAD’ 1274 | ay[j] = GGML_F16_VEC_LOAD(y + i + j*GGML_F16_EPR, j); | ^~~~~~~~~~~~~~~~~ In file included from /usr/lib/gcc/x86_64-linux-gnu/10/include/immintrin.h:113, from ggml.c:155: /usr/lib/gcc/x86_64-linux-gnu/10/include/f16cintrin.h:52:1: error: inlining failed in call to ‘always_inline’ ‘_mm256_cvtph_ps’: target specific option mismatch 52 | _mm256_cvtph_ps (__m128i __A) | ^~~~~~~~~~~~~~~ ggml.c:911:33: note: called from here 911 | #define GGML_F32Cx8_LOAD(x) _mm256_cvtph_ps(_mm_loadu_si128((__m128i *)(x))) | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ggml.c:921:37: note: in expansion of macro ‘GGML_F32Cx8_LOAD’ 921 | #define GGML_F16_VEC_LOAD(p, i) GGML_F32Cx8_LOAD(p) | ^~~~~~~~~~~~~~~~ ggml.c:1273:21: note: in expansion of macro ‘GGML_F16_VEC_LOAD’ 1273 | ax[j] = GGML_F16_VEC_LOAD(x + i + j*GGML_F16_EPR, j); | ^~~~~~~~~~~~~~~~~ In file included from /usr/lib/gcc/x86_64-linux-gnu/10/include/immintrin.h:113, from ggml.c:155: /usr/lib/gcc/x86_64-linux-gnu/10/include/f16cintrin.h:52:1: error: inlining failed in call to ‘always_inline’ ‘_mm256_cvtph_ps’: target specific option mismatch 52 | _mm256_cvtph_ps (__m128i __A) | ^~~~~~~~~~~~~~~ ggml.c:911:33: note: called from here 911 | #define GGML_F32Cx8_LOAD(x) _mm256_cvtph_ps(_mm_loadu_si128((__m128i *)(x))) | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ggml.c:921:37: note: in expansion of macro ‘GGML_F32Cx8_LOAD’ 921 | #define GGML_F16_VEC_LOAD(p, i) GGML_F32Cx8_LOAD(p) | ^~~~~~~~~~~~~~~~ ggml.c:1274:21: note: in expansion of macro ‘GGML_F16_VEC_LOAD’ 1274 | ay[j] = GGML_F16_VEC_LOAD(y + i + j*GGML_F16_EPR, j); | ^~~~~~~~~~~~~~~~~ make: *** [Makefile:186: ggml.o] Error 1

[gjmulder]

• Please format your error so it is more readable.
• Then please review issues Error: inlining failed in call to always_inline ‘_mm256_cvtph_ps’: target specific option mismatch #107 and Build on Debian Docker #108 and if they do not help, similarly provide more details of your build environment.

[jahnke]

The issue was caused by it being compiled on a machine with very old hardware and software. Everything worked as it was supposed to on a updated system with modern hardware.