happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

ggml-cpu: fix lmul in vec_dot_bf16

This commit is contained in:
taimur-10x 2025-11-17 15:45:38 +05:00
parent 1bda8fb232
commit e07238d113
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
ggml/src/ggml-cpu/vec.cpp
View File

@ -234,6 +234,7 @@ void ggml_vec_dot_bf16(int n, float * GGML_RESTRICT s, size_t bs, ggml_bf16_t *
// reduce // reduce
vl = __riscv_vsetvlmax_e32m2(); vl = __riscv_vsetvlmax_e32m2();
vfloat32m2_t acc0 = __riscv_vfadd_vv_f32m2(__riscv_vget_v_f32m4_f32m2(vsum0, 0), __riscv_vget_v_f32m4_f32m2(vsum0, 1), vl); vfloat32m2_t acc0 = __riscv_vfadd_vv_f32m2(__riscv_vget_v_f32m4_f32m2(vsum0, 0), __riscv_vget_v_f32m4_f32m2(vsum0, 1), vl);
vl = __riscv_vsetvlmax_e32m1();
vfloat32m1_t acc1 = __riscv_vfadd_vv_f32m1(__riscv_vget_v_f32m2_f32m1(acc0, 0), __riscv_vget_v_f32m2_f32m1(acc0, 1), vl); vfloat32m1_t acc1 = __riscv_vfadd_vv_f32m1(__riscv_vget_v_f32m2_f32m1(acc0, 0), __riscv_vget_v_f32m2_f32m1(acc0, 1), vl);
vfloat32m1_t redsum = __riscv_vfredusum_vs_f32m1_f32m1(acc1, __riscv_vfmv_v_f_f32m1(0.0f, 1), vl); vfloat32m1_t redsum = __riscv_vfredusum_vs_f32m1_f32m1(acc1, __riscv_vfmv_v_f_f32m1(0.0f, 1), vl);
sumf += __riscv_vfmv_f_s_f32m1_f32(redsum); sumf += __riscv_vfmv_f_s_f32m1_f32(redsum);