LLM inference in C/C++
C++ ggml
ggml-cpu: use runtime SVE width in FWHT (#24059)
Charles Xu3571fa5435ac
diff --git a/ggml/src/ggml-cpu/ops.cpp b/ggml/src/ggml-cpu/ops.cppindex dc73696ad9..3a1912ae91 100644--- a/ggml/src/ggml-cpu/ops.cpp+++ b/ggml/src/ggml-cpu/ops.cpp@@ -8955,7 +8955,12 @@ static void ggml_compute_forward_flash_attn_ext_f16(k->type == v->type &&neq1 >= Q_TILE_SZ);#ifdef GGML_SIMD- use_tiled &= (DV % GGML_F32_EPR == 0);+#if defined(__ARM_FEATURE_SVE)+ const int64_t f32_epr = svcntw();+#else+ const int64_t f32_epr = GGML_F32_EPR;+#endif+ use_tiled &= (DV % f32_epr == 0);#endifint current_chunk = ith;@@ -11358,7 +11363,11 @@ static void ggml_compute_forward_fwht_f32(const ggml_compute_params * params, gg// Scalar passes#if defined(GGML_SIMD)+#if defined(__ARM_FEATURE_SVE)+ const int step = svcntw();+#elseconst int step = GGML_F32_EPR;+#endif#elseconst int step = n;#endif