diff options
author | aditya <bluenerd@protonmail.com> | 2023-08-10 12:32:35 +0530 |
---|---|---|
committer | aditya <bluenerd@protonmail.com> | 2023-08-10 12:32:35 +0530 |
commit | a9ff78b3f48dc9f81943c41531c4959ce7e2ae9d (patch) | |
tree | 49ee8c3c9148038f04112802265d928ef1aba428 /tests/test-double-float.cpp | |
parent | 2516af4cd61f509c995b4f78fdf123cba33f3509 (diff) | |
parent | 916a9acdd0a411426690400ebe2bb7ce840a6bba (diff) |
resolve merge conflict
Diffstat (limited to 'tests/test-double-float.cpp')
-rw-r--r-- | tests/test-double-float.cpp | 55 |
1 files changed, 55 insertions, 0 deletions
diff --git a/tests/test-double-float.cpp b/tests/test-double-float.cpp new file mode 100644 index 0000000..b506f27 --- /dev/null +++ b/tests/test-double-float.cpp @@ -0,0 +1,55 @@ +// These tests may take a long time! +// They are to prove that conversion from double to float of various functions in ggml.c doesn't affect the result. +// This is done by checking all finite (non-NaN, non-infinite) floats. + +#undef NDEBUG +#include <cassert> +#include <immintrin.h> +#include <cmath> +#include <cstdint> +#include <cstring> + +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wdouble-promotion" + +// ggml.c::quantize_row_q4_0_reference +inline static uint8_t round_orig(float v0) { return ((int8_t) (round(v0))) + 8; } + +// ggml.c::ggml_silu_f32 +inline static float silu_orig(float x) { + return x/(1.0 + exp(-x)); +} + +#pragma GCC diagnostic pop + +// ggml.c::quantize_row_q4_0_reference +inline static uint8_t round_float(float v0) { return (int8_t)roundf(v0) + 8; } + +// ggml.c::ggml_silu_f32 +inline static float silu_float(float x) { + return x/(1.0f + expf(-x)); +} + +int main(void) { + uint32_t x = UINT32_MAX; + do { + float f; + memcpy(&f, &x, sizeof(x)); + assert(!std::isfinite(f) || (round_orig(f) == round_float(f))); + } while (x--); + +#ifdef __F16C__ + // GELU and SILU implementations are used with a FP16 lookup table. + // The original and float-only results are not equal for all inputs after converting to FP16. + // GELU is an approximation anyway (tanh), not tested here. + // For SILU, verify that the results are at least the closest floating point numbers, if the FP16 values don't match. + for (x = 0; x <= UINT16_MAX; x++) { + float f = _cvtsh_ss(x); + const float so = silu_orig(f); + const float sf = silu_float(f); + assert( (_cvtss_sh(so, 0) == _cvtss_sh(sf, 0)) + || (nextafterf(so, sf) == sf) + || (nextafterf(sf, so) == so)); + } +#endif +} |