Function ggml_compute_forward_mul_f32

ggml.c:7756–7834

// ggml_compute_forward_mul

static void ggml_compute_forward_mul_f32(
        const struct ggml_compute_params * params,
        const struct ggml_tensor * src0,
        const struct ggml_tensor * src1,
        struct ggml_tensor * dst) {
    GGML_ASSERT(ggml_can_repeat_rows(src1, src0) && ggml_are_same_shape(src0, dst));

    if (params->type == GGML_TASK_INIT || params->type == GGML_TASK_FINALIZE) {
        return;
    }
    const int ith = params->ith;
    const int nth = params->nth;

#ifdef GGML_USE_CLBLAST
    if (src1->backend == GGML_BACKEND_GPU) {
        if (ith == 0) {
            ggml_cl_mul(src0, src1, dst);
        }
        return;
    }
#endif

    const int64_t nr = ggml_nrows(src0);

    GGML_TENSOR_BINARY_OP_LOCALS

    GGML_ASSERT( nb0 == sizeof(float));
    GGML_ASSERT(nb00 == sizeof(float));
    GGML_ASSERT(ne00 == ne10);

    if (nb10 == sizeof(float)) {
        for (int64_t ir = ith; ir < nr; ir += nth) {
            // src0 and dst are same shape => same indices
            const int64_t i03 = ir/(ne02*ne01);
            const int64_t i02 = (ir - i03*ne02*ne01)/ne01;
            const int64_t i01 = (ir - i03*ne02*ne01 - i02*ne01);

            const int64_t i13 = i03 % ne13;
            const int64_t i12 = i02 % ne12;
            const int64_t i11 = i01 % ne11;

            float * dst_ptr  = (float *) ((char *) dst->data  + i03*nb3  + i02*nb2  + i01*nb1 );
            float * src0_ptr = (float *) ((char *) src0->data + i03*nb03 + i02*nb02 + i01*nb01);
            float * src1_ptr = (float *) ((char *) src1->data + i13*nb13 + i12*nb12 + i11*nb11);

#ifdef GGML_USE_ACCELERATE
            UNUSED(ggml_vec_mul_f32);

            vDSP_vmul( src0_ptr, 1, src1_ptr, 1, dst_ptr,  1, ne00);
#else
            ggml_vec_mul_f32(ne00, dst_ptr, src0_ptr, src1_ptr);
#endif
                // }
            // }
        }
    } else {
        // src1 is not contiguous
        for (int64_t ir = ith; ir < nr; ir += nth) {