ggml : prevent builds with -ffinite-math-only (#7726)

This enforces a check that -fno-finite-math-only was set and that the operating
compiling mode is not in finite maths mode. This is because during rewriting of
silu and softmax for cpu #7154 there emerged an issue where the result that was
observed when >1 slot was nondeterministic as found by @JohannesGaessler.

@LostRuins narrowed the problem down to -ffinite-math-only which was theorised
to be due to SiLU, instead of flushing small values to 0, returns NaN or some 
other garbage. @jart proposed a fix that @ggerganov then implemented in this fix

ref https://github.com/ggerganov/llama.cpp/pull/7154#issuecomment-2145661825
This commit is contained in:
Georgi Gerganov 2024-06-04 10:01:09 +03:00 committed by GitHub
parent bde7cd3cd9
commit 6d1616944d
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 6 additions and 1 deletions

View File

@ -9,7 +9,7 @@ set( CMAKE_CXX_COMPILER clang++ )
set( CMAKE_C_COMPILER_TARGET ${target} )
set( CMAKE_CXX_COMPILER_TARGET ${target} )
set( arch_c_flags "-march=armv8.7-a -fvectorize -ffp-model=fast" )
set( arch_c_flags "-march=armv8.7-a -fvectorize -ffp-model=fast -fno-finite-math-only" )
set( warn_c_flags "-Wno-format -Wno-unused-variable -Wno-unused-function -Wno-gnu-zero-variadic-macro-arguments" )
set( CMAKE_C_FLAGS_INIT "${arch_c_flags} ${warn_c_flags}" )

5
ggml.c
View File

@ -2272,6 +2272,11 @@ inline static float ggml_silu_f32(float x) {
return x/(1.0f + expf(-x));
}
#if __FINITE_MATH_ONLY__
#error "some routines in ggml.c require non-finite math arithmetics -- pass -fno-finite-math-only to the compiler to fix"
#error "ref: https://github.com/ggerganov/llama.cpp/pull/7154#issuecomment-2143844461"
#endif
#if defined(__ARM_NEON) && defined(__aarch64__)
// adapted from arm limited optimized routine