mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-10-27 08:21:30 +00:00
ggml : fix GGML_F32_VEC_FMA argument order in ggml_vec_mad1_f32 (#16307)
* fix GGML_F32_VEC_FMA argument order in ggml_vec_mad1_f32 * add test that fails on simd
This commit is contained in:
@@ -610,7 +610,7 @@ inline static void ggml_vec_mad1_f32(const int n, float * y, const float * x, co
|
||||
for (int i = 0; i < np; i += GGML_F32_STEP) {
|
||||
for (int j = 0; j < GGML_F32_ARR; j++) {
|
||||
ay[j] = GGML_F32_VEC_LOAD(x + i + j*GGML_F32_EPR);
|
||||
ay[j] = GGML_F32_VEC_FMA(ay[j], vs, vb);
|
||||
ay[j] = GGML_F32_VEC_FMA(vb, ay[j], vs);
|
||||
|
||||
GGML_F32_VEC_STORE(y + i + j*GGML_F32_EPR, ay[j]);
|
||||
}
|
||||
|
||||
@@ -6155,6 +6155,7 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
|
||||
test_cases.emplace_back(new test_add1());
|
||||
test_cases.emplace_back(new test_scale());
|
||||
test_cases.emplace_back(new test_scale(GGML_TYPE_F32, {10, 10, 10, 10}, 2.0f, 1.0f));
|
||||
test_cases.emplace_back(new test_scale(GGML_TYPE_F32, {100, 10, 10, 10}, 2.0f, 1.0f));
|
||||
test_cases.emplace_back(new test_softcap(GGML_TYPE_F32, {10, 10, 10, 10}, 50.0f));
|
||||
test_cases.emplace_back(new test_silu_back());
|
||||
|
||||
|
||||
Reference in New Issue
Block a user